HVDROPDB datasets for research in retinopathy of prematurity.

Retinopathy of prematurity (ROP) is a retinal disorder that may bring about blindness in preterm infants. Early detection and treatment of ROP can prevent this blindness. The gold standard technique for ROP screening is indirect ophthalmoscopy performed by ophthalmologists. The scarcity of medical professionals and inter-observer heterogeneity in ROP grading are two of the screening concerns. Researchers employ artificial intelligence (AI) driven ROP screening systems to assist medical experts. A major hurdle in developing these systems is the unavailability of annotated data sets of fundus images. Anatomical landmarks in the retina, such as the optic disc, macula, blood vessels, and ridge, are used to identify ROP characteristics. HVDROPDB is the first dataset to be published for the retinal structure segmentation of fundus images of preterm infants. It is prepared from two diverse imaging systems on the Indian population for segmenting the lesions mentioned above and annotated by a group of ROP experts. Each dataset contains retinal fundus images of premature infants with the ground truths prepared manually to assist researchers in developing explainable automated screening systems.

Machine learning for cognitive behavioral analysis: datasets, methods, paradigms, and research directions.

Human behaviour reflects cognitive abilities. Human cognition is fundamentally linked to the different experiences or characteristics of consciousness/emotions, such as joy, grief, anger, etc., which assists in effective communication with others. Detection and differentiation between thoughts, feelings, and behaviours are paramount in learning to control our emotions and respond more effectively in stressful circumstances. The ability to perceive, analyse, process, interpret, remember, and retrieve information while making judgments to respond correctly is referred to as Cognitive Behavior. After making a significant mark in emotion analysis, deception detection is one of the key areas to connect human behaviour, mainly in the forensic domain. Detection of lies, deception, malicious intent, abnormal behaviour, emotions, stress, etc., have significant roles in advanced stages of behavioral science. Artificial Intelligence and Machine learning (AI/ML) has helped a great deal in pattern recognition, data extraction and analysis, and interpretations. The goal of using AI and ML in behavioral sciences is to infer human behaviour, mainly for mental health or forensic investigations. The presented work provides an extensive review of the research on cognitive behaviour analysis. A parametric study is presented based on different physical characteristics, emotional behaviours, data collection sensing mechanisms, unimodal and multimodal datasets, modelling AI/ML methods, challenges, and future research directions.

Integrative gene expression analysis for the diagnosis of Parkinson's disease using machine learning and explainable AI.

Parkinson's disease (PD) is a progressive neurodegenerative disorder. Various symptoms and diagnostic tests are used in combination for the diagnosis of PD; however, accurate diagnosis at early stages is difficult. Blood-based markers can support physicians in the early diagnosis and treatment of PD. In this study, we used Machine Learning (ML) based methods for the diagnosis of PD by integrating gene expression data from different sources and applying explainable artificial intelligence (XAI) techniques to find the significant set of gene features contributing to diagnosis. We utilized the Least Absolute Shrinkage and Selection Operator (LASSO), and Ridge regression for the feature selection process. We utilized state-of-the-art ML techniques for the classification of PD cases and healthy controls. Logistic regression and Support Vector Machine showed the highest diagnostic accuracy. SHapley Additive exPlanations (SHAP) based global interpretable model-agnostic XAI method was utilized for the interpretation of the Support Vector Machine model. A set of significant biomarkers that contributed to the diagnosis of PD were identified. Some of these genes are associated with other neurodegenerative diseases. Our results suggest that the utilization of XAI can be useful in making early therapeutic decisions for the treatment of PD. The integration of datasets from different sources made this model robust. We believe that this research article will be of interest to clinicians as well as computational biologists in translational research.

A systematic review of privacy-preserving methods deployed with blockchain and federated learning for the telemedicine.

The unexpected and rapid spread of the COVID-19 pandemic has amplified the acceptance of remote healthcare systems such as telemedicine. Telemedicine effectively provides remote communication, better treatment recommendation, and personalized treatment on demand. It has emerged as the possible future of medicine. From a privacy perspective, secure storage, preservation, and controlled access to health data with consent are the main challenges to the effective deployment of telemedicine. It is paramount to fully overcome these challenges to integrate the telemedicine system into healthcare. In this regard, emerging technologies such as blockchain and federated learning have enormous potential to strengthen the telemedicine system. These technologies help enhance the overall healthcare standard when applied in an integrated way. The primary aim of this study is to perform a systematic literature review of previous research on privacy-preserving methods deployed with blockchain and federated learning for telemedicine. This study provides an in-depth qualitative analysis of relevant studies based on the architecture, privacy mechanisms, and machine learning methods used for data storage, access, and analytics. The survey allows the integration of blockchain and federated learning technologies with suitable privacy techniques to design a secure, trustworthy, and accurate telemedicine model with a privacy guarantee.

How Well Do Self-Supervised Models Transfer to Medical Imaging?

Self-supervised learning approaches have seen success transferring between similar medical imaging datasets, however there has been no large scale attempt to compare the transferability of self-supervised models against each other on medical images. In this study, we compare the generalisability of seven self-supervised models, two of which were trained in-domain, against supervised baselines across eight different medical datasets. We find that ImageNet pretrained self-supervised models are more generalisable than their supervised counterparts, scoring up to 10% better on medical classification tasks. The two in-domain pretrained models outperformed other models by over 20% on in-domain tasks, however they suffered significant loss of accuracy on all other tasks. Our investigation of the feature representations suggests that this trend may be due to the models learning to focus too heavily on specific areas.

A comprehensive survey on computational learning methods for analysis of gene expression data.

Computational analysis methods including machine learning have a significant impact in the fields of genomics and medicine. High-throughput gene expression analysis methods such as microarray technology and RNA sequencing produce enormous amounts of data. Traditionally, statistical methods are used for comparative analysis of gene expression data. However, more complex analysis for classification of sample observations, or discovery of feature genes requires sophisticated computational approaches. In this review, we compile various statistical and computational tools used in analysis of expression microarray data. Even though the methods are discussed in the context of expression microarrays, they can also be applied for the analysis of RNA sequencing and quantitative proteomics datasets. We discuss the types of missing values, and the methods and approaches usually employed in their imputation. We also discuss methods of data normalization, feature selection, and feature extraction. Lastly, methods of classification and class discovery along with their evaluation parameters are described in detail. We believe that this detailed review will help the users to select appropriate methods for preprocessing and analysis of their data based on the expected outcome.

Machine learning techniques and older adults processing of online information and misinformation: A covid 19 study.

This study is informed by two research gaps. One, Artificial Intelligence's (AI's) Machine Learning (ML) techniques have the potential to help separate information and misinformation, but this capability has yet to be empirically verified in the context of COVID-19. Two, while older adults can be particularly susceptible to the virus as well as its online infodemic, their information processing behaviour amid the pandemic has not been understood. Therefore, this study explores and understands how ML techniques (Study 1), and humans, particularly older adults (Study 2), process the online infodemic regarding COVID-19 prevention and cure. Study 1 employed ML techniques to classify information and misinformation. They achieved a classification accuracy of 86.7% with the Decision Tree classifier, and 86.67% with the Convolutional Neural Network model. Study 2 then investigated older adults' information processing behaviour during the COVID-19 infodemic period using some of the posts from Study 1. Twenty older adults were interviewed. They were found to be more willing to trust traditional media rather than new media. They were often left confused about the veracity of online content related to COVID-19 prevention and cure. Overall, the paper breaks new ground by highlighting how humans' information processing differs from how algorithms operate. It offers fresh insights into how during a pandemic, older adults-a vulnerable demographic segment-interact with online information and misinformation. On the methodological front, the paper represents an intersection of two very disparate paradigms-ML techniques and interview data analyzed using thematic analysis and concepts drawn from grounded theory to enrich the scholarly understanding of human interaction with cutting-edge technologies.

Employing Multimodal Machine Learning for Stress Detection.

In the current information age, the human lifestyle has become more knowledge-oriented, leading to sedentary employment. This has given rise to a number of health and mental disorders. Mental wellness is one of the most neglected, however crucial, aspects of today's fast-paced world. Mental health issues can, both directly and indirectly, affect other sections of human physiology and impede an individual's day-to-day activities and performance. However, identifying the stress and finding the stress trend for an individual that may lead to serious mental ailments is challenging and involves multiple factors. Such identification can be achieved accurately by fusing these multiple modalities (due to various factors) arising from a person's behavioral patterns. Specific techniques are identified in the literature for this purpose; however, very few machine learning-based methods are proposed for such multimodal fusion tasks. In this work, a multimodal AI-based framework is proposed to monitor a person's working behavior and stress levels. We propose a methodology for efficiently detecting stress due to workload by concatenating heterogeneous raw sensor data streams (e.g., face expressions, posture, heart rate, and computer interaction). This data can be securely stored and analyzed to understand and discover personalized unique behavioral patterns leading to mental strain and fatigue. The contribution of this work is twofold: firstly, proposing a multimodal AI-based strategy for fusion to detect stress and its level and, secondly, identifying a stress pattern over a period of time. We were able to achieve 96.09% accuracy on the test set in stress detection and classification. Further, we were able to reduce the stress scale prediction model loss to 0.036 using these modalities. This work can prove important for the community at large, specifically those working sedentary jobs, to monitor and identify stress levels, especially in current times of COVID-19.

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions.

The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models' performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

Incremental learning of LSTM framework for sensor fusion in attitude estimation.

This paper presents a novel method for attitude estimation of an object in 3D space by incremental learning of the Long-Short Term Memory (LSTM) network. Gyroscope, accelerometer, and magnetometer are few widely used sensors in attitude estimation applications. Traditionally, multi-sensor fusion methods such as the Extended Kalman Filter and Complementary Filter are employed to fuse the measurements from these sensors. However, these methods exhibit limitations in accounting for the uncertainty, unpredictability, and dynamic nature of the motion in real-world situations. In this paper, the inertial sensors data are fed to the LSTM network which are then updated incrementally to incorporate the dynamic changes in motion occurring in the run time. The robustness and efficiency of the proposed framework is demonstrated on the dataset collected from a commercially available inertial measurement unit. The proposed framework offers a significant improvement in the results compared to the traditional method, even in the case of a highly dynamic environment. The LSTM framework-based attitude estimation approach can be deployed on a standard AI-supported processing module for real-time applications.

Assistive Framework for Automatic Detection of All the Zones in Retinopathy of Prematurity Using Deep Learning.

Retinopathy of prematurity (ROP) is a potentially blinding disorder seen in low birth weight preterm infants. In India, the burden of ROP is high, with nearly 200,000 premature infants at risk. Early detection through screening and treatment can prevent this blindness. The automatic screening systems developed so far can detect "severe ROP" or "plus disease," but this information does not help schedule follow-up. Identifying vascularized retinal zones and detecting the ROP stage is essential for follow-up or discharge from screening. There is no automatic system to assist these crucial decisions to the best of the authors' knowledge. The low contrast of images, incompletely developed vessels, macular structure, and lack of public data sets are a few challenges in creating such a system. In this paper, a novel method using an ensemble of "U-Network" and "Circle Hough Transform" is developed to detect zones I, II, and III from retinal images in which macula is not developed. The model developed is generic and trained on mixed images of different sizes. It detects zones in images of variable sizes captured by two different imaging systems with an accuracy of 98%. All images of the test set (including the low-quality images) are considered. The time taken for training was only 14 min, and a single image was tested in 30 ms. The present study can help medical experts interpret retinal vascular status correctly and reduce subjective variation in diagnosis.

Stance detection with BERT embeddings for credibility analysis of information on social media.

The evolution of electronic media is a mixed blessing. Due to the easy access, low cost, and faster reach of the information, people search out and devour news from online social networks. In contrast, the increasing acceptance of social media reporting leads to the spread of fake news. This is a minacious problem that causes disputes and endangers the societal stability and harmony. Fake news spread has gained attention from researchers due to its vicious nature. proliferation of misinformation in all media, from the internet to cable news, paid advertising and local news outlets, has made it essential for people to identify the misinformation and sort through the facts. Researchers are trying to analyze the credibility of information and curtail false information on such platforms. Credibility is the believability of the piece of information at hand. Analyzing the credibility of fake news is challenging due to the intent of its creation and the polychromatic nature of the news. In this work, we propose a model for detecting fake news. Our method investigates the content of the news at the early stage i.e., when the news is published but is yet to be disseminated through social media. Our work interprets the content with automatic feature extraction and the relevance of the text pieces. In summary, we introduce stance as one of the features along with the content of the article and employ the pre-trained contextualized word embeddings BERT to obtain the state-of-art results for fake news detection. The experiment conducted on the real-world dataset indicates that our model outperforms the previous work and enables fake news detection with an accuracy of 95.32%.

Comparison of machine learning and deep learning techniques in promoter prediction across diverse species.

Gene promoters are the key DNA regulatory elements positioned around the transcription start sites and are responsible for regulating gene transcription process. Various alignment-based, signal-based and content-based approaches are reported for the prediction of promoters. However, since all promoter sequences do not show explicit features, the prediction performance of these techniques is poor. Therefore, many machine learning and deep learning models have been proposed for promoter prediction. In this work, we studied methods for vector encoding and promoter classification using genome sequences of three distinct higher eukaryotes viz. yeast (Saccharomyces cerevisiae), A. thaliana (plant) and human (Homo sapiens). We compared one-hot vector encoding method with frequency-based tokenization (FBT) for data pre-processing on 1-D Convolutional Neural Network (CNN) model. We found that FBT gives a shorter input dimension reducing the training time without affecting the sensitivity and specificity of classification. We employed the deep learning techniques, mainly CNN and recurrent neural network with Long Short Term Memory (LSTM) and random forest (RF) classifier for promoter classification at k-mer sizes of 2, 4 and 8. We found CNN to be superior in classification of promoters from non-promoter sequences (binary classification) as well as species-specific classification of promoter sequences (multiclass classification). In summary, the contribution of this work lies in the use of synthetic shuffled negative dataset and frequency-based tokenization for pre-processing. This study provides a comprehensive and generic framework for classification tasks in genomic applications and can be extended to various classification problems.

Cascaded Complementary Filter Architecture for Sensor Fusion in Attitude Estimation.

Attitude estimation is the process of computing the orientation angles of an object with respect to a fixed frame of reference. Gyroscope, accelerometer, and magnetometer are some of the fundamental sensors used in attitude estimation. The orientation angles computed from these sensors are combined using the sensor fusion methodologies to obtain accurate estimates. The complementary filter is one of the widely adopted techniques whose performance is highly dependent on the appropriate selection of its gain parameters. This paper presents a novel cascaded architecture of the complementary filter that employs a nonlinear and linear version of the complementary filter within one framework. The nonlinear version is used to correct the gyroscope bias, while the linear version estimates the attitude angle. The significant advantage of the proposed architecture is its independence of the filter parameters, thereby avoiding tuning the filter's gain parameters. The proposed architecture does not require any mathematical modeling of the system and is computationally inexpensive. The proposed methodology is applied to the real-world datasets, and the estimation results were found to be promising compared to the other state-of-the-art algorithms.