Current Machine Learning Techniques Research Articles

Implementing the analogous neural network using chaotic strange attractors

Machine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors’ nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks.

A REVIEW ON EXTENSIVELY USED MACHINE LEARNING TECHNIQUES FOR THE PREDICTION OF COVID-19

Forecasting with a precise evaluation of new cases and the rate of occurrence is essential for the effective implementation of governmental initiatives and early prevention of any infectious illness. Despite the extensive research done on the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus since the outbreak, not enough knowledge could be gained about the virus in terms of immune function, virus-host interactions, pathogenesis, propagation, and mutations. In this paper, various statistical models, namely Supervised Machine Learning techniques (ML), are being discussed for previous diseases and for the recent COVID-19 pandemic. Namely, the use of the Support Vector Machine (SVM) model and a variety of time series regression models is demonstrated for several infectious diseases, including COVID-19. As infectious diseases evolve throughout time, they provide data on a single variable, that is, “the figure of contaminations that occurred over time”; thus, researchers tend to use time series models to fit the data and make predictions using different evaluation metrics to find the best-fitting model. This review developed ideas about how to enhance the current modeling techniques. Furthermore, findings of current Machine Learning Techniques are being evaluated, which attempts to estimate the COVID-19 spread. Researchers looking for approaches to advance SARS-CoV-2 research as well as individuals curious about the field’s current condition will find this review to be helpful.

Machine learning of the prime distribution.

In the present work we use maximum entropy methods to derive several theorems in probabilistic number theory, including a version of the Hardy-Ramanujan Theorem. We also provide a theoretical argument explaining the experimental observations of Y.-H. He about the learnability of primes, and posit that the Erdős-Kac law would very unlikely be discovered by current machine learning techniques. Numerical experiments that we perform corroborate our theoretical findings.

Fake news detection using machine learning: an adversarial collaboration approach

PurposePurveyors of fake news perpetuate information that can harm society, including businesses. Social media's reach quickly amplifies distortions of fake news. Research has not yet fully explored the mechanisms of such adversarial behavior or the adversarial techniques of machine learning that might be deployed to detect fake news. Debiasing techniques are also explored to combat against the generation of fake news using adversarial data. The purpose of this paper is to present the challenges and opportunities in fake news detection.Design/methodology/approachFirst, this paper provides an overview of adversarial behaviors and current machine learning techniques. Next, it describes the use of long short-term memory (LSTM) to identify fake news in a corpus of articles. Finally, it presents the novel adversarial behavior approach to protect targeted business datasets from attacks.FindingsThis research highlights the need for a corpus of fake news that can be used to evaluate classification methods. Adversarial debiasing using IBM's Artificial Intelligence Fairness 360 (AIF360) toolkit can improve the disparate impact of unfavorable characteristics of a dataset. Debiasing also demonstrates significant potential to reduce fake news generation based on the inherent bias in the data. These findings provide avenues for further research on adversarial collaboration and robust information systems.Originality/valueAdversarial debiasing of datasets demonstrates that by reducing bias related to protected attributes, such as sex, race and age, businesses can reduce the potential of exploitation to generate fake news through adversarial data.

Harnessing Knowledge-Based Concepts for Streamlined Mind Mapping in Academic Study

The main goal of this research project is to build and implement a knowledge-based system that will produce more accurate and significant mind maps from textual input. This study suggests the creation of a knowledge-based system devoted to mind map construction, as opposed to current text mining algorithms and machine learning techniques, which might not be able to properly capture the semantic subtleties of input material. The suggested system aims to reduce the constraints of conventional techniques by incorporating domain-specific information and rules into the analytical process. The accuracy and relevance of the produced mind maps are projected to improve with the addition of this knowledge. This project's main objective is to build a knowledge-based framework that overcomes the limitations of the existing text mining and machine learning approaches, resulting in more sophisticated and theoretically rich mind maps from textual data.

Developing an Artificial Intelligence-Based Representation of a Virtual Patient Model for Real-Time Diagnosis of Acute Respiratory Distress Syndrome.

Acute Respiratory Distress Syndrome (ARDS) is a condition that endangers the lives of many Intensive Care Unit patients through gradual reduction of lung function. Due to its heterogeneity, this condition has been difficult to diagnose and treat, although it has been the subject of continuous research, leading to the development of several tools for modeling disease progression on the one hand, and guidelines for diagnosis on the other, mainly the "Berlin Definition". This paper describes the development of a deep learning-based surrogate model of one such tool for modeling ARDS onset in a virtual patient: the Nottingham Physiology Simulator. The model-development process takes advantage of current machine learning and data-analysis techniques, as well as efficient hyperparameter-tuning methods, within a high-performance computing-enabled data science platform. The lightweight models developed through this process present comparable accuracy to the original simulator (per-parameter R2 > 0.90). The experimental process described herein serves as a proof of concept for the rapid development and dissemination of specialised diagnosis support systems based on pre-existing generalised mechanistic models, making use of supercomputing infrastructure for the development and testing processes and supported by open-source software for streamlined implementation in clinical routines.

Current Trends in Deep Learning

This paper provides an overview of the current artificial intelligence (AI) and machine learning (ML) techniques, including Convolutional Neural Networks(CNN), Adversarial and Generative Techniques, Natural Language Processing (NLP), and Reinforcement Learning(RL). The paper discusses the background, applications, and future trends of these techniques, highlighting their potential for solving real-world problems. The purpose of the paper is to illustrate the trends that are emerging in these areas, as well as the challenges that must be addressed in order to fully realize their potential. By identifying several key areas, this paper concludes the future research and development.

Malicious Software Detection based on URL-API Intensity Feature Selection Using Deep Spectral Neural Classification for Improving Host Security

In recent years, the internet of services has been more responsive to access through the development of various application program interfaces (API). Accessing an HTTP uniform resource locator (URL) contains malicious software intended by the attacker to create security breaches through the use of APIs from various services on the internet. By default, the non-attentive URL downloads and installs malware in the background without the user’s knowledge. The host does not analyze the API-URL security certificate contract due to the feature access by the user. Therefore, the current Machine Learning (ML) techniques only check malware signatures and certificates rather than analyzing URL behaviour based on the impact of a URL accessed from the internet. To address this problem, we propose a novel intelligent malicious software based on URL-API intensity feature selection (IFS) and deep spectral neural classification (DSNC) for improving Host Security. Initially, the URL — successive certificate signing (SCS) of the user link accessibility is verified based on API download rate logs. This system identifies the best malware software. The Link Redirection Stability Rate (LRSR) is estimated based on the Redirection URL by accessing the direct link and redirect link. The domain transformation matrix (DTM) was created to create a pattern to access successive features. URL-API Intensity Feature Selection selects each estimated feature, and the selected features are based on soft-max logical activation with a recurrent neural network (RNN) optimized for deep learning. RNN is trained in the spectral domain for improving computation and efficiency. It predicts the class based on the risk of malicious weight to categorize class by reference. The proposed IFS-DSNC achieves accuracy of 95.6% than the other algorithms such as KNN, NB, CNN, LCS, GCRNC AGSCR. The experimental result shows that the proposed method provides better performance in finding malware software than the existing approaches, thereby improving the security against host breaching.

A New Centralized Detection-Based Process for Evaluating Anomalies and Analyzing the First Causes Using Machine Learning and Web Semantic

In the last decades, many works have been done to enhance data performances in the computer field. Data performance consists to describe all improvements which can be added to data traffic. More precisely, we are talking about techniques allowing improving the evaluation of big data using machine learning. Data evaluation is composed of several variables such as security, quality of service, data synchronization, scalability, and data structuring. In this work, we complete our proceedings done to supervise the continuity of technological evolution in terms of big data and safety. In other words, we aim to add brick to our previous processes to take into consideration the enhancement of the analysis of the causes generating frauds and intrusions preventing data traffic. To achieve this end, we increase current machine learning techniques with prior knowledge based on data thresholds set by experts in the first place. We also aim to integrate knowledge facilitating the interpretation of the causes causing all kinds of anomalies in the second place. Finally, our process will be endowed with the requirements to improve the rate of detection of anomalies and reduce human involvement operation.

Mesh deep Q network: A deep reinforcement learning framework for improving meshes in computational fluid dynamics

Meshing is a critical, but user-intensive process necessary for stable and accurate simulations in computational fluid dynamics (CFD). Mesh generation is often a bottleneck in CFD pipelines. Adaptive meshing techniques allow the mesh to be updated automatically to produce an accurate solution for the problem at hand. Existing classical techniques for adaptive meshing require either additional functionality out of solvers, many training simulations, or both. Current machine learning techniques often require substantial computational cost for training data generation, and are restricted in scope to the training data flow regime. Mesh Deep Q Network (MeshDQN) is developed as a general purpose deep reinforcement learning framework to iteratively coarsen meshes while preserving target property calculation. A graph neural network based deep Q network is used to select mesh vertices for removal and solution interpolation is used to bypass expensive simulations at each step in the improvement process. MeshDQN requires a single simulation prior to mesh coarsening, while making no assumptions about flow regime, mesh type, or solver, only requiring the ability to modify meshes directly in a CFD pipeline. MeshDQN successfully improves meshes for two 2D airfoils.

A decision-support framework for data anonymization with application to machine learning processes

The application of machine learning techniques to large and distributed data archives might result in the disclosure of sensitive information about the data subjects. Data often contain sensitive identifiable information, and even if these are protected, the excessive processing capabilities of current machine learning techniques might facilitate the identification of individuals, raising privacy concerns. To this end, we propose a decision-support framework for data anonymization, which relies on a novel approach that exploits data correlations, expressed in terms of relaxed functional dependencies (rfds) to identify data anonymization strategies providing suitable trade-offs between privacy and data utility. Moreover, we investigate how to generate anonymization strategies that leverage multiple data correlations simultaneously to increase the utility of anonymized datasets. In addition, our framework provides support in the selection of the anonymization strategy to apply by enabling an understanding of the trade-offs between privacy and data utility offered by the obtained strategies. Experiments on real-life datasets show that our approach achieves promising results in terms of data utility while guaranteeing the desired privacy level, and it allows data owners to select anonymization strategies balancing their privacy and data utility requirements.

Machine Learning Techniques, Features, Datasets, and Algorithm Performance Parameters for Sentiment Analysis: A Systematic Review

The purpose of this paper is to review various studies on current machine learning techniques used in sentiment analysis with the primary focus on finding the most suitable combinations of the techniques, datasets, data features, and algorithm performance parameters used in most applications. To accomplish this, we performed a systematic review of 24 articles published between 2013 and 2020 covering machine learning techniques for sentiment analysis. The review shows that Support Vector Machine as well as Naïve Bayes techniques are the most popular machine learning techniques; word stem and n-grams are the most extensively applied features, and the Twitter dataset is the most predominant. This review further revealed that machine learning algorithms' performance depends on many factors, including the dataset, extracted features, and size of data used. Accuracy is the most commonly used algorithm performance metric. These findings offer important information for researchers and businesses to use when selecting suitable techniques, features, and datasets for sentiment analysis for various business applications such as brand reputation monitoring.

Multiple Cost Optimisation for Alzheimer's Disease Diagnosis.

Current machine learning techniques for dementia diagnosis often do not take into account real-world practical constraints, which may include, for example, the cost of diagnostic assessment time and financial budgets. In this work, we built on previous cost-sensitive feature selection approaches by generalising to multiple cost types, while taking into consideration that stakeholders attempting to optimise the dementia care pathway might face multiple non-fungible budget constraints. Our new optimisation algorithm involved the searching of cost-weighting hyperparameters while constrained by total budgets. We then provided a proof of concept using both assessment time cost and financial budget cost. We showed that budget constraints could control the feature selection process in an intuitive and practical manner, while adjusting the hyperparameter increased the range of solutions selected by feature selection. We further showed that our budget-constrained cost optimisation framework could be implemented in a user-friendly graphical user interface sandbox tool to encourage non-technical users and stakeholders to adopt and to further explore and audit the model - a humans-in-the-loop approach. Overall, we suggest that setting budget constraints initially and then fine tuning the cost-weighting hyperparameters can be an effective way to perform feature selection where multiple cost constraints exist, which will in turn lead to more realistic optimising and redesigning of dementia diagnostic assessments. Clinical Relevance-By optimising diagnostic accuracy against various costs (e.g. assessment administration time and financial budget) predictive yet practical dementia diagnostic assessments can be redesigned to suit clinical use.

Forecasting football injuries by combining screening, monitoring and machine learning

Identifying players or circumstances associated with an increased risk of injury is fundamental for successful risk management in football. So far, time-constant and volatile risk factors are generally considered separately in either a screening (constant) or a monitoring (volatile) approach each resulting in a restricted set of explanatory variables. Consequently, improvements in predictive accuracy may be expected when screening and monitoring data are combined, especially when analysed with current machine learning (ML) techniques. This trial was designed as a prospective observational cohort study aiming to forecast non-contact time-loss injuries in male professional football (soccer). Injuries were registered according to the Fuller consensus. Gradient boosting with ROSE upsampling within a leave-one-out cross-validation was used for data analysis. The hierarchical data structure was considered throughout. Different splits of the original dataset were used to probe the robustness of results. Data of 88 players from 4 teams and 51 injuries could be analysed. The cross-validated performance of the gradient boosted model (ROC area under the curve 0.61) was promising and higher compared to models without integration of screening data. Importantly, holdout test set performance was similar (ROC area under the curve 0.62) indicating prospect of generalizability to new cases. However, the variation of predictive accuracy and feature importance with different splits of the original dataset reflects the relatively low number of events. It is concluded that ML-based injury forecasting based on the integration of screening and monitoring data is promising. However, external prospective verification and continued model development are required.

Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning.

Spiking neural networks (SNNs) are regarded as a promising candidate to deal with the major challenges of current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the few-shot learning performance of artificial neural networks. Importantly, existing spike-based few-shot learning models do not target robust learning based on spatiotemporal dynamics and superior machine learning theory. In this paper, we propose a novel spike-based framework with the entropy theory, namely, heterogeneous ensemble-based spike-driven few-shot online learning (HESFOL). The proposed HESFOL model uses the entropy theory to establish the gradient-based few-shot learning scheme in a recurrent SNN architecture. We examine the performance of the HESFOL model based on the few-shot classification tasks using spiking patterns and the Omniglot data set, as well as the few-shot motor control task using an end-effector. Experimental results show that the proposed HESFOL scheme can effectively improve the accuracy and robustness of spike-driven few-shot learning performance. More importantly, the proposed HESFOL model emphasizes the application of modern entropy-based machine learning methods in state-of-the-art spike-driven learning algorithms. Therefore, our study provides new perspectives for further integration of advanced entropy theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.

Diagnosis of Obesity Level based on Bagging Ensemble Classifier and Feature Selection Methods

In the current era, the amount of data generated from various device sources and business transactions is rising exponentially, and the current machine learning techniques are not feasible for handling the massive volume of data. Two commonly adopted schemes exist to solve such issues scaling up the data mining algorithms and data reduction. Scaling the data mining algorithms is not the best way, but data reduction is feasible. There are two approaches to reducing datasets selecting an optimal subset of features from the initial dataset or eliminating those that contribute less information. Overweight and obesity are increasing worldwide, and forecasting future overweight or obesity could help intervention. Our primary objective is to find the optimal subset of features to diagnose obesity. This article proposes adapting a bagging algorithm based on filter-based feature selection to improve the prediction accuracy of obesity with a minimal number of feature subsets. We utilized several machine learning algorithms for classifying the obesity classes and several filter feature selection methods to maximize the classifier accuracy. Based on the results of experiments, Pairwise Consistency and Pairwise Correlation techniques are shown to be promising tools for feature selection in respect of the quality of obtained feature subset and computation efficiency. Analyzing the results obtained from the original and modified datasets has improved the classification accuracy and established a relationship between obesity/overweight and common risk factors such as weight, age, and physical activity patterns.

Robust Spike-Based Continual Meta-Learning Improved by Restricted Minimum Error Entropy Criterion.

The spiking neural network (SNN) is regarded as a promising candidate to deal with the great challenges presented by current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the online meta-learning performance of artificial neural networks. Importantly, existing spike-based online meta-learning models do not target the robust learning based on spatio-temporal dynamics and superior machine learning theory. In this invited article, we propose a novel spike-based framework with minimum error entropy, called MeMEE, using the entropy theory to establish the gradient-based online meta-learning scheme in a recurrent SNN architecture. We examine the performance based on various types of tasks, including autonomous navigation and the working memory test. The experimental results show that the proposed MeMEE model can effectively improve the accuracy and the robustness of the spike-based meta-learning performance. More importantly, the proposed MeMEE model emphasizes the application of the modern information theoretic learning approach on the state-of-the-art spike-based learning algorithms. Therefore, in this invited paper, we provide new perspectives for further integration of advanced information theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.

Bridging the Gap Between AI and Explainability in the GDPR: Towards Trustworthiness-by-Design in Automated Decision-Making

Can satisfactory explanations for complex machine learning models be achieved in high-risk automated decision-making? How can such explanations be integrated into a data protection framework safeguarding a right to explanation? This article explores from an interdisciplinary point of view the connection between existing legal requirements for the explainability of AI systems set out in the General Data Protection Regulation (GDPR) and the current state of the art in the field of explainable AI. It studies the challenges of providing human legible explanations for current and future AI-based decision-making systems in practice, based on two scenarios of automated decision-making in credit scoring risks and medical diagnosis of COVID-19. These scenarios exemplify the trend towards increasingly complex machine learning algorithms in automated decision-making, both in terms of data and models. Current machine learning techniques, in particular those based on deep learning, are unable to make clear causal links between input data and final decisions. This represents a limitation for providing exact, human-legible reasons behind specific decisions, and presents a serious challenge to the provision of satisfactory, fair and transparent explanations. Therefore, the conclusion is that the quality of explanations might not be considered as an adequate safeguard for automated decision-making processes under the GDPR. Accordingly, additional tools should be considered to complement explanations. These could include algorithmic impact assessments, other forms of algorithmic justifications based on broader AI principles, and new technical developments in trustworthy AI. This suggests that eventually all of these approaches would need to be considered as a whole.

Land-Use Classification via Transfer Learning with a Deep Convolutional Neural Network

Land cover classification provides efficient and accurate information regarding human land-use, which is crucial for monitoring urban development patterns, management of water and other natural resources, and land-use planning and regulation. However, land-use classification requires highly trained, complex learning algorithms for accurate classification. Current machine learning techniques already exist to provide accurate image recognition. This research paper develops an image-based land-use classifier using transfer learning with a pre-trained ResNet-18 convolutional neural network. Variations of the resulting approach were compared to show a direct relationship between training dataset size and epoch length to accuracy. Experiment results show that transfer learning is an effective way to create models to classify satellite images of land-use with a predictive performance. This approach would be beneficial to the monitoring and predicting of urban development patterns, management of water and other natural resources, and land-use planning.

Explainable Convolutional Neural Network to Investigate Age-Related Changes in Multi-Order Functional Connectivity

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by the current machine learning techniques because of a lack of physiological understanding. To investigate the suitability of FC in BCIs for the elderly, we propose the decoding of lower- and higher-order FC using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. A total of 17 young adults 24.5±2.7 years and 12 older 72.5±3.2 years adults were recruited to perform tasks related to hand-force control with or without mental calculation. The CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increased the classification accuracy by 88.3% compared to the filter-bank common spatial pattern. The LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe, depending on the task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.