Abstract Physics-Informed Neural Networks (PINN) are neural networks (NNs) that encode model equations, like Partial Differential Equations (PDE), as a component of the neural network itself. PINNs are nowadays used to solve PDEs, fractional equations, integral-differential equations, and stochastic PDEs. This novel methodology has arisen as a multi-task learning framework in which a NN must fit observed data while reducing a PDE residual. This article provides a comprehensive review of the literature on PINNs: while the primary goal of the study was to characterize these networks and their related advantages and disadvantages. The review also attempts to incorporate publications on a broader range of collocation-based physics informed neural networks, which stars form the vanilla PINN, as well as many other variants, such as physics-constrained neural networks (PCNN), variational hp-VPINN, and conservative PINN (CPINN). The study indicates that most research has focused on customizing the PINN through different activation functions, gradient optimization techniques, neural network structures, and loss function structures. Despite the wide range of applications for which PINNs have been used, by demonstrating their ability to be more feasible in some contexts than classical numerical techniques like Finite Element Method (FEM), advancements are still possible, most notably theoretical issues that remain unresolved. 

/pdf/scientific-machine-learning-through-physics-informed-neural-3uhx9t2l.pdf

Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next

With the continuous expansion and evolution of IoT applications, attacks on those IoT applications continue to grow rapidly. In this systematic literature review (SLR) paper, our goal is to provide a research asset to researchers on recent research trends in IoT security. As the main driver of our SLR paper, we proposed six research questions related to IoT security and machine learning. This extensive literature survey on the most recent publications in IoT security identified a few key research trends that will drive future research in this field. With the rapid growth of large scale IoT attacks, it is important to develop models that can integrate state of the art techniques and technologies from big data and machine learning. Accuracy and efficiency are key quality factors in finding the best algorithms and models to detect IoT attacks in real or near real-time

Machine learning approaches to IoT security: A systematic literature review

Machine Learning Approaches in COVID-19 Diagnosis, Mortality, and Severity Risk Prediction: A Review.

Rice is one of the most important crops in the world, and most people consume rice as a staple food, especially in Asian countries. Various rice plant diseases have a negative effect on crop yields. If proper detection is not taken, they can spread and lead to a significant decline in agricultural productions. In severe cases, they may even cause no grain harvest entirely, thus having a devastating impact on food security. The deep learning-based CNN methods have become the standard methods to address most of the technical challenges related to image identification and classification. In this study, to enhance the learning capability for minute lesion features, we chose the MobileNet-V2 pre-trained on ImageNet as the backbone network and added the attention mechanism to learn the importance of inter-channel relationship and spatial points for input features. In the meantime, the loss function was optimized and the transfer learning was performed twice for model training. The proposed procedure presents a superior performance relative to other state-of-the-art methods. It achieves an average identification accuracy of 99.67% on the public dataset. Even under complicated backdrop conditions, the average accuracy reaches 98.48% for identifying rice plant diseases. Experimental findings demonstrate the validity of the proposed procedure, and it is accomplished efficiently for rice disease identification.

Identification of rice plant diseases using lightweight attention networks

Online Social Networks are perpetually evolving and used in plenteous applications such as content sharing, chatting, making friends/followers, customer engagements, commercials, product reviews/promotions, online games, and news, etc. The substantial issues related to the colossal flood of social spam in social media are polarizing sentiments, impacting users’ online interaction time, degrading available information quality, network bandwidth, computing power, and speed. Simultaneously, groups of coordinated automated accounts/bots often use social networking sites to spread spam, rumors, bogus reviews, and fake news for targeted users or mass communication. The latest developments in the form of artificial intelligence-enabled Deepfakes have exacerbated these issues at large. Consequently, it becomes extremely relevant to review recent work concerning social spam and spammer detection to counter this issue and its effect. This paper provides a brief introduction to social spam, the spamming process, and social spam taxonomy. The comprehensive review entails several dimensionality reduction techniques used for feature selection/extraction, features used, various machine learning and deep learning techniques used for social spam and spammer detection, and their merits and demerits. Artificial intelligence and deep learning empowered Deepfake (text, image, and video) spam, and their countermeasures are also explored. Furthermore, meticulous discussions, existing challenges, and emerging issues such as robustness of detection systems, scalability, real-time datasets, evade strategies used by spammers, coordinated inauthentic behavior, and adversarial attacks on machine learning-based spam detectors, etc., have been discussed with possible directions for future research.

A review on social spam detection: Challenges, open issues, and future directions

Nowadays, deep learning is a current and a stimulating field of machine learning. Deep learning is the most effective, supervised, time and cost efficient machine learning approach. Deep learning is not a restricted learning approach, but it abides various procedures and topographies which can be applied to an immense speculum of complicated problems. The technique learns the illustrative and differential features in a very stratified way. Deep learning methods have made a significant breakthrough with appreciable performance in a wide variety of applications with useful security tools. It is considered to be the best choice for discovering complex architecture in high-dimensional data by employing back propagation algorithm. As deep learning has made significant advancements and tremendous performance in numerous applications, the widely used domains of deep learning are business, science and government which further includes adaptive testing, biological image classification, computer vision, cancer detection, natural language processing, object detection, face recognition, handwriting recognition, speech recognition, stock market analysis, smart city and many more. This paper focuses on the concepts of deep learning, its basic and advanced architectures, techniques, motivational aspects, characteristics and the limitations. The paper also presents the major differences between the deep learning, classical machine learning and conventional learning approaches and the major challenges ahead. The main intention of this paper is to explore and present chronologically, a comprehensive survey of the major applications of deep learning covering variety of areas, study of the techniques and architectures used and further the contribution of that respective application in the real world. Finally, the paper ends with the conclusion and future aspects.

A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning

Biometrics is the branch of science that deals with the identification and verification of an individual based on the physiological and behavioral traits. These traits or identifiers are permanent, unique and can separate one individual from another. Biometric recognition systems integrate complex definitional, technological and operational selection under various contexts. The systems are not going to replace the authentication tools and technologies, but the combination of biometric approaches and authentication methods to help in improving the security aspects of the applications where user cooperation can be inferred. Biometric based recognition methods and tools have become popular for the development of many useful, challenging and widely accepted applications such as security issues, surveillance, forensic investigations, fraudulent technologies, identity access management and access control. These systems also help to identify an individual in group of industrial networks, home/office building and control system. For the successful implementation of the biometric systems, deep artificial neural networks are in great demand. These systems can be built up either on the single modality or multiple modalities. This article explicates the comprehensive and deep survey that compactly and systematically summarizes the literature work done on unimodal and multimodal biometric systems and analyzes the feature extraction techniques, classifiers, datasets, results, efficiency and reliability of the system with high and multi-dimensional perspectives. This article also justifies in detail the classical methods, influential methods and taxonomy based on the biometric attributes. The goal is to aware the researchers of this area regarding various dimensions for the development of biometric systems to enhance the security aspects. The article begins with the fundamentals, types, need of system, challenges, uncertainties, motivations and then to the survey work. The tabular representation prepares for each biometric trait shows the author, year, major findings and results achieved with the synthesis analysis and the evaluation. The article finally ends up with the 3D biometric, a future perspective and concluding remarks.

A comprehensive survey on the biometric recognition systems based on physiological and behavioral modalities

Writer identification is a challenging move in the field of pattern recognition and reflects advanced perceptions into the handwriting research. It is the process of determining the author or writer of the text by matching it with the training database. It is an exigent task because the writing style of an individual is distinct from other because of unique intrinsic characteristics and is different even if the same writer writes that text with the same pen next time. It is concerned with the writing styles, feelings, perception, behavior and the brain of an individual and it is one of the neoteric applications of biometric identification. Biometric identification is the branch of computer science that deals with identification of an individual from a group using unique identifiers such as fingerprints, retina, handwriting and signatures. It is a term used for the body measurements and calculations. This paper presents a comprehensive and transparent panorama on the work done for the writer identification system on different Indic and non-Indic scripts and a widespread view towards this peculiar research area. The structure of the paper comprises introduction, motivation for the work, background, sources of information, schemes, process, reported works, synthesis analysis, study of features and classifiers for writer identification, and finally the conclusion and future directions. The main focus of this paper is to present in a systematic way, the reported works on writer identification systems on Indic scripts such as Bengali, Gujarati, Gurumukhi, Kannada, Malayalam, Oriya, Tamil and Telugu and Non-Indic scripts such as Arabic, Chinese, French, Persian, Roman and finally exposes the synthesis analysis based on the findings. This study gives the cognizance and beneficial assistance to the novice researchers in this field by providing in a nut shell the studies of various feature extraction methods and classification techniques required for writer identification on both Indic and non-Indic scripts. It is observed that work done on the writer identification systems with good accuracy rates in Indic scripts is limited as compared to non-Indic scripts and truly presents a future direction.

Writer Identification System for Indic and Non-Indic Scripts: State-of-the-Art Survey

A biometric identification system based on single and multiple modalities has been an evolving concept for solving criminal issues, security and privacy maintenance and for checking the authentication of an individual. The writer identification system is a type of biometric identification in which handwriting of an individual is taken as a biometric identifier. It is a system in which the writer can be identified based on his handwritten text. These systems employ machine learning and pattern recognition algorithms for the generation of a framework. In this paper, the authors have presented a novel system for the writer identification based upon the pre-segmented characters of Devanagari script and also presenting comprehensive state-of-the-art work. The experiment is performed on the corpus consisting of five copies of each character of Devanagari script written by 100 different writers, selected randomly at the public places and consisting of total 24,500 samples of Devanagari characters. Four feature extraction methodologies such as zoning, diagonal, transition and peak extent-based features and classification methods such as k-NN and linear SVM are used with identification accuracy of 91.53% when using zoning, transition and peak extent-based features with a linear SVM classifier.

Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM

Gender classification system is an automated, challenging, and efficacious system due to the analogous vision of males and females with handwriting. Gender classification is a binary problem that is based on physiological and behavioral biometric traits. It is widely used for forensic-based investigations, autopsy determination, suspected areas, and questioned documents. The proposed study has been considered for the behavioral biometric trait, i.e., handwriting in the Gurumukhi script. The novelty of this study can be seen from the three perspectives, i.e., hybridization of feature extraction techniques, principal component analysis (PCA) for dimensionality reduction, and hybridization of classification techniques. Zoning, Diagonal, Transition, and Peak Extent-based feature extractions were implemented followed by their hybridization. The classification techniques such as Decision Trees, Random Forest, and Extreme Gradient Boosting classifiers were experienced with the hybridized approach using a majority voting scheme. Also, the comparison and critical analysis of gender classification accuracy with CPU elapsed time has also been presented before and after implementing PCA. There are many novel ideas for the researchers such as gender classification through online handwriting, prediction of age, personality, state, nationality, and stress prediction through handwriting, and further gender classification problem can be enhanced to third or trans-gender too using handwriting as a biometric modality. The system can be implemented with many other Indic scripts and presenting novel track in the handwriting-based researches.

Shaveta Dargan

Papers

A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning

A comprehensive survey on the biometric recognition systems based on physiological and behavioral modalities

Writer Identification System for Indic and Non-Indic Scripts: State-of-the-Art Survey

Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM

PCA-based gender classification system using hybridization of features and classification techniques