Convolutional neural network-based classification and monitoring models for lung cancer detection: 3D perspective approach

Recent developments in technology and research have offered a wide variety of new techniques for image and data analysis within the medical field. Medical research helps doctors and researchers acquire not only knowledge about health and new diseases, but also techniques of prevention and treatment. In particular, radiomic analysis is mainly used to extract quantitative data from medical images and to build a model strong enough to diagnose focal diseases. However, finding a model capable to fit all patient situations is not an easy task. In this paper frame prediction models and classification models are reported in order to predict the evolution of a given data series and determine whether an anomaly exists or not. This article also shows how to build and make use of a convolutional neural network-based architecture aiming to accomplish prediction task for medical images, not only using common computer tomography scans, but also 3D volumes.

CatSight, a direct path to proper multi-variate time series change detection: perceiving a concept drift through common spatial pattern

Detecting changes in data streams, with the data flowing continuously, is an important problem which Industry 4.0 has to deal with. In industrial monitoring, the data distribution may vary after a change in the machine’s operating point; this situation is known as concept drift, and it is key to detecting this change. One drawback of conventional machine learning algorithms is that they are usually static, trained offline, and require monitoring at the input level. A change in the distribution of data, in the relationship between the input and the output data, would result in the deterioration of the predictive performance of the models due to the lack of an ability to generalize the model to new concepts. Drift detecting methods emerge as a solution to identify the concept drift in the data. This paper proposes a new approach for concept drift detection—a novel approach to deal with sudden or abrupt drift, the most common drift found in industrial processes-, called CatSight. Briefly, this method is composed of two steps: (i) Use of Common Spatial Patterns (a statistical approach to deal with data streaming, closely related to Principal Component Analysis) to maximize the difference between two different distributions of a multivariate temporal data, and (ii) Machine Learning conventional algorithms to detect whether a change in the data flow has been occurred or not. The performance of the CatSight method, has been evaluated on a real use case, training six state of the art Machine Learning (ML) classifiers; obtained results indicate how adequate the new approach is.

RANSAC for Robotic Applications: A Survey

Random Sample Consensus, most commonly abbreviated as RANSAC, is a robust estimation method for the parameters of a model contaminated by a sizable percentage of outliers. In its simplest form, the process starts with a sampling of the minimum data needed to perform an estimation, followed by an evaluation of its adequacy, and further repetitions of this process until some stopping criterion is met. Multiple variants have been proposed in which this workflow is modified, typically tweaking one or several of these steps for improvements in computing time or the quality of the estimation of the parameters. RANSAC is widely applied in the field of robotics, for example, for finding geometric shapes (planes, cylinders, spheres, etc.) in cloud points or for estimating the best transformation between different camera views. In this paper, we present a review of the current state of the art of RANSAC family methods with a special interest in applications in robotics.

Sign language recognition by means of common spatial patterns: An analysis

Currently there are around 466 million hard of hearing people and this amount is expected to grow in the coming years. Despite the efforts that have been made, there is a communication barrier between deaf and hard of hearing signers and non-signers in environments without an interpreter. Different approaches have been developed lately to try to deal with this issue. In this work, we present an Argentinian Sign Language (LSA) recognition system which uses hand landmarks extracted from videos of the LSA64 dataset in order to distinguish between different signs. Different features are extracted from the signals created with the hand landmarks values, which are first transformed by the Common Spatial Patterns (CSP) algorithm. CSP is a dimensionality reduction algorithm and it has been widely used for EEG systems. The features extracted from the transformed signals have been then used to feed different classifiers, such as Random Forest (RF), K-Nearest Neighbors (KNN) or Multilayer Perceptron (MLP). Several experiments have been performed from which promising results have been obtained, achieving accuracy values between 0.90 and 0.95 on a set of 42 signs.

Brain Mapping of Behavioral Domains Using Multi-Scale Networks and Canonical Correlation Analysis

Simultaneous mapping of multiple behavioral domains into brain networks remains a major challenge. Here, we shed some light on this problem by employing a combination of machine learning, structural and functional brain networks at different spatial resolutions (also known as scales), together with performance scores across multiple neurobehavioral domains, including sensation, motor skills, and cognition. Provided by the Human Connectome Project, we make use of three cohorts: 640 participants for model training, 160 subjects for validation, and 200 subjects for model performance testing thus enhancing prediction generalization. Our modeling consists of two main stages, namely dimensionality reduction in brain network features at multiple scales, followed by canonical correlation analysis, which determines an optimal linear combination of connectivity features to predict multiple behavioral performance scores. To assess the differences in the predictive power of each modality, we separately applied three different strategies: structural unimodal, functional unimodal, and multimodal, that is, structural in combination with functional features of the brain network. Our results show that the multimodal association outperforms any of the unimodal analyses. Then, to answer which human brain structures were most involved in predicting multiple behavioral scores, we simulated different synthetic scenarios in which in each case we completely deleted a brain structure or a complete resting state network, and recalculated performance in its absence. In deletions, we found critical structures to affect performance when predicting single behavioral domains, but this occurred in a lesser manner for prediction of multi-domain behavior. Overall, our results confirm that although there are synergistic contributions between brain structure and function that enhance behavioral prediction, brain networks may also be mutually redundant in predicting multidomain behavior, such that even after deletion of a structure, the connectivity of the others can compensate for its lack in predicting behavior.

A Cyber-Physical Data Collection System Integrating Remote Sensing and Wireless Sensor Networks for Coffee Leaf Rust Diagnosis

Coffee Leaf Rust (CLR) is a fungal epidemic disease that has been affecting coffee trees around the world since the 1980s. The early diagnosis of CLR would contribute strategically to minimize the impact on the crops and, therefore, protect the farmers' profitability. In this research, a cyber-physical data-collection system was developed, by integrating Remote Sensing and Wireless Sensor Networks, to gather data, during the development of the CLR, on a test bench coffee-crop. The system is capable of automatically collecting, structuring, and locally and remotely storing reliable multi-type data from different field sensors, Red-Green-Blue (RGB) and multi-spectral cameras (RE and RGN). In addition, a data-visualization dashboard was implemented to monitor the data-collection routines in real-time. The operation of the data collection system allowed to create a three-month size dataset that can be used to train CLR diagnosis machine learning models. This result validates that the designed system can collect, store, and transfer reliable data of a test bench coffee-crop towards CLR diagnosis.

Measurement Time Reduction by Means of Mathematical Modeling of Enzyme Mediated RedOx Reaction in Food Samples Biosensors

The possibility of measuring in real time the different types of analytes present in food is becoming a requirement in food industry. In this context, biosensors are presented as an alternative to traditional analytical methodologies due to their specificity, high sensitivity and ability to work in real time. It has been observed that the behavior of the analysis curves of the biosensors follow a trend that is reproducible among all the measurements and that is specific to the reaction that occurs in the electrochemical cell and the analyte being analyzed. Kinetic reaction modeling is a widely used method to model processes that occur within the sensors, and this leads to the idea that a mathematical approximation can mimic the electrochemical reaction that takes place while the analysis of the sample is ongoing. For this purpose, a novel mathematical model is proposed to approximate the enzymatic reaction within the biosensor in real time, so the output of the measurement can be estimated in advance. The proposed model is based on adjusting an exponential decay model to the response of the biosensors using a nonlinear least-square method to minimize the error. The obtained results show that our proposed approach is capable of reducing about 40% the required measurement time in the sample analysis phase, while keeping the error rate low enough to meet the accuracy standards of the food industry.

3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts

Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone.

An Agave Counting Methodology Based on Mathematical Morphology and Images Acquired through Unmanned Aerial Vehicles

Blue agave is an important commercial crop in Mexico, and it is the main source of the traditional mexican beverage known as tequila. The variety of blue agave crop known as Tequilana Weber is a crucial element for tequila agribusiness and the agricultural economy in Mexico. The number of agave plants in the field is one of the main parameters for estimating production of tequila. In this manuscript, we describe a mathematical morphology-based algorithm that addresses the agave automatic counting task. The proposed methodology was applied to a set of real images collected using an Unmanned Aerial Vehicle equipped with a digital Red-Green-Blue (RGB) camera. The number of plants automatically identified in the collected images was compared to the number of plants counted by hand. Accuracy of the proposed algorithm depended on the size heterogeneity of plants in the field and illumination. Accuracy ranged from 0.8309 to 0.9806, and performance of the proposed algorithm was satisfactory.

Shedding Light on People Action Recognition in Social Robotics by Means of Common Spatial Patterns

Action recognition in robotics is a research field that has gained momentum in recent years. In this work, a video activity recognition method is presented, which has the ultimate goal of endowing a robot with action recognition capabilities for a more natural social interaction. The application of Common Spatial Patterns (CSP), a signal processing approach widely used in electroencephalography (EEG), is presented in a novel manner to be used in activity recognition in videos taken by a humanoid robot. A sequence of skeleton data is considered as a multidimensional signal and filtered according to the CSP algorithm. Then, characteristics extracted from these filtered data are used as features for a classifier. A database with 46 individuals performing six different actions has been created to test the proposed method. The CSP-based method along with a Linear Discriminant Analysis (LDA) classifier has been compared to a Long Short-Term Memory (LSTM) neural network, showing that the former obtains similar or better results than the latter, while being simpler.

ORdensity: user-friendly R package to identify differentially expressed genes

Background

Microarray technology provides the expression level of many genes. Nowadays, an important issue is to select a small number of informative differentially expressed genes that provide biological knowledge and may be key elements for a disease. With the increasing volume of data generated by modern biomedical studies, software is required for effective identification of differentially expressed genes. Here, we describe an R package, called ORdensity, that implements a recent methodology (Irigoien and Arenas, 2018) developed in order to identify differentially expressed genes. The benefits of parallel implementation are discussed.

Results

ORdensity gives the user the list of genes identified as differentially expressed genes in an easy and comprehensible way. The experimentation carried out in an off-the-self computer with the parallel execution enabled shows an improvement in run-time. This implementation may also lead to an important use of memory load. Results previously obtained with simulated and real data indicated that the procedure implemented in the package is robust and suitable for differentially expressed genes identification.

Conclusions

The new package, ORdensity, offers a friendly and easy way to identify differentially expressed genes, which is very useful for users not familiar with programming.

Availability

https://github.com/rsait/ORdensity

Video Activity Recognition: State-of-the-Art

Video activity recognition, although being an emerging task, has been the subject of important research efforts due to the importance of its everyday applications. Surveillance by video cameras could benefit greatly by advances in this field. In the area of robotics, the tasks of autonomous navigation or social interaction could also take advantage of the knowledge extracted from live video recording. The aim of this paper is to survey the state-of-the-art techniques for video activity recognition while at the same time mentioning other techniques used for the same task that the research community has known for several years. For each of the analyzed methods, its contribution over previous works and the proposed approach performance are discussed.

A hierarchical architecture for recognising intentionality in mental tasks on a brain-computer interface

A brain-computer interface (BCI), based on motor imagery EEG, uses information extracted from the electroencephalography signals generated by a person who intends to perform any action. One of the most important issues of current research is how to detect automatically whether the user intends to send some message to a certain device. This study presents a proposal, based on a hierarchical structured system, for recognising intentional and non-intentional mental tasks on a BCI system by applying machine learning techniques to the EEG signals. First-level clustering is performed to distinguish between intentional control (IC) and non-intentional control (NC) state patterns. Then, the patterns recognised as IC are passed on to a second stage where supervised learning techniques are used to classify them. In BCI applications, it is critical to correctly classify NC states with a low false positive rate (FPR) to avoid undesirable effects. According to the literature, we selected a maximum FPR of 10%. Under these conditions, our proposal achieved an average test accuracy of 66.6%, with an 8.2% FPR, for the BCI competition IIIa dataset. The main contribution of this paper is the hierarchical approach, based on machine learning paradigms, which performs intentional and non-intentional discrimination and, depending on the case, classifies the intended command selected by the user.

Natural multimodal communication for human–robot collaboration

This article presents a semantic approach for multimodal interaction between humans and industrial robots to enhance the dependability and naturalness of the collaboration between them in real industrial settings. The fusion of several interaction mechanisms is particularly relevant in industrial applications in which adverse environmental conditions might affect the performance of vision-based interaction (e.g. poor or changing lighting) or voice-based interaction (e.g. environmental noise). Our approach relies on the recognition of speech and gestures for the processing of requests, dealing with information that can potentially be contradictory or complementary. For disambiguation, it uses semantic technologies that describe the robot characteristics and capabilities as well as the context of the scenario. Although the proposed approach is generic and applicable in different scenarios, this article explains in detail how it has been implemented in two real industrial cases in which a robot and a worker collaborate in assembly and deburring operations.

Human–robot collaboration in industrial applications

Human–robot collaboration is a key factor for the development of factories of the future, a space in which humans and robots can work and carry out tasks together. Safety is one of the most critical aspects in this collaborative human–robot paradigm. This article describes the experiments done and results achieved by the authors in the context of the FourByThree project, aiming to measure the trust of workers on fenceless human–robot collaboration in industrial robotic applications as well as to gauge the acceptance of different interaction mechanisms between robots and human beings.

A Multi-Disciplinary Approach to Remote Sensing through Low-Cost UAVs

The use of Unmanned Aerial Vehicles (UAVs) based on remote sensing has generated low cost monitoring, since the data can be acquired quickly and easily. This paper reports the experience related to agave crop analysis with a low cost UAV. The data were processed by traditional photogrammetric flow and data extraction techniques were applied to extract new layers and separate the agave plants from weeds and other elements of the environment. Our proposal combines elements of photogrammetry, computer vision, data mining, geomatics and computer science. This fusion leads to very interesting results in agave control. This paper aims to demonstrate the potential of UAV monitoring in agave crops and the importance of information processing with reliable data flow.

Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech

In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an improvement of a bi-level multi-classifier system known as stacking generalization by means of an integration of an estimation of distribution algorithm (EDA) in the first layer to select the optimal subset from the standard base classifiers. The good performance of the proposed new paradigm was demonstrated over different configurations and datasets. First, several CSS stacking classifiers were constructed on the RekEmozio dataset, using some specific standard base classifiers and a total of 123 spectral, quality and prosodic features computed using in-house feature extraction algorithms. These initial CSS stacking classifiers were compared to other multi-classifier systems and the employed standard classifiers built on the same set of speech features. Then, new CSS stacking classifiers were built on RekEmozio using a different set of both acoustic parameters (extended version of the Geneva Minimalistic Acoustic Parameter Set (eGeMAPS)) and standard classifiers and employing the best meta-classifier of the initial experiments. The performance of these two CSS stacking classifiers was evaluated and compared. Finally, the new paradigm was tested on the well-known Berlin Emotional Speech database. We compared the performance of single, standard stacking and CSS stacking systems using the same parametrization of the second phase. All of the classifications were performed at the categorical level, including the six primary emotions plus the neutral one.

RGB-D, Laser and Thermal Sensor Fusion for People following in a Mobile Robot

Detecting and tracking people is a key capability for robots that operate in populated environments. In this paper, we used a multiple sensor fusion approach that combines three kinds of sensors in order to detect people using RGB-D vision, lasers and a thermal sensor mounted on a mobile platform. The Kinect sensor offers a rich data set at a significantly low cost, however, there are some limitations to its use in a mobile platform, mainly that the Kinect algorithms for people detection rely on images captured by a static camera. To cope with these limitations, this work is based on the combination of the Kinect and a Hokuyo laser and a thermopile array sensor. A real-time particle filter system merges the information provided by the sensors and calculates the position of the target, using probabilistic leg and thermal patterns, image features and optical flow to this end. Experimental results carried out with a mobile platform in a Science museum have shown that the combination of different sensory cues increases the reliability of the people following system.

ICGE: an R package for detecting relevant clusters and atypical units in gene expression

BACKGROUND

Gene expression technologies have opened up new ways to diagnose and treat cancer and other diseases. Clustering algorithms are a useful approach with which to analyze genome expression data. They attempt to partition the genes into groups exhibiting similar patterns of variation in expression level. An important problem associated with gene classification is to discern whether the clustering process can find a relevant partition as well as the identification of new genes classes. There are two key aspects to classification: the estimation of the number of clusters, and the decision as to whether a new unit (gene, tumor sample...) belongs to one of these previously identified clusters or to a new group.

RESULTS

ICGE is a user-friendly R package which provides many functions related to this problem: identify the number of clusters using mixed variables, usually found by applied biomedical researchers; detect whether the data have a cluster structure; identify whether a new unit belongs to one of the pre-identified clusters or to a novel group, and classify new units into the corresponding cluster. The functions in the ICGE package are accompanied by help files and easy examples to facilitate its use.

CONCLUSIONS

We demonstrate the utility of ICGE by analyzing simulated and real data sets. The results show that ICGE could be very useful to a broad research community.

Antibodies from patients with dengue viral infection mediate cellular cytotoxicity

Acute and late convalescent sera (collected at day 5 of disease onset and 1 year later) from dengue fever (DF) and dengue hemorrhagic fever/dengue shock syndrome (DHF/DSS) laboratory confirmed cases, were tested for antibody-dependent cell-mediated cytotoxicity (ADCC) activity using dengue 1 (DENV-1) or dengue 2 (DENV-2) infected cells as target. All patients experienced their first dengue virus (DENV) infection 20 years before. ADCC activity was detected in acute sera from DHF/DSS but not in sera from DF patients. However, 1 year after illness, ADCC activity was observed in all cases. This preliminary report represents one of the few studies of ADCC in dengue patients and suggests that ADCC could be implicated in dengue pathogenesis.

Carboxy-terminally truncated Dengue 4 virus envelope glycoprotein expressed in Pichia pastoris induced neutralizing antibodies and resistance to Dengue 4 virus challenge in mice

We have expressed a recombinant Dengue 4 virus envelope glycoprotein (E4rec), truncated at its C-terminus by 53 amino acids, in Pichia pastoris. The presence of E4rec was confirmed by Western-blot using anti-DEN 4 hyper immune mouse ascitic fluid. E4rec migrated during SDS-PAGE as a 64 kDa protein. Treatment with endoglycosidases showed that the E protein was modified by the addition of short mannose chains and the absence of hyperglycosylation. When administered to BALB-C mice, E4rec elicited a DEN 4 neutralizing antibody response haemagglutination inhibition antibodies and specific memory T cell response. Mice immunized were also significantly protected against lethal DEN 4 virus challenge (86.6%, p < 0.001).

Feature subset selection by genetic algorithms and estimation of distribution algorithms. A case study in the survival of cirrhotic patients treated with TIPS

The transjugular intrahepatic portosystemic shunt (TIPS) is an interventional treatment for cirrhotic patients with portal hypertension. In the light of our medical staff's experience, the consequences of TIPS are not homogeneous for all the patients and a subgroup dies in the first 6 months after TIPS placement. Actually, there is no risk indicator to identify this subgroup of patients before treatment. An investigation for predicting the survival of cirrhotic patients treated with TIPS is carried out using a clinical database with 107 cases and 77 attributes. Four supervised machine learning classifiers are applied to discriminate between both subgroups of patients. The application of several feature subset selection (FSS) techniques has significantly improved the predictive accuracy of these classifiers and considerably reduced the amount of attributes in the classification models. Among FSS techniques, FSS-TREE, a new randomized algorithm inspired on the new EDA (estimation of distribution algorithm) paradigm has obtained the best average accuracy results for each classifier.

A phase I clinical trial of a multi-epitope polypeptide TAB9 combined with Montanide ISA 720 adjuvant in non-HIV-1 infected human volunteers

A phase I clinical trial was performed to examine the safety and immunogenicity of a multi-epitope polypeptide comprising the central 15 amino acids of the V3 loop from six HIV-1 isolates. This protein called TAB9 was emulsified in Montanide ISA720 (Seppic, Paris) and administered intramuscularly at doses of 0, 0.2 and 1 mg to 24 healthy, HIV-1 seronegative adult males. Three immunisations were given at months 0, 1 and 6 in a randomised, double blind, placebo controlled clinical trial. The placebo was generally well tolerated. However, severe local reactions were observed in TAB9 vaccinated subjects after the second and third inoculations. Seven out of eight volunteers from the lower dose group showed moderate or severe local inflammation, while four out of eight subjects from the higher dose group developed granulomas and sterile abscesses. In general, the reactogenicity depended on the number of inoculations given and the dose of TAB9. Both doses were immunogenic, all immunised volunteers seroconverted and antibodies were broadly reactive against the V3 peptides included in the protein. All vaccine's sera reacted against gp120 in Western blot and 50% of them also neutralised at least one out of five laboratory isolates tested. No differences between doses were found. Anti TAB9 lymphoproliferative responses were observed, being more intense in the high dose group. Due to the strong local reactions that were found in this study, a change in the formulation will be required for further trials with this vaccine candidate in humans.

Using Bayesian networks in the construction of a bi-level multi-classifier. A case study using intensive care unit patients data

Combining the predictions of a set of classifiers has shown to be an effective way to create composite classifiers that are more accurate than any of the component classifiers. There are many methods for combining the predictions given by component classifiers. We introduce a new method that combine a number of component classifiers using a Bayesian network as a classifier system given the component classifiers predictions. Component classifiers are standard machine learning classification algorithms, and the Bayesian network structure is learned using a genetic algorithm that searches for the structure that maximises the classification accuracy given the predictions of the component classifiers. Experimental results have been obtained on a datafile of cases containing information about ICU patients at Canary Islands University Hospital. The accuracy obtained using the presented new approach statistically improve those obtained using standard machine learning methods.

Predicting survival in malignant skin melanoma using Bayesian networks automatically induced by genetic algorithms. An empirical comparison between different approaches

In this work we introduce a methodology based on genetic algorithms for the automatic induction of Bayesian networks from a file containing cases and variables related to the problem. The structure is learned by applying three different methods: The Cooper and Herskovits metric for a general Bayesian network, the Markov blanket approach and the relaxed Markov blanket method. The methodologies are applied to the problem of predicting survival of people after 1, 3 and 5 years of being diagnosed as having malignant skin melanoma. The accuracy of the obtained models, measured in terms of the percentage of well-classified subjects, is compared to that obtained by the so-called Naive-Bayes. In the four approaches, the estimation of the model accuracy is obtained from the 10-fold cross-validation method.