Machine and deep learning algorithms for classifying different types of dementia: A literature review

This study presents a comparative analysis of the classification performance of facial and emotion recognition systems using Machine Learning (ML) and Deep Learning (DL) algorithms. The primary objective of this work is to evaluate the applicability of emotion recognition in fields such as psychotherapy and crime analysis, using the FER-2013 dataset.The study was conducted with ML algorithms such as Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Decision Trees, and Gradient Boosting, as well as the DL algorithm, Convolutional Neural Network (CNN). Supported by the application of feature selection, preprocessing, and feature extraction techniques, the model’s performance was measured using standard metrics such as accuracy, precision, F1-score, and AUC-ROC.The experimental results showed that the highest classification accuracy (46.61%) was achieved with the CNN model. While the ML models generally offered lower accuracy, they provided advantages in terms of computational efficiency in specific scenarios.This study aims to contribute to the literature by providing a comparative analysis of ML and DL algorithms and by highlighting the effect of data preprocessing on performance. The findings set targets for future work, such as real-time system integration and hybrid model development.

Wind energy being a notable and eligible source, has the possibility for bringing out energy in a very constant and sustainable manner. However, wind energy does include numerous challenges like, the halted asset of wind plants, early investment costs, and the strain in discovering areas of wind efficiency. The major objective for proposing this work is to determine the power efficiency of wind turbines, which also aids in the formulation of a proposal to reduce wind turbine maintenance costs. During this research, data analysis of turbine generators is performed on day-to-day wind speed info using machine learning and deep learning algorithms. A way is put forward to support deep learning and machine learning algorithms which can predict different values of power reliably. Hence, the execution of machine and deep learning algorithms are analyzed. For forecasting for a longer term, these algorithms may be used for wind generation rate with historical relation to wind speed info. Moreover, the application of deep and machine learning-based models is place distinct to that of model-trained places. This data analysis demonstrates that in unspecified geographies of wind plants, these sets of algorithms could be successfully implied by utilizing the base location model. The entire project focuses on wind turbine generators and includes the use of data visualization of data analytics to analyze the data and detect the factors that influence wind power generation. With the support of previous data output, wind power is anticipated using both machine learning and deep learning models, where different datasets are used for training and testing. This adds to the uniqueness of this work.

The proliferation of Android malware has become a significant concern in the cyber security landscape. Traditional signature-based detection methods are no longer effective against the rapidly evolving malware threats. Machine Learning (ML) and Deep Learning (DL) algorithms have emerged as a promising solution for Android malware classification and detection. This study aims to investigate the effectiveness of various ML and DL algorithms for Android malware detection. This work analyses the performance of several algorithms, including Support Vector Machines (SVM), Random Forest (RF), and Recurrent Neural Network (RNN). From this analysis, reveals the DL algorithms, particularly RNN, outperform traditional ML algorithms in terms of accuracy, precision, and recall. This finding suggests that the DL algorithm and selects the features can provide an effective solution for Android malware classification and detection. The results of this study can be used to develop a robust and efficient Android malware detection system, which can help protect against the increasing threats of mobile malware. Overall, this study demonstrates the potential of ML and DL algorithms in detecting Android malware and provides insights into the development of effective detection systems.

The main objective of this research is to analyze and compare the performance of machine learning (ML) and deep learning (DL) algorithms in detecting online hate speech. Therefore, Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Convolution Neural Network (CNN), Recurrent Neural Network_Long Short-Term Memory (RNN_LSTM), BERT (Bidirectional Encoder Representations from Transformers), and Distil BERT algorithms have been explored and analyzed in this research. This research has applied the dataset on hate speech which was developed by Andry Samoshyn which is publicly available in Kaggle. ML algorithms and DL algorithms have got good scores in accuracy. In ML, SVM, RF, and LR have got top accuracy values. In DL algorithms, RNN_LSTM, Distil BERT, and BERT have performed well in accuracy. Based on F-measurement, DL classifiers have outperformed ML algorithms. Distil BERT has obtained the highest F-measurement scores. When we compare the overall performances, DL is performed well rather than ML in detecting hate speech. Especially transformer-based models of DL are more efficient than other DL and ML algorithms.KeywordsHate speechMachine learningDeep learning TwitterAnd performance comparison

Wind energy has the possibility for bringing out energy in a very constant and sustainable manner being a notable and eligible source. Although, wind energy does include numerous challenges like, the halted asset of wind plants, early investment costs, and therefore, the strain in discovering areas of wind efficiency. The major objective for proposing this work is to determine the power efficiency of wind turbines, which will also aid in the formulation of a proposal to reduce wind turbine maintenance costs. During this research, data analysis of turbine generators is performed on day to day wind speed info using machine learning and deep learning algorithms. A way is put forward by us to support deep learning and machine learning algorithms which can predict different values of power reliably. Hence, the execution of machine and deep learning algorithms are analyzed. For forecasting for a longer term these algorithms may be used for wind generation rate with historical relation to wind speed info. Index Terms: Wind turbine,machine learning algorithm

Nine novel ensemble models for solar radiation forecasting in Indian cities based on VMD and DWT integration with the machine and deep learning algorithms

Insolvency prediction is one of the crucial abilities in corporate finance and financial management. It is critical in accounts receivable management, capital budgeting decisions, financial analysis, capital structure management, going concern assessment and co-operation with other companies. The purpose of this paper is to compare the efficiency of selected deep learning and machine learning algorithms trained on a representative sample of Polish companies for the period 2008–2017. In particular, the paper tested the following popular machine learning algorithms: discriminant analysis (DA), logit (L), support vector machines (SVM), random forest (RF), gradient boosting decision trees (GB), neural network with one hidden layer (NN), convolutional neural network (CNN), and naïve Bayes (NB). The research hypotheses evaluated in the paper state that if one has access to a large sample of companies, the most accurate algorithm (first choice) in bankruptcy prediction will be gradient boosting decision trees (H1), random forest (H2) and neural networks (H3) (deep learning) algorithms. The initial hypotheses were formulated based on the practitioners’ opinions regarding the usefulness of various machine learning and artificial intelligence algorithms in bankruptcy prediction. As the results of the research suggest, both deep learning and machine learning algorithms proved to have very comparable efficiency. The new factor introduced in the paper was that the training of the models was carried out on a representative sample of companies (for years 2008–2013) and also the testing phase used a significant number of bankrupt and active companies (validation included a completely different set of companies than those used in the training phase: data were taken from a different time period, 2014–2017, and companies in both sets were also completely different).

Up to the present, various methods such as Data Mining, Machine Learning, and Artificial Intelligence have been used to get the best assess from huge and important data resource. Deep Learning, one of these methods, is extended version of Artificial Neural Networks. Within the scope of this study, a model has been developed to classify the success of tele-marketing with different machine learning algorithms especially with Deep Learning algorithm. Naïve Bayes, C5.0, Extreme Learning Machine and Deep Learning algorithms have been used for modelling. To examine the effect of class label distribution on model success, Synthetic Minority Oversampling Technique have been used. The results have revealed the success of Deep Learning and Decision Trees algorithms. When the data set was not balanced, the Deep Learning algorithm performed better in terms of sensitivity. Among all models, the best performance in terms of accuracy, precision and F-score have been achieved with the C5.0 algorithm.

This work aims to compare the performance of Machine Learning (ML) and Deep Learning (DL) algorithms in detecting users' heartbeats on a smart bed. Targeting non-intrusive, continuous heart monitoring during sleep time, the smart bed is equipped with a 3D solid-state accelerometer. Acceleration signals are processed through an STM 32-bit microcontroller board and transmitted to a PC for recording. A photoplethysmographic sensor is simultaneously checked for ground truth reference. A dataset has been built, by acquiring measures in a real-world set-up: 10 participants were involved, resulting in 120 min of acceleration traces which were utilized to train and evaluate various Artificial Intelligence (AI) algorithms. The experimental analysis utilizes K-fold cross-validation to ensure robust model testing across different subsets of the dataset. Various ML and DL algorithms are compared, each being trained and tested using the collected data. The Random Forest algorithm exhibited the highest accuracy among all compared models. While it requires longer training time compared to some ML models such as Naïve Bayes, Linear Discrimination Analysis, and K-Nearest Neighbour Classification, it keeps substantially faster than Support Vector Machine and Deep Learning models. The Random Forest model demonstrated robust performance metrics, including recall, precision, F1-scores, macro average, weighted average, and overall accuracy well above 90%. The study highlights the better performance of the Random Forest algorithm for the specific use case, achieving superior accuracy and performance metrics in detecting user heartbeats in comparison to other ML and DL models tested. The drawback of longer training times is not too relevant in the long-term monitoring target scenario, so the Random Forest model stands out as a viable solution for real-time ballistocardiographic heartbeat detection, showcasing potential for healthcare and wellness monitoring applications.

Owing to recent development in technology, major changes have been noticed in human being's life. Today's lives of human being are becoming more convenient (i.e., in terms of living standard). In current real-world applications, we have shifted our attention from wired devices to wireless devices. As a result, we moved into the era of smart technology, where a lot of Internet devices are connected together in a distributed and decentralized manner. Such Internet-connected devices (ICDs) or Internet of Things (IoTs) engender tremendous data (i.e., via communicating other smart devices). With the tremendous increase in the amount of data, there is a higher requirement to process this huge amount of data (generated through billions of ICDs) using efficient machine learning (ML) algorithms.In the past decade, we refer data mining algorithms to make some decision from collected data-sets. But, due to increasing data on a large scale, data mining fail to handle this data. So, as substitute of data mining algorithms and to refine this information in an efficient manner, we require tradition analytics algorithms, i.e., ML or data mining algorithms. In current scenario, some of the ML algorithms (available to analysis this data) are supervised (used with labeled data), unsupervised (used with unlabelled data) and semi-supervised (work as reward-based learning). Supervised learning algorithms are like linear regression, classification and k-nearest neighbor (KNN), etc. Whereas, unsupervised learning algorithms are clustering, k-means, etc. In general, ML focuses on building the systems that learn and hence improves with the knowledge and experience. Being the heart of artificial intelligence (AI) and data science, ML is gaining popularity day by day. Several algorithms have already been developed (in the past decade) for processing of data, although this field focuses on developing new learning algorithm for big data computability with minimum complexity (i.e., in terms of time and space). ML algorithms are not only applicable to computer science field but also extend to medical, psychological, marketing, manufacturing, automobile, etc.On another side, Big Data including deep learning are the two primary and highly demandable fields of data science. A subset of ML, computer vision or AI, deep learning is used here. The large (or massive) amount of data related to a specific domain which forms Big Data (in form of 5 V's like velocity, volume, value, variety, and veracity) contains valuable information related to various fields like marketing, automobile, finance, cyber security, medical, fraud detection, etc. Such real-world applications are creating a lot of information every day. The valuable (i.e., needful or meaningful) information are required to be processed (or retrieved) from analysis of this unstructured/ large amount of data for further processing of the data for future use (or for prediction). Big organizations have to accord with the tremendous volume of data for prediction, classification, decision making, etc. The use of ML algorithms for big data analytics, which extracts the high-level semantics from the valuable (meaningful) information form the data. It uses hierarchical process for efficient processing and retrieving the complex abstraction from the data.Hence, this chapter discusses several algorithms of ML, to analysis of Big Data. Also, the subset AI like ML algorithms, deep learning algorithms are being discussed here (i.e., to analysis this Big Data for efficient prediction). Later, this chapter focuses on benefits of ML, deep learning algorithms in analyzing tremendous volume of data (i.e., in unsupervised or unstructured form) for numerous complex problems like information retrieval, medical diagnosis, cognitive science, indexing using semantic analysis, data tagging, speech recognition, natural language processing, etc. Also, weakness, raised issues, and challenges (during analysis big data) using (in) ML or deep learning have been discussed in detail. In other words, research gaps in using ML, deep learning algorithms for big data will also be discussed (covering future research aspects/trends). Finally, this chapter discusses the significance of the smart era, computational intelligence, and AI in depth.

Digital image processing has witnessed a significant transformation, owing to the adoption of deep learning (DL) algorithms, which have proven to be vastly superior to conventional methods for crop detection. These DL algorithms have recently found successful applications across various domains, translating input data, such as images of afflicted plants, into valuable insights, like the identification of specific crop diseases. This innovation has spurred the development of cutting-edge techniques for early detection and diagnosis of crop diseases, leveraging tools such as convolutional neural networks (CNN), K-nearest neighbour (KNN), support vector machines (SVM), and artificial neural networks (ANN). This paper offers an all-encompassing exploration of the contemporary literature on methods for diagnosing, categorizing, and gauging the severity of crop diseases. The review examines the performance analysis of the latest machine learning (ML) and DL techniques outlined in these studies. It also scrutinizes the methodologies and datasets and outlines the prevalent recommendations and identified gaps within different research investigations. As a conclusion, the review offers insights into potential solutions and outlines the direction for future research in this field. The review underscores that while most studies have concentrated on traditional ML algorithms and CNN, there has been a noticeable dearth of focus on emerging DL algorithms like capsule neural networks and vision transformers. Furthermore, it sheds light on the fact that several datasets employed for training and evaluating DL models have been tailored to suit specific crop types, emphasizing the pressing need for a comprehensive and expansive image dataset encompassing a wider array of crop varieties. Moreover, the survey draws attention to the prevailing trend where the majority of research endeavours have concentrated on individual plant diseases, ML, or DL algorithms. In light of this, it advocates for the development of a unified framework that harnesses an ensemble of ML and DL algorithms to address the complexities of multiple plant diseases effectively.

The rapid growth of the Internet and information technologies and also the diminution of the price of hardware components like wireless sensors leads to the fast growth in Wireless Sensor Network (WSN). The WSN is a bunch/group of sensors that are located across the area, in order to monitor and determine environmental conditions such as temperature, humidity, vibrations, wind, water levels, pollution levels. WSNs are susceptible to major attacks like Denial of Service (DOS), Wormhole attack, Sinkhole attack, etc. The main threat to the WSN is because of the broadcast nature of the nodes in the network. Therefore, the security of WSNs is the essential part that must be done. Hence, to overcome these problems or threats, we are trying to detect it using AI technology. With the expanding fields of Machine Learning and Deep Learning, we can apply various algorithms in order to classify different types of attacks. Once we detect the attack properly, we can prevent it accordingly. We are using WSN-DS. It has 4 classes of attacks which are Grayhole, Blackhole, TDMA(Scheduling), and Flooding which comes under the category of DOS attacks. In this chapter, we have analysed and compared the accuracies of 5 main machine learning classification algorithms. Also, we have analysed the 1 deep learning algorithm. The ANN (Artificial Neural Network) and 5 machine learning algorithms have been trained on the dataset. Furthermore, we have used K-fold cross-validation to get even more accurate predictions. After analysis of these algorithms, we came to the point that, the Machine Learning algorithms like Random Forest, Support Vector Machines and Deep Learning algorithm, namely, Artificial Neural Network can help us for detecting intrusions in the system or network. This will help researchers in designing their own machine learning model on top of our suggested model.

Atrial fibrillation (AF) is a common arrhythmia that can result in adverse cardiovascular outcomes but is often difficult to detect. The use of machine learning (ML) algorithms for detecting AF has become increasingly prevalent in recent years. This study aims to systematically evaluate and summarize the overall diagnostic accuracy of the ML algorithms in detecting AF in electrocardiogram (ECG) signals. The searched databases included PubMed, Web of Science, Embase, and Google Scholar. The selected studies were subjected to a meta-analysis of diagnostic accuracy to synthesize the sensitivity and specificity. A total of 14 studies were included, and the forest plot of the meta-analysis showed that the pooled sensitivity and specificity were 97% (95% confidence interval [CI]: 0.94-0.99) and 97% (95% CI: 0.95-0.99), respectively. Compared to traditional machine learning (TML) algorithms (sensitivity: 91.5%), deep learning (DL) algorithms (sensitivity: 98.1%) showed superior performance. Using multiple datasets and public datasets alone or in combination demonstrated slightly better performance than using a single dataset and proprietary datasets. ML algorithms are effective for detecting AF from ECGs. DL algorithms, particularly those based on convolutional neural networks (CNN), demonstrate superior performance in AF detection compared to TML algorithms. The integration of ML algorithms can help wearable devices diagnose AF earlier.

ACS mortality prediction in Asian in-hospital patients with deep learning using machine learning feature selection

The popularity of machine learning (ML), deep learning (DL) and artificial intelligence (AI) has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML and DL algorithms are often perceived as opaque, and their relationship to classical data analysis tools remains debated. Although it is often assumed that ML and DL excel primarily at making predictions, ML and DL can also be used for analytical tasks traditionally addressed with statistical models. Moreover, most recent discussions and reviews on ML focus mainly on DL, failing to synthesise the wealth of ML algorithms with different advantages and general principles. Here, we provide a comprehensive overview of the field of ML and DL, starting by summarizing its historical developments, existing algorithm families, differences to traditional statistical tools, and universal ML principles. We then discuss why and when ML and DL models excel at prediction tasks and where they could offer alternatives to traditional statistical methods for inference, highlighting current and emerging applications for ecological problems. Finally, we summarize emerging trends such as scientific and causal ML, explainable AI, and responsible AI that may significantly impact ecological data analysis in the future. We conclude that ML and DL are powerful new tools for predictive modelling and data analysis. The superior performance of ML and DL algorithms compared to statistical models can be explained by their higher flexibility and automatic data‐dependent complexity optimization. However, their use for causal inference is still disputed as the focus of ML and DL methods on predictions creates challenges for the interpretation of these models. Nevertheless, we expect ML and DL to become an indispensable tool in ecology and evolution, comparable to other traditional statistical tools.