Training Machine Research Articles

Annotated interictal discharges in intracranial EEG sleep data and related machine learning detection scheme

Interictal epileptiform discharges (IEDs) such as spikes and sharp waves represent pathological electrophysiological activities occurring in epilepsy patients between seizures. IEDs occur preferentially during non-rapid eye movement (NREM) sleep and are associated with impaired memory and cognition. Despite growing interest, most studies involving IED detections rely on visual annotations or employ simple amplitude threshold approaches. Alternatively, advanced computerized detection methods are not standardized or publicly available. To address this gap, we introduce a novel dataset comprising multichannel intracranial electroencephalography (iEEG) data recorded at two medical centers during overnight sleep with IED annotations performed by expert neurologists. Utilizing these annotations to train machine learning models via a gradient-boosting algorithm, we demonstrate automated IED detection with high precision (94.4%) and sensitivity (94.3%) that can generalize across individuals and surpass performance of a leading commercial software. The dataset featuring multi-channel annotations with sub-second resolution including hippocampus and medial temporal lobe (MTL) regions is made publicly available, together with the detection algorithm, to advance research on detection methodology, epilepsy, sleep, and cognition.

How Users' Personality Traits Predict Sentiment Tendencies of User-Generated Content in Social Media: A Mixed Method of Configuration Analysis and Machine Learning.

Social media content created by users with different personality traits presents various sentiment tendencies, easily leading to irrational public opinion. This study aims to explore the relationships between users' personality traits and sentiment tendencies of user-generated content (UGC). We crawled 18,686 tweets of 1, 215 users from Twitter to figure out the relationships between personality traits and sentiment tendencies. This study utilizes Essays and Sentiment datasets to train machine learning models for the identification of personality traits and sentiment tendencies and then explores the configuration effect of personality traits on sentiment tendency via crisp-set Qualitative Comparative Analysis (csQCA). The findings suggest that (1) one-dimensional personality trait is not a necessary condition for the sentiment tendencies of UGC. (2) There are multiple equivalent configurations that lead to the sentiment tendencies of UGC. The study suggests that the sentiment tendencies pattern of UGC can be discovered via the configurations of various dimensions of personality traits.

Dynamic SelectOut and voting-based federated learning for enhanced medical image analysis

Abstract Federated Learning (FL) is a promising technique for training machine learning models on distributed, privacy-aware datasets. Nevertheless, FL faces difficulties with agent/client participation, model performance, and the heterogeneous nature of networked data sources when it comes to distributed healthcare systems. When these agents work together in the system, it is imperative to tackle the complexities of distributed deep learning. We suggest a novel approach that uses a voting mechanism and dynamic SelectOut inside the FL framework to address these problems. Local medical imaging datasets frequently show diversity in distribution and data imbalances. In certain situations, traditional FL techniques like FedProx and Federated Averaging (FedAvg), which depend on data size to weight contributions, might not be the optimal choice. We improve parameter aggregation and client selection unpredictability and increase the model's adaptability to imbalanced and heterogeneous datasets, our proposed FedVoteNet model introduces SelectOut techniques based on Voting methodology. Based on how much their local performance has improved from the last communication cycle, we arbitrarily remove clients. Additionally eliminated are clients whose model weights when combined with the global model adversely affect its performance. After each communication cycle, clients that improve both their local performance and their contribution to the global model are awarded higher voting values. This encourages more significant and effective contributions from clients by providing incentives for them to actively increase the diversity of their training data. We assess our approach on a dataset of medical images, including MRI scans, and find that the FL model performs noticeably better (F1 Score=0.968, Sensitivity=0.977, Specificity=0.945, and AUC=0.950). The voting system and the dynamic SelectOut algorithms improve the convergence of the FL model and successfully handle the difficulties presented by uneven and heterogeneous datasets. To sum up, our proposed approach uses voting and dynamic SelectOut techniques to improve FL performance on a variety of uneven, distributed, and varied datasets. This strategy has a lot of potential to improve FL across a range of applications, especially those that prioritize data privacy, diversity, and performance.

Backdoor Attack Against Dataset Distillation in Natural Language Processing

Dataset distillation has become an important technique for enhancing the efficiency of data when training machine learning models. It finds extensive applications across various fields, including computer vision (CV) and natural language processing (NLP). However, it essentially consists of a deep neural network (DNN) model, which remain susceptible to security and privacy vulnerabilities (e.g., backdoor attacks). Existing studies have primarily focused on optimizing the balance between computational efficiency and model performance, overlooking the accompanying security and privacy risks. This study presents the first backdoor attack targeting NLP models trained on distilled datasets. We introduce malicious triggers into synthetic data during the distillation phase to execute a backdoor attack on downstream models trained with these data. We employ several widely used datasets to assess how different architectures and dataset distillation techniques withstand our attack. The experimental findings reveal that the attack achieves strong performance with a high (above 0.9 and up to 1.0) attack success rate (ASR) in most cases. For backdoor attacks, high attack performance often comes at the cost of reduced model utility. Our attack maintains high ASR while maximizing the preservation of downstream model utility, as evidenced by results showing that the clean test accuracy (CTA) of the backdoored model is very close to that of the clean model. Additionally, we performed comprehensive ablation studies to identify key factors affecting attack performance. We tested our attack method against five defense strategies, including NAD, Neural Cleanse, ONION, SCPD, and RAP. The experimental results show that these defense methods are unable to reduce the attack success rate without compromising the model’s performance on normal tasks. Therefore, these methods cannot effectively defend against our attack.

Self-driving AMADAP laboratory: Accelerating the discovery and optimization of emerging perovskite photovoltaics

AbstractThe development of new solar materials for emerging perovskite photovoltaics poses intricate multi-objective optimization challenges in a large high-dimensional composition and parameter space, with in some cases, millions of potential candidates to be explored. Solving it necessitates reproducible, user-independent laboratory work and intelligent preselection of innovative experimental methods. Materials Acceleration Platforms (MAPs) seamlessly combine robotic materials synthesis, characterization, and AI-driven data analysis, enabling the exploration of new materials. They revolutionize material development by replacing trial-and-error methods with precise, rapid experimentation and generating high-quality data for training machine learning (ML) algorithms. Device Acceleration Platforms (DAPs) focus on optimizing functional energy films and multilayer stacks. Unlike MAPs, DAPs concentrate on refining processing conditions for predetermined materials, crucial for disordered semiconductors. By fine-tuning processing parameters, DAPs significantly advance disordered semiconductor devices such as emerging photovoltaics. This article examines recent advancements in automated laboratories for perovskite material discovery and photovoltaics device optimization, showcasing in-house-developed MAPs and a DAP. These platforms cover the entire value chain, from materials to devices, addressing optimization challenges through robot-based high-throughput experimentation (HTE). Ultimately, a self-driven Autonomous Material and Device Acceleration Platforms (AMADAP) laboratory concept is proposed for autonomous functional solar material discovery using AI-guided combinational approaches. Graphical abstract

Privacy-by-Design with Federated Learning will drive future Rare Disease Research

Up to 6% of the global population is estimated to be affected by one of about 10,000 distinct rare diseases (RDs). RDs are, to this day, often not understood, and thus, patients are heavily underserved. Most RD studies are chronically underfunded, and research faces inherent difficulties in analyzing scarce data. Furthermore, the creation and analysis of representative datasets are often constrained by stringent data protection regulations, such as the EU General Data Protection Regulation. This review examines the potential of federated learning (FL) as a privacy-by-design approach to training machine learning on distributed datasets while ensuring data privacy by maintaining the local patient data and only sharing model parameters, which is particularly beneficial in the context of sensitive data that cannot be collected in a centralized manner. FL enhances model accuracy by leveraging diverse datasets without compromising data privacy. This is particularly relevant in rare diseases, where heterogeneity and small sample sizes impede the development of robust models. FL further has the potential to enable the discovery of novel biomarkers, enhance patient stratification, and facilitate the development of personalized treatment plans. This review illustrates how FL can facilitate large-scale, cross-institutional collaboration, thereby enabling the development of more accurate and generalizable models for improved diagnosis and treatment of rare diseases. However, challenges such as non-independently distributed data and significant computational and bandwidth requirements still need to be addressed. Future research must focus on applying FL technology for rare disease datasets while exploring standardized protocols for cross-border collaborations that can ultimately pave the way for a new era of privacy-preserving and distributed data-driven rare disease research.

Machine learning‐assisted performance analysis of organic photovoltaics

AbstractAlthough the power conversion efficiency of organic solar cells (OSCs) has been rapidly improved, there is still a lot of room for designing and developing new materials and their combinations to approach the efficiency limit. In this work, we establish a database of ∼100 bulk heterojunction OSCs composed of representative donors and acceptors reported in the literature, and train machine learning models to identify the efficiency potential of donor‐acceptor combinations. We find that the fully connected neural network achieves a Pearson coefficient of up to 0.88 for predicting the efficiency of OSCs with different combinations of donors and acceptors. We use sure independence screening and sparsifying method with feature analysis to analyze and evaluate the performance of OSCs. To prove the reliability and viability of the predictive model, we introduce the theoretical efficiency limits and confidence tests into the process, which provides a simple but reliable solution to quickly analyze and evaluate the potential of OSC materials and material combinations.

Swin Wavelet Transformer (SWT): Mixing Tokens with Wavelet and Multiwavelet Transforms

The Swin Transformer possess a hierarchical structure, a robust structure, and an efficient self-attention mechanism. This makes it superior in performance for a wide variety of artificial intelligence and machine training tasks. It has revolutionized the field of digital signal processing and its applications by creating vision in multiple fields. It uses non-overlapping windows which leads to creating a distinct perspective and understanding of the context of the digital signals. However, it possess a very complicated hierarchical structure an complexities together. By reducing calculations and complexities together. This will lead to robust performance that make it a powerful tool for a wide range of computer vision tasks. In this research, simplified symbol mixing methods were developed for coding structures similar to transformers, by forming various semantics in the text through linear mixing transformation and in combination with nonlinearity in the feed-forward layers. Hence, we were able to successfully propose a Swin Wavelet Transformer (SWT) model in which the self-attention sublayer was replaced by a Wavelet transform. In a second attempt, the wavelet transform was replaced by the multi-wavelet transform. These two proposed models are achieved a better performance from their FNets and BERT counterparts and are highly competitive with traditional and efficient transformers.

A Green Multi-Attribute Client Selection for Over-The-Air Federated Learning: A Grey-Wolf-Optimizer Approach

Federated Learning (FL) has gained attention across various industries for its capability to train machine learning models without centralizing sensitive data. While this approach offers significant benefits such as privacy preservation and decreased communication overhead, it presents several challenges, including deployment complexity and interoperability issues, particularly in heterogeneous scenarios or resource-constrained environments. Over-the-air (OTA) FL was introduced to tackle these challenges by disseminating model updates without necessitating direct device-to-device connections or centralized servers. However, OTA-FL brought forth limitations associated with heightened energy consumption and network latency. In this paper, we propose a multi-attribute client selection framework employing the grey wolf optimizer (GWO) to strategically control the number of participants in each round and optimize the OTA-FL process while considering accuracy, energy, delay, reliability, and fairness constraints of participating devices. We evaluate the performance of our multi-attribute client selection approach in terms of model loss minimization, convergence time reduction, and energy efficiency. In our experimental evaluation, we assessed and compared the performance of our approach against the existing state-of-the-art methods. Our results demonstrate that the proposed GWO-based client selection outperforms these baselines across various metrics. Specifically, our approach achieves a notable reduction in model loss, accelerates convergence time, and enhances energy efficiency while maintaining high fairness and reliability indicators.

Quality Assessment of MRI-Radiomics-Based Machine Learning Methods in Classification of Brain Tumors: Systematic Review.

Brain tumors present a complex challenge in clinical oncology, where precise diagnosis and classification are pivotal for effective treatment planning. Radiomics, a burgeoning field in neuro-oncology, involves extracting and analyzing numerous quantitative features from medical images. This approach captures subtle spatial and textural information imperceptible to the human eye. However, implementation in clinical practice is still distant, and concerns have been raised regarding the methodological quality of radiomic studies. A systematic literature search was performed to identify original articles focused on the use of radiomics for brain tumors from 2015 based on the inclusion and exclusion criteria. The radiomic features train machine learning models for glioma classification, and data are split into training and testing subsets to validate the model accuracy, reliability, and generalizability. The present study systematically reviews the status of radiomic studies concerning brain tumors, also using the radiomics quality score (RQS) to assess the quality of the methodology used in each study. A systematic search of PubMed identified 300 articles, with 18 studies meeting the inclusion criteria for qualitative synthesis. These studies collectively demonstrate the potential of radiomics-based machine learning models in accurately distinguishing between glioma subtypes and grades. Various imaging modalities, including MRI, PET/CT, and advanced techniques like ASL and DTI, were utilized to extract radiomic features for analysis. Machine learning algorithms such as deep learning networks, support vector machines, random forests, and logistic regression were applied to develop predictive models. The present study indicates high accuracies in glioma classification, outperforming traditional imaging methods and inexperienced radiologists in some cases. Further validation and standardization efforts are warranted to facilitate the clinical integration of radiomics into routine practice, ultimately enhancing glioma management and patient outcomes. Open science practices: Machine learning using MRI radiomic features provides a simple, noninvasive, and cost-effective method for glioma classification, enhancing transparency, reproducibility, and collaboration within the scientific community.

Optimization of convolutional neural network and visual geometry group-16 using genetic algorithms for pneumonia detection.

Pneumonia is still a major global health issue, so effective diagnostic methods are needed. This research proposes a new methodology for improving convolutional neural networks (CNNs) and the Visual Geometry Group-16 (VGG16) model by incorporating genetic algorithms (GAs) to detect pneumonia. The work uses a dataset of 5,856 frontal chest radiography images critical in training and testing machine learning algorithms. The issue relates to challenges of medical image classification, the complexity of which can be significantly addressed by properly optimizing CNN. Moreover, our proposed methodology used GAs to determine the hyperparameters for CNNs and VGG16 and fine-tune the architecture to improve the existing performance measures. The evaluation of the optimized models showed some good performances with purely convolutional neural network archetyping, averaging 97% in terms of training accuracy and 94% based on the testing process. At the same time, it has a low error rate of 0.072. Although adding this layer affected the training and testing time, it created a new impression on the test accuracy and training accuracy of the VGG16 model, with 90.90% training accuracy, 90.90%, and a loss of 0.11. Future work will involve contributing more examples so that a richer database of radiographic images is attained, optimizing the GA parameters even more, and pursuing the use of ensemble applications so that the diagnosis capability is heightened. Apart from emphasizing the contribution of GAs in improving the CNN architecture, this study also seeks to contribute to the early detection of pneumonia to minimize the complications faced by patients, especially children.

AI Based Hazardous Asteroid Detection

As the need for early detection and mitigation of potential threats from near-Earth objects grows, this study presents a comprehensive approach to predicting hazardous asteroids using machine learning techniques. Given the increasing importance of protecting our planet from potential impact events, accurately classifying and predicting hazardous asteroids is cru- cial. The study proposes a comprehensive system for predicting and mitigating asteroid hazards using advanced data processing, machine learning, and simulation techniques. The proposed study collect real-time and historical asteroid data, process and clean this data, extract relevant features, and train machine learning models to predict potentially hazardous asteroids. Additionally, Monte Carlo simulations are employed to assess the collision risks of these asteroids with Earth. A forecasting module predicts future asteroid behavior based on historical and simulated data. The system also includes an alert mechanism that notifies relevant stakeholders when a potentially hazardous asteroid is detected

Training machine learning models to detect rare inborn errors of metabolism (IEMs) based on GC–MS urinary metabolomics for diseases screening

Training machine learning models to detect rare inborn errors of metabolism (IEMs) based on GC–MS urinary metabolomics for diseases screening

Non-invasive and continuous monitoring of 3D stem cell culture in a bioreactor

Abstract The development and discovery of new drugs and therapy products in regenerative medicine are carried out through multiple stages which involve several strict quality protocols. The use of cell-based model systems is the most relevant alternative to deviate from animal testing. However, the underlying biomanufacturing process in a 3D environment can be prone to failures or unexpected behaviors such as cell growth anomalies or inconsistencies in cell aggregation, which can seriously affect the quality of the result. Therefore, it is necessary to establish a non-invasive and continuous monitoring mechanism that minimizes contamination risks, allows taking early decisions and enables large-scale production in the long term. The results of our embedded machine learning approach show that it is feasible to train machine learning models that can operate on a resourcelimited embedded board with acceptable prediction accuracy for the estimation of the average size of growing stem cell spheroids. Further experiments are needed to investigate the full information potential of the recorded process data.

Advanced Machine Learning Approaches for Multi-Class Lung Disease Classification Using Respiratory Acoustics

This study introduces a novel method for the multi-class classification of lung diseases using respiratory sounds. Lung diseases represent a major global health issue, and early detection is essential for effective treatment and management. Traditional diagnostic techniques often involve specialized equipment and expertise, which can limit accessibility and increase costs. In this research, we propose a machine learning-based approach that utilizes respiratory sounds, which can be easily collected with affordable, non-invasive devices like digital stethoscopes or smartphone apps. Our method involves extracting features from respiratory sound signals and training machine learning models to classify various lung conditions, including pneumonia, asthma, chronic obstructive pulmonary disease (COPD), and bronchiectasis. We validate our approach using realworld respiratory sound datasets and evaluate its performance based on accuracy, sensitivity, and specificity. The results highlight the potential of using respiratory sounds for multi-class lung disease classification, providing an effective solution for early diagnosis and remote monitoring, especially in resource-constrained environments. This research contributes to the evolution of digital healthcare technologies, offering significant potential for enhancing respiratory disease management and improving patient outcomes

Word Sense Disambiguation using NLP

Word Sense Disambiguation (WSD) is a critical task in Natural Language Processing (NLP) aimed at determining the correct meaning of a word based on its context within a text. We categorize WSD techniques into three main paradigms: knowledge-based methods, supervised learning approaches, and neural network-based models. Knowledge-based methods leverage lexical resources like WordNet and other semantic networks to disambiguate word senses by comparing context with predefined sense definitions. These methods often rely on similarity measures and heuristic rules but may struggle with the flexibility and variability of natural language. Supervised learning approaches utilize annotated corpora to train machine learning models that predict word senses. These methods, including decision trees, support vector machines, and ensemble techniques, have shown significant improvements with the advent of large-scale labelled datasets and feature engineering. Keywords: Lexical Semantics, Sense Inventory, Knowledge- based WSD, Contextual Disambiguation

NLP-Powered Resume Matching For Recruitment

More recently, recruitment has largely relied on the automation of the matching process between candidates and job roles. In this regard, this paper focuses on the development of a resume parser application utilizing NLP techniques, PDF text extraction, and machine learning-based evaluation of resumes according to job descriptions. In developing the application using the Flask framework, users are allowed to upload resume and job description files in PDF format. The system automatically extracts the text, preprocesses it, and performs the task of skill matching. It also computes a semantic similarity score based on term frequency-inverse document frequency and cosine similarity techniques. Using a trained machine learning model, the application predicts a binary job fit score based on its semantic similarity and skills matching metrics scores. This paper outlines the design, implementation, and evaluation of the system, and it indeed has the potential to assist the recruiters in pre-screening the candidates.

Fatigue Detection of Air Traffic Controllers Through Their Eye Movements

Eye movement patterns have become an essential element in modern approaches for identifying air traffic controller fatigue. By observing eye movements among various individuals and environments, researchers have discovered correlations with multiple physiological metrics and cognitive processing abilities. This study involved human-in-the-loop simulations to collect eye movement and fatigue data from air traffic controllers and students. The eye movements were classified into three main types: fixation, saccade, and blink. Statistical analyses were performed to determine the most important indicators. Using support vector machine and random forest models for training and prediction, it was found that the fixation characteristic is significantly important for monitoring air traffic controller fatigue. The implementation of this model has the potential to identify forthcoming instances of controller fatigue during their shifts, thereby helping to avert the possibility of unsafe situations.

Farm-flow dataset: Intrusion detection in smart agriculture based on network flows

In recent years, the Internet of Things (IoT) revolutionized agricultural management by enabling data-driven decision-making through seamless connectivity among various devices and equipment. The security of Agricultural IoT (AG-IoT) devices becomes increasingly evident as reliance on them grows. On the other hand, machine learning models for intrusion detection show promise in identifying vulnerabilities, but their effectiveness depends on being trained on representative data. Indeed, there is a notable gap in network intrusion detection for AG-IoT, as existing datasets for training machine learning models lack the context of AG-IoT scenarios. Also, most existing ones rely on packed-based features (and not on network flow data), and analysing such data can be resource-consuming.In this work, we present the “Farm-Flow” dataset. We created a realistic AG-IoT scenario to build the dataset and executed eight types of network attacks. Over one million instances of relevant data were collected, which we combined into network flows, organized and made publicly available via http://doi.org/10.5281/zenodo.10964647.The dataset created has been evaluated using multiple intrusion detection models in terms of their capabilities to identify and classify malicious traffic. The assessed models presented high performance and even achieved an F1-score of more than 90% while identifying malicious traffic. The “Farm-Flow” may support the training of intrusion detection methods, and the performance results contribute to future benchmarking.

Artificial Intelligence and Its Transformative Impact on Modern Politics

Abstract. Since the advent of artificial intelligence (AI) with the Turing test and the Dartmouth Conference, AI has continued to evolve. This evolution has encompassed the introduction of cybernetics, big data, and machine training. However, as the development of artificial intelligence becomes more sophisticated, several issues have begun to emerge. This paper examines the increasing influence of artificial intelligence (AI) in the political sphere over time, specifically examines how AI is being used in the political process, including applications such as sentiment analysis, targeted advertising, and more. It also considers the challenges that have emerged alongside the development of AI, including those related to privacy, voter manipulation, and the transparency of the political process. The paper presents case studies of the 2016 US presidential election and the 2019 Indian general election, which demonstrate how artificial intelligence is exerting a significant influence on democratic political processes, and concludes that as AI becomes increasingly beneficial to human society, concerns are emerging regarding regulations, ethics, political involvement, and other issues. The research addressed the issue of maintaining democratic integrity in politics while advancing artificial intelligence, which offers numerous benefits for modern politics. The paper calls for implementing regulatory policies that would prevent the unethical involvement of artificial intelligence in politics. Additionally, it emphasizes the importance of ensuring that the advantages of artificial intelligence are utilized effectively and fully in the modern political landscape.