1
|
A hybridized feature extraction for COVID-19 multi-class classification on computed tomography images. Heliyon 2024; 10:e26939. [PMID: 38463848 PMCID: PMC10920381 DOI: 10.1016/j.heliyon.2024.e26939] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Revised: 02/20/2024] [Accepted: 02/21/2024] [Indexed: 03/12/2024] Open
Abstract
COVID-19 has killed more than 5 million individuals worldwide within a short time. It is caused by SARS-CoV-2 which continuously mutates and produces more transmissible new different strains. It is therefore of great significance to diagnose COVID-19 early to curb its spread and reduce the death rate. Owing to the COVID-19 pandemic, traditional diagnostic methods such as reverse-transcription polymerase chain reaction (RT-PCR) are ineffective for diagnosis. Medical imaging is among the most effective techniques of respiratory disorders detection through machine learning and deep learning. However, conventional machine learning methods depend on extracted and engineered features, whereby the optimum features influence the classifier's performance. In this study, Histogram of Oriented Gradient (HOG) and eight deep learning models were utilized for feature extraction while K-Nearest Neighbour (KNN) and Support Vector Machines (SVM) were used for classification. A combined feature of HOG and deep learning feature was proposed to improve the performance of the classifiers. VGG-16 + HOG achieved 99.4 overall accuracy with SVM. This indicates that our proposed concatenated feature can enhance the SVM classifier's performance in COVID-19 detection.
Collapse
|
2
|
Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model's explainability. Dentomaxillofac Radiol 2024; 53:115-126. [PMID: 38166356 DOI: 10.1093/dmfr/twad011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Revised: 11/16/2023] [Accepted: 11/16/2023] [Indexed: 01/04/2024] Open
Abstract
OBJECTIVES The objectives of this study are to explore and evaluate the automation of anatomical landmark localization in cephalometric images using machine learning techniques, with a focus on feature extraction and combinations, contextual analysis, and model interpretability through Shapley Additive exPlanations (SHAP) values. METHODS We conducted extensive experimentation on a private dataset of 300 lateral cephalograms to thoroughly study the annotation results obtained using pixel feature descriptors including raw pixel, gradient magnitude, gradient direction, and histogram-oriented gradient (HOG) values. The study includes evaluation and comparison of these feature descriptions calculated at different contexts namely local, pyramid, and global. The feature descriptor obtained using individual combinations is used to discern between landmark and nonlandmark pixels using classification method. Additionally, this study addresses the opacity of LGBM ensemble tree models across landmarks, introducing SHAP values to enhance interpretability. RESULTS The performance of feature combinations was assessed using metrics like mean radial error, standard deviation, success detection rate (SDR) (2 mm), and test time. Remarkably, among all the combinations explored, both the HOG and gradient direction operations demonstrated significant performance across all context combinations. At the contextual level, the global texture outperformed the others, although it came with the trade-off of increased test time. The HOG in the local context emerged as the top performer with an SDR of 75.84% compared to others. CONCLUSIONS The presented analysis enhances the understanding of the significance of different features and their combinations in the realm of landmark annotation but also paves the way for further exploration of landmark-specific feature combination methods, facilitated by explainability.
Collapse
|
3
|
Hybrid Feature Extractor Using Discrete Wavelet Transform and Histogram of Oriented Gradient on Convolutional-Neural-Network-Based Palm Vein Recognition. SENSORS (BASEL, SWITZERLAND) 2024; 24:341. [PMID: 38257434 PMCID: PMC10820403 DOI: 10.3390/s24020341] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 12/29/2023] [Accepted: 12/30/2023] [Indexed: 01/24/2024]
Abstract
Biometric recognition techniques have become more developed recently, especially in security and attendance systems. Biometrics are features attached to the human body that are considered safer and more reliable since they are difficult to imitate or lose. One of the popular biometrics considered in research is palm veins. They are an intrinsic biometric located under the human skin, so they have several advantages when developing verification systems. However, palm vein images obtained based on infrared spectra have several disadvantages, such as nonuniform illumination and low contrast. This study, based on a convolutional neural network (CNN), was conducted on five public datasets from CASIA, Vera, Tongji, PolyU, and PUT, with three parameters: accuracy, AUC, and EER. Our proposed VeinCNN recognition method, called verification scheme with VeinCNN, uses hybrid feature extraction from a discrete wavelet transform (DWT) and histogram of oriented gradient (HOG). It shows promising results in terms of accuracy, AUC, and EER values, especially in the total parameter values. The best result was obtained for the CASIA dataset with 99.85% accuracy, 99.80% AUC, and 0.0083 EER.
Collapse
|
4
|
PFP- HOG: Pyramid and Fixed-Size Patch-Based HOG Technique for Automated Brain Abnormality Classification with MRI. J Digit Imaging 2023; 36:2441-2460. [PMID: 37537514 PMCID: PMC10584767 DOI: 10.1007/s10278-023-00889-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 07/18/2023] [Accepted: 07/24/2023] [Indexed: 08/05/2023] Open
Abstract
Detecting neurological abnormalities such as brain tumors and Alzheimer's disease (AD) using magnetic resonance imaging (MRI) images is an important research topic in the literature. Numerous machine learning models have been used to detect brain abnormalities accurately. This study addresses the problem of detecting neurological abnormalities in MRI. The motivation behind this problem lies in the need for accurate and efficient methods to assist neurologists in the diagnosis of these disorders. In addition, many deep learning techniques have been applied to MRI to develop accurate brain abnormality detection models, but these networks have high time complexity. Hence, a novel hand-modeled feature-based learning network is presented to reduce the time complexity and obtain high classification performance. The model proposed in this work uses a new feature generation architecture named pyramid and fixed-size patch (PFP). The main aim of the proposed PFP structure is to attain high classification performance using essential feature extractors with both multilevel and local features. Furthermore, the PFP feature extractor generates low- and high-level features using a handcrafted extractor. To obtain the high discriminative feature extraction ability of the PFP, we have used histogram-oriented gradients (HOG); hence, it is named PFP-HOG. Furthermore, the iterative Chi2 (IChi2) is utilized to choose the clinically significant features. Finally, the k-nearest neighbors (kNN) with tenfold cross-validation is used for automated classification. Four MRI neurological databases (AD dataset, brain tumor dataset 1, brain tumor dataset 2, and merged dataset) have been utilized to develop our model. PFP-HOG and IChi2-based models attained 100%, 94.98%, 98.19%, and 97.80% using the AD dataset, brain tumor dataset1, brain tumor dataset 2, and merged brain MRI dataset, respectively. These findings not only provide an accurate and robust classification of various neurological disorders using MRI but also hold the potential to assist neurologists in validating manual MRI brain abnormality screening.
Collapse
|
5
|
Lateral Cephalometric Landmark Annotation Using Histogram Oriented Gradients Extracted from Region of Interest Patches. J Maxillofac Oral Surg 2023; 22:806-812. [PMID: 38105853 PMCID: PMC10719201 DOI: 10.1007/s12663-023-02025-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Accepted: 09/24/2023] [Indexed: 12/19/2023] Open
Abstract
Introduction Two-dimensional cephalometric image analysis plays a crucial role in orthodontic diagnosis and treatment planning. While deep learning-based algorithms have emerged to automate the laborious task of anatomical landmark annotation, their effectiveness is hampered by the challenges of acquiring and labelling clinical data. In this study, we propose a model that leverages conventional machine learning techniques to enhance the accuracy of landmark detection using limited dataset. Materials and methods Our methodology involves coarse localization through region of interest (ROI) extraction and fine localization utilizing histogram-oriented gradient (HOG) feature. The image patch containing landmark pixels is classified using the light gradient boosting machine (LGBM) algorithm. To evaluate our model's performance, we conducted rigorous tests on the ISBI Cephalometric dataset and Dental Cepha dataset, aiming to achieve accuracy within a 2 mm radial precision range. We also employed cross-validation to assess our approach, providing a robust evaluation. Results Our model's performance on the ISBI Cephalometric dataset showed an accuracy rate of 77.11% within the desired 2 mm radial precision range. The cross-validation results further confirmed the effectiveness of our approach, yielding a mean accuracy of 78.17%. Additionally, we applied our model to the Dental Cepha dataset, where we achieved a remarkable landmark detection accuracy of 84%. Conclusion The results demonstrate that traditional machine learning techniques can be effective for accurate landmark detection in cephalometric images, even with limited data. Our findings highlight the potential of these techniques for clinical applications, where large datasets of labelled images may not be available.
Collapse
|
6
|
Turnover and bypass of p21-activated kinase during Cdc42-dependent MAPK signaling in yeast. J Biol Chem 2023; 299:105297. [PMID: 37774975 PMCID: PMC10641623 DOI: 10.1016/j.jbc.2023.105297] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 08/10/2023] [Accepted: 08/12/2023] [Indexed: 10/01/2023] Open
Abstract
Mitogen-activated protein kinase (MAPK) pathways regulate multiple cellular behaviors, including the response to stress and cell differentiation, and are highly conserved across eukaryotes. MAPK pathways can be activated by the interaction between the small GTPase Cdc42p and the p21-activated kinase (Ste20p in yeast). By studying MAPK pathway regulation in yeast, we recently found that the active conformation of Cdc42p is regulated by turnover, which impacts the activity of the pathway that regulates filamentous growth (fMAPK). Here, we show that Ste20p is regulated in a similar manner and is turned over by the 26S proteasome. This turnover did not occur when Ste20p was bound to Cdc42p, which presumably stabilized the protein to sustain MAPK pathway signaling. Although Ste20p is a major component of the fMAPK pathway, genetic approaches here identified a Ste20p-independent branch of signaling. Ste20p-independent signaling partially required the fMAPK pathway scaffold and Cdc42p-interacting protein, Bem4p, while Ste20p-dependent signaling required the 14-3-3 proteins, Bmh1p and Bmh2p. Interestingly, Ste20p-independent signaling was inhibited by one of the GTPase-activating proteins for Cdc42p, Rga1p, which unexpectedly dampened basal but not active fMAPK pathway activity. These new regulatory features of the Rho GTPase and p21-activated kinase module may extend to related pathways in other systems.
Collapse
|
7
|
Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques. Cancers (Basel) 2023; 15:5247. [PMID: 37958422 PMCID: PMC10650156 DOI: 10.3390/cancers15215247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Revised: 10/22/2023] [Accepted: 10/25/2023] [Indexed: 11/15/2023] Open
Abstract
Oral cancer is a fatal disease and ranks seventh among the most common cancers throughout the whole globe. Oral cancer is a type of cancer that usually affects the head and neck. The current gold standard for diagnosis is histopathological investigation, however, the conventional approach is time-consuming and requires professional interpretation. Therefore, early diagnosis of Oral Squamous Cell Carcinoma (OSCC) is crucial for successful therapy, reducing the risk of mortality and morbidity, while improving the patient's chances of survival. Thus, we employed several artificial intelligence techniques to aid clinicians or physicians, thereby significantly reducing the workload of pathologists. This study aimed to develop hybrid methodologies based on fused features to generate better results for early diagnosis of OSCC. This study employed three different strategies, each using five distinct models. The first strategy is transfer learning using the Xception, Inceptionv3, InceptionResNetV2, NASNetLarge, and DenseNet201 models. The second strategy involves using a pre-trained art of CNN for feature extraction coupled with a Support Vector Machine (SVM) for classification. In particular, features were extracted using various pre-trained models, namely Xception, Inceptionv3, InceptionResNetV2, NASNetLarge, and DenseNet201, and were subsequently applied to the SVM algorithm to evaluate the classification accuracy. The final strategy employs a cutting-edge hybrid feature fusion technique, utilizing an art-of-CNN model to extract the deep features of the aforementioned models. These deep features underwent dimensionality reduction through principal component analysis (PCA). Subsequently, low-dimensionality features are combined with shape, color, and texture features extracted using a gray-level co-occurrence matrix (GLCM), Histogram of Oriented Gradient (HOG), and Local Binary Pattern (LBP) methods. Hybrid feature fusion was incorporated into the SVM to enhance the classification performance. The proposed system achieved promising results for rapid diagnosis of OSCC using histological images. The accuracy, precision, sensitivity, specificity, F-1 score, and area under the curve (AUC) of the support vector machine (SVM) algorithm based on the hybrid feature fusion of DenseNet201 with GLCM, HOG, and LBP features were 97.00%, 96.77%, 90.90%, 98.92%, 93.74%, and 96.80%, respectively.
Collapse
|
8
|
Fusing Local Shallow Features and Global Deep Features to Identify Beaks. Animals (Basel) 2023; 13:2891. [PMID: 37760291 PMCID: PMC10526073 DOI: 10.3390/ani13182891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Revised: 09/04/2023] [Accepted: 09/06/2023] [Indexed: 09/29/2023] Open
Abstract
Cephalopods are an essential component of marine ecosystems, which are of great significance for the development of marine resources, ecological balance, and human food supply. At the same time, the preservation of cephalopod resources and the promotion of sustainable utilization also require attention. Many studies on the classification of cephalopods focus on the analysis of their beaks. In this study, we propose a feature fusion-based method for the identification of beaks, which uses the convolutional neural network (CNN) model as its basic architecture and a multi-class support vector machine (SVM) for classification. First, two local shallow features are extracted, namely the histogram of the orientation gradient (HOG) and the local binary pattern (LBP), and classified using SVM. Second, multiple CNN models were used for end-to-end learning to identify the beaks, and model performance was compared. Finally, the global deep features of beaks were extracted from the Resnet50 model, fused with the two local shallow features, and classified using SVM. The experimental results demonstrate that the feature fusion model can effectively fuse multiple features to recognize beaks and improve classification accuracy. Among them, the HOG+Resnet50 method has the highest accuracy in recognizing the upper and lower beaks, with 91.88% and 93.63%, respectively. Therefore, this new approach facilitated identification studies of cephalopod beaks.
Collapse
|
9
|
Detecting Dementia from Face-Related Features with Automated Computational Methods. Bioengineering (Basel) 2023; 10:862. [PMID: 37508889 PMCID: PMC10376259 DOI: 10.3390/bioengineering10070862] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 07/13/2023] [Accepted: 07/14/2023] [Indexed: 07/30/2023] Open
Abstract
Alzheimer's disease (AD) is a type of dementia that is more likely to occur as people age. It currently has no known cure. As the world's population is aging quickly, early screening for AD has become increasingly important. Traditional screening methods such as brain scans or psychiatric tests are stressful and costly. The patients are likely to feel reluctant to such screenings and fail to receive timely intervention. While researchers have been exploring the use of language in dementia detection, less attention has been given to face-related features. The paper focuses on investigating how face-related features can aid in detecting dementia by exploring the PROMPT dataset that contains video data collected from patients with dementia during interviews. In this work, we extracted three types of features from the videos, including face mesh, Histogram of Oriented Gradients (HOG) features, and Action Units (AU). We trained traditional machine learning models and deep learning models on the extracted features and investigated their effectiveness in dementia detection. Our experiments show that the use of HOG features achieved the highest accuracy of 79% in dementia detection, followed by AU features with 71% accuracy, and face mesh features with 66% accuracy. Our results show that face-related features have the potential to be a crucial indicator in automated computational dementia detection.
Collapse
|
10
|
ExHiF: Alzheimer's disease detection using exemplar histogram-based features with CT and MR images. Med Eng Phys 2023; 115:103971. [PMID: 37120169 DOI: 10.1016/j.medengphy.2023.103971] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Revised: 03/16/2023] [Accepted: 03/18/2023] [Indexed: 05/01/2023]
Abstract
PURPOSE The classification of medical images is an important priority for clinical research and helps to improve the diagnosis of various disorders. This work aims to classify the neuroradiological features of patients with Alzheimer's disease (AD) using an automatic hand-modeled method with high accuracy. MATERIALS AND METHOD This work uses two (private and public) datasets. The private dataset consists of 3807 magnetic resonance imaging (MRI) and computer tomography (CT) images belonging to two (normal and AD) classes. The second public (Kaggle AD) dataset contains 6400 MR images. The presented classification model comprises three fundamental phases: feature extraction using an exemplar hybrid feature extractor, neighborhood component analysis-based feature selection, and classification utilizing eight different classifiers. The novelty of this model is feature extraction. Vision transformers inspire this phase, and hence 16 exemplars are generated. Histogram-oriented gradients (HOG), local binary pattern (LBP) and local phase quantization (LPQ) feature extraction functions have been applied to each exemplar/patch and raw brain image. Finally, the created features are merged, and the best features are selected using neighborhood component analysis (NCA). These features are fed to eight classifiers to obtain highest classification performance using our proposed method. The presented image classification model uses exemplar histogram-based features; hence, it is called ExHiF. RESULTS We have developed the ExHiF model with a ten-fold cross-validation strategy using two (private and public) datasets with shallow classifiers. We have obtained 100% classification accuracy using cubic support vector machine (CSVM) and fine k nearest neighbor (FkNN) classifiers for both datasets. CONCLUSIONS Our developed model is ready to be validated with more datasets and has the potential to be employed in mental hospitals to assist neurologists in confirming their manual screening of AD using MRI/CT images.
Collapse
|
11
|
Strain-dependent differences in coordination of yeast signalling networks. FEBS J 2023; 290:2097-2114. [PMID: 36416575 PMCID: PMC10121740 DOI: 10.1111/febs.16689] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Revised: 09/30/2022] [Accepted: 10/18/2022] [Indexed: 11/24/2022]
Abstract
The yeast mitogen-activated protein kinase pathways serve as a model system for understanding how network interactions affect the way in which cells coordinate the response to multiple signals. We have quantitatively compared two yeast strain backgrounds YPH499 and ∑1278b (both of which have previously been used to study these pathways) and found several important differences in how they coordinate the interaction between the high osmolarity glycerol (HOG) and mating pathways. In the ∑1278b background, in response to simultaneous stimulus, mating pathway activation is dampened and delayed in a dose-dependent manner. In the YPH499 background, only dampening is dose-dependent. Furthermore, leakage from the HOG pathway into the mating pathway (crosstalk) occurs during osmostress alone in the ∑1278b background only. The mitogen-activated protein kinase Hog1p suppresses crosstalk late in an induction time course in both strains but does not affect the early crosstalk seen in the ∑1278b background. Finally, the kinase Rck2p plays a greater role suppressing late crosstalk in the ∑1278b background than in the YPH499 background. Our results demonstrate that comparisons between laboratory yeast strains provide an important resource for understanding how signalling network interactions are tuned by genetic variation without significant alteration to network structure.
Collapse
|
12
|
Vision-Based HAR in UAV Videos Using Histograms and Deep Learning Techniques. SENSORS (BASEL, SWITZERLAND) 2023; 23:2569. [PMID: 36904773 PMCID: PMC10007408 DOI: 10.3390/s23052569] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/15/2022] [Revised: 02/17/2023] [Accepted: 02/21/2023] [Indexed: 06/18/2023]
Abstract
Activity recognition in unmanned aerial vehicle (UAV) surveillance is addressed in various computer vision applications such as image retrieval, pose estimation, object detection, object detection in videos, object detection in still images, object detection in video frames, face recognition, and video action recognition. In the UAV-based surveillance technology, video segments captured from aerial vehicles make it challenging to recognize and distinguish human behavior. In this research, to recognize a single and multi-human activity using aerial data, a hybrid model of histogram of oriented gradient (HOG), mask-regional convolutional neural network (Mask-RCNN), and bidirectional long short-term memory (Bi-LSTM) is employed. The HOG algorithm extracts patterns, Mask-RCNN extracts feature maps from the raw aerial image data, and the Bi-LSTM network exploits the temporal relationship between the frames for the underlying action in the scene. This Bi-LSTM network reduces the error rate to the greatest extent due to its bidirectional process. This novel architecture generates enhanced segmentation by utilizing the histogram gradient-based instance segmentation and improves the accuracy of classifying human activities using the Bi-LSTM approach. Experimental outcomes demonstrate that the proposed model outperforms the other state-of-the-art models and has achieved 99.25% accuracy on the YouTube-Aerial dataset.
Collapse
|
13
|
Blind detection of circular image rotation angle based on ensemble transfer regression and fused HOG. Front Neurorobot 2022; 16:1037381. [PMID: 36590081 PMCID: PMC9797098 DOI: 10.3389/fnbot.2022.1037381] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Accepted: 09/28/2022] [Indexed: 12/23/2022] Open
Abstract
Introduction Aiming at the problems of low accuracy in estimating the rotation angle after the rotation of circular image data within a wide range (0°-360°) and difficulty in blind detection without a reference image, a method based on ensemble transfer regression network, fused HOG, and Rotate Loss is adopted to solve such problems. Methods The proposed Rotate Loss was combined to solve the angle prediction error, especially the huge error when near 0°. Fused HOG was mainly used to extract directional features. Then, the feature learning was conducted by the ensemble transfer regression model combined with the feature extractor and the ensemble regressors to estimate an exact rotation angle. Based on miniImageNet and Minist, we made the circular random rotation dataset Circular-ImageNet and random rotation dataset Rot-Minist, respectively. Results Experiments showed that for the proposed evaluation index MSE_Rotate, the best single regressor could be as low as 28.79 on the training set of Circular-ImageNet and 2686.09 on the validation set. For MSE_Rotate, MSE, MAE, and RMSE on the test set were 1,702.4325, 0.0263, 0.0881, and 0.1621, respectively. And under the ensemble transfer regression network, it could continue to decrease by 15%. The mean error rate on Rot-Minist could be just 0.59%, significantly working easier in a wide range than other networks in recent years. Based on the ensemble transfer regression model, we also completed the application of image righting blindly.
Collapse
|
14
|
Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets. SENSORS (BASEL, SWITZERLAND) 2022; 22:8121. [PMID: 36365821 PMCID: PMC9654483 DOI: 10.3390/s22218121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Revised: 10/20/2022] [Accepted: 10/21/2022] [Indexed: 06/16/2023]
Abstract
The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients (HOG) are extracted from the segmented traffic. Furthermore, a multi-class support vector machine classifier is employed to categorize different traffic vehicle types, including passenger cars, passenger trucks, motorcycles, buses, and small and large utility trucks. It handles multiple vehicle detections through an iterative k-means clustering over-segmentation process. The proposed algorithm reduced the processed data by an average of 40%. Compared to recent techniques, it showed an average improvement of 15% in segmentation accuracy, and it is 55% faster than the compared segmentation techniques on average. Moreover, a comparative analysis of 23 different deep learning architectures is presented. The resulting algorithm outperformed the compared deep learning algorithms for the quality of vehicle classification accuracy. Furthermore, the timing analysis showed that it could operate in real-time scenarios.
Collapse
|
15
|
A New Traffic Sign Recognition Technique Taking Shuffled Frog-Leaping Algorithm into Account. WIRELESS PERSONAL COMMUNICATIONS 2022; 125:3425-3441. [PMID: 35789577 PMCID: PMC9244287 DOI: 10.1007/s11277-022-09718-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 04/14/2022] [Indexed: 06/15/2023]
Abstract
Everyday humans use cars to move faster, and the world is a chaotic place, and a little distraction or a mistake could be the reason for an accident and bring people great pain. An assistance system that can distinguish and detect signs on the roads and brings the driver's attention to road signs and make them aware of their meaning could be beneficial. The most important part of the Traffic Sign Recognition System is the algorithm. In this paper, a new way toward Traffic Sign Recognition algorithm taking the advantages of Color Segmentation, support vector machines, and histograms of oriented gradients on the GTSRB dataset is proposed. The unsupervised shuffled frog-leaping algorithm is employed for segmenting the images. The results show remarkable improvements by using meta-heuristic algorithms.
Collapse
|
16
|
COVID-19 Isolation Control Proposal via UAV and UGV for Crowded Indoor Environments: Assistive Robots in the Shopping Malls. Front Public Health 2022; 10:855994. [PMID: 35734764 PMCID: PMC9208298 DOI: 10.3389/fpubh.2022.855994] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2022] [Accepted: 05/10/2022] [Indexed: 11/13/2022] Open
Abstract
Artificial intelligence researchers conducted different studies to reduce the spread of COVID-19. Unlike other studies, this paper isn't for early infection diagnosis, but for preventing the transmission of COVID-19 in social environments. Among the studies on this is regarding social distancing, as this method is proven to prevent COVID-19 to be transmitted from one to another. In the study, Robot Operating System (ROS) simulates a shopping mall using Gazebo, and customers are monitored by Turtlebot and Unmanned Aerial Vehicle (UAV, DJI Tello). Through frames analysis captured by Turtlebot, a particular person is identified and followed at the shopping mall. Turtlebot is a wheeled robot that follows people without contact and is used as a shopping cart. Therefore, a customer doesn't touch the shopping cart that someone else comes into contact with, and also makes his/her shopping easier. The UAV detects people from above and determines the distance between people. In this way, a warning system can be created by detecting places where social distance is neglected. Histogram of Oriented-Gradients (HOG)-Support Vector Machine (SVM) is applied by Turtlebot to detect humans, and Kalman-Filter is used for human tracking. SegNet is performed for semantically detecting people and measuring distance via UAV. This paper proposes a new robotic study to prevent the infection and proved that this system is feasible.
Collapse
|
17
|
Detection and classification of COVID-19 disease from X-ray images using convolutional neural networks and histogram of oriented gradients. Biomed Signal Process Control 2022; 74:103530. [PMID: 35096125 PMCID: PMC8789569 DOI: 10.1016/j.bspc.2022.103530] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Revised: 01/04/2022] [Accepted: 01/21/2022] [Indexed: 12/11/2022]
Abstract
COVID-19 is now regarded as the most lethal disease caused by the novel coronavirus disease of humans. The COVID-19 pandemic has spread to every country on the planet and has wreaked havoc on these countries by increasing the number of human deaths, and in addition, caused intense hunger, and lowered economic productivity. Due to a lack of sufficient radiologist, a restricted amount of COVID-19 test kits is available in hospitals, and this is also accompanied by a shortage of equipment due to the daily increase in cases, as a result of increase in the number of persons infected with COVID-19 . Even for experienced radiologists, examining chest X-rays is a difficult task. Many people have died as a result of inaccurate COVID-19 diagnosis and treatment, as well as ineffective detection measures. This paper, therefore presents a unique detection and classification approach (DCCNet) for quick diagnosis of COVID-19 using chest X-ray images of patients. To achieve quick diagnosis, a convolutional neural network (CNN) and histogram of oriented gradients (HOG) method is proposed in this paper to help medical experts diagnose COVID-19 disease. The diagnostic performance of the hybrid CNN model and HOG-based method was then evaluated using chest X-ray images collected from University of Gondar and online databases. The experiment was performed using Keras (with TensorFlow as a backend) and Python. After the DCCNet model was evaluated, a 99.9% training accuracy and 98.3% test accuracy was achieved, while a 100% training accuracy and 98.5% test accuracy was achieved using HOG. After the evaluation, the hybrid model achieved 99.97% and 99.67% training and testing accuracy for detection and classification of COVID-19 which was better by 1.37% compared to when features were extracted using CNN and 1.17% when HOG was used. The DCCNet achieved a result that outperformed state-of-the-art models by 6.7%.
Collapse
|
18
|
Multi-resolution 3D- HOG feature learning method for Alzheimer's Disease diagnosis. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 214:106574. [PMID: 34902802 DOI: 10.1016/j.cmpb.2021.106574] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/05/2021] [Revised: 11/25/2021] [Accepted: 12/01/2021] [Indexed: 06/14/2023]
Abstract
BACKGROUND AND OBJECTIVE Alzheimer's Disease (AD) is a progressive irreversible neurodegeneration disease and thus timely identification is critical to delay its progression. METHODS In this work, we focus on the traditional branch to design discriminative feature extraction and selection strategies to achieve explainable AD identification. Specifically, a spatial pyramid based three-dimensional histogram of oriented gradient (3D-HOG) feature learning method is proposed. Both global and local texture changes are included in spatial pyramid 3D-HOG (SPHOG) features for comprehensive analysis. Then a modified wrapper-based feature selection algorithm is introduced to select the discriminative features for AD identification while reduce feature dimensions. RESULTS Discriminative SPHOG histograms with various resolutions are selected, which can represent the atrophy characteristics of cerebral cortex with promising performance. As subareas corresponding to selected histograms are consistent with clinical experience, explanatory is emphasized and illustrated with Hippocampus. CONCLUSION Experimental results illustrate the effectiveness of the proposed method on feature learning based on samples obtained from common dataset and a clinical dataset. The proposed method will be useful for further medical analysis as its explanatory on other region-of-interests (ROIs) of the brain for early diagnosis of AD.
Collapse
|
19
|
Computer-aided diagnosis of COVID-19 from chest X-ray images using histogram-oriented gradient features and Random Forest classifier. MULTIMEDIA TOOLS AND APPLICATIONS 2022; 81:40451-40468. [PMID: 35572385 PMCID: PMC9090123 DOI: 10.1007/s11042-022-13183-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2021] [Revised: 01/30/2022] [Accepted: 04/28/2022] [Indexed: 05/13/2023]
Abstract
The decision-making process is very crucial in healthcare, which includes quick diagnostic methods to monitor and prevent the COVID-19 pandemic disease from spreading. Computed tomography (CT) is a diagnostic tool used by radiologists to treat COVID patients. COVID x-ray images have inherent texture variations and similarity to other diseases like pneumonia. Manually diagnosing COVID X-ray images is a tedious and challenging process. Extracting the discriminant features and fine-tuning the classifiers using low-resolution images with a limited COVID x-ray dataset is a major challenge in computer aided diagnosis. The present work addresses this issue by proposing and implementing Histogram Oriented Gradient (HOG) features trained with an optimized Random Forest (RF) classifier. The proposed HOG feature extraction method is evaluated with Gray-Level Co-Occurrence Matrix (GLCM) and Hu moments. Results confirm that HOG is found to reflect the local description of edges effectively and provide excellent structural features to discriminate COVID and non-COVID when compared to the other feature extraction techniques. The performance of the RF is compared with other classifiers such as Linear Regression (LR), Linear Discriminant Analysis (LDA), K-nearest neighbor (kNN), Classification and Regression Trees (CART), Random Forest (RF), Support Vector Machine (SVM), and Multi-layer perceptron neural network (MLP). Experimental results show that the highest classification accuracy (99. 73%) is achieved using HOG trained by using the Random Forest (RF) classifier. The proposed work has provided promising results to assist radiologists/physicians in automatic COVID diagnosis using X-ray images.
Collapse
|
20
|
Sensing and Responding to Hypersaline Conditions and the HOG Signal Transduction Pathway in Fungi Isolated from Hypersaline Environments: Hortaea werneckii and Wallemia ichthyophaga. J Fungi (Basel) 2021; 7:jof7110988. [PMID: 34829275 PMCID: PMC8620582 DOI: 10.3390/jof7110988] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 11/11/2021] [Accepted: 11/15/2021] [Indexed: 11/16/2022] Open
Abstract
Sensing and responding to changes in NaCl concentration in hypersaline environments is vital for cell survival. In this paper, we identified and characterized key components of the high-osmolarity glycerol (HOG) signal transduction pathway, which is crucial in sensing hypersaline conditions in the extremely halotolerant black yeast Hortaea werneckii and in the obligate halophilic fungus Wallemia ichthyophaga. Both organisms were isolated from solar salterns, their predominating ecological niche. The identified components included homologous proteins of both branches involved in sensing high osmolarity (SHO1 and SLN1) and the homologues of mitogen-activated protein kinase module (MAPKKK Ste11, MAPKK Pbs2, and MAPK Hog1). Functional complementation of the identified gene products in S. cerevisiae mutant strains revealed some of their functions. Structural protein analysis demonstrated important structural differences in the HOG pathway components between halotolerant/halophilic fungi isolated from solar salterns, salt-sensitive S. cerevisiae, the extremely salt-tolerant H. werneckii, and halophilic W. ichthyophaga. Known and novel gene targets of MAP kinase Hog1 were uncovered particularly in halotolerant H. werneckii. Molecular studies of many salt-responsive proteins confirm unique and novel mechanisms of adaptation to changes in salt concentration.
Collapse
|
21
|
Improved Visual Recognition Memory Model Based on Grid Cells for Face Recognition. Front Neurosci 2021; 15:718541. [PMID: 34675765 PMCID: PMC8525539 DOI: 10.3389/fnins.2021.718541] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Accepted: 08/19/2021] [Indexed: 11/13/2022] Open
Abstract
Traditional facial recognition methods depend on a large number of training samples due to the massive turning of synaptic weights for low-level feature extractions. In prior work, a brain-inspired model of visual recognition memory suggested that grid cells encode translation saccadic eye movement vectors between salient stimulus features. With a small training set for each recognition type, the relative positions among the selected features for each image were represented using grid and feature label cells in Hebbian learning. However, this model is suitable only for the recognition of familiar faces, objects, and scenes. The model's performance for a given face with unfamiliar facial expressions was unsatisfactory. In this study, an improved computational model via grid cells for facial recognition was proposed. Here, the initial hypothesis about stimulus identity was obtained using the histograms of oriented gradients (HOG) algorithm. The HOG descriptors effectively captured the sample edge or gradient structure features. Thus, most test samples were successfully recognized within three saccades. Moreover, the probability of a false hypothesis and the average fixations for successful recognition were reduced. Compared with other neural network models, such as convolutional neural networks and deep belief networks, the proposed method shows the best performance with only one training sample for each face. Moreover, it is robust against image occlusion and size variance or scaling. Our results may give insight for efficient recognition with small training samples based on neural networks.
Collapse
|
22
|
Pebrine diagnosis using quantitative phase imaging and machine learning. JOURNAL OF BIOPHOTONICS 2021; 14:e202100044. [PMID: 33960704 DOI: 10.1002/jbio.202100044] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/05/2021] [Revised: 05/04/2021] [Accepted: 05/05/2021] [Indexed: 06/12/2023]
Abstract
Pebrine is the most dreaded infectious disease of the silkworm and has devastated sericulture in Europe during the 18th century. Thereafter, if it is detected, the crop is burned to prevent further dissemination. The conventional microscopic examination of moth's body fluid is erroneous and it exacerbates on Metarhizium anisopliae (MA) contaminated test samples. This is due to the resemblance of pebrine and MA spores in the microscopic examination. Therefore, this study aims to demonstrate an efficient pebrine detection technique. In the proposed method, a motorised brightfield microscope is custom-made to acquire focused and defocused images of test spores. These images are used to produce quantitative phase images of the spores by the transport of intensity equation method. The phase images' histogram of oriented gradients feature is used by a machine learning classifier to categorise the spores. This system classified 92 pebrine and 185 MA spores with an accuracy of 97% at 0.04 seconds/spore. The duration taken for image acquisition is 2.5 minutes per sample (10 fields of view covering an area of 302 × 260 μm2 ). The proposed method shows reliable results in pebrine diagnosis and would be an efficient alternative for current approaches.
Collapse
|
23
|
Osmolyte Signatures for the Protection of Aspergillus sydowii Cells under Halophilic Conditions and Osmotic Shock. J Fungi (Basel) 2021; 7:414. [PMID: 34073303 PMCID: PMC8228332 DOI: 10.3390/jof7060414] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2021] [Revised: 05/11/2021] [Accepted: 05/20/2021] [Indexed: 11/16/2022] Open
Abstract
Aspergillus sydowii is a moderate halophile fungus extensively studied for its biotechnological potential and halophile responses, which has also been reported as a coral reef pathogen. In a recent publication, the transcriptomic analysis of this fungus, when growing on wheat straw, showed that genes related to cell wall modification and cation transporters were upregulated under hypersaline conditions but not under 0.5 M NaCl, the optimal salinity for growth in this strain. This led us to study osmolyte accumulation as a mechanism to withstand moderate salinity. In this work, we show that A. sydowii accumulates trehalose, arabitol, mannitol, and glycerol with different temporal dynamics, which depend on whether the fungus is exposed to hypo- or hyperosmotic stress. The transcripts coding for enzymes responsible for polyalcohol synthesis were regulated in a stress-dependent manner. Interestingly, A. sydowii contains three homologs (Hog1, Hog2 and MpkC) of the Hog1 MAPK, the master regulator of hyperosmotic stress response in S. cerevisiae and other fungi. We show a differential regulation of these MAPKs under different salinity conditions, including sustained basal Hog1/Hog2 phosphorylation levels in the absence of NaCl or in the presence of 2.0 M NaCl, in contrast to what is observed in S. cerevisiae. These findings indicate that halophilic fungi such as A. sydowii utilize different osmoadaptation mechanisms to hypersaline conditions.
Collapse
|
24
|
Behavioral Biometric Data Analysis for Gender Classification Using Feature Fusion and Machine Learning. Front Robot AI 2021; 8:685966. [PMID: 34026859 PMCID: PMC8139629 DOI: 10.3389/frobt.2021.685966] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2021] [Accepted: 04/20/2021] [Indexed: 12/13/2022] Open
Abstract
Biometric security applications have been employed for providing a higher security in several access control systems during the past few years. The handwritten signature is the most widely accepted behavioral biometric trait for authenticating the documents like letters, contracts, wills, MOU’s, etc. for validation in day to day life. In this paper, a novel algorithm to detect gender of individuals based on the image of their handwritten signatures is proposed. The proposed work is based on the fusion of textural and statistical features extracted from the signature images. The LBP and HOG features represent the texture. The writer’s gender classification is carried out using machine learning techniques. The proposed technique is evaluated on own dataset of 4,790 signatures and realized an encouraging accuracy of 96.17, 98.72 and 100% for k-NN, decision tree and Support Vector Machine classifiers, respectively. The proposed method is expected to be useful in design of efficient computer vision tools for authentication and forensic investigation of documents with handwritten signatures.
Collapse
|
25
|
A Comparative Analysis for 2D Object Recognition: A Case Study with Tactode Puzzle-Like Tiles. J Imaging 2021; 7:65. [PMID: 34460515 PMCID: PMC8321360 DOI: 10.3390/jimaging7040065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 03/26/2021] [Accepted: 03/27/2021] [Indexed: 11/17/2022] Open
Abstract
Object recognition represents the ability of a system to identify objects, humans or animals in images. Within this domain, this work presents a comparative analysis among different classification methods aiming at Tactode tile recognition. The covered methods include: (i) machine learning with HOG and SVM; (ii) deep learning with CNNs such as VGG16, VGG19, ResNet152, MobileNetV2, SSD and YOLOv4; (iii) matching of handcrafted features with SIFT, SURF, BRISK and ORB; and (iv) template matching. A dataset was created to train learning-based methods (i and ii), and with respect to the other methods (iii and iv), a template dataset was used. To evaluate the performance of the recognition methods, two test datasets were built: tactode_small and tactode_big, which consisted of 288 and 12,000 images, holding 2784 and 96,000 regions of interest for classification, respectively. SSD and YOLOv4 were the worst methods for their domain, whereas ResNet152 and MobileNetV2 showed that they were strong recognition methods. SURF, ORB and BRISK demonstrated great recognition performance, while SIFT was the worst of this type of method. The methods based on template matching attained reasonable recognition results, falling behind most other methods. The top three methods of this study were: VGG16 with an accuracy of 99.96% and 99.95% for tactode_small and tactode_big, respectively; VGG19 with an accuracy of 99.96% and 99.68% for the same datasets; and HOG and SVM, which reached an accuracy of 99.93% for tactode_small and 99.86% for tactode_big, while at the same time presenting average execution times of 0.323 s and 0.232 s on the respective datasets, being the fastest method overall. This work demonstrated that VGG16 was the best choice for this case study, since it minimised the misclassifications for both test datasets.
Collapse
|
26
|
Complex Human Action Recognition Using a Hierarchical Feature Reduction and Deep Learning-Based Method. ACTA ACUST UNITED AC 2021; 2:94. [PMID: 33615240 PMCID: PMC7881322 DOI: 10.1007/s42979-021-00484-0] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2020] [Accepted: 01/22/2021] [Indexed: 01/18/2023]
Abstract
Automated human action recognition is one of the most attractive and practical research fields in computer vision. In such systems, the human action labelling is based on the appearance and patterns of the motions in the video sequences; however, majority of the existing research and most of the conventional methodologies and classic neural networks either neglect or are not able to use temporal information for action recognition prediction in a video sequence. On the other hand, the computational cost of a proper and accurate human action recognition is high. In this paper, we address the challenges of the preprocessing phase, by an automated selection of representative frames from the input sequences. We extract the key features of the representative frame rather than the entire features. We propose a hierarchical technique using background subtraction and HOG, followed by application of a deep neural network and skeletal modelling method. The combination of a CNN and the LSTM recursive network is considered for feature selection and maintaining the previous information; and finally, a Softmax-KNN classifier is used for labelling the human activities. We name our model as "Hierarchical Feature Reduction & Deep Learning"-based action recognition method, or HFR-DL in short. To evaluate the proposed method, we use the UCF101 dataset for the benchmarking which is widely used among researchers in the action recognition research field. The dataset includes 101 complicated activities in the wild. Experimental results show a significant improvement in terms of accuracy and speed in comparison with eight state-of-the-art methods.
Collapse
|
27
|
Biochemical analysis of leptospiral LPS explained the difference between pat hogenic and non-pathogenic serogroups. Microb Pathog 2021; 152:104738. [PMID: 33529737 DOI: 10.1016/j.micpath.2021.104738] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2020] [Revised: 01/02/2021] [Accepted: 01/07/2021] [Indexed: 10/22/2022]
Abstract
Lipopolysaccharide (LPS) is the major surface antigen of Leptospira. In this study, the genes involved in the LPS biosynthesis were analyzed and compared by bioinformatics tools. Also, the chemical composition analysis of leptospiral lipopolysaccharides (LPS) extracted from 5 pathogenic serovars like Autumnalis, Australis, Ballum, Grippotyphosa, Pomona, and the nonpathogenic serovar Andamana was performed. Methods used were Limulus amebocyte lysate assay (LAL), gas chromatography-mass spectrometry (GC-MS), fourier transform infrared spectroscopy (FT-IR), and nuclear magnetic resonance spectroscopy (NMR). LAL assay showed a significantly higher level of endotoxicity among pathogenic serovars (~0.490 EU/mL) than that of nonpathogenic Andamana (~0.102 EU/mL). FAMES analysis showed the presence of palmitic acid (C16:0), hydroxy lauric acid (3-OH-C12:0), and oleic acid (C18:0). Palmitoleic acid (C16: 1), and 3- hydroxy palmitate (3-OH-C16:0) was detected only in pathogenic serovars. In contrast myristoleic acid (C14:1) and stearic acid (C18:0) were present in Andamana. FTIR analysis revealed C-O-C stretch of esters, 3°ROH functional groups and carbohydrate vibration range were similar among pathogenic serovars. The NMR analysis reveals similarity for 6 deoxy sugars and methyl groups of Autumnalis, Australis, and Ballum. Further, the presence of palmitoleic acid and 3-hydroxy palmitate may be the significant pathogen-associated predisposing factor. This mediates high osmolarity glycerol (HOG) mediated stress response in leptospiral LPS mediated pathogenesis.
Collapse
|
28
|
Corrigendum: Sho1 and Msb2 Play Complementary but Distinct Roles in Stress Responses, Sexual Differentiation, and Pat hogenicity of Cryptococcus neoformans. Front Microbiol 2020; 11:1956. [PMID: 33071993 PMCID: PMC7542305 DOI: 10.3389/fmicb.2020.01956] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Accepted: 07/24/2020] [Indexed: 11/13/2022] Open
Abstract
[This corrects the article DOI: 10.3389/fmicb.2018.02958.].
Collapse
|
29
|
An exemplar pyramid feature extraction based humerus fracture classification method. Med Hypotheses 2020; 140:109663. [PMID: 32163795 DOI: 10.1016/j.mehy.2020.109663] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2020] [Revised: 02/25/2020] [Accepted: 03/02/2020] [Indexed: 12/20/2022]
Abstract
Humerus fracture have been widely seen disease in the orthopedic clinics and classification of them is a hard process for orthopedist. The main aim of the proposed method is to classify humerus fracture by using a naïve and multileveled method. We collected a novel humerus fracture X-ray image dataset. This dataset consists of 115 images. In this paper, a novel stable feature extraction method is presented to classify humerus fractures. This method is called exemplar pyramid method and it is inspired by exemplar facial expression recognition methods. To classify humerus fractures, X-ray images were employed as input. In this study, X-ray images are resized to 512 × 512 sized image. Then, the used humerus fracture images are divided into 64 × 64 size of exemplars. To create levels, maximum pooling which has been mostly used in deep networks is used and four levels are created. Histogram of oriented gradients (HOG) and local binary pattern (LBP) are employed for feature generation. The most discriminative ones of the generated and concatenated features are selected by using ReliefF and Neighborhood Component Analysis (NCA) based two levelled feature selector (RFNCA). To emphasize success of the proposed exemplar pyramid model based feature generation, four conventional classifiers are chosen for classification and the proposed exemplar pyramid model achieved 99.12% classification accuracy by using leave one out cross validation (LOOCV). Results and tests clearly illustrates success of the proposed exemplar pyramid model based humerus fracture classification method. The results also shown that the proposed exemplar pyramid model achieved higher classification rate than Orthopedist specialized in shoulder.
Collapse
|
30
|
Reappraisal of Human HOG and MO3.13 Cell Lines as a Model to Study Oligodendrocyte Functioning. Cells 2019; 8:cells8091096. [PMID: 31533280 PMCID: PMC6769895 DOI: 10.3390/cells8091096] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2019] [Revised: 09/09/2019] [Accepted: 09/10/2019] [Indexed: 02/07/2023] Open
Abstract
Myelination of neuronal axons is essential for proper brain functioning and requires mature myelinating oligodendrocytes (myOLs). The human OL cell lines HOG and MO3.13 have been widely used as in vitro models to study OL (dys) functioning. Here we applied a number of protocols aimed at differentiating HOG and MO3.13 cells into myOLs. However, none of the differentiation protocols led to increased expression of terminal OL differentiation or myelin-sheath formation markers. Surprisingly, the applied protocols did cause changes in the expression of markers for early OLs, neurons, astrocytes and Schwann cells. Furthermore, we noticed that mRNA expression levels in HOG and MO3.13 cells may be affected by the density of the cultured cells. Finally, HOG and MO3.13 co-cultured with human neuronal SH-SY5Y cells did not show myelin formation under several pro-OL-differentiation and pro-myelinating conditions. Together, our results illustrate the difficulty of inducing maturation of HOG and MO3.13 cells into myOLs, implying that these oligodendrocytic cell lines may not represent an appropriate model to study the (dys)functioning of human (my)OLs and OL-linked disease mechanisms.
Collapse
|
31
|
Aspergillus fumigatus High Osmolarity Glycerol Mitogen Activated Protein Kinases SakA and MpkC Physically Interact During Osmotic and Cell Wall Stresses. Front Microbiol 2019; 10:918. [PMID: 31134001 PMCID: PMC6514138 DOI: 10.3389/fmicb.2019.00918] [Citation(s) in RCA: 21] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2018] [Accepted: 04/11/2019] [Indexed: 11/30/2022] Open
Abstract
Aspergillusfumigatus, a saprophytic filamentous fungus, is a serious opportunistic pathogen of mammals and it is the primary causal agent of invasive aspergillosis (IA). Mitogen activated protein Kinases (MAPKs) are important components involved in diverse cellular processes in eukaryotes. A. fumigatus MpkC and SakA, the homologs of the Saccharomyces cerevisiae Hog1 are important to adaptations to oxidative and osmotic stresses, heat shock, cell wall damage, macrophage recognition, and full virulence. We performed protein pull-down experiments aiming to identify interaction partners of SakA and MpkC by mass spectrometry analysis. In presence of osmotic stress with sorbitol, 118, and 213 proteins were detected as possible protein interactors of SakA and MpkC, respectively. Under cell wall stress caused by congo red, 420 and 299 proteins were detected interacting with SakA and MpkC, respectively. Interestingly, a group of 78 and 256 proteins were common to both interactome analysis. Co-immunoprecipitation (Co-IP) experiments showed that SakA::GFP is physically associated with MpkC:3xHA upon osmotic and cell wall stresses. We also validated the association between SakA:GFP and the cell wall integrity MAPK MpkA:3xHA and the phosphatase PtcB:3xHA, under cell wall stress. We further characterized A. fumigatus PakA, the homolog of the S. cerevisiae sexual developmental serine/threonine kinase Ste20, as a component of the SakA/MpkC MAPK pathway. The ΔpakA strain is more sensitive to cell wall damaging agents as congo red, calcofluor white, and caspofungin. Together, our data supporting the hypothesis that SakA and MpkC are part of an osmotic and general signal pathways involved in regulation of the response to the cell wall damage, oxidative stress, drug resistance, and establishment of infection. This manuscript describes an important biological resource to understand SakA and MpkC protein interactions. Further investigation of the biological roles played by these protein interactors will provide more opportunities to understand and combat IA.
Collapse
|
32
|
Mass Surveilance of C. elegans-Smartphone-Based DIY Microscope and Machine-Learning-Based Approach for Worm Detection. SENSORS 2019; 19:s19061468. [PMID: 30917520 PMCID: PMC6471353 DOI: 10.3390/s19061468] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/18/2019] [Revised: 03/17/2019] [Accepted: 03/20/2019] [Indexed: 11/16/2022]
Abstract
The nematode Caenorhabditis elegans (C. elegans) is often used as an alternative animal model due to several advantages such as morphological changes that can be seen directly under a microscope. Limitations of the model include the usage of expensive and cumbersome microscopes, and restrictions of the comprehensive use of C. elegans for toxicological trials. With the general applicability of the detection of C. elegans from microscope images via machine learning, as well as of smartphone-based microscopes, this article investigates the suitability of smartphone-based microscopy to detect C. elegans in a complete Petri dish. Thereby, the article introduces a smartphone-based microscope (including optics, lighting, and housing) for monitoring C. elegans and the corresponding classification via a trained Histogram of Oriented Gradients (HOG) feature-based Support Vector Machine for the automatic detection of C. elegans. Evaluation showed classification sensitivity of 0.90 and specificity of 0.85, and thereby confirms the general practicability of the chosen approach.
Collapse
|
33
|
Sho1 and Msb2 Play Complementary but Distinct Roles in Stress Responses, Sexual Differentiation, and Pat hogenicity of Cryptococcus neoformans. Front Microbiol 2018; 9:2958. [PMID: 30564211 PMCID: PMC6288190 DOI: 10.3389/fmicb.2018.02958] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2018] [Accepted: 11/16/2018] [Indexed: 01/22/2023] Open
Abstract
The high-osmolarity glycerol response (HOG) pathway is pivotal in environmental stress response, differentiation, and virulence of Cryptococcus neoformans, which causes fatal meningoencephalitis. A putative membrane sensor protein, Sho1, has been postulated to regulate HOG pathway, but its regulatory mechanism remains elusive. In this study, we characterized the function of Sho1 with relation to the HOG pathway in C. neoformans. Sho1 played minor roles in osmoresistance, thermotolerance, and maintenance of membrane integrity mainly in a HOG-independent manner. However, it was dispensable for cryostress resistance, primarily mediated through the HOG pathway. A mucin-like transmembrane (TM) protein, Msb2, which interacts with Sho1 in Saccharomyces cerevisiae, was identified in C. neoformans, but found not to interact with Sho1. MSB2 codeletion with SHO1 further decreased osmoresistance and membrane integrity, but not thermotolerance, of sho1Δ mutant, indicating that both factors play to some level redundant but also discrete roles in C. neoformans. Sho1 and Msb2 played redundant roles in promoting the filamentous growth in sexual differentiation in a Cpk1-independent manner, in contrast to the inhibitory effect of the HOG pathway in the process. However, both factors contributed independently to Cpk1 phosphorylation during vegetative growth and endoplasmic reticulum (ER) stress response. Finally, Sho1 and Msb2 play distinct but complementary roles in the pulmonary virulence of C. neoformans. Overall, Sho1 and Msb2 play complementary but distinct roles in stress response, differentiation, and pathogenicity of C. neoformans.
Collapse
|
34
|
Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs. J Med Syst 2018; 42:146. [PMID: 29959539 DOI: 10.1007/s10916-018-0991-9] [Citation(s) in RCA: 46] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2017] [Accepted: 06/12/2018] [Indexed: 01/05/2023]
Abstract
To detect pulmonary abnormalities such as Tuberculosis (TB), an automatic analysis and classification of chest radiographs can be used as a reliable alternative to more sophisticated and technologically demanding methods (e.g. culture or sputum smear analysis). In target areas like Kenya TB is highly prevalent and often co-occurring with HIV combined with low resources and limited medical assistance. In these regions an automatic screening system can provide a cost-effective solution for a large rural population. Our completely automatic TB screening system is processing the incoming CXRs (chest X-ray) by applying image preprocessing techniques to enhance the image quality followed by an adaptive segmentation based on model selection. The delineated lung regions are described by a multitude of image features. These characteristics are than optimized by a feature selection strategy to provide the best description for the classifier, which will later decide if the analyzed image is normal or abnormal. Our goal is to find the optimal feature set from a larger pool of generic image features, -used originally for problems such as object detection, image retrieval, etc. For performance evaluation measures such as under the curve (AUC) and accuracy (ACC) were considered. Using a neural network classifier on two publicly available data collections, -namely the Montgomery and the Shenzhen dataset, we achieved the maximum area under the curve and accuracy of 0.99 and 97.03%, respectively. Further, we compared our results with existing state-of-the-art systems and to radiologists' decision.
Collapse
|
35
|
Pure FPGA Implementation of an HOG Based Real-Time Pedestrian Detection System. SENSORS 2018; 18:s18041174. [PMID: 29649146 PMCID: PMC5948663 DOI: 10.3390/s18041174] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/07/2018] [Revised: 04/09/2018] [Accepted: 04/09/2018] [Indexed: 11/23/2022]
Abstract
In this study, we propose a real-time pedestrian detection system using a FPGA with a digital image sensor. Comparing with some prior works, the proposed implementation realizes both the histogram of oriented gradients (HOG) and the trained support vector machine (SVM) classification on a FPGA. Moreover, the implementation does not use any external memory or processors to assist the implementation. Although the implementation implements both the HOG algorithm and the SVM classification in hardware without using any external memory modules and processors, the proposed implementation’s resource utilization of the FPGA is lower than most of the prior art. The main reasons resulting in the lower resource usage are: (1) simplification in the Getting Bin sub-module; (2) distributed writing and two shift registers in the Cell Histogram Generation sub-module; (3) reuse of each sum of the cell histogram in the Block Histogram Normalization sub-module; and (4) regarding a window of the SVM classification as 105 blocks of the SVM classification. Moreover, compared to Dalal and Triggs’s pure software HOG implementation, the proposed implementation‘s average detection rate is just about 4.05% less, but can achieve a much higher frame rate.
Collapse
|
36
|
A Hybrid Vehicle Detection Method Based on Viola-Jones and HOG + SVM from UAV Images. SENSORS 2016; 16:s16081325. [PMID: 27548179 PMCID: PMC5017490 DOI: 10.3390/s16081325] [Citation(s) in RCA: 72] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/25/2016] [Revised: 08/05/2016] [Accepted: 08/15/2016] [Indexed: 11/24/2022]
Abstract
A new hybrid vehicle detection scheme which integrates the Viola-Jones (V-J) and linear SVM classifier with HOG feature (HOG + SVM) methods is proposed for vehicle detection from low-altitude unmanned aerial vehicle (UAV) images. As both V-J and HOG + SVM are sensitive to on-road vehicles’ in-plane rotation, the proposed scheme first adopts a roadway orientation adjustment method, which rotates each UAV image to align the roads with the horizontal direction so the original V-J or HOG + SVM method can be directly applied to achieve fast detection and high accuracy. To address the issue of descending detection speed for V-J and HOG + SVM, the proposed scheme further develops an adaptive switching strategy which sophistically integrates V-J and HOG + SVM methods based on their different descending trends of detection speed to improve detection efficiency. A comprehensive evaluation shows that the switching strategy, combined with the road orientation adjustment method, can significantly improve the efficiency and effectiveness of the vehicle detection from UAV images. The results also show that the proposed vehicle detection method is competitive compared with other existing vehicle detection methods. Furthermore, since the proposed vehicle detection method can be performed on videos captured from moving UAV platforms without the need of image registration or additional road database, it has great potentials of field applications. Future research will be focusing on expanding the current method for detecting other transportation modes such as buses, trucks, motors, bicycles, and pedestrians.
Collapse
|
37
|
Facial expression recognition and histograms of oriented gradients: a comprehensive study. SPRINGERPLUS 2015; 4:645. [PMID: 26543779 PMCID: PMC4628009 DOI: 10.1186/s40064-015-1427-3] [Citation(s) in RCA: 86] [Impact Index Per Article: 9.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/24/2015] [Accepted: 10/12/2015] [Indexed: 11/26/2022]
Abstract
Automatic facial expression recognition (FER) is a topic of growing interest mainly due to the rapid spread of assistive technology applications, as human–robot interaction, where a robust emotional awareness is a key point to best accomplish the assistive task. This paper proposes a comprehensive study on the application of histogram of oriented gradients (HOG) descriptor in the FER problem, highlighting as this powerful technique could be effectively exploited for this purpose. In particular, this paper highlights that a proper set of the HOG parameters can make this descriptor one of the most suitable to characterize facial expression peculiarities. A large experimental session, that can be divided into three different phases, was carried out exploiting a consolidated algorithmic pipeline. The first experimental phase was aimed at proving the suitability of the HOG descriptor to characterize facial expression traits and, to do this, a successful comparison with most commonly used FER frameworks was carried out. In the second experimental phase, different publicly available facial datasets were used to test the system on images acquired in different conditions (e.g. image resolution, lighting conditions, etc.). As a final phase, a test on continuous data streams was carried out on-line in order to validate the system in real-world operating conditions that simulated a real-time human–machine interaction.
Collapse
|
38
|
Cadmium induces the activation of cell wall integrity pathway in budding yeast. Chem Biol Interact 2015; 240:316-23. [PMID: 26362500 DOI: 10.1016/j.cbi.2015.09.007] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2015] [Revised: 08/07/2015] [Accepted: 09/02/2015] [Indexed: 11/20/2022]
Abstract
MAP kinases are important signaling molecules regulating cell survival, proliferation and differentiation, and can be activated by cadmium stress. In this study, we demonstrate that cadmium induces phosphorylation of the yeast cell wall integrity (CWI) pathway_MAP kinase Slt2, and this cadmium-induced CWI activation is mediated by the cell surface sensor Mid2 through the GEF Rom1, the central regulator Rho1 and Bck1. Nevertheless, cadmium stress does not affect the subcellular localization of Slt2 proteins. In addition, this cadmium-induced CWI activation is independent on the calcium/calcineurin signaling and the high osmolarity glycerol (HOG) signaling pathways in yeast cells. Furthermore, we tested the cadmium sensitivity of 42 paired double-gene deletion mutants between six CWI components and seven components of the HOG pathway. Our results indicate that the CWI pathway is epistatic to the HOG pathway in cadmium sensitivity. However, gene deletion mutations for the Swi4/Swi6 transcription factor complex show synergistic effects with mutations of HOG components in cadmium sensitivity.
Collapse
|
39
|
Detection and segmentation of virus plaque using HOG and SVM: toward automatic plaque assay. Biomed Mater Eng 2014; 24:3187-98. [PMID: 25227027 DOI: 10.3233/bme-141140] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Plaque assaying, measurement of the number, diameter, and area of plaques in a Petri dish image, is a standard procedure gauging the concentration of phage in biology. This paper presented a novel and effective method for implementing automatic plaque assaying. The method was mainly comprised of the following steps: In the training stage, after pre-processing the images for noise suppression, an initial training set was readied by sampling positive (with a plaque at the center) and negative (plaque-free) patches from the training images, and extracting the HOG features from each patch. The linear SVM classifier was trained in a self-learnt supervised learning strategy to avoid possible missing detection. Specifically, the training set which contained positive and negative patches sampled manually from training images was used to train the preliminary classifier which exhaustively searched the training images to predict the label for the unlabeled patches. The mislabeled patches were evaluated by experts and relabeled. And all the newly labeled patches and their corresponding HOG features were added to the initial training set to train the final classifier. In the testing stage, a sliding-window technique was first applied to the unseen image for obtaining HOG features, which were inputted into the classifier to predict whether the patch was positive. Second, a locally adaptive Otsu method was performed on the positive patches to segment the plaques. Finally, after removing the outliers, the parameters of the plaques were measured in the segmented plaques. The experimental results demonstrated that the accuracy of the proposed method was similar to the one measured manually by experts, but it took less than 30 seconds.
Collapse
|
40
|
Calculation of melatonin and resveratrol effects on steatosis hepatis using soft computing methods. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2013; 111:498-506. [PMID: 23746907 DOI: 10.1016/j.cmpb.2013.04.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/04/2012] [Revised: 03/19/2013] [Accepted: 04/19/2013] [Indexed: 06/02/2023]
Abstract
In this work, beneficial effects of melatonin and resveratrol drugs on liver damage in rats, induced by application of acute and chronic carbon tetrachloride (CCl4) have been examined. The study consists of three main stages: (1) DATA ACQUISITION: light microscopic images were obtained from 60 rats separated into 10 groups after the preparation of liver tissue samples for histological examination. Rats in first five experimental groups for the four-day and the other five groups for twenty-day were examined. (2) Data processing: by the help of histograms of oriented gradient (HOG) method, obtaining low-dimensional image features (color, shape and texture) and classifying five different group characteristics by using these features with artificial neural networks (ANNs), and support vector machines (SVMs) have been provided. (3) Calculation of drug effectiveness: firstly to determine the differences between group characteristics of rats, a pilot group has been selected (diseased group-CCl4), and the responses of ANN and SVM trained by HOG features have been calculated. As a result of ANN, it has been seen that melatonin and resveratrol drugs have %65.62-%75.12 positive effects at the end of the fourth day, %84.12-%98.89 positive effects on healing steatosis hepatis at the end of the twentieth day respectively and as a result of SVM, it has been seen that melatonin and resveratrol drugs have %62.5-%68.75 positive effects at the end of the fourth day, %45.12-%60.89 positive effects on healing steatosis hepatis at the end of the twentieth day respectively.
Collapse
|