Search

This paper presents the topology and machine learning-based intelligent control of high-power PV inverter for maximum power extraction and optimal energy utilization. Modular converters with reduced components economic and reliable for high power applications. The proposed integrated intelligent machine learning based control delivers power conversion control with maximum power extraction and supervisory control for optimal load demand control. The topology of the inverter, operating modes, power control and supervisory control aspects are presented. Simulation is carried out in MATLAB/SIMULINK to verify the feasibility of the proposed inverter and control algorithm. The experimental study is presented to validate the simulation results. The operational performance of the proposed topology is evaluated in terms of operational parameters such as regulation of output power, and load relay control and is compared to existing topologies. The economic performance is also evaluated in terms of power switch sizing and reliability in power delivery concerning switch or power sources failure., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Srungaram, Yadlapati. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

The rise of social media has changed how people view connections. Machine Learning (ML)-based sentiment analysis and news categorization help understand emotions and access news. However, most studies focus on complex models requiring heavy resources and slowing inference times, making deployment difficult in resource-limited environments. In this paper, we process both structured and unstructured data, determining the polarity of text using the TextBlob scheme to determine the sentiment of news headlines. We propose a Stochastic Gradient Descent (SGD)-based Ridge classifier (RC) for blending SGDR with an advanced string processing technique to effectively classify news articles. Additionally, we explore existing supervised and unsupervised ML algorithms to gauge the effectiveness of our SGDR classifier. The scalability and generalization capability of SGD and L2 regularization techniques in RCs to handle overfitting and balance bias and variance provide the proposed SGDR with better classification capability. Experimental results highlight that our string processing pipeline significantly boosts the performance of all ML models. Notably, our ensemble SGDR classifier surpasses all state-of-the-art ML algorithms, achieving an impressive 98.12% accuracy. McNemar's significance tests reveal that our SGDR classifier achieves a 1% significance level improvement over K-Nearest Neighbor, Decision Tree, and AdaBoost and a 5% significance level improvement over other algorithms. These findings underscore the superior proficiency of linear models in news categorization compared to tree-based and nonlinear counterparts. This study contributes valuable insights into the efficacy of the proposed methodology, elucidating its potential for news categorization and sentiment analysis., Competing Interests: Authors have no conflict of interest to declare., (Copyright: © 2024 Hasan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Thyroid disease classification plays a crucial role in early diagnosis and effective treatment of thyroid disorders. Machine learning (ML) techniques have demonstrated remarkable potential in this domain, offering accurate and efficient diagnostic tools. Most of the real-life datasets have imbalanced characteristics that hamper the overall performance of the classifiers. Existing data balancing techniques process the whole dataset at a time that sometimes causes overfitting and underfitting. However, the complexity of some ML models, often referred to as "black boxes," raises concerns about their interpretability and clinical applicability. This paper presents a comprehensive study focused on the analysis and interpretability of various ML models for classifying thyroid diseases. In our work, we first applied a new data-balancing mechanism using a clustering technique and then analyzed the performance of different ML algorithms. To address the interpretability challenge, we explored techniques for model explanation and feature importance analysis using eXplainable Artificial Intelligence (XAI) tools globally as well as locally. Finally, the XAI results are validated with the domain experts. Experimental results have shown that our proposed mechanism is efficient in diagnosing thyroid disease and can explain the models effectively. The findings can contribute to bridging the gap between adopting advanced ML techniques and the clinical requirements of transparency and accountability in diagnostic decision-making., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Akter, Mustafa. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

In the current era, quantum resources are extremely limited, and this makes difficult the usage of quantum machine learning (QML) models. Concerning the supervised tasks, a viable approach is the introduction of a quantum locality technique, which allows the models to focus only on the neighborhood of the considered element. A well-known locality technique is the k-nearest neighbors (k-NN) algorithm, of which several quantum variants have been proposed; nevertheless, they have not been employed yet as a preliminary step of other QML models. Instead, for the classical counterpart, a performance enhancement with respect to the base models has already been proven. In this paper, we propose and evaluate the idea of exploiting a quantum locality technique to reduce the size and improve the performance of QML models. In detail, we provide (i) an implementation in Python of a QML pipeline for local classification and (ii) its extensive empirical evaluation. Regarding the quantum pipeline, it has been developed using Qiskit, and it consists of a quantum k-NN and a quantum binary classifier, both already available in the literature. The results have shown the quantum pipeline's equivalence (in terms of accuracy) to its classical counterpart in the ideal case, the validity of locality's application to the QML realm, but also the strong sensitivity of the chosen quantum k-NN to probability fluctuations and the better performance of classical baseline methods like the random forest., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Zardini et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

When judging the quality of a computational system for a pathological screening task, several factors seem to be important, like sensitivity, specificity, accuracy, etc. With machine learning based approaches showing promise in the multi-label paradigm, they are being widely adopted to diagnostics and digital therapeutics. Metrics are usually borrowed from machine learning literature, and the current consensus is to report results on a diverse set of metrics. It is infeasible to compare efficacy of computational systems which have been evaluated on different sets of metrics. From a diagnostic utility standpoint, the current metrics themselves are far from perfect, often biased by prevalence of negative samples or other statistical factors and importantly, they are designed to evaluate general purpose machine learning tasks. In this paper we outline the various parameters that are important in constructing a clinical metric aligned with diagnostic practice, and demonstrate their incompatibility with existing metrics. We propose a new metric, MedTric that takes into account several factors that are of clinical importance. MedTric is built from the ground up keeping in mind the unique context of computational diagnostics and the principle of risk minimization, penalizing missed diagnosis more harshly than over-diagnosis. MedTric is a unified metric for medical or pathological screening system evaluation. We compare this metric against other widely used metrics and demonstrate how our system outperforms them in key areas of medical relevance., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Saha et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

The study of non-human animals' communication systems generally relies on the transcription of vocal sequences using a finite set of discrete units. This set is referred to as a vocal repertoire, which is specific to a species or a sub-group of a species. When conducted by human experts, the formal description of vocal repertoires can be laborious and/or biased. This motivates computerised assistance for this procedure, for which machine learning algorithms represent a good opportunity. Unsupervised clustering algorithms are suited for grouping close points together, provided a relevant representation. This paper therefore studies a new method for encoding vocalisations, allowing for automatic clustering to alleviate vocal repertoire characterisation. Borrowing from deep representation learning, we use a convolutional auto-encoder network to learn an abstract representation of vocalisations. We report on the quality of the learnt representation, as well as of state of the art methods, by quantifying their agreement with expert labelled vocalisation types from 8 datasets of other studies across 6 species (birds and marine mammals). With this benchmark, we demonstrate that using auto-encoders improves the relevance of vocalisation representation which serves repertoire characterisation using a very limited number of settings. We also publish a Python package for the bioacoustic community to train their own vocalisation auto-encoders or use a pretrained encoder to browse vocal repertoires and ease unit wise annotation., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Best et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

The retrieval of important information from a dataset requires applying a special data mining technique known as data clustering (DC). DC classifies similar objects into a groups of similar characteristics. Clustering involves grouping the data around k-cluster centres that typically are selected randomly. Recently, the issues behind DC have called for a search for an alternative solution. Recently, a nature-based optimization algorithm named Black Hole Algorithm (BHA) was developed to address the several well-known optimization problems. The BHA is a metaheuristic (population-based) that mimics the event around the natural phenomena of black holes, whereby an individual star represents the potential solutions revolving around the solution space. The original BHA algorithm showed better performance compared to other algorithms when applied to a benchmark dataset, despite its poor exploration capability. Hence, this paper presents a multi-population version of BHA as a generalization of the BHA called MBHA wherein the performance of the algorithm is not dependent on the best-found solution but a set of generated best solutions. The method formulated was subjected to testing using a set of nine widespread and popular benchmark test functions. The ensuing experimental outcomes indicated the highly precise results generated by the method compared to BHA and comparable algorithms in the study, as well as excellent robustness. Furthermore, the proposed MBHA achieved a high rate of convergence on six real datasets (collected from the UCL machine learning lab), making it suitable for DC problems. Lastly, the evaluations conclusively indicated the appropriateness of the proposed algorithm to resolve DC issues., Competing Interests: he authors have declared that no competing interests exist., (Copyright: © 2023 Salih et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Plant electrophysiological response contains useful signature of its environment and health which can be utilized using suitable statistical analysis for developing an inverse model to classify the stimulus applied to the plant. In this paper, we have presented a statistical analysis pipeline to tackle a multiclass environmental stimuli classification problem with unbalanced plant electrophysiological data. The objective here is to classify three different environmental chemical stimuli, using fifteen statistical features, extracted from the plant electrical signals and compare the performance of eight different classification algorithms. A comparison using reduced dimensional projection of the high dimensional features via principal component analysis (PCA) has also been presented. Since the experimental data is highly unbalanced due to varying length of the experiments, we employ a random under-sampling approach for the two majority classes to create an ensemble of confusion matrices to compare the classification performances. Along with this, three other multi-classification performance metrics commonly used for unbalanced data viz. balanced accuracy, F1-score and Matthews correlation coefficient have also been analyzed. From the stacked confusion matrices and the derived performance metrics, we choose the best feature-classifier setting in terms of the classification performances carried out in the original high dimensional vs. the reduced feature space, for this highly unbalanced multiclass problem of plant signal classification due to different chemical stress. Difference in the classification performances in the high vs. reduced dimensions are also quantified using the multivariate analysis of variance (MANOVA) hypothesis testing. Our findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly unbalanced datasets, employing a combination of existing machine learning algorithms. This work also advances existing studies on environmental pollution level monitoring using plant electrophysiological data., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Bhadra et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Recommendation algorithms save a lot of valuable time for people to get the information they are interested in. However, the feature calculation and extraction process of each machine learning or deep learning recommendation algorithm are different, so how to obtain various features with different dimensions, i.e., how to integrate the advantages of each model and improve the model inference efficiency, becomes the focus of this paper. In this paper, a better deep learning model is obtained by integrating several cutting-edge deep learning models. Meanwhile, to make the integrated learning model converge better and faster, the parameters of the integrated module are initialized, constraints are imposed, and a new activation function is designed for better integration of the sub-models. Finally, the integrated large model is distilled for knowledge distillation, which greatly reduces the number of model parameters and improves the model inference efficiency., Competing Interests: The authors have declared that no competing interests exist.

With the advancement in machine learning, researchers continue to devise and implement effective intelligent methods for fraud detection in the financial sector. Indeed, credit card fraud leads to billions of dollars in losses for merchants every year. In this paper, a multi-classifier framework is designed to address the challenges of credit card fraud detections. An ensemble model with multiple machine learning classification algorithms is designed, in which the Behavior-Knowledge Space (BKS) is leveraged to combine the predictions from multiple classifiers. To ascertain the effectiveness of the developed ensemble model, publicly available data sets as well as real financial records are employed for performance evaluations. Through statistical tests, the results positively indicate the effectiveness of the developed model as compared with the commonly used majority voting method for combination of predictions from multiple classifiers in tackling noisy data classification as well as credit card fraud detection problems., Competing Interests: The authors have declared that no competing interests exist.

This paper presents a multi-algorithm fusion model (StackingGroup) based on the Stacking ensemble learning framework to address the variable selection problem in high-dimensional group structure data. The proposed algorithm takes into account the differences in data observation and training principles of different algorithms. It leverages the strengths of each model and incorporates Stacking ensemble learning with multiple group structure regularization methods. The main approach involves dividing the data set into K parts on average, using more than 10 algorithms as basic learning models, and selecting the base learner based on low correlation, strong prediction ability, and small model error. Finally, we selected the grSubset + grLasso, grLasso, and grSCAD algorithms as the base learners for the Stacking algorithm. The Lasso algorithm was used as the meta-learner to create a comprehensive algorithm called StackingGroup. This algorithm is designed to handle high-dimensional group structure data. Simulation experiments showed that the proposed method outperformed other R2, RMSE, and MAE prediction methods. Lastly, we applied the proposed algorithm to investigate the risk factors of low birth weight in infants and young children. The final results demonstrate that the proposed method achieves a mean absolute error (MAE) of 0.508 and a root mean square error (RMSE) of 0.668. The obtained values are smaller compared to those obtained from a single model, indicating that the proposed method surpasses other algorithms in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Background: Cancer diagnosis based on machine learning has become a popular application direction. Support vector machine (SVM), as a classical machine learning algorithm, has been widely used in cancer diagnosis because of its advantages in high-dimensional and small sample data. However, due to the high-dimensional feature space and high feature redundancy of gene expression data, SVM faces the problem of poor classification effect when dealing with such data. Methods: Based on this, this paper proposes a hybrid feature selection algorithm combining information gain and grouping particle swarm optimization (IG-GPSO). The algorithm firstly calculates the information gain values of the features and ranks them in descending order according to the value. Then, ranked features are grouped according to the information index, so that the features in the group are close, and the features outside the group are sparse. Finally, grouped features are searched using grouping PSO and evaluated according to in-group and out-group. Results: Experimental results show that the average accuracy (ACC) of the SVM on the feature subset selected by the IG-GPSO is 98.50%, which is significantly better than the traditional feature selection algorithm. Compared with KNN, the classification effect of the feature subset selected by the IG-GPSO is still optimal. In addition, the results of multiple comparison tests show that the feature selection effect of the IG-GPSO is significantly better than that of traditional feature selection algorithms. Conclusion: The feature subset selected by IG-GPSO not only has the best classification effect, but also has the least feature scale (FS). More importantly, the IG-GPSO significantly improves the ACC of SVM in cancer diagnostic. [ABSTRACT FROM AUTHOR]

The paper presents an algorithm to approach the problem of Maximum Clique Enumeration, a well known NP-hard problem that have several real world applications. The proposed solution, called LGP-MCE, exploits Geometric Deep Learning, a Machine Learning technique on graphs, to filter out nodes that do not belong to maximum cliques and then applies an exact algorithm to the pruned network. To assess the LGP-MCE, we conducted multiple experiments using a substantial dataset of real-world networks, varying in size, density, and other characteristics. We show that LGP-MCE is able to drastically reduce the running time, while retaining all the maximum cliques. [ABSTRACT FROM AUTHOR]

This paper focuses on 6D pose estimation for weakly textured targets from RGB-D images. A 6D pose estimation algorithm (DOPE++) based on a deep neural network for weakly textured objects is proposed to solve the poor real-time pose estimation and low recognition efficiency in the robot grasping process of parts with weak texture. More specifically, we first introduce the depthwise separable convolution operation to lighten the original deep object pose estimation (DOPE) network structure to improve the network operation speed. Second, an attention mechanism is introduced to improve network accuracy. In response to the low recognition efficiency of the original DOPE network for parts with occlusion relationships and the false recognition problem in recognizing parts with scales that are too large or too small, a random mask local processing method and a multiscale fusion pose estimation module are proposed. The results show that our proposed DOPE++ network improves the real-time performance of 6D pose estimation and enhances the recognition of parts at different scales without loss of accuracy. To address the problem of a single background representation of the part pose estimation dataset, a virtual dataset is constructed for data expansion to form a hybrid dataset. [ABSTRACT FROM AUTHOR]

The application of pattern mining algorithms to extract movement patterns from sports big data can improve training specificity by facilitating a more granular evaluation of movement. Since movement patterns can only occur as consecutive, non-consecutive, or non-sequential, this study aimed to identify the best set of movement patterns for player movement profiling in professional rugby league and quantify the similarity among distinct movement patterns. Three pattern mining algorithms (l-length Closed Contiguous [LCCspm], Longest Common Subsequence [LCS] and AprioriClose) were used to extract patterns to profile elite rugby football league hookers (n = 22 players) and wingers (n = 28 players) match-games movements across 319 matches. Jaccard similarity score was used to quantify the similarity between algorithms' movement patterns and machine learning classification modelling identified the best algorithm's movement patterns to separate playing positions. LCCspm and LCS movement patterns shared a 0.19 Jaccard similarity score. AprioriClose movement patterns shared no significant Jaccard similarity with LCCspm (0.008) and LCS (0.009) patterns. The closed contiguous movement patterns profiled by LCCspm best-separated players into playing positions. Multi-layered Perceptron classification algorithm achieved the highest accuracy of 91.02% and precision, recall and F1 scores of 0.91 respectively. Therefore, we recommend the extraction of closed contiguous (consecutive) over non-consecutive and non-sequential movement patterns for separating groups of players. [ABSTRACT FROM AUTHOR]

Q-learning is a classical reinforcement learning algorithm and one of the most important methods of mobile robot path planning without a prior environmental model. Nevertheless, Q-learning is too simple when initializing Q-table and wastes too much time in the exploration process, causing a slow convergence speed. This paper proposes a new Q-learning algorithm called the Paired Whale Optimization Q-learning Algorithm (PWOQLA) which includes four improvements. Firstly, to accelerate the convergence speed of Q-learning, a whale optimization algorithm is used to initialize the values of a Q-table. Before the exploration process, a Q-table which contains previous experience is learned to improve algorithm efficiency. Secondly, to improve the local exploitation capability of the whale optimization algorithm, a paired whale optimization algorithm is proposed in combination with a pairing strategy to speed up the search for prey. Thirdly, to improve the exploration efficiency of Q-learning and reduce the number of useless explorations, a new selective exploration strategy is introduced which considers the relationship between current position and target position. Fourthly, in order to balance the exploration and exploitation capabilities of Q-learning so that it focuses on exploration in the early stage and on exploitation in the later stage, a nonlinear function is designed which changes the value of ε in ε-greedy Q-learning dynamically based on the number of iterations. Comparing the performance of PWOQLA with other path planning algorithms, experimental results demonstrate that PWOQLA achieves a higher level of accuracy and a faster convergence speed than existing counterparts in mobile robot path planning. The code will be released at https://github.com/wanghanyu0526/improveQL.git. [ABSTRACT FROM AUTHOR]

Kmeans clustering algorithm is an iterative unsupervised learning algorithm that tries to partition the given dataset into k pre-defined distinct non-overlapping clusters where each data point belongs to only one group. However, its performance is affected by its sensitivity to the initial cluster centroids with the possibility of convergence into local optimum and specification of cluster number as the input parameter. Recently, the hybridization of metaheuristics algorithms with the K-Means algorithm has been explored to address these problems and effectively improve the algorithm's performance. Nonetheless, most metaheuristics algorithms require rigorous parameter tunning to achieve an optimum result. This paper proposes a hybrid clustering method that combines the well-known symbiotic organisms search algorithm with K-Means using the SOS as a global search metaheuristic for generating the optimum initial cluster centroids for the K-Means. The SOS algorithm is more of a parameter-free metaheuristic with excellent search quality that only requires initialising a single control parameter. The performance of the proposed algorithm is investigated by comparing it with the classical SOS, classical K-means and other existing hybrids clustering algorithms on eleven (11) UCI Machine Learning Repository datasets and one artificial dataset. The results from the extensive computational experimentation show improved performance of the hybrid SOSK-Means for solving automatic clustering compared to the standard K-Means, symbiotic organisms search clustering methods and other hybrid clustering approaches. [ABSTRACT FROM AUTHOR]

Every year, millions of new devices are added to the Internet of things, which has both great benefits and serious security risks for user data privacy. It is the device owners' responsibility to ensure that the ownership settings of Internet of things devices are maintained, allowing them to communicate with other user devices autonomously. The ultimate goal of the future Internet of Things is for it to be able to make decisions on its own, without the need for human intervention. Therefore, trust computing and prediction have become more vital in the processing and handling of data as well as in the delivery of services. In this paper, we compute trust in social IoT scenarios using a hybrid approach that combines a distributed computation technique and a global machine learning approach. The approach considers social similarity while assessing other users' ratings and utilize a cloud-based architecture. Further, we propose a dynamic way to aggregate the different computed trust values. According to the results of the experimental work, it is shown that the proposed approaches outperform related work. Besides, it is shown that the use of machine learning provides slightly better performance than the computing model. Both proposed approaches were found successful in degrading malicious ratings without the need for more complex algorithms. [ABSTRACT FROM AUTHOR]

Measurements of the physical outputs of speech—vocal tract geometry and acoustic energy—are high-dimensional, but linguistic theories posit a low-dimensional set of categories such as phonemes and phrase types. How can it be determined when and where in high-dimensional articulatory and acoustic signals there is information related to theoretical categories? For a variety of reasons, it is problematic to directly quantify mutual information between hypothesized categories and signals. To address this issue, a multi-scale analysis method is proposed for localizing category-related information in an ensemble of speech signals using machine learning algorithms. By analyzing how classification accuracy on unseen data varies as the temporal extent of training input is systematically restricted, inferences can be drawn regarding the temporal distribution of category-related information. The method can also be used to investigate redundancy between subsets of signal dimensions. Two types of theoretical categories are examined in this paper: phonemic/gestural categories and syntactic relative clause categories. Moreover, two different machine learning algorithms were examined: linear discriminant analysis and neural networks with long short-term memory units. Both algorithms detected category-related information earlier and later in signals than would be expected given standard theoretical assumptions about when linguistic categories should influence speech. The neural network algorithm was able to identify category-related information to a greater extent than the discriminant analyses. [ABSTRACT FROM AUTHOR]

In order to realize the optimization of autonomous navigation of mobile robot under the condition of partial environmental knowledge known. An improved Q-learning reinforcement learning algorithm based on prior knowledge is proposed to solve the problem of slow convergence and low learning efficiency in mobile robot path planning. Prior knowledge is used to initialize the Q-value, so as to guide the agent to move toward the target direction with a greater probability from the early stage of the algorithm, eliminating a large number of invalid iterations. The greedy factor ε is dynamically adjusted based on the number of times the agent successfully reaches the target position, so as to better balance exploration and exploitation and accelerate convergence. Simulation results show that the improved Q-learning algorithm has a faster convergence rate and higher learning efficiency than the traditional algorithm. The improved algorithm has practical significance for improving the efficiency of autonomous navigation of mobile robots. [ABSTRACT FROM AUTHOR]

Network attacks using Command and Control (C&C) servers have increased significantly. To hide their C&C servers, attackers often use Domain Generation Algorithms (DGA), which automatically generate domain names for C&C servers. Researchers have constructed many unique feature sets and detected DGA domains through machine learning or deep learning models. However, due to the limited features contained in the domain name, the DGA detection results are limited. In order to overcome this problem, the domain name features, the Whois features and the N-gram features are extracted for DGA detection. To obtain the N-gram features, the domain name whitelist and blacklist substring feature sets are constructed. In addition, a deep learning model based on BiLSTM, Attention and CNN is constructed. Additionally, the Domain Center is constructed for fast classification of domain names. Multiple comparative experiment results prove that the proposed model not only gets the best Accuracy, Precision, Recall and F1, but also greatly reduces the detection time. [ABSTRACT FROM AUTHOR]

Unsupervised image-to-image translation (UI2I) tasks aim to find a mapping between the source and the target domains from unpaired training data. Previous methods can not effectively capture the differences between the source and the target domain on different scales and often leads to poor quality of the generated images, noise, distortion, and other conditions that do not match human vision perception, and has high time complexity. To address this problem, we propose a multi-scale training structure and a progressive growth generator method to solve UI2I task. Our method refines the generated images from global structures to local details by adding new convolution blocks continuously and shares the network parameters in different scales and also in the same scale of network. Finally, we propose a new Cross-CBAM mechanism (CRCBAM), which uses a multi-layer spatial attention and channel attention cross structure to generate more refined style images. Experiments on our collected Opera Face, and other open datasets Summer↔Winter, Horse↔Zebra, Photo↔Van Gogh, show that the proposed algorithm is superior to other state-of-art algorithms. [ABSTRACT FROM AUTHOR]

The fast-growing quantity of information hinders the process of machine learning, making it computationally costly and with substandard results. Feature selection is a pre-processing method for obtaining the optimal subset of features in a data set. Optimization algorithms struggle to decrease the dimensionality while retaining accuracy in high-dimensional data set. This article proposes a novel chaotic opposition fruit fly optimization algorithm, an improved variation of the original fruit fly algorithm, advanced and adapted for binary optimization problems. The proposed algorithm is tested on ten unconstrained benchmark functions and evaluated on twenty-one standard datasets taken from the Univesity of California, Irvine repository and Arizona State University. Further, the presented algorithm is assessed on a coronavirus disease dataset, as well. The proposed method is then compared with several well-known feature selection algorithms on the same datasets. The results prove that the presented algorithm predominantly outperform other algorithms in selecting the most relevant features by decreasing the number of utilized features and improving classification accuracy. [ABSTRACT FROM AUTHOR]

Cluster analysis is a valuable unsupervised machine learning technique that is applied in a multitude of domains to identify similarities or clusters in unlabelled data. However, its performance is dependent of the characteristics of the data it is being applied to. There is no universally best clustering algorithm, and hence, there are numerous clustering algorithms available with different performance characteristics. This raises the problem of how to select an appropriate clustering algorithm for the given analytical purposes. We present and validate an analysis framework to address this problem. Unlike most current literature which focuses on characterizing the clustering algorithm itself, we present a wider holistic approach, with a focus on the user's needs, the data's characteristics and the characteristics of the clusters it may contain. In our analysis framework, we utilize a softer qualitative approach to identify appropriate characteristics for consideration when matching clustering algorithms to the intended application. These are used to generate a small subset of suitable clustering algorithms whose performance are then evaluated utilizing quantitative cluster validity indices. To validate our analysis framework for selecting clustering algorithms, we applied it to four different types of datasets: three datasets of homemade explosives spectroscopy, eight datasets of publicly available spectroscopy data covering food and biomedical applications, a gene expression cancer dataset, and three classic machine learning datasets. Each data type has discernible differences in the composition of the data and the context within which they are used. Our analysis framework, when applied to each of these challenges, recommended differing subsets of clustering algorithms for final quantitative performance evaluation. For each application, the recommended clustering algorithms were confirmed to contain the top performing algorithms through quantitative performance indices. [ABSTRACT FROM AUTHOR]

By classifying patients into subgroups, clinicians can provide more effective care than using a uniform approach for all patients. Such subgroups might include patients with a particular disease subtype, patients with a good (or poor) prognosis, or patients most (or least) likely to respond to a particular therapy. Transcriptomic measurements reflect the downstream effects of genomic and epigenomic variations. However, high-throughput technologies generate thousands of measurements per patient, and complex dependencies exist among genes, so it may be infeasible to classify patients using traditional statistical models. Machine-learning classification algorithms can help with this problem. However, hundreds of classification algorithms exist—and most support diverse hyperparameters—so it is difficult for researchers to know which are optimal for gene-expression biomarkers. We performed a benchmark comparison, applying 52 classification algorithms to 50 gene-expression datasets (143 class variables). We evaluated algorithms that represent diverse machine-learning methodologies and have been implemented in general-purpose, open-source, machine-learning libraries. When available, we combined clinical predictors with gene-expression data. Additionally, we evaluated the effects of performing hyperparameter optimization and feature selection using nested cross validation. Kernel- and ensemble-based algorithms consistently outperformed other types of classification algorithms; however, even the top-performing algorithms performed poorly in some cases. Hyperparameter optimization and feature selection typically improved predictive performance, and univariate feature-selection algorithms typically outperformed more sophisticated methods. Together, our findings illustrate that algorithm performance varies considerably when other factors are held constant and thus that algorithm selection is a critical step in biomarker studies. Author summary: When a patient is treated in a medical setting, a clinician may extract a tissue sample and use transcriptome-profiling technologies to quantify the extent to which thousands of genes are expressed in the sample. These measurements reflect biological activity that may influence disease development, progression, and/or treatment responses. Patterns that differ between patients in distinct groups (for example, patients who do or do not have a disease or do or do not respond to a treatment) may be used to classify future patients into these groups. This study is a large-scale benchmark comparison of algorithms that can be used to perform such classifications. Additionally, we evaluated feature-selection algorithms, which can be used to identify which variables (genes and/or patient characteristics) are most relevant for classification. Through a series of analyses that build on each other, we show that classification performance varies considerably, depending on which algorithms are used, whether feature selection is used, which settings are used when executing the algorithms, and which metrics are used to evaluate the algorithms' performance. Researchers can use these findings as a resource for deciding which algorithms and settings to prioritize when deriving transcriptome-based biomarkers in future efforts. [ABSTRACT FROM AUTHOR]

Background: Left ventricular hypertrophy detected by echocardiography (Echo-LVH) is an independent predictor of mortality. Integration of the Philips DXL-16 algorithm into the electrocardiogram (ECG) extensively analyses the electricity of the heart. Machine learning techniques such as the C5.0 could lead to a new decision tree criterion to detect Echo-LVH. Objectives: To search for a new combination of ECG parameters predictive of Echo-LVH. The final model is called the Cardiac Hypertrophy Computer-based model (CHCM). Methods: We extracted the 458 ECG parameters provided by the Philips DXL-16 algorithm in patients with Echo-LVH and controls. We used the C5.0 ML algorithm to train, test, and validate the CHCM. We compared its diagnostic performance to validate state-of-the-art criteria in our patient cohort. Results: We included 439 patients and considered an alpha value of 0.05 and a power of 99%. The CHCM includes T voltage in I (≤0.055 mV), peak-to-peak QRS distance in aVL (>1.235 mV), and peak-to-peak QRS distance in aVF (>0.178 mV). The CHCM had an accuracy of 70.5% (CI95%, 65.2–75.5), a sensitivity of 74.3%, and a specificity of 68.7%. In the external validation cohort (n = 156), the CHCM had an accuracy of 63.5% (CI95%, 55.4–71), a sensitivity of 42%, and a specificity of 82.9%. The accuracies of the most relevant state-of-the-art criteria were: Romhilt-Estes (57.4%, CI95% 49–65.5), VDP Cornell (55.7%, CI95%47.6–63.7), Cornell (59%, CI95%50.8–66.8), Dalfó (62.9%, CI95%54.7–70.6), Sokolow Lyon (53.9%, CI95%45.7–61.9), and Philips DXL-16 algorithm (54.5%, CI95%46.3–62.5). Conclusion: ECG computer-based data and the C5.0 determined a new set of ECG parameters to predict Echo-LVH. The CHCM classifies patients as Echo-LVH with repolarization abnormalities or LVH with increased voltage. The CHCM has a similar accuracy, and is slightly more sensitive than the state-of-the-art criteria. [ABSTRACT FROM AUTHOR]

Many machine learning procedures, including clustering analysis are often affected by missing values. This work aims to propose and evaluate a Kernel Fuzzy C-means clustering algorithm considering the kernelization of the metric with local adaptive distances (VKFCM-K-LP) under three types of strategies to deal with missing data. The first strategy, called Whole Data Strategy (WDS), performs clustering only on the complete part of the dataset, i.e. it discards all instances with missing data. The second approach uses the Partial Distance Strategy (PDS), in which partial distances are computed among all available resources and then re-scaled by the reciprocal of the proportion of observed values. The third technique, called Optimal Completion Strategy (OCS), computes missing values iteratively as auxiliary variables in the optimization of a suitable objective function. The clustering results were evaluated according to different metrics. The best performance of the clustering algorithm was achieved under the PDS and OCS strategies. Under the OCS approach, new datasets were derive and the missing values were estimated dynamically in the optimization process. The results of clustering under the OCS strategy also presented a superior performance when compared to the resulting clusters obtained by applying the VKFCM-K-LP algorithm on a version where missing values are previously imputed by the mean or the median of the observed values. [ABSTRACT FROM AUTHOR]