Intersection Of Machine Learning Research Articles

Synergies between Machine Learning, Artificial Intelligence, and Game Theory for Complex Decision-Making

The special focus of this paper is to discuss a likely intersection of machine learning, artificial intelligence (AI) technology, and game theory, pointing at the importance of this synthesis both in mathematics and engineering. As these domains develop various means of addressing decision-making problems become more and more sophisticated and can be used in different areas such as economics, security, and social sciences. We will also address selected game-theoretic issues including the concept of decision making in terms of Nash equilibria or in the distinction of games as being cooperative or non-cooperative and how they work in synergy with machine learning approaches bringing in reinforcements and deep learning to leverage forecasting and strategizing. The paper makes references to problem-oriented branches of studies such as autonomous systems or market strategies stressing the importance of the novel direction for further studies. Within the scope of machine learning and game theory the goal is to implement better complex models which utilize real world intricacies for enhancing decision making within a populated agent environment.

NIMG-67. THE CURRENT STATE OF LARGE LANGUAGE MODELS AND NEURO-ONCOLOGY IMAGING

Abstract INTRODUCTION Large language models (LLM), such as chatGPT by OpenAI, exist at the intersection of machine learning and natural language processing, and are poised to transform healthcare with rapid growth in recent years. The ability of these models to process visual data has also advanced in recent years, with GPT-4 being the first model to publicly process visual data, and GPT-4o adding additional capabilities. There has been significant interest in the application of GPT-4o to healthcare image processing. OBJECTIVE This study sought to examine the ability of GPT-4o in determining a final diagnosis based on a single MRI image of an intracranial neoplasm. We then compared the performance to GPT-4, as well as to humans including neurosurgery residents, fellow, and attendings. METHODS GPT-4 and GPT-4o were given a standard prompt and an accompanying image requesting the most likely diagnosis for 20 brain MRI images, including 5 gliomas, 5 meningiomas, 5 pituitary tumors, and 5 sham non-tumor images. These were compared to a survey of neurosurgery attendings, fellows, senior residents, and junior residents. RESULTS GPT-4 supplied correct diagnoses in just 40% of the cases, while GPT-4o correctly identified the pathology in 70% of cases. Neurosurgeons yielded correct responses in 92% of cases, with neurosurgery senior residents faring the best (albeit with a small sample size). CONCLUSION GPT-4 and GPT-4o underperformed neurosurgery residents, fellows, and attendings in correctly identifying CNS malignancies. Still, with no additional training, GPT-4o yielded significantly better results than GPT-4, showing rapid advancement in the LLM over is predecessor in identifying intracranial neoplasms via single-image MRIs.

When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs

The use of machine learning (ML) models to assess and score textual data has become increasingly pervasive in an array of contexts including natural language processing, information retrieval, search and recommendation, and credibility assessment of online content. A significant disruption at the intersection of ML and text are text-generating large-language models (LLMs) such as generative pre-trained transformers (GPTs). We empirically assess the differences in how ML-based scoring models trained on human content assess the quality of content generated by humans versus GPTs. To do so, we propose an analysis framework that encompasses essay scoring ML-models, human and ML-generated essays, and a statistical model that parsimoniously considers the impact of type of respondent, prompt genre, and the ML model used for assessment model. A rich testbed is utilized that encompasses 18,460 human-generated and GPT-based essays. Results of our benchmark analysis reveal that LLMs and transformer pretrained language models (PLMs) more accurately score human essay quality as compared to CNN/RNN and feature-based ML methods. Interestingly, we find that LLMs and transformer PLMs tend to score GPT-generated text 10-20% higher on average, relative to human-authored documents. Conversely, traditional deep learning and feature-based ML models score human text considerably higher. Further analysis reveals that even though the LLMs and transformer PLMs are exclusively fine-tuned on human text, they more prominently attend to certain tokens appearing only in GPT-generated text, possibly (in part) due to familiarity/overlap in pre-training. Our framework and results have implications for text classification settings where automated scoring of text is likely to be disrupted by generative AI.

A Human-Centered View of Continual Learning: Understanding Interactions, Teaching Patterns, and Perceptions of Human Users Toward a Continual Learning Robot in Repeated Interactions

Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human–Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions with humans. Most research in CL, however, has been robot-centered to develop CL algorithms that can quickly learn new information on systematically collected static datasets. In this article, we take a human-centered approach to CL, to understand how humans interact with, teach, and perceive CL robots over the long term, and if there are variations in their teaching styles. We developed a socially guided CL system that integrates CL models for object recognition with a mobile manipulator robot and allows humans to directly teach and test the robot in real time over multiple sessions. We conducted an in-person study with 60 participants who interacted with the CL robot in 300 sessions with 5 sessions per participant. In this between-participant study, we used three different CL models deployed on a mobile manipulator robot. An extensive qualitative and quantitative analysis of the data collected in the study shows that there is significant variation among the teaching styles of individual users indicating the need for personalized adaptation to their distinct teaching styles. Our analysis shows that the constrained experimental setups that have been widely used to test most CL models are not adequate, as real users interact with and teach CL robots in a variety of ways. Finally, our analysis shows that although users have concerns about CL robots being deployed in our daily lives, they mention that with further improvements CL robots could assist older adults and people with disabilities in their homes.

Power generation mix in Colombia including wind power: Markowitz portfolio efficient frontier analysis with machine learning

The Colombian power market is hydro-dominated since 67 % of the power produced comes from hydro-power sources. In addition, it has thermal power from natural gas and coal, and in the last years, alternative energy sources such as wind and solar have been introduced, although so far their share is not significant. Due to this condition, the Colombian power market is very volatile and depends on weather conditions. Usually, in rainy seasons prices are low and power is available, while in dry seasons, prices are high and power can be scarce. One of the main advantages of the new energy sources is that they are complementary to hydro-power, in the case of wind regimes, they are higher during dry seasons and lower during rainy seasons. We propose a complementarity analysis in the energy mix using Markowitz Portfolio analysis to determine if the efficient frontier is improved by introducing wind power to the system and the traditional port-folio analysis is improved by introducing Machine Learning (ML) into calculations. Results show that wind power improves the return while minimizing risk. Therefore, wind power would significantly reduce prices in Colombia's power mix while reducing volatility. This work follows the Open Innovation (OI) paradigm, the intersection of Machine Learning, portfolio optimization, and renewable energy presents a promising landscape for research and practical applications. Continued interdisciplinary collaboration and innovation are essential for harnessing the full potential of these technologies for a sustainable energy future.

The Intersection of Machine Learning and Wireless Sensor Network Security for Cyber-Attack Detection: A Detailed Analysis.

This study provides a thorough examination of the important intersection of Wireless Sensor Networks (WSNs) with machine learning (ML) for improving security. WSNs play critical roles in a wide range of applications, but their inherent constraints create unique security challenges. To address these problems, numerous ML algorithms have been used to improve WSN security, with a special emphasis on their advantages and disadvantages. Notable difficulties include localisation, coverage, anomaly detection, congestion control, and Quality of Service (QoS), emphasising the need for innovation. This study provides insights into the beneficial potential of ML in bolstering WSN security through a comprehensive review of existing experiments. This study emphasises the need to use ML's potential while expertly resolving subtle nuances to preserve the integrity and dependability of WSNs in the increasingly interconnected environment.

Physics-Inspired Evolutionary Machine Learning Method: From the Schrödinger Equation to an Orbital-Free-DFT Kinetic Energy Functional.

We introduce a machine learning (ML)-supervised model function (which is in fact a functional rather than a regular function) that is inspired by the variational principle of physics. This ML hypothesis evolutionary method, termed ML-Ω, allows us to go from data to differential equation(s) underlying the physical (chemical, engineering, etc.) phenomena from which the data are derived from. The fundamental equations of physics can be derived from this ML-Ω evolutionary method when the proper training data is used. By training the ML-Ω model function with only three hydrogen-like atom energies, the method can find Schrödinger's exact functional and, from it, Schrödinger's fundamental equation. Then, in the field of density functional theory (DFT), when the model function is trained with the energies from the known Thomas-Fermi (TF) formula , it correctly finds the exact TF functional. Finally, the method is applied to find a local orbital-free (OF) functional expression of the independent electron kinetic energy functional Ts based on the γTFλvW model. By considering the theoretical energies of only five atoms (He, Be, Ne, Mg, and Ar) as the training set, the evolutionary ML-Ω method finds an ML-Ω-OF-DFT local Ts functional (γTFλvW(0.964,1/4)) that outperforms all the OF-DFT functionals of a representative group. Moreover, our ML-Ω-OF functional overcomes the difficulty of LDA's and some local generalized gradient approximation (GGA)-DFT's functionals to describe the stretched bond region at the correct spin configuration of diatomic molecules. Nonsmooth and nonclosed form functionals can be considered in the ML-Ω model function and still be effectively trained. Although our evolutionary ML-Ω model function can work without an explicit prior-form functional, by using the techniques of symbolic regression, in this work, we exploit prior-form functional expressions to make the training process simpler and faster. The ML-Ω method can be considered at the intersection of ML and the natural sciences.

Stable attractors for neural networks classification via ordinary differential equations (SA-nODE)

Abstract A novel approach for supervised classification is presented which sits at the intersection of machine learning and dynamical systems theory. At variance with other methodologies that employ ordinary differential equations for classification purposes, the untrained model is a priori constructed to accommodate for a set of pre-assigned stationary stable attractors. Classifying amounts to steer the dynamics towards one of the planted attractors, depending on the specificity of the processed item supplied as an input. Asymptotically the system will hence converge on a specific point of the explored multi-dimensional space, flagging the category of the object to be eventually classified. Working in this context, the inherent ability to perform classification, as acquired ex post by the trained model, is ultimately reflected in the shaped basin of attractions associated to each of the target stable attractors. The performance of the proposed method is here challenged against simple toy models crafted for the purpose, as well as by resorting to well established reference standards. More precisely, we achieved an accuracy of 98.06 % on the MNIST test set and 88.21% on the Fashion MNIST test set. Although this method does not reach the performance of state-of-the-art deep learning algorithms, it illustrates that continuous dynamical systems with closed analytical interaction terms can serve as high-performance classifiers.

Transformers in single-cell omics: a review and new perspectives.

Recent efforts to construct reference maps of cellular phenotypes have expanded the volume and diversity of single-cell omics data, providing an unprecedented resource for studying cell properties. Despite the availability of rich datasets and their continued growth, current single-cell models are unable to fully capitalize on the information they contain. Transformers have become the architecture of choice for foundation models in other domains owing to their ability to generalize to heterogeneous, large-scale datasets. Thus, the question arises of whether transformers could set off a similar shift in the field of single-cell modeling. Here we first describe the transformer architecture and its single-cell adaptations and then present a comprehensive review of the existing applications of transformers in single-cell analysis and critically discuss their future potential for single-cell biology. By studying limitations and technical challenges, we aim to provide a structured outlook for future research directions at the intersection of machine learning and single-cell biology.

Reminiscences on Influential Papers

This issue's contributors all work at the intersection of machine learning and databases. Coincidentally, three of them picked papers that received the VLDB 10-Year Best Paper award, and one of them picked a paper that, in my opinion, should receive the CIDR Test-of-Time award at some point. Their write-ups highlight very well why these four papers still continue to leave a mark on us personally and the real-world data systems. Enjoy reading! While I will keep inviting members of the data management community, and neighboring communities, to contribute to this column, I also welcome unsolicited contributions. Please contact me if you are interested.

Intersection of machine learning and mobile crowdsourcing: a systematic topic-driven review

Intersection of machine learning and mobile crowdsourcing: a systematic topic-driven review

Targeted metabolomics combined with machine learning to identify and validate new biomarkers for early SLE diagnosis and disease activity

BackgroundThe early diagnosis of systemic lupus erythematosus (SLE) and the assessment of disease activity progression remain a great challenge. Targeted metabolomics has great potential to identify new biomarkers of SLE. MethodsSerum from 44 healthy participants and 89 SLE patients were analyzed using HM400 high-throughput targeted metabolomics. Machine learning (ML) with seven learning models and trained the model several times iteratively selected the two best prediction model in a competitive way, which were independent validated by enzyme-linked immunosorbent (ELISA) with 90 SLE patients. ResultsIn this study, 146 differential metabolites, most of them organic acids, amino acids, and bile acids, were detected between patients with initial SLE and healthy participants, and 8 potential biomarkers were found by intersection of ML and statistics (area under the curve [AUC] > 0.95) showing a significant positive correlation with clinical indicators. In addition, we identified and validated 2 potential biomarkers for SLE classification (P < 0.05, AUC > 0.775; N-Methyl-L-glutamic acid, L-2-aminobutyric acid) showing a significant correlation with the SLE Disease Activity Index. These differential metabolites were mainly involved in metabolic pathways, amino acid biosynthesis, 2-oxocarboxylic acid metabolism and other pathways. ConclusionThis study indicated that the tricarboxylic acid cycle might be associated with SLE drug therapy. We identified 8 diagnostic models biomarkers and 2 biomarkers that could be used to identify initial SLE and distinguish different activity degree, which will promote the development of new tools for the diagnosis and evaluation of SLE.

A Comprehensive Survey of Artificial Intelligence and Machine Learning Application in Healthcare

The ongoing technological transformation, driven by rapid advancements in machine learning (ML), holds the potential to profoundly impact our lives and redefine the essence of humanity. Recent years have witnessed significant progress in ML, fuelled by the widespread adoption of artificial intelligence (AI) due to machines' capacity for large-scale data processing and management. The intersection of ML and healthcare encompasses both computer science along with medical science. Within medical science, ML techniques have enabled the examination of complex medical data, marking a significant advancement. In the healthcare industry, ML functions as the cognitive and knowledge counterpart of healthcare professionals. This paper explores the benefits of ML-based solutions and their applications in healthcare, emphasizing their role in automating data analysis for patients' health records along with making predictions per the extracted insights. The integration of ML in healthcare promises transformative outcomes, shaping the future of medical diagnostics and decision-making.

Enhancing Cloud Compliance: A Machine Learning Approach

The intersection of machine learning (ML) and cloud computing presents significant opportunities to enhance cloud compliance and security practices. This research paper explores the role of ML in improving cloud compliance, focusing on proactive threat detection, automated incident response, and adaptive security controls. The importance of ML-driven approaches lies in their ability to analyse large datasets, detect anomalies, and mitigate risks in dynamic cloud environments. Methods employed include case studies and experiments showcasing real-world applications of ML in cloud security, such as Google Cloud's Context-Aware Access and AWS GuardDuty for threat detection. Experimental findings demonstrate the effectiveness of ML models in reducing mean time to detect (MTTD) security incidents and improving incident response capabilities. Results highlight the transformative impact of ML technologies in bolstering cloud security effectiveness and resilience. ML-powered compliance monitoring systems, like Netflix's, have significantly improved compliance posture while reducing operational costs. Implications of this research include enhanced security governance, reduced compliance risks, and improved operational efficiencies within cloud infrastructures. Future directions entail exploring advanced ML techniques, addressing ethical considerations, and integrating ML-driven security frameworks into holistic cloud governance strategies.

Innovative Machine Learning Applications in Non-Revenue Water Management: Challenges and Future Solution

The escalating global concerns surrounding Non-Revenue Water (NRW) necessitate a paradigm shift in water management strategies, and innovative machine learning (ML) applications emerge as a transformative solution. This paper investigates the intersection of ML and NRW management, recognizing the pressing need to curb water losses due to leaks, theft, and inaccuracies. As water utilities grapple with the economic and environmental repercussions of NRW, this paper explores the potential of ML algorithms, such as predictive analytics to revolutionize traditional approaches. The discussion encompasses the intricate landscape of challenges, including data quality issues, model interpretability, and the inherent complexity of implementation. Recognizing the multidisciplinary nature of these challenges, the journal emphasizes the collaborative efforts required to harmonize technological innovation with practical implementation. As the world confronts the imperative to optimize water resources, this paper posits that innovative ML applications present a pivotal opportunity to not only enhance the accuracy and efficiency of NRW management but also to foster a more sustainable and resilient water infrastructure. Through a comprehensive grasp of challenges and a proactive pursuit of remedies, stakeholders can establish sustainable, resilient, and equitable water management systems. This paper acts as a valuable reference, providing a detailed discussion encompassing Europe, China, Japan, South Korea, and specific states within Malaysia, with a specific focus on non-revenue water (NRW) systems.

A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions

Modern power systems, characterized by complex interconnected networks and renewable energy sources, necessitate innovative approaches for protection and control. Traditional protection schemes are often failing to harness the vast data generated by modern grid systems and are increasingly found inadequate and challenging for some applications. Recognizing the need to address these issues, this paper explores data-driven solutions, focusing on the potential of machine learning (ML) in power system protection and control. It presents a comprehensive review highlighting various applications which are challenging to address from conventional methods. Despite its promise, the integration of ML into power system protection introduces unique challenges. These challenges are examined in the paper, and suggestions are provided to overcome them. Furthermore, the paper identifies potential future research directions, reflecting the progressive trends in ML and its relevance to power system protection and control. This review thereby serves as an essential resource for practitioners and researchers working at the intersection of ML and power systems.

Implications of Machine Learning in the Generation of Renewable Energies in Latin America from a Globalized Vision: A Systematic Review

The global energy industry fundamentally transformed towards renewable energy sources, driven by the sustainability paradigm. This shift was crucial in addressing the challenges of climate change and resource scarcity. Machine Learning (ML) played a pivotal role in enhancing the efficiency and reliability of renewable energy systems. This study conducted a comprehensive analysis of scientific production at the intersection of ML and renewable energy generation, focusing on Latin America. Employing a methodology based on documentary research and bibliometric processes, utilizing the Scopus database with the support of R and VOSviewer software, our research revealed a significant increase in interest and investment in research related to ML and renewable energies since 2020. This exponential growth scenario in this knowledge area had significant implications for Latin America and the world, fostering technological advancements and the adoption of renewable energies. Countries such as China, India, the United States, South Korea, and Saudi Arabia represented 61% of the global scientific production in this field, underscoring its global relevance. This growth indicated a growing interest and investment in ML applications in renewable energies, aligning with the 2030 Agenda for Sustainable Development. This research aligns with the Sustainable Development Goals (SDGs), particularly SDG 7 (Affordable and Clean Energy) and SDG 9 (Industry, Innovation, and Infrastructure). It contributed to progress toward a more sustainable future, benefiting society through more efficient and sustainable energy systems, the energy industry through increased innovation and the adoption of clean technologies, and Latin America, which could leverage these findings to sustainably drive its economic and environmental development.

Human Activity Recognition Using Inertial Sensors in a Smartphone: Technical Background(Review)

Human Activity Recognition (HAR) stands at the intersection of machine learning, deep learning, and sensor technology, primarily focusing on leveraging inertial sensors in smartphones and wearable devices. This paper presents a comprehensive technical overview of HAR, examining the amalgamation of machine learning and deep learning systems while considering the data inputs from mobile and wearable inertial sensors. The review encompasses a broad spectrum of methodologies applied to HAR, ranging from classical machine learning algorithms to cutting-edge deep learning architectures. Emphasis is placed on the nuanced challenges and opportunities posed using inertial sensors in smartphones and wearables. This includes discussions on data preprocessing strategies, feature extraction methods, and model architectures, accounting for the unique characteristics of sensor data, such as noise, variability, and power consumption. The paper explores recent advancements, scrutinizing state-of-the-art approaches, innovative model architectures, and emerging trends in HAR. Through a comparative evaluation of various machine learning and deep learning techniques, the review aims to guide researchers and practitioners in selecting the most appropriate methods for HAR applications across diverse scenarios. In conclusion, this paper serves as an inclusive guide to the technical landscape of HAR, incorporating insights from both mobile and wearable inertial sensors. By synthesizing existing knowledge and addressing future research directions, it aims to propel advancements in developing robust and efficient systems for recognizing human activities, accommodating the evolving landscape of sensor technologies in mobile and wearable devices.

Machine Learning Applications in Healthcare: Current Trends and Future Prospects

The integration of machine learning (ML) in healthcare has witnessed remarkable advancements, transforming the landscape of medical diagnosis, treatment, and overall patient care. This article provides a comprehensive review of the current trends and future prospects of machine learning applications in the healthcare domain.The current landscape is characterized by the utilization of ML algorithms for disease diagnosis and risk prediction, personalized treatment plans, and efficient healthcare resource management. Notable applications include image recognition for radiology and pathology, predictive analytics for disease prognosis, and the development of precision medicine tailored to individual patient profiles.This review explores the evolving role of ML in improving patient outcomes, enhancing clinical decision-making, and optimizing healthcare workflows. It delves into the challenges faced in integrating ML into existing healthcare systems, such as data privacy concerns, interpretability of complex models, and the need for robust validation processes.Additionally, the article discusses future prospects and emerging trends in ML healthcare applications, including the potential for predictive analytics to preemptively identify health issues, the integration of wearable devices and remote monitoring for continuous patient care, and the intersection of ML with genomics for personalized medicine.The overarching goal of this article is to provide healthcare professionals, researchers, and policymakers with insights into the current state of ML applications in healthcare, along with an outlook on the transformative potential that machine learning holds for the future of healthcare delivery and patient outcomes.

Optimizing lower limb rehabilitation: the intersection of machine learning and rehabilitative robotics.

Lower limb rehabilitation is essential for recovery post-injury, stroke, or surgery, improving functional mobility and quality of life. Traditional therapy, dependent on therapists' expertise, faces challenges that are addressed by rehabilitation robotics. In the domain of lower limb rehabilitation, machine learning is progressively manifesting its capabilities in high personalization and data-driven approaches, gradually transforming methods of optimizing treatment protocols and predicting rehabilitation outcomes. However, this evolution faces obstacles, including model interpretability, economic hurdles, and regulatory constraints. This review explores the synergy between machine learning and robotic-assisted lower limb rehabilitation, summarizing scientific literature and highlighting various models, data, and domains. Challenges are critically addressed, and future directions proposed for more effective clinical integration. Emphasis is placed on upcoming applications such as Virtual Reality and the potential of deep learning in refining rehabilitation training. This examination aims to provide insights into the evolving landscape, spotlighting the potential of machine learning in rehabilitation robotics and encouraging balanced exploration of current challenges and future opportunities.