An Intelligent System for Monitoring Skin Diseases

An evaluation of the effectiveness of 'ULTRACOL 200' in enhancing nasolabial fold wrinkles through cutaneous repair

BACKGROUND

Injectable filler, a nonsurgical beauty method, has gained popularity in rejuvenating sagging skin. In this study, polydioxanone (PDO) was utilized as the main component of the ULTRACOL200 filler that helps stimulate collagenesis and provide skin radiant effects. The study aimed to evaluate and compare the effectiveness of ULTRACOL200 with other commercialized products in visually improving dermatological problems.

METHODS

Herein, 31 participants aged between 20 and 59 years were enrolled in the study. 1 mL of the testing product, as well as the quantity for the compared groups was injected into each participants face side individually. Subsequently, skin texture and sunken volume of skin were measured using ANTERA 3D CS imaging technology at three periods: before the application, 4 weeks after the initial application, and 4 weeks after the 2nd application of ULTRACOL200.

RESULTS

The final results of skin texture and wrinkle volume evaluation consistently demonstrated significant enhancement. Consequently, subjective questionnaires were provided to the participants to evaluate the efficacy of the testing product, illustrating satisfactory responses after the twice applications.

CONCLUSION

The investigation has contributed substantially to the comprehension of a PDO-based filler (ULTRACOL200) for skin enhancement and provided profound insight for future clinical trials.

PMJAF-Net: Pyramidal multi-scale joint attention and adaptive fusion network for explainable skin lesion segmentation

Traditional convolutional neural networks have achieved remarkable success in skin lesion segmentation. However, the successive pooling operations and convolutional spans reduce the feature resolution and hinder the dense prediction for spatial information, resulting in blurred boundaries, low accuracy and poor interpretability for irregular lesion segmentation under low contrast. To solve the above issues, a pyramidal multi-scale joint attention and adaptive fusion network for explainable (PMJAF-Net) skin lesion segmentation is proposed. Firstly, an adaptive spatial attention module is designed to establish the long-term correlation between pixels, enrich the global and local contextual information, and refine the detailed features. Subsequently, an efficient pyramidal multi-scale channel attention module is proposed to capture the multi-scale information and edge features by using the pyramidal module. Meanwhile, a channel attention module is devised to establish the long-term correlation between channels and highlight the most related feature channels to capture the multi-scale key information on each channel. Thereafter, a multi-scale adaptive fusion attention module is put forward to efficiently fuse the scale features at different decoding stages. Finally, a novel hybrid loss function based on region salient features and boundary quality is presented to guide the network to learn from map-level, patch-level and pixel-level and to accurately predict the lesion regions with clear boundaries. In addition, visualizing attention weight maps are utilized to visually enhance the interpretability of our proposed model. Comprehensive experiments are conducted on four public skin lesion datasets, and the results demonstrate that the proposed network outperforms the state-of-the-art methods, with the segmentation assessment evaluation metrics Dice, JI, and ACC improved to 92.65%, 87.86% and 96.26%, respectively.

The Influence of a Fire at an Illegal Landfill in Southern Poland on the Formation of Toxic Compounds and Their Impact on the Natural Environment

Landfill fires pose a real threat to the environment as they cause the migration of pollutants to the atmosphere and water sources. A greater risk is observed in the case of wild landfills, which do not have adequate isolation from the ground. The aim of this article is to present the results of studies on the toxicity of waste from a fire in a landfill in Trzebinia (southern Poland). Both soil and waste samples were investigated. The samples were analyzed using the GC-MS method and the leachates using ICP-OES. A total of 32 samples of incinerated waste and soil were collected. The organic compounds included naphthalene, fluorene, phenanthrene, anthracene, acenaphthene, acenaphthylene, fluoranthene, pyrene, benzo (c) phenanthrene, benzo (a) anthracene, chrysene, benzo (ghi) fluoranthene, benzo (b + k) fluoranthene, benzo (a) fluoranthene, benzo (c) fluoranthene, benzo (a) pyrene, benzo (e) pyrene, perylene, indeno[1,2,3-cd] pyrene, benzo (ghi) perylene, and dibenzo (a + h) anthracene. Among the inorganic parameters, sulfates, chlorides, arsenic, boron, cadmium, copper, lead, and zinc were taken into account. Phenanthrene reached values exceeding 33 mg/L. Fluoranthene dominated in most of the samples. Sulfates and chlorides were present in the samples in concentrations exceeding 400 and 50 mg/L, respectively. Compounds contained in burnt waste may have a negative impact on soil and water health safety. Therefore, it is important to conduct research and counteract the negative effects of waste fires.

Analysis of Skin Cancer and Patient Healthcare Using Data Mining Techniques

Skin cancer is the uncontrolled growth of irregular cancer cells in the human-skin's outer layer. Skin cells commonly grow in an uneven pattern on exposed skin surfaces. The majority of melanomas, aside from this variety, form in areas that are rarely exposed to sunlight. Harmful sunlight, which results in a mutation in the DNA and irreparable DNA damage, is the primary cause of skin cancer. This demonstrates a close connection between skin cancer and molecular biology and genetics. Males and females both experience the same incidence rate. Avoiding revelation to ultraviolet (UV) emissions can lower the risk rate. This needed to be known about in order to be prevented from happening. To identify skin cancer, an improved image analysis technique was put forth in this work. The skin alterations are routinely monitored by this proposed skin cancer categorization approach. Therefore, early detection of suspicious skin changes can aid in the early discovery of skin cancer, increasing the likelihood of a favourable outcome. Due to the blessing of diagnostic technology and recent advancements in cancer treatment, the survival rate of patients with skin cancer has grown. The strategy for detecting skin cancer using image processing technologies is presented in this paper. The system receives the image of the skin lesion as an input and analyses it using cutting-edge image processing methods to determine whether skin cancer is present. The Lesion Image Analysis Tools use texture, size, and shape assessment for image segmentation and feature phases to check for various cancer criteria including asymmetries, borders, pigment, and diameter. The image is classified as Normal skin and a lesion caused by skin cancer using the derived feature parameters.

Skin Diseases Classification Using Hybrid AI Based Localization Approach

One of the most prevalent diseases that can be initially identified by visual inspection and further identified with the use of dermoscopic examination and other testing is skin cancer. Since eye observation provides the earliest opportunity for artificial intelligence to intercept various skin images, some skin lesion classification algorithms based on deep learning and annotated skin photos display improved outcomes. The researcher used a variety of strategies and methods to identify and stop diseases earlier. All of them yield positive results for identifying and categorizing diseases, but proper disease categorization is still lacking. Computer-aided diagnosis is one of the most crucial methods for more accurate disease detection, although it is rarely used in dermatology. For Feature Extraction, we introduced Spectral Centroid Magnitude (SCM). The given dataset is classified using an enhanced convolutional neural network; the first stage of preprocessing uses a median filter, and the final stage compares the accuracy results to the current method.

A Secure Framework toward IoMT-Assisted Data Collection, Modeling, and Classification for Intelligent Dermatology Healthcare Services

The abnormal growth of the skin cells is known as skin cancer. It is one of the main problems in the dermatology area. Skin lesions or malignancies have been a source of worry for many individuals in recent years. Irrespective of the skin tone, there exist three major classes of skin lesions, i.e., basal cell carcinoma, squamous cell carcinoma, and melanoma. The early diagnosis of these lesions is equally important for human life. In the proposed work, a secure IoMT-Assisted framework is introduced that can help the patients to do the initial screening of skin lesions remotely. The initially proposed approach uses an IoMT-based data collection device which is accessible by patients to capture skin lesions images. Next, the captured skin sample is encrypted and sent to the collected image toward cloud storage. Later, the received sample image is classified into appropriate class labels using an ensemble classifier. In the proposed framework, four CNN models were ensemble i.e., VGG-16, DenseNet-201, Inception-V3, and Efficient-B7. The framework has experimented with the "HAM10000" dataset having 7 different kinds of skin lesions data. Although DenseNet-201 performed well, the ensemble model provides the highest accuracy with 87.22 percent as well as its test loss/error is lower than others with 0.4131. Moreover, the ensemble model's classification ability is much higher with an AUC score of 0.9745. Moreover, A recommendation team has been assigned to assess the sample of the patient as well as suggest the patient according to classified results by the CAD.

Deep Learning Application for Effective Classification of Different Types of Psoriasis

Psoriasis is a chronic inflammatory skin disorder mediated by the immune response that affects a large number of people. According to latest worldwide statistics, 125 million individuals are suffering from psoriasis. Deep learning techniques have demonstrated success in the prediction of skin diseases and can also lead to the classification of different types of psoriasis. Hence, we propose a deep learning-based application for effective classification of five types of psoriasis namely, plaque, guttate, inverse, pustular, and erythrodermic as well as the prediction of normal skin. We used 172 images of normal skin from the BFL NTU dataset and 301 images of psoriasis from the Dermnet dataset. The input sample images underwent image preprocessing including data augmentation, enhancement, and segmentation which was followed by color, texture, and shape feature extraction. Two deep learning algorithms of convolutional neural network (CNN) and long short-term memory (LSTM) were applied with the classification models being trained with 80% of the images. The reported accuracies of CNN and LSTM are 84.2% and 72.3%, respectively. A paired sample T-test exhibited significant differences between the accuracies generated by the two deep learning algorithms with a $p<0.001$ . The accuracies reported from this study demonstrate potential of this deep learning application to be applied to other areas of dermatology for better prediction.

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

Multi skin lesions classification using fine-tuning and data-augmentation applying NASNet

Skin lesions are one of the typical symptoms of many diseases in humans and indicative of many types of cancer worldwide. Increased risks caused by the effects of climate change and a high cost of treatment, highlight the importance of skin cancer prevention efforts like this. The methods used to detect these diseases vary from a visual inspection performed by dermatologists to computational methods, and the latter has widely used automatic image classification applying Convolutional Neural Networks (CNNs) in medical image analysis in the last few years. This article presents an approach that uses CNNs with a NASNet architecture to recognize in a more accurate way, without segmentation, eight skin diseases. The model was trained end-to-end on Keras with augmented skin diseases images from the International Skin Imaging Collaboration (ISIC). The CNN architectures were initialized with weight from ImageNet, fine-tuned in order to discriminate well among the different types of skin lesions, and then 10-fold cross-validation was applied. Finally, some evaluation metrics are calculated as accuracy, sensitivity, and specificity and compare with other CNN trained architectures. This comparison shows that the proposed system offers higher accuracy results, with a significant reduction on the training paraments. To the best of our knowledge and based in the state-of-art recompiling in this work, the application of the NASNet architecture training with skin image lesion from ISIC archive for multi-class classification and evaluated by cross-validation, represents a novel skin disease classification system.

A Review of Lysimeter Experiments Carried Out on Municipal Landfill Waste

The groundwater risk assessment in the vicinity of landfill sites requires, among others, representative monitoring and testing for pollutants leaching from the waste. Lysimeter studies can serve as an example of dynamic leaching tests. However, due to the bacteriological composition of the municipal waste, they are rarely carried out. These tests allow for the proper design of the landfill protection system against migration of pollutants into the ground, assessment of bacteriological, biochemical and chemical risk for the groundwater, determination of the water balance of leachate as well as examination of the course of processes taking place in the waste landfill with a diversified access to oxygen. This paper addresses the issue of performing lysimeter studies on a sample of municipal waste in various scientific centers. It analyzes the size of lysimeters, their construction, the method of water supply, the duration of the experiment, the scope of research, and the purpose of lysimeter studies.

The Internet of Things: Impact and Implications for Health Care Delivery

The Internet of Things (IoT) is a system of wireless, interrelated, and connected digital devices that can collect, send, and store data over a network without requiring human-to-human or human-to-computer interaction. The IoT promises many benefits to streamlining and enhancing health care delivery to proactively predict health issues and diagnose, treat, and monitor patients both in and out of the hospital. Worldwide, government leaders and decision makers are implementing policies to deliver health care services using technology and more so in response to the novel COVID-19 pandemic. It is now becoming increasingly important to understand how established and emerging IoT technologies can support health systems to deliver safe and effective care. The aim of this viewpoint paper is to provide an overview of the current IoT technology in health care, outline how IoT devices are improving health service delivery, and outline how IoT technology can affect and disrupt global health care in the next decade. The potential of IoT-based health care is expanded upon to theorize how IoT can improve the accessibility of preventative public health services and transition our current secondary and tertiary health care to be a more proactive, continuous, and coordinated system. Finally, this paper will deal with the potential issues that IoT-based health care generates, barriers to market adoption from health care professionals and patients alike, confidence and acceptability, privacy and security, interoperability, standardization and remuneration, data storage, and control and ownership. Corresponding enablers of IoT in current health care will rely on policy support, cybersecurity-focused guidelines, careful strategic planning, and transparent policies within health care organizations. IoT-based health care has great potential to improve the efficiency of the health system and improve population health.

A Proposal of an Adaptive Neuro-Fuzzy Inference System for Modeling Experimental Data in Manufacturing Engineering

In Manufacturing Engineering there is a need to be able to model the behavior of technological variables versus input parameters in order to predict their behavior in advance, so that it is possible to determine the levels of variation that lead to optimal values of the response variables to be obtained. In recent years, it has been a common practice to rely on regression techniques to carry out the above-mentioned task. However, such models are sometimes not accurate enough to predict the behavior of these response variables, especially when they have significant non-linearities. In this present study a comparative analysis between the precision of different techniques based on conventional regression and soft computing is initially carried out. Specifically, regression techniques, based on the response surface model, as well as the use of artificial neural networks and fuzzy inference systems along with adaptive neuro-fuzzy inference systems will be employed to predict the behavior of the aforementioned technological variables. It will be shown that when there are difficulties in predicting the response parameters by using regression models, soft computing models are highly effective, being much more efficient than conventional regression models. In addition, a new method is proposed in this study that consists of using an iterative process to obtain a fuzzy inference system from a design of experiments and then using an adaptive neuro-fuzzy inference system for tuning the constants of the membership functions. As will be shown, with this method it is possible to obtain improved results in the validation metrics. The means of selecting the membership functions to develop this model from the design of experiments is discussed in this present study in order to obtain an initial solution, which will be then tuned by using an adaptive neuro-fuzzy inference system, to predict the behavior of the response variables. Moreover, the obtained results will also be compared.

Accuracy of Computer-Aided Diagnosis of Melanoma: A Meta-analysis

IMPORTANCE

The recent advances in the field of machine learning have raised expectations that computer-aided diagnosis will become the standard for the diagnosis of melanoma.

OBJECTIVE

To critically review the current literature and compare the diagnostic accuracy of computer-aided diagnosis with that of human experts.

DATA SOURCES

The MEDLINE, arXiv, and PubMed Central databases were searched to identify eligible studies published between January 1, 2002, and December 31, 2018.

STUDY SELECTION

Studies that reported on the accuracy of automated systems for melanoma were selected. Search terms included melanoma, diagnosis, detection, computer aided, and artificial intelligence.

DATA EXTRACTION AND SYNTHESIS

Evaluation of the risk of bias was performed using the QUADAS-2 tool, and quality assessment was based on predefined criteria. Data were analyzed from February 1 to March 10, 2019.

MAIN OUTCOMES AND MEASURES

Summary estimates of sensitivity and specificity and summary receiver operating characteristic curves were the primary outcomes.

RESULTS

The literature search yielded 1694 potentially eligible studies, of which 132 were included and 70 offered sufficient information for a quantitative analysis. Most studies came from the field of computer science. Prospective clinical studies were rare. Combining the results for automated systems gave a melanoma sensitivity of 0.74 (95% CI, 0.66-0.80) and a specificity of 0.84 (95% CI, 0.79-0.88). Sensitivity was lower in studies that used independent test sets than in those that did not (0.51; 95% CI, 0.34-0.69 vs 0.82; 95% CI, 0.77-0.86; P < .001); however, the specificity was similar (0.83; 95% CI, 0.71-0.91 vs 0.85; 95% CI, 0.80-0.88; P = .67). In comparison with dermatologists' diagnosis, computer-aided diagnosis showed similar sensitivities and a 10 percentage points lower specificity, but the difference was not statistically significant. Studies were heterogeneous and substantial risk of bias was found in all but 4 of the 70 studies included in the quantitative analysis.

CONCLUSIONS AND RELEVANCE

Although the accuracy of computer-aided diagnosis for melanoma detection is comparable to that of experts, the real-world applicability of these systems is unknown and potentially limited owing to overfitting and the risk of bias of the studies at hand.

Intrusion Detection Based on Device-Free Localization in the Era of IoT

Device-free localization (DFL) locates targets without being equipped with the attached devices, which is of great significance for intrusion detection or monitoring in the era of the Internet-of-Things (IoT). Aiming at solving the problems of low accuracy and low robustness in DFL approaches, in this paper, we first treat the RSS signal as an RSS-image matrix and conduct a process of eliminating the background to dig out the variation component with distinguished features. Then, we make use of these feature-rich images by formulating DFL as an image classification problem. Furthermore, a deep convolutional neural network (CNN) is designed to extract features automatically for classification. The localization performance of the proposed background elimination-based CNN (BE-CNN) scheme is validated with a real-world dataset of outdoor DFL. In addition, we also validate the robust performance of the proposal by conducting numerical experiments with different levels of noise. Experimental results demonstrate that the proposed scheme has an obvious advantage in terms of improving localization accuracy and robustness for DFL. Particularly, the BE-CNN can maintain the highest localization accuracy of 100%, even in noisy conditions when the SNR is over −5 dB. The BE-based methods can outperform all the corresponding raw data-based methods in terms of the localization accuracy. In addition, the proposed method can outperform the comparison methods, deep neural network with autoencoder, K-nearest-neighbor (KNN), support vector machines (SVM), etc., in terms of the localization accuracy and robustness.

A Multi-Agent Gamification System for Managing Smart Homes

Rapid development and conducted experiments in the field of the introduction the fifth generation of the mobile network standard allow for the flourishing of the Internet of Things. This is one of the most important reasons to design and test systems that can be implemented to increase the quality of our lives. In this paper, we propose a system model for managing tasks in smart homes using multi-agent solutions. The proposed solution organizes work and distributes tasks to individual family members. An additional advantage is the introduction of gamification, not only between household members, but also between families. The solution was tested to simulate the entire solution as well as the individual components that make up the system. The proposal is described with regard to the possibility of implementing smart homes in future projects.

Improving Accuracy of the Kalman Filter Algorithm in Dynamic Conditions Using ANN-Based Learning Module

Prediction algorithms enable computers to learn from historical data in order to make accurate decisions about an uncertain future to maximize expected benefit or avoid potential loss. Conventional prediction algorithms are usually based on a trained model, which is learned from historical data. However, the problem with such prediction algorithms is their inability to adapt to dynamic scenarios and changing conditions. This paper presents a novel learning to prediction model to improve the performance of prediction algorithms under dynamic conditions. In the proposed model, a learning module is attached to the prediction algorithm, which acts as a supervisor to monitor and improve the performance of the prediction algorithm continuously by analyzing its output and considering external factors that may have an influence on its performance. To evaluate the effectiveness of the proposed learning to prediction model, we have developed the artificial neural network (ANN)-based learning module to improve the prediction accuracy of the Kalman filter algorithm as a case study. For experimental analysis, we consider a scenario where the Kalman filter algorithm is used to predict actual temperature from noisy sensor readings. the Kalman filter algorithm uses fixed process error covariance R, which is not suitable for dynamic situations where the error in sensor readings varies due to some external factors. In this study, we assume variable error in temperature sensor readings due to the changing humidity level. We have developed a learning module based on ANN to estimate the amount of error in current readings and to update R in the Kalman filter accordingly. Through experiments, we observed that the Kalman filter with the learning module performed better (4.41%–11.19%) than the conventional Kalman filter algorithm in terms of the root mean squared error metric.

Joint Node Selection and Resource Allocation for Task Offloading in Scalable Vehicle-Assisted Multi-Access Edge Computing

The resource limitation of multi-access edge computing (MEC) is one of the major issues in order to provide low-latency high-reliability computing services for Internet of Things (IoT) devices. Moreover, with the steep rise of task requests from IoT devices, the requirement of computation tasks needs dynamic scalability while using the potential of offloading tasks to mobile volunteer nodes (MVNs). We, therefore, propose a scalable vehicle-assisted MEC (SVMEC) paradigm, which cannot only relieve the resource limitation of MEC but also enhance the scalability of computing services for IoT devices and reduce the cost of using computing resources. In the SVMEC paradigm, a MEC provider can execute its users’ tasks by choosing one of three ways: (i) Do itself on local MEC, (ii) offload to the remote cloud, and (iii) offload to the MVNs. We formulate the problem of joint node selection and resource allocation as a Mixed Integer Nonlinear Programming (MINLP) problem, whose major objective is to minimize the total computation overhead in terms of the weighted-sum of task completion time and monetary cost for using computing resources. In order to solve it, we adopt alternative optimization techniques by decomposing the original problem into two sub-problems: Resource allocation sub-problem and node selection sub-problem. Simulation results demonstrate that our proposed scheme outperforms the existing schemes in terms of the total computation overhead.

High Precision Detection of Salient Objects Based on Deep Convolutional Networks with Proper Combinations of Shallow and Deep Connections

In this paper, a high precision detection method of salient objects is presented based on deep convolutional networks with proper combinations of shallow and deep connections. In order to achieve better performance in the extraction of deep semantic features of salient objects, based on a symmetric encoder and decoder architecture, an upgrade of backbone networks is carried out with a transferable model on the ImageNet pre-trained ResNet50. Moreover, by introducing shallow and deep connections on multiple side outputs, feature maps generated from various layers of the deep neural network (DNN) model are well fused so as to describe salient objects from local and global aspects comprehensively. Afterwards, based on a holistically nested edge detector (HED) architecture, multiple fused side outputs with various sizes of receptive fields are integrated to form detection results of salient objects accordingly. A series of experiments and assessments on extensive benchmark datasets demonstrate the dominant performance of our DNN model for the detection of salient objects in accuracy, which has outperformed those of other published works.

AD or Non-AD: A Deep Learning Approach to Detect Advertisements from Magazines

The processing and analyzing of multimedia data has become a popular research topic due to the evolution of deep learning. Deep learning has played an important role in addressing many challenging problems, such as computer vision, image recognition, and image detection, which can be useful in many real-world applications. In this study, we analyzed visual features of images to detect advertising images from scanned images of various magazines. The aim is to identify key features of advertising images and to apply them to real-world application. The proposed work will eventually help improve marketing strategies, which requires the classification of advertising images from magazines. We employed convolutional neural networks to classify scanned images as either advertisements or non-advertisements (i.e., articles). The results show that the proposed approach outperforms other classifiers and the related work in terms of accuracy.

Developing Secure IoT Services: A Security-Oriented Review of IoT Platforms

Undoubtedly, the adoption of the Internet of Things (IoT) paradigm has impacted on our every-day life, surrounding us with smart objects. Thus, the potentialities of this new market attracted the industry, so that many enterprises developed their own IoT platforms aiming at helping IoT services’ developers. In the multitude of possible platforms, selecting the most suitable to implement a specific service is not straightforward, especially from a security perspective. This paper analyzes some of the most prominent proposals in the IoT platforms market-place, performing an in-depth security comparison using five common criteria. These criteria are detailed in sub-criteria, so that they can be used as a baseline for the development of a secure IoT service. Leveraging the knowledge gathered from our in-depth study, both researchers and developers may select the IoT platform which best fits their needs. Additionally, an IoT service for monitoring commercial flights is implemented in two previously analyzed IoT platforms, giving an adequate detail level to represent a solid guideline for future IoT developers.

A Comparison of Regularization Techniques in Deep Neural Networks

Artificial neural networks (ANN) have attracted significant attention from researchers because many complex problems can be solved by training them. If enough data are provided during the training process, ANNs are capable of achieving good performance results. However, if training data are not enough, the predefined neural network model suffers from overfitting and underfitting problems. To solve these problems, several regularization techniques have been devised and widely applied to applications and data analysis. However, it is difficult for developers to choose the most suitable scheme for a developing application because there is no information regarding the performance of each scheme. This paper describes comparative research on regularization techniques by evaluating the training and validation errors in a deep neural network model, using a weather dataset. For comparisons, each algorithm was implemented using a recent neural network library of TensorFlow. The experiment results showed that an autoencoder had the worst performance among schemes. When the prediction accuracy was compared, data augmentation and the batch normalization scheme showed better performance than the others.

Sequential Dual Attention: Coarse-to-Fine-Grained Hierarchical Generation for Image Captioning

Image caption generation is a fundamental task to build a bridge between image and its description in text, which is drawing increasing interest in artificial intelligence. Images and textual sentences are viewed as two different carriers of information, which are symmetric and unified in the same content of visual scene. The existing image captioning methods rarely consider generating a final description sentence in a coarse-grained to fine-grained way, which is how humans understand the surrounding scenes; and the generated sentence sometimes only describes coarse-grained image content. Therefore, we propose a coarse-to-fine-grained hierarchical generation method for image captioning, named SDA-CFGHG, to address the two problems above. The core of our SDA-CFGHG method is a sequential dual attention that is used to fuse different grained visual information with sequential means. The advantage of our SDA-CFGHG method is that it can achieve image captioning in a coarse-to-fine-grained way and the generated textual sentence can capture details of the raw image to some degree. Moreover, we validate the impressive performance of our method on benchmark datasets—MS COCO, Flickr—with several popular evaluation metrics—CIDEr, SPICE, METEOR, ROUGE-L, and BLEU.

Deep Refinement Network for Natural Low-Light Image Enhancement in Symmetric Pathways

Due to the cost limitation of camera sensors, images captured in low-light environments often suffer from low contrast and multiple types of noise. A number of algorithms have been proposed to improve contrast and suppress noise in the input low-light images. In this paper, a deep refinement network, LL-RefineNet, is built to learn from the synthetical dark and noisy training images, and perform image enhancement for natural low-light images in symmetric—forward and backward—pathways. The proposed network utilizes all the useful information from the down-sampling path to produce the high-resolution enhancement result, where global features captured from deeper layers are gradually refined using local features generated by earlier convolutions. We further design the training loss for mixed noise reduction. The experimental results show that the proposed LL-RefineNet outperforms the comparative methods both qualitatively and quantitatively with fast processing speed on both synthetic and natural low-light image datasets.