ML Applications Research Articles

Knowledge structure and global trends of machine learning in stroke over the past decade: A scientometric analysis

ObjectiveMachine learning (ML) models have been widely applied in stroke prediction, diagnosis, treatment, and prognosis assessment. We aimed to conduct a comprehensive scientometrics analysis of studies related to ML in stroke and reveal its current status, knowledge structure, and global trends. MethodsAll documents related to ML in stroke were retrieved from the Web of Science database on March 15, 2023. We refined the documents by including only original articles and reviews in the English language. The literature published over the past decade was imported into scientometrics software for influence detection and collaborative network analysis. Results2389 related publications were included. The annual publication outputs demonstrated explosive growth, with an average growth rate of 63.99 %. Among the 90 countries/regions involved, the United States (729 articles) and China (636 articles) were the most productive countries. Frontiers in Neurology was the most prolific journal with 94 articles. 234 highly cited articles, each with more than 31 citations, were detected. Keyword analysis revealed a total of 5333 keywords, with a predominant focus on the application of ML models in the early diagnosis, classification, and prediction of “acute ischemic stroke” and “atrial fibrillation-related stroke”. The keyword “classification” had the first and longest burst, spanning from 2013 to 2018. ‘Upport vector machine’ got the strongest burst strength with 6.2. Keywords such as ‘mechanical thrombectomy’, ‘expression’, and 'prognosis' experienced bursts in 2022 and have continued to be prominent. ConclusionThe applications of ML in stroke are increasingly diverse and extensive, with researchers showing growing interest over the past decade. However, the clinical application of ML in stroke is still in its early stages, and several limitations and challenges need to be addressed for its widespread adoption in clinical practice.

Why "ML in Health Science"

This is the first editorial of the journal, discussing the balance between humans and AI in healthcare and emphasizing the need for a human-centric approach in AI and ML applications.

The Role of Artificial Intelligence and Machine Learning in Healthcare: Implications for Actuarial Models and Predictive Analytics in Lagos State Nigeria

This paper examined the role of artificial intelligence and machine learning in healthcare using implications for actuarial models and predictive analytics in Lagos State, Nigeria. Four research questions guided the study. The descriptive survey research design was adopted for this study. The population of this study comprised of all the healthcare professionals in Lagos State University Teaching Hospital (LASUTH) and all actuarial managers from the 27 insurance companies in Lagos State, Nigeria. The purposive sampling technique was used to select an actuarial manager from each of the 27 insurance companies in Lagos State, making a total of 27 actuarial managers that participated in the study. Purposive sampling technique was also used to select 30 healthcare professionals in LASUTH. In total, the sample size consisted of 57 respondents. The study used a structured questionnaire called “Role of Artificial Intelligence and Machine Learning in Healthcare Questionnaire” (RAIMLHQ) to gather data on the application of AI and ML in healthcare. The questionnaire was divided into two sections and responses were based on a 4-point Likert scale. The researchers administered the questionnaire directly, and descriptive statistics were used to analyze the bio-data. The results showed that healthcare professionals and actuarial managers had low knowledge of AI and ML’s application in healthcare. However, they rated AI and ML technologies as effective in improving healthcare outcomes in Lagos State. Furthermore, they agreed on the implications of integrating AI and ML into actuarial models for healthcare insurance in Lagos State.

Deep learning applications in investment portfolio management: a systematic literature review

PurposeMachine learning (ML), and deep learning in particular, is gaining traction across a myriad of real-life applications. Portfolio management is no exception. This paper provides a systematic literature review of deep learning applications for portfolio management. The findings are likely to be valuable for industry practitioners and researchers alike, experimenting with novel portfolio management approaches and furthering investment management practice.Design/methodology/approachThis review follows the guidance and methodology of Linnenluecke et al. (2020), Massaro et al. (2016) and Fisch and Block (2018) to first identify relevant literature based on an appropriately developed search phrase, filter the resultant set of publications and present descriptive and analytical findings of the research itself and its metadata.FindingsThe authors find a strong dominance of reinforcement learning algorithms applied to the field, given their through-time portfolio management capabilities. Other well-known deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN) and its derivatives, have shown to be well-suited for time-series forecasting. Most recently, the number of papers published in the field has been increasing, potentially driven by computational advances, hardware accessibility and data availability. The review shows several promising applications and identifies future research opportunities, including better balance on the risk-reward spectrum, novel ways to reduce data dimensionality and pre-process the inputs, stronger focus on direct weights generation, novel deep learning architectures and consistent data choices.Originality/valueSeveral systematic reviews have been conducted with a broader focus of ML applications in finance. However, to the best of the authors’ knowledge, this is the first review to focus on deep learning architectures and their applications in the investment portfolio management problem. The review also presents a novel universal taxonomy of models used.

Boosting RRAM-Based Mixed-Signal Accelerators in FD-SOI Technology for ML Applications

Boosting RRAM-Based Mixed-Signal Accelerators in FD-SOI Technology for ML Applications

Assessing the Potential of AI–ML in Urban Climate Change Adaptation and Sustainable Development

This study addresses a notable gap in the climate change literature by examining the potential of artificial intelligence and machine learning (AI–ML) in urban climate change adaptation and sustainable development across major global continents. While much attention has been given to mitigation strategies, this study uniquely delves into the AI–ML’s underexplored role in catalyzing climate change adaptation in contemporary and future urban centers. The research thoroughly explores diverse case studies from Africa, Asia, Australasia, Europe, North America, and South America, utilizing a methodological framework involving six-step and five-step models for systematic literature reviews. The findings underscore AI–ML achievements, illuminate challenges, and emphasize the need for context-specific and collaborative approaches. The findings imply that a one-size-fits-all approach is insufficient. Instead, successful adaptation strategies must be intricately linked to the particular characteristics, vulnerabilities, and intricacies of each region. Furthermore, the research underscores the importance of international collaboration, knowledge sharing, and technology transfer to expedite the integration of AI–ML into climate adaptation strategies globally. The study envisions a promising trajectory for AI–ML in the climate adaptation domain, emphasizing the necessity for ongoing research, innovation, and practical AI–ML applications. As climate change remains a defining challenge, this research predicts an increasingly pivotal role for AI–ML in constructing climate-resilient urban centers and promoting sustainable development. Continuous efforts to advance AI–ML technologies, establish robust policy frameworks, and ensure universal access are crucial for harnessing AI–ML’s transformative capabilities to combat climate change consequences.

Machine Learning in Cardiovascular Risk Prediction and Precision Preventive Approaches.

In this review, we sought to provide an overview of ML and focus on the contemporary applications of ML in cardiovascular risk prediction and precision preventive approaches. We end the review by highlighting the limitations of ML while projecting on the potential of ML in assimilating these multifaceted aspects of CAD in order to improve patient-level outcomes and further population health. Coronary artery disease (CAD) is estimated to affect 20.5 million adults across the USA, while also impacting a significant burden at the socio-economic level. While the knowledge of the mechanistic pathways that govern the onset and progression of clinical CAD has improved over the past decade, contemporary patient-level risk models lag in accuracy and utility. Recently, there has been renewed interest in combining advanced analytic techniques that utilize artificial intelligence (AI) with a big data approach in order to improve risk prediction within the realm of CAD. By virtue of being able to combine diverse amounts of multidimensional horizontal data, machine learning has been employed to build models for improved risk prediction and personalized patient care approaches. The use of ML-based algorithms has been used to leverage individualized patient-specific data and the associated metabolic/genomic profile to improve CAD risk assessment. While the tool can be visualized to shift the paradigm toward a patient-specific care, it is crucial to acknowledge and address several challenges inherent to ML and its integration into healthcare before it can be significantly incorporated in the daily clinical practice.

An Intelligent Heart Disease Prediction Framework Using Machine Learning and Deep Learning Techniques

Cardiovascular diseases (CVD) rank among the leading global causes of mortality. Early detection and diagnosis are paramount in minimizing their impact. The application of ML and DL in classifying the occurrence of cardiovascular diseases holds significant potential for reducing diagnostic errors. This research endeavors to construct a model capable of accurately predicting cardiovascular diseases, thereby mitigating the fatality associated with CVD. In this paper, the authors introduce a novel approach that combines an artificial intelligence network (AIN)-based feature selection (FS) technique with cutting-edge DL and ML classifiers for the early detection of heart diseases based on patient medical histories. The proposed model is rigorously evaluated using two real-world datasets sourced from the University of California. The authors conduct extensive data preprocessing and analysis, and the findings from this study demonstrate that the proposed methodology surpasses the performance of existing state-of-the-art methods, achieving an exceptional accuracy rate of 99.99%.

Teaching Machine Learning to Middle and High School Students from a Low Socio-Economic Status Background

Knowledge about Machine Learning is becoming essential, yet it remains a restricted privilege that may not be available to students from a low socio-economic status background. Thus, in order to provide equal opportunities, we taught ML concepts and applications to 158 middle and high school students from a low socio-economic background in Brazil. Results show that these students can understand how ML works and execute the main steps of a human-centered process for developing an image classification model. No substantial differences regarding class periods, educational stage, and sex assigned at birth were observed. The course was perceived as fun and motivating, especially to girls. Despite the limitations in this context, the results show that they can be overcome. Mitigating solutions involve partnerships between social institutions and university, an adapted pedagogical approach as well as increased on-by-one assistance. These findings can be used to guide course designs for teaching ML in the context of underprivileged students from a low socio-economic status background and thus contribute to the inclusion of these students.

SAGA: A Scalable Framework for Optimizing Data Cleaning Pipelines for Machine Learning Applications

In the exploratory data science lifecycle, data scientists often spent the majority of their time finding, integrating, validating and cleaning relevant datasets. Despite recent work on data validation, and numerous error detection and correction algorithms, in practice, data cleaning for ML remains largely a manual, unpleasant, and labor-intensive trial and error process, especially in large-scale, distributed computation. The target ML application---such as classification or regression models---can be used as a signal of valuable feedback though, for selecting effective data cleaning strategies. In this paper, we introduce SAGA, a framework for automatically generating the top-K most effective data cleaning pipelines. SAGA adopts ideas from Auto-ML, feature selection, and hyper-parameter tuning. Our framework is extensible for user-provided constraints, new data cleaning primitives, and ML applications; automatically generates hybrid runtime plans of local and distributed operations; and performs pruning by interesting properties (e.g., monotonicity). Instead of full automation---which is rather unrealistic---SAGA simplifies the mechanical aspects of data cleaning. Our experiments show that SAGA yields robust accuracy improvements over state-of-the-art, and good scalability regarding increasing data sizes and number of evaluated pipelines.

Survey of Applications of Ml in Stress Detection

Stress is a common and pervasive issue that affects millions of people worldwide. It can lead to a variety of negative health outcomes, including anxiety, depression, and physical health problems. Early detection of stress is crucial for effective management and prevention of these negative outcomes. Stress detection technologies using machine learning algorithms can provide individuals with valuable information about their stress levels and help them manage their stress in more effective ways. This can lead to improved mental and physical health outcomes, as well as increased productivity and overall well-being. Therefore, stress detection is an important area of research that has the potential to positively impact the lives of many people. 
 This paper presents a survey of techniques applicable to the field of stress detection using machine learning (ML) algorithms. We categorize these techniques based on the approach they take and discuss various challenges, open questions, and future work in this area. We present a taxonomy of existing research and finally discuss gaps and future directions of research to advance the study of stress management using most recent ML techniques. These technologies
 provide individuals with valuable information about their stress levels and can help them manage their stress in more effective ways.

Evaluation of Current Trends in Biomedical Applications Using Soft Computing

Abstract: With the rapid advancement in analyzing high-volume and complex data, machine learning has become one of the most critical and essential tools for classification and prediction. This study reviews machine learning (ML) and deep learning (DL) methods for the classification and prediction of biological signals. The effective utilization of the latest technology in numerous applications, along with various challenges and possible solutions, is the main objective of this present study. A PICO-based systematic review is performed to analyze the applications of ML and DL in different biomedical signals, viz. electroencephalogram (EEG), electromyography (EMG), electrocardiogram (ECG), and wrist pulse signal from 2015 to 2022. From this analysis, one can measure machine learning's effectiveness and key characteristics of deep learning. This literature survey finds a clear shift toward deep learning techniques compared to machine learning used in the classification of biomedical signals.

Product-Based Collaborative Filtering Recommendation System for E- Commerce

Recommendation System are an application of ML. RS in any E-commerce websites are an important aspect as they are needed to satisfy the customers and for a better user experience. They help to suggest the best possible products a user might want to buy. The Product- based Collaborative Filtering is used in RS to suggest the desired products in an efficient way. They will allow a customer using the website to buy a product of a particular brand or of a certain price limit. Further it will not need much struggle as it will use the previous history of the user to recommend the products. This method can further enhance the UI. Further RS also has its roots in DL where we can use Neural networks for the RS.

EEG-based Mouse Cursor Control

The last decade has seen an increase in the use of artificial intelligence (AI) and machine learning. Recent advances in the field of BC have led to renewed interest in the use of electroencephalography (EEG) for different fields. EEG is used in medical and biomedical applications such as analyzing mental workload and fatigue, diagnosing brain tumors, and rehabilitation of central nervous system disorders; EEG-based movement analysis and classification is widely used in many areas, from clinical applications to brain-machine interface and robotic applications. This article reviews applications of several BC algorithms used in EEG signal processing, introducing commonly used algorithms, typical application scenarios, key advances, and current problems. The study explored current ML applications in EEG, including brain-computer interfaces, cognitive neuroscience, diagnosis of brain disorders. First, the basic principles of ML algorithms used in EEG signal processing, including convolutional neural networks, support vector machines, K-nearest neighbor, and omnidirectional convolutional neural networks, are briefly described. Additionally, a general survey of BC applications used in EEG analysis is presented. As a result, it was determined that SVM methods were used most in the studies, and the study topics were mainly on epilepsy, BCI, and Emotion, and least on Sleep States and Perception.

Development of clustered machine learning technique for the modeling of scour profile induced by propeller jets

In this study novel clustered machine learning (CML) models were developed by applying different base learners including multi linear regression (MLR), adaptive neuro-fuzzy inference system (ANFIS), classification and regression trees (CART), least-squares boosting (LSBoost), and random forest (RF) to predict scour profile induced by the jet of a propeller. Moreover, the results of CML models were compared with regular ML algorithms. The results show that the tree-based ensemble models, RF and LSBoost, are more accurate than CART. The ANIFS has the worst performance compared with other regular nonlinear methods, RMSE = 17.414 mm. The performance of MLR is also weak, RMSE = 35.63 mm and R2 = 0.088. However, the implementation of CML drastically increases the performance of MLR, RMSE = 15.053 mm, and R2 = 0.871. The CANFIS with RMSE = 8.757 mm, R2 = 0.976, and SI = 0 is ranked as the most accurate model. The results show that CLM enhances the performance of regular ML by up to 59.90%. The application of clustered ML is recommended for other complex problems. Finally, the results show that the derived models trained by other datasets very well predict measured scour profiles which datasets were not used in the training process.

Lumpy Diseases Detection using Machine Learning

Machine learning algorithms for improving animal health monitoring have accelerated the creation of ML applications for behavioral and physiological monitoring systems, including ML-based animal health monitoring systems. Currently, farm animals are raised all over the world, and it is necessary to monitor their physiological processes. It is suggested in this article to use machine learning models to continuously monitor each animal's vital signs and look for biological changes. In this model, crucial data is gathered via IoT devices, and data analysis is carried out using machine learning techniques to identify potential dangers from changes in an animal's physiological state. The results of the experiments demonstrate that the suggested model is accurate and efficient enough to identify animal situations. For our purposes, the CNN and YOLO accuracy of more than 90% is a promising outcome. Keywords- Lumpy disease , Machine learning, Images

Chromium mediated damaging effects on growth, nitrogen metabolism and chlorophyll synthesis in tomato can be alleviated by foliar application of melatonin and jasmonic acid priming

Efficiency of methyl-jasmonate (5 µM Me-J) priming and the foliar application of melatonin (100 µM ML) in assuaging the deleterious effects of chromium (Cr) toxicity on growth, nitrogen metabolism, chlorophyll synthesis and photosynthesis in tomato were studied. Chromium toxicity reduced growth, chlorophyll synthesis and photosynthesis significantly, however Me-J and ML significantly enhanced the parameters. Decline in the intermediates of chlorophyll biosynthesis pathway i.e., glutamate 1-semialdehyde, δ-amino levulinic acid, Mg-prototoporphyrin IX, prototoporphyrin IX and protochlorophyllide due to Cr was alleviated to considerable levels due to Me-J and ML treatment. Toxicity of Cr was evident as increased production of superoxide and hydrogen peroxide, and activity of lipoxygenase and protease while as Me-J and ML treatment alleviated the oxidative damage by causing significant decline in these parameters. Priming with Me-J and foliar application of ML alleviated the Cr toxicity induced decline in the activities of nitrogen metabolising enzymes. Treatment of Me-J and ML up-regulated the antioxidant system functioning, increased the content of secondary metabolites and activity of phenylalanine ammonia lyase. Accumulation of osmolytes increased due to Me-J and ML under normal as well as Cr toxicity conditions. Treatment of Me-J and ML increased the γ-glutamyl kinase activity with significant reduction in proline oxidase.

A novel method for petroleum and natural gas resource potential evaluation and prediction by support vector machines (SVM)

Petroleum and natural gas resources (PNGR) are some of the major forms of fossil energy that are important for the development of industry and energy security. Along with the growing demand of petroleum consumption and the requirement for enhancing drilling success rate, reducing the exploration risk and saving exploration cost, prediction method for PNGR potential with high accuracy and wide practicability is needed. However, the existing PNGR evaluation and prediction methods based on traditional statistical principles are far from meeting the requirements of the present petroleum exploration and exploitation. Therefore, this study introduces a novel method for PNGR potential prediction by applying support vector machines (SVM) in the context of the rapid development of artificial intelligence and machine learning. This novel machine learning methodology first proposed a combination of support vector classification (SVC) for hydrocarbon accumulation probability prediction and then support vector regression (SVR) for reserve abundance prediction. The combining use of classification and regression model can fully utilize the professional knowledge of petroleum geology and the powerful data processing capabilities of machine learning algorithms and hence significantly improve the performance of the method. Furthermore, the dataset is set based on petroleum geology knowledge with the feature variables of source rock, sandstone reservoirs, sealing capacity and hydrocarbon migration, whose distribution are predictable and thus ensures the predictive effect in practical petroleum exploration. The results show that the testing accuracy of the hydrocarbon accumulation probability evaluation model by SVC ranges from 80% to 100% with an average of 88.92%. The performance of the SVR model for evaluating reserve abundance also performs well with the highest correlation coefficient of 0.767. In addition, several validation ways are applied for testing the reliability and stability of the model. For a hold-out test for a new zone, the model provides precise prediction of hydrocarbon accumulation probability and reserve abundance with an accuracy of 72.5% and a correlation coefficient of 0.744. The evaluation metric of the F1-score shows an average of 0.91 for the SVC models, the 4-fold cross-validation shows an average correlation coefficient of 0.663 for SVR model, which indicates the good performance of the SVC and SVR model. To conclude, this study not only provides an intelligent ML method system for PNGR potential precisely evaluation and prediction with the combination of SVC and SVR which is firstly used by application of ML in petroleum industry field, but is also significant for the application of ML in petroleum and natural gas exploration and exploitation.

(Invited) Machine Learning for Solid-State Batteries – Progress Versus Hype

Machine learning in materials science and solid-state batteries are two topics that have captured the imagination of researchers in recent years. Therefore, it is unsurprising that many researchers have attempted to apply the advances in ML to the discovery and study of materials for solid-state batteries. In this talk, I will discuss the importance of going back to fundamentals in the application of ML to materials for solid-state batteries, in particular, the critical solid electrolyte component and its interfaces. I will highlight areas where ML has had a transformative impact on our understanding and discovery of solid electrolytes, and what are some of the remaining challenges that remain to be surmounted.

Athlete injury detection and emergency treatment in mobile smart medical system

Using the sports injury monitoring system to detect injury symptoms in time and take effective treatment measures in time can reduce the damage caused by sports injuries to athletes. However, many current detection methods lack the support of advanced technologies and algorithms, resulting in poor performance in sports injury detection. Based on this, a mobile intelligent medical system is designed in this paper, and an athlete injury detection method based on CNN and sensors is proposed. The method includes three parts: motion region acquisition, motion injury feature extraction, and motion injury detection. In addition, for emergency treatment, this paper proposes a variety of CNN-based image data analysis methods to ensure the accuracy of the processing process. The experimental results show that the athlete injury detection method based on the convolutional neural network improves the detection accuracy by 6.73% compared with the traditional method, which also provides an important reference for the future application of ML in medical treatment. The research confirms that the construction and analysis of mobile intelligent medical system can effectively improve the accuracy of sports injury detection.