Search

This paper develops an integrated framework to forecast the volatility of crude oil prices by considering the impacts of extreme events (structural breaks). The impacts of extreme events are vital to improving prediction accuracy. Aiming to demonstrate the crude oil price fluctuation and the impacts of external events, this paper employs the complementary ensemble empirical mode decomposition (CEEMD). It decomposes the crude oil price into some constituents at various frequencies to extract a market fluctuation, a shock from extreme events and a long-term trend. The shock from extreme events is found to be the most crucial element in deciding the crude oil prices. Then we combine the iterative cumulative sum of squares (ICSS) test with the Chow test to get the structural breaks and analyze the extreme event impacts. Finally, this paper combines the structural breaks, the autoregressive integrated moving average (ARIMA) model, and the support vector machine (SVM) to make a forecast of the crude oil prices. The empirical process proves that the CEEMD-ARIMA-SVM model with structural breaks performs the best when compared with the other ARIMA-type models and SVM-type models. The framework offers an insightful view to help decision-makers and can be used in many areas. [ABSTRACT FROM AUTHOR]

With the actual demand of international communication, intelligent translation of English has become a key direction of artificial intelligence development in the current English field. For the existing English intelligent translation, how to deal with the massive data effectively is always a big problem. Therefore, it is necessary to use the principle of machine learning to optimize the English intelligent translation model. The purpose of this paper is to optimize the existing English intelligent translation model through spectral clustering to remove outliers, so as to make it more suitable for the use of massive data. Moreover, this paper uses deep learning methods to improve on the basis of the PoseNet network structure and adds regularization to the convolutional layer, which reduces the problem of gradient disappearance and reduces the computational complexity. In addition, this paper uses adaptive weighting to remove invalid model assumptions. In the conceptual space of the similarity matrix, the interior point is farther from the origin than the outlier point. The algorithm in this paper can detect and eliminate the outliers in a paragraph of English. At the same time, the normal English content will be classified into data categories, and the final translation result will be obtained. Through the experimental test, it can be seen that the model proposed in this paper has good performance and can cope with massive data, so it has certain superiority. [ABSTRACT FROM AUTHOR]

Accurate assessment of road conditions can effectively alleviate traffic congestion and guide people's travel plans, traffic control decisions of transportation departments, and formulation of traffic-related laws and regulations. This paper proposes a quantum particle swarm optimization (QPSO) and adaptive hybrid exponential smoothing with residual correction (AHES-RC) for the nonlinearity and randomness of traffic flow. In the proposed algorithm, the single–double-exponential smoothing method is mixed with adaptive weights to form AHES, a new method of mixing weights according to real-time traffic trend changes. After the residual correction of AHES is calculated by the extreme learning machine algorithm, the parameters of AHES-RC are optimized using QPSO to improve the prediction accuracy further. This paper comprehensively compares the QPSO-AHES-RC algorithm with other benchmark models through testing on 26 real-world data sets. The results show that the proposed algorithm can adaptive forecasting under various traffic conditions, yielding the best forecasting performance in terms of various forecast error metrics. Compared with advanced machine learning algorithms such as XGBoost and CatBoost, the mean RMSE and mean MAPE have been improved by over 20% on average. In addition, it is revealed that the real-time dynamic capture of traffic flow can effectively improve prediction accuracy. [ABSTRACT FROM AUTHOR]

After entering the twenty-first century, with the development of science and technology represented by artificial intelligence, the content of art design and creation is increasingly rich. Its intelligence, interactivity and digital content expression make the relationship between science and technology, art and people more close and also bring new opportunities for the development of interactive art. Among them, human–computer interaction is more and more widely used. With the promotion of this kind of technology, interactive art is no longer based on auditory sensory experience, but on the in-depth study of human nature and comprehensive senses. On this basis, human–computer interaction technology is introduced, thus forming a comprehensive visual art form, which communicates and expresses through strong interaction, initiative and emotion. Based on machine learning technology and human–computer visual interaction technology, this paper explores the art visual communication module based on human–computer interaction system. By analyzing the audience's line of sight and visual differences, we can get the audience satisfaction, so as to improve the expression of the work. Firstly, this paper proposes the design of human–computer interaction visual structure and introduces the basic structure of art visual communication system, the simulation of art visual scene, the process and evaluation index of human–computer interaction recognition, visual recognition effect, etc., based on the needs of visual interaction. Finally, it analyzes the common forms of human–computer interaction in art visual communication, the reconstruction of thinking mode of art visual communication and the development direction of art visual communication. This paper believes that human–computer interaction technology plays a leading role in the development of the art field. It has a variety of functions, displays methods and values. By studying machine learning algorithm and human–computer interaction system, this paper applies it to the field of artistic vision, thus promoting the development of artistic visual communication. [ABSTRACT FROM AUTHOR]

Calculus equation is an important tool for mathematical research and plays an important role in most natural science research. Since the beginning of the eighteenth century, people have gradually used differential and integral equations to solve physical problems. In general, several different aspects of differential equations in the field of mathematics are concerned and studied by most scholars. However, this paper studies and establishes the optimal model for numerical solution of differential equations through deep learning and genetic algorithm. In this paper, the solution of ordinary differential equations is solved through the use of polynomial function space, while the linear combination of simple function x and its product nx can obtain multinomial function space. The space function form of polynomial is very simple, and the operation ability is very strong. Almost all functions can be approximated, and the function space can be transformed by a simple function. Through data simulation test results, it can be found that the oscillation of neural network output is stronger and stronger with the increase in depth, that is to say, the deeper depth endows the neural network with stronger oscillation properties, so for the oscillation function, the depth neural network fitting effect is better than the shallow neural network. Therefore, by combining deep learning and genetic algorithm, this paper studies and establishes the optimal model for numerical solution of differential equations, and finds that the deep neural network can largely complete data simulation. [ABSTRACT FROM AUTHOR]

In order to achieve accurate fault diagnosis of rolling bearing under random noise, a new fault diagnosis method based on wavelet packet-variational mode decomposition (WP-VMD) and kernel extreme learning machine (KELM) optimized by particle swarm optimization (PSO) is proposed in this paper. Firstly, the time–frequency domain feature vectors of the original rolling bearing fault signals are effectively obtained by preprocessing of WMD and decomposition and reconstruction of VMD. Then, the extracted two-dimensional feature vector is input into the KELM neural network for fault identification, and combined with PSO, KELM parameters were optimized. The experimental results show that the proposed method can effectively diagnose the rolling bearing under random noise, with the features of fast speed, stable performance and high accuracy. By comparison, this paper obtains better accuracy and real-time performance with fewer features, which provides a simple and efficient solution for fault diagnosis of rolling bearings. [ABSTRACT FROM AUTHOR]

At present, wearable devices have some problems, such as poor adaptability to human motion behavior, and the recognition accuracy required for different wearers cannot be achieved. Based on the principle of deep learning algorithm, this paper realizes the development of intelligent rope skipping movement data monitoring system. Through the universal human body analysis model, the attention mechanism is introduced and embedded into the decoding network. The data set of rope skipping is classified by multiple labels, and the convolution of spatial graph is constructed, which is extended to the time series dynamics of moving human skeleton data. Aiming at the problem of complex information data in the process of moving human body recognition, we use pose estimation to calculate the key points of moving human body, extract the dynamic structure information of human skeleton sequence. Due to the problems of line of sight occlusion in the process of moving human target tracking, a target tracking algorithm based on multi domain convolution neural network is adopted to improve the feature extraction ability of the algorithm by segmenting the target to be tracked and identifying the area around the target. The data set of rope skipping is collected by wearable sensors, and the difference in the numerical range may be large, so the data is normalized. Finally, through the loss function, the fitting effect of neural network can be evaluated, and the gradient optimization model parameters can be calculated, and coping with different data changes. Through the final system performance test, it is verified that the accuracy rate of the system designed in this paper is above 90%, which can effectively monitor the data of skipping rope and be used in the actual operation of skipping rope. [ABSTRACT FROM AUTHOR]

Textual emotion recognition is an increasingly popular research area, which recognizes human emotions by capturing textual information posted by people, and the recognition results depend on the composition of the system framework. In this paper, we propose a textual emotion recognition method based on ALBERT-BiLSTM model and SVM-NB classification. Firstly, the text is pre-processed based on ALBERT pre-training model. Then, the word vector-related features are obtained by BiLSTM Recurrent Neural Network for machine learning to make them have a specific form for classification in order to improve the accuracy of emotion recognition. In the link of emotion classification, this paper innovatively proposes a classification method SVM-NB to obtain more emotional polarities. Finally, the classifier is used to obtain the emotional polarities of the text, including positive and negative categories. The negative emotions are divided into three sub-categories of anger, sad and disgust. The experiments show that the proposed emotion recognition method has better robustness and higher accuracy than the general modal recognition method. [ABSTRACT FROM AUTHOR]

Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this topic. This editorial presents a background of the special issue and a brief introduction to the 12 contributions. [ABSTRACT FROM AUTHOR]

In order to solve the problems of low learning efficiency and slow convergence speed when mobile robot uses reinforcement learning method for path planning in complex environment, a reinforcement learning method based on each round path planning result is proposed. Firstly, the algorithm adds obstacle learning matrix to improve the success rate of path planning; and introduces heuristic reward to speed up the learning process by reducing the search space; then proposes a method of dynamically adjusting the exploration factor to balance the exploration and utilization in path planning, so as to further improve the performance of the algorithm. Finally, the simulation experiment in grid environment shows that compared with Q-learning algorithm, the improved algorithm not only shortens the average path length of the robot to reach the target position, but also speeds up the learning efficiency of the algorithm, so that the robot can find the optimal path more quickly. The code of EPRQL algorithm proposed in this paper has been published to GitHub: https://github.com/panpanpanguoguoqian/mypaper1.git. [ABSTRACT FROM AUTHOR]

Due to the heterogeneity of program language and natural language query, it is difficult to identify the semantic relationship between them, which leads to the low efficiency of code recommendation. In order to solve the problems of the above code recommendation technology, a code recommendation method based on joint embedded attention network (JEAN) is proposed in this paper. The method uses GRU Network to embed code snippets and describe queries into vector representation, which solves the problem of heterogeneous code snippets and natural language queries. The Attention mechanism is then used to distribute totally different weights to different components of every mode of the code snippet. The reason for the Attention mechanism is that different components of every mode of the code snippet contribute differently to the semantic vector of the final code snippet, making it interpretable. Finally, two commonly used evaluation indexes of information retrieval, SuccessRate@k and MRR, are used for experimental comparison with other baseline models. The experimental results show that the code recommendation method based on joint embedded attention network proposed in this paper can effectively recommend appropriate code snippets according to the needs of developers, and its performance is better than other baseline methods. [ABSTRACT FROM AUTHOR]

In this current era, the field of robotics has made much advancement and has also produced novelties than any other advanced research areas. The usage of robots has become an imperative part of the defense-oriented applications. The missions which are difficult to be performed by human beings can certainly be accomplished by the robots nowadays. The most crucial part for an industrial- and defense-based robot is to perform pose movements accurately for optimal usage of robotics as a replacement of human beings. This paper proposes a comprehensive introduction to the proposed hybrid approach PSO–RL which uses reinforcement learning (RL) and Particle swarm optimization (PSO). It summarizes the usage of proposed PSO-RL for pose measurement of robots in defense and industrial manufacturing systems. The hybrid PSO–RL is a promising technique for measuring poses in robots with accuracy and for optimizing obstacle avoidance error. In this paper, robot's core movements are analyzed; speed of movements is given importance, and an attempt is made to provide more accurate moves with high precision. In order to optimize the efficiency of robotic operations, a full freedom pose measurement method based on PSO–RL is proposed. By using the characteristics of two-wheel independent driving industrial robot, the performance of the robot in three moving modes is evaluated. The experimental results show that the proposed PSO-RL method has the advantages of high accuracy, high measurement efficiency, high success rate of grabbing and avoiding obstacles. It outperforms the existing methods such as least square method and micro-displacement cyclic correction method with respect to maximum error, RMSE score and time complexity. [ABSTRACT FROM AUTHOR]

Due to the large number of stock companies, complex stock categories and inconsistent evaluation standards of market value, it is not conducive to the choice of investors. Based on the theory and practice of traditional stock performance evaluation model, this paper integrates the algorithm thought structure of Fama–French five-factor model and proposes a machine learning algorithm model for stock performance research. In addition, this paper also builds a model that can evaluate the style and timing ability of fund managers to improve the fund performance evaluation system to a greater extent. With the help of the performance evaluation updating function of the model, it provides a new experience material in the empirical research composition of the fund performance field. In the system test module, the former prediction data and the actual experimental data are integrated, and the two are sorted out and compared, which proves the feasibility and effectiveness of the proposed algorithm model. The final experimental results verify the usefulness of the model in stock return prediction and analysis of influencing factors. [ABSTRACT FROM AUTHOR]

Public activities are mostly carried out in large public buildings, which are closely related to social management. At present, people's demand for public building facilities is increasing, its shape evolution is becoming more complex, and the scientific and technological content of construction-related technology is also increasing. The development trend of green public buildings is more and more strong. The traditional building design cannot effectively deal with the energy consumption of public buildings and people's demand for their performance. This paper introduces BIM and machine learning technology to study their practical application in the design of green public buildings and tests the perfect machine learning algorithm. According to the experimental test results, the building energy consumption decreased by 14.3%, the carbon emission decreased by 11.39%, and the absolute value of PMV thermal comfort decreased by 34.7%, which obviously achieved the optimization effect. BIM technology parametric design can enable the design model formed by conceptual design research to automatically draw construction drawings, detailed drawings and other drawings according to the drawing requirements and standards, thus saving the designer's time and enabling him to transfer the drawing time to the program design. Finally, through experiments, the economy, rationality and operability of using BIM technology to design green public buildings are confirmed. In this paper, machine learning and BIM technology are introduced, so as to carry out design research for green public building design. [ABSTRACT FROM AUTHOR]

Software defect prediction is the process of developing predictive models that helps in the early identification of defect-prone modules based on software metrics and defect data. It enables the project managers to allocate resources optimally. Recently search-based techniques have been widely adopted for providing optimal solutions to develop effective software defect prediction models. When merged with statistical or machine learning techniques, these techniques give rise to hybridization. Hybrid techniques significantly improve the performance of search-based techniques and the quality of solutions produced by them. In this systematic review, we have investigated 72 papers published from January 2000 to December 2021 that ascertain the use of hybrid techniques and their effectiveness in predicting software defects. The review identifies and evaluates various techniques, experimental design, fitness functions, performance measures, threats to validity, and well-known statistical tests in the studies that apply these hybrid techniques. We also compared the performance of hybrid techniques among themselves and statistical and machine learning techniques present in the literature. According to the findings, the predictive capability of hybrid techniques is encouraging. The results of this review paper will serve as guidelines for the researchers and practitioners, allowing them to make appropriate choices for applying hybrid techniques in the software defect prediction process. [ABSTRACT FROM AUTHOR]

Label-specific features learning can effectively exploit the unique features of each label, which alleviates the high dimensionality and improves the classification performance of multi-label. However, most existing label-specific features learning algorithms assume that label space is complete, ignoring the effect of missing labels on the classification accuracy. Some methods try to recover the missing labels first and then learn the mapping between the completed label matrix and the feature matrix. However, early intervention in the recovery of missing labels may affect the distribution of original labels to a certain extent. In this paper, feature-label dual-mapping for missing label-specific features learning is proposed. According to the information that the label depends on the feature, the dual-mapping weight of the complete feature space and the missing label space is jointly learned. Therefore, the proposed algorithm is to conduct latent missing labels recovery by feature-label dual-mapping to directly obtain target weight in this paper, avoiding the negative influence of early label recovery intervention. Compared with several state-of-the-art methods in 10 benchmark multi-label data sets, the results show that the proposed algorithm is reasonable and effective. [ABSTRACT FROM AUTHOR]

In order to improve the effect of intelligent language translation, this paper analyzes the problems of the MSE cost function used by most of the current DNN-based speech enhancement algorithms and proposes a deep learning speech enhancement algorithm based on perception-related cost functions. Moreover, this paper embeds the suppression gain parameter estimation into the architecture of the traditional speech enhancement algorithm and converts the relationship between the noisy speech spectrum and the enhanced speech spectrum into a simple multiplication relationship based on suppression gain combined with deep learning algorithms to construct an intelligent language translation system. Moreover, this paper evaluates the translation effect of the system, analyzes the actual results, and uses simulation tests to verify the performance of the intelligent language translation model constructed in this paper. From the experimental results, it can be seen that the intelligent language translation system based on deep learning algorithms has good results. [ABSTRACT FROM AUTHOR]

The number of papers on machine learning and deep neural networks applied to intrusion detection systems (IDS) is ever-increasing. Differently from existing work on the topic, this paper explores the effect of training-time randomness of deep neural networks, which is overlooked by the related literature. Training-time randomness is regulated by the seed of the pseudorandom number generator, and affects the performance of IDS models. The seed selection is studied in conjunction with other critical learning parameters: to the best of our knowledge, there are no similar studies in IDS. The experiments are done with a recent and widely consolidated intrusion detection benchmark, which is used to train and test a neural network under different combinations of seeds and parameters both in supervised and semi-supervised learning modes. The results are inferred by a mixture of explorative analysis, design of experiments, and analysis of variance. According to the results, the choice of the seed yields either excellent or scarce detection metrics; more importantly, the seed selection might be as relevant as the other major learning parameters assessed. [ABSTRACT FROM AUTHOR]

In recent years, the rapid advancement of artificial intelligence (AI) technology has made remarkable strides in the music industry, profoundly impacting various aspects of our lives. This progress has extended to revolutionizing industries, streamlining processes, and enhancing personalization in music. AI's expanding capabilities have driven computer vision, natural language processing, and machine learning breakthroughs. As music enthusiasts increasingly turn to online platforms, the need for effective recommendation systems has become more pressing. The exponential growth of musical content poses a challenge in discovering music tailored to individual tastes. This paper proposed a personalized music recommendation system powered by deep learning, explicitly utilizing convolutional neural networks (CNNs) to address the challenges posed by expanding music libraries and diverse song resources. In today's era of ever-growing music databases and increasing content diversity, more than traditional retrieval methods are needed to efficiently connect users with their preferred track. Traditional music platforms rely solely on retrieval mechanisms, necessitating manual inputs such as artist names and titles to locate specific songs. However, this approach needs in-depth music data analysis and delivers personalized recommendations generated by various deep learning-based algorithms. This paper bridges this gap by harnessing deep learning algorithms for comprehensive music data analysis and personalized song suggestions. The proposed CNN-based recommendation system explores the domains of deep learning and content-based approaches, empowering users to discover their favorite tunes swiftly. This innovative mechanism leverages CNNs and deep learning algorithms to offer efficient, personalized, and data-driven music recommendations, transforming the user experience with their music collections. In experimental results, the proposed CNN model is compared with various deep learning algorithms, including DNN, RNN, and LSTM, as well as traditional algorithms like SVM, KNN, RF, and DT. Impressively, the CNN model achieved the highest accuracy at 95%, surpassing all other algorithms. [ABSTRACT FROM AUTHOR]

In recent years, the rapid advancement of artificial intelligence (AI) has revolutionized various industries, with image processing playing an important role in the revolution. AI-powered image analysis has opened up new possibilities in healthcare diagnostics, autonomous navigation, and security surveillance, fuelling demand for sophisticated image-processing solutions. This paper describes an innovative approach to AI image processing that combines multi-sensor data fusion with convolutional neural networks (CNNs) within a fuzzy neural network framework. This integration uses data from various sensors, including cameras, lidar, and radar, to improve the robustness and precision of image analysis and interpretation. The T–S model serves as the foundation for the information fusion strategy. A comprehensive investigation of deep learning algorithms reveals inherent strengths such as robustness and parallelism. However, it also identifies limitations, particularly in image segmentation tasks, characterized by challenges like premature convergence and prolonged computation times. The paper proposes a quantization technique for deep learning algorithms to address these issues and introduces chaotic optimization to expedite convergence rates. It also presents a novel three-dimensional Otsu threshold segmentation method based on CNNs, which overcomes noise susceptibility in traditional two-dimensional approaches. Integrating Gray morphology and this three-dimensional Otsu threshold segmentation method results in the development of a three-dimensional Gray Otsu model. This model is the basis for designing a fitness function for the CNN algorithm, optimizing its efficacy. Experimental validation demonstrates the proposed algorithm's effectiveness, achieving an impressive 91% accuracy rate while displaying robust noise resistance and versatility. Comparative assessments against other leading AI architectures, including multilayer perceptron, radial basis function network, recurrent neural network, and long short-term memory network, affirm the superior performance achieved by the proposed approach. [ABSTRACT FROM AUTHOR]

These days, exploring information retrieval models is one of the most essential aspects of English sentence retrieval research. These models are driven by diverse retrieval mechanisms that offer varying similarity calculations and directly influence the final result ranking. However, despite decades of work due to technical constraints, deep semantic analysis has been challenging. This gap emphasizes the importance of a precise semantic understanding of information acquisition through learning approaches. Based on the above opening, this paper establishes a fast retrieval model of English sentences based on the statistical language model (SLM). First, the proposed method utilizes SLM to extract significant feature words from the corpus. These feature words are identified by analyzing co-occurrence patterns and frequency distributions within the standard. Second, it employs the N-gram model to calculate the probabilities of word occurrences based on their contextual dependencies. This framework represents feature words and their associated probabilities in a structured manner by capturing the intricate nuances of language semantics. Third, the model integrates ontology to bridge the gap between human language and machine understanding by enabling the mapping natural language expressions to conceptual entities. Finally, the suggested model retrieves English sentences through semantic matching by leveraging the comprehensive semantic framework and ontology-based search. The experimental study revealed that the proposed model demonstrated an impressive retrieval ratio of 98.5% by outperforming existing models in the comparison. Moreover, these results show that the proposed algorithm performs better than the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm, and the accuracy of this algorithm is improved by 7.52% compared with TF-IDF. When the labelled corpus is very small and the unlabeled corpus is relatively large, the algorithm enhances the classifier's performance by 12.6%. This shows that the algorithm used in this paper reduces the influence of the synonym processing stage on the overall performance while retaining the advantages of high precision and accuracy of calculation results. [ABSTRACT FROM AUTHOR]

Computer, Internet, and Smartphone have changed our life as never before. Today, we cannot even imagine our life without these technologies. If we look around, we find everything, everywhere connected and controlled by system and software. We find amazing software and mobile applications which have become nerve of our daily life. Our dependency on this software and systems is so and so much that it is scary even to imagine, what if this system fails at any point in time. There is always a threat surrounded by various types of cyber-attacks. Every day cybercriminals are evolving their attacking strategy. Cyber-attacks using ever-more sophisticated malware are the major cause of concern for all types of users. Cyber-world has witnessed rapid changes in malware attacking strategy in the recent past. The volume, velocity, and complexity of malware are posing new challenges for malware detection systems. A scalable malware detection system with the capability to detect complex attacks is the time of need. In this paper, we have proposed a scalable malware detection system using big data and a machine learning approach. The machine learning model proposed in the system is implemented using Apache Spark which supports distributed learning. Locality-sensitive hashing is used for malware detection, which significantly reduces the malware detection time. A five-stage iterative process has been used to carry out the implementation and experimental analysis. The proposed model shown in the paper has achieved 99.8% accuracy. The proposed model has also significantly reduced the learning and malware detection time compared to models proposed by other researchers. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence and data acquisition technology are growing, the research on deep learning algorithm has gone deep into various fields. At this stage, the demand supply matching model under the comprehensive passenger transport hub travel system is obtained by analyzing the travel mode data. This paper takes traffic time as the research direction, uses machine learning and complex network theory to conduct in-depth learning algorithm research, respectively, discusses, explores and forecasts the traffic supply and demand mode data, and explores the traffic mode supply and demand model under the comprehensive passenger transport hub travel service system. It is shown in traffic data that using the prediction form of deep learning to predict traffic conditions and travel pressure can enable traffic managers to master traffic dynamics and lead the direction for future traffic development. Finally, from the perspective of MaaS system, the paper uses big data and information processing methods to explore the supply and demand matching model in terms of transportation modes. The research shows that MaaS system can make overall planning in terms of traffic resources, provide reasonable travel modes for traffic travelers and match corresponding travel services. It not only makes overall planning and guarantee for travel services, but also promotes the sustainable development of the transportation supply and demand system. [ABSTRACT FROM AUTHOR]

With the acceleration of Internet informatization and the vigorous development of social media, tourists are inclined to share their travel feelings online. This paper proposes a new framework for exploring the image of destinations from the perspective of tourists based on the online reviews of scenic spots. This study divides the image of destinations into three dimensions, mining the information of online reviews through statistical analysis and text matching, and analyzing the LDA topic model and emotional tendency. Combining the theory and method of probabilistic linguistic term set to obtain the element endowment information of scenic spots and form the destination image. Finally, the proposed method is successfully applied to the image perception of 10 5A scenic spots, and relevant policy suggestions are provided for managers. [ABSTRACT FROM AUTHOR]

Neural network methods are widely used in business problems for prediction, clustering, and risk management to improving customer satisfaction and business outcome. The ability of a neural network to learn complex nonlinear relationship is due to its architecture that uses weight parameters to transform input data within the hidden layers. Such methods perform well in many situations where the ordering of inputs is simple. However, for a complex reordering of a decision-maker, the process is not enough to get an optimal prediction result. Moreover, existing machine learning algorithms cannot reduce computational complexity by reducing data size without losing any information. This paper proposes an induced ordered weighted averaging (IOWA) operator for the artificial neural network IOWA-ANN. The operator reorders the data according to the order-inducing variable. The proposed sorting mechanism in the neural network can handle a complex nonlinear relationship of a dataset, which results in reduced computational complexities. The proposed approach deals with the complexity of the neuron, collects the data and allows a degree of customisation of the structure. The application further extended to IGOWA and Quasi-IOWA operators. We present a numerical example in a financial decision-making process to demonstrate the approach's effectiveness in handling complex situations. This paper opens a new research area for various complex nonlinear predictions where the dataset is big enough, such as cloud QoS and IoT sensors data. The approach can be used with different machine learning, neural networks or hybrid fuzzy neural methods with other extensions of the OWA operator. [ABSTRACT FROM AUTHOR]

It is hard to come up with a strong learning algorithm with high cross-media retrieval accuracy, but finding a weak learning algorithm with slightly higher accuracy than random prediction is simple. This paper proposes an innovative Bagging-based cross-media retrieval algorithm (called BCMR) based on this concept. First, we use bootstrap sampling to take a random sample from the original set. The amount of sample abstracted by bootstrapping is set to be the same as the amount of sample abstracted by the original dataset. Secondly, 50 bootstrap replicates are used to train 50 weak classifiers. In our experiments, we used homogeneous individual classifiers and eight different baseline methods. Last but not least, we generate the final strong classifier from 50 weak classifiers using the sample voting integration strategy. Using collective wisdom, we can get rid of bad decisions, giving the integrated model a much better generalization ability. Extensive experiments on three datasets show that BCMR can significantly improve cross-media retrieval accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes to predict traffic accidents based on IoTs and deep learning to address the current problem of inaccurate traffic accident prediction. Since traditional traffic accident prediction often applies classical prediction algorithms to a small portion of data, the obtained models can only predict a small range of traffic accidents. Most accident prediction models are limited by the lack of data features, do not consider the problems of practical application scenarios, and do not incorporate regional heterogeneity, so the prediction accuracy of accident prediction models is poor. This paper analyzes and summarizes the relationship between traffic accidents and influencing factors from five aspects, such as people, vehicles, roads and environment, and proves the influence of regional heterogeneity on accidents, which paves the way for traffic accident prediction. The data and heterogeneous spatial data are preprocessed and feature selected, respectively. Logistic regression and random forest algorithm are used to train the corresponding prediction models. The results show that the prediction model combined with regional heterogeneity has better comprehensive performance than the original data. [ABSTRACT FROM AUTHOR]

Presently, novel coronavirus outbreak 2019 (COVID-19) is a major threat to public health. Mathematical epidemic models can be utilized to forecast the course of an epidemic and cultivate approaches for controlling it. This paper utilizes the real data of spreading COVID-19 in Saudi Arabia for mathematical modeling and complex analyses. This paper introduces the Susceptible, Exposed, Infectious, Recovered, Undetectable, and Deceased (SEIRUD) and Machine learning algorithm to predict and control COVID-19 in Saudi Arabia.This COVID-19 has initiated many methods, such as cloud computing, edge-computing, IoT, artificial intelligence. The use of sensor devices has increased enormously. Similarly, several developments in solving the COVID-19 crisis have been used by IoT applications. The new technology relies on IoT variables and the roles of symptoms using wearable sensors to forecast cases of COVID-19. The working model involves wearable devices, occupational therapy, condition control, testing of cases, suspicious and IoT elements. Mathematical modeling is useful for understanding the fundamental principle of the transmission of COVID-19 and providing guidance for possible predictions. The method suggested predicts whether COVID-19 would expand or die in the long term in the population. The mathematical study results and related simulation are described here as a way of forecasting the progress and the possible end of the epidemic with three forms of scenarios: 'No Action,' 'Lockdowns and New Medicine.' The lock case slows it down the peak by minimizing infection and impacts area equality of the infected deformation. This study familiarizes the ideal protocol, which can support the Saudi population to breakdown spreading COVID-19 in an accurate and timely way. The simulation findings have been executed, and the suggested model enhances the accuracy ratio of 89.3%, prediction ratio of 88.7%, the precision ratio of 87.7%, recall ratio of 86.4%, and F1 score of 90.9% compared to other existing methods. [ABSTRACT FROM AUTHOR]

Music expresses thoughts and emotions in artistic form and is made up of different components including harmony, rhythm, and melody. Several musical elements are tied together during the songwriting process in order to generate melodies that are harmonic. A music melody is the essential element of any music to generate strong feelings from listeners and capture their interest. In the process of music appreciation, melody controls the emotional changes of music. It is an efficiently perceived part and the tone of a song. In recent years, Sichuan unvoiced music has developed rapidly and attracted much attention. This paper selects Sichuan unvoiced music as the main research theme and constructs a melody generation algorithm by utilizing the state-of-the-art techniques of deep learning (DL) and evolutionary algorithms (EAs) such as recurrent neural network-long short-term memory (RNN-LSTM) and genetic algorithm (GA). Firstly, this paper briefly describes the concept of DL algorithms, the deep generation model, and sequence to sequence model, as they constitute the technological foundation for this research. Secondly, this paper proposes a melody generation algorithm that utilizes RNN-LSTM for melody generation and GA for melody optimization. More specifically, the melody is generated by preprocessing data, creating, and training the RNN-LSTM model. A GA was used to determine the melodic fitness function for eight songs as the fitness function directly affects the selected termination condition. The fitness function can be thought of as either a person or an evolutionary rule. Finally, the average score of these songs, before and after evolution, is calculated, which demonstrates that the analysis and rotation creation methods are more precise and that the song's average melody score is higher. The method proposed in this study has been thoroughly compared to the existing approaches proposed in earlier studies, and it was found that the approach we propose is more effective in terms of accuracy and the average melody score. [ABSTRACT FROM AUTHOR]

Controlling complex nonlinear dynamical systems using traditional methods has always been a difficult task because the majority of systems seen in nature have intricate nonlinear mathematical relationships. Artificial neural network (ANN) models are a good option for handling such intricate nonlinear systems since they include a number of significant properties like faster learning, adaptation, parallel processing, and nonlinear mapping capabilities. Several recurrent neural networks (RNNs)-based controllers have been suggested in the literature for implementing adaptive control, but the majority of these models have extremely complex topologies and many of them are challenging to train. In this paper, an attempt is made to put forward the RNN model (called as higher-order recurrent neural network (HORNN)) which is based on a higher order Pi-Sigma neural network (PSNN) model and implemented for the indirect adaptive control of the nonlinear dynamical system. The parameters of the proposed controller are tuned using the gradient-descent-based asynchronous back-propagation (BP) method. The proposed controller consists of two additional internal feedback loop layers (denoted by F L 1 and F L 2 ) corresponding to the hidden and the output layer, respectively. The nodes present in F L 1 and F L 2 layers are having weighted connections with the hidden and the output layer neurons, respectively, and these feedback connections enrich the controller with a memory property. The second contribution of the paper is to improve the performance of the learning algorithm which is achieved by incorporating an adaptive learning rate scheme (that ensures the correct setting of the learning rate value in each iteration). Another advantage of the HORNN-based controller is that it is only provided with three inputs irrespective of the dynamics of the plant and only 3 hidden neurons are included in its hidden layer (this reduces the overall structural complexity of the proposed model). The performance of the HORNN-based controller is compared with some of the popular neural networks such as diagonal recurrent neural network (DRNN), Jordan recurrent neural network (JRNN), feed-forward neural network (FFNN), and PSNN. Through simulation experiments, it is observed that the response obtained from the plant under HORNN-based controller is found to be better as compared to responses obtained with other ANN-based controllers. Further, the instantaneous mean square error (IMSE) obtained with HORNN-based controller is quite less and is equal to 0.058 as compared to 0.077, 0.082, 1.74, 13.43, and 1.86 with DRNN, JRNN, PSNN, FFNN, and FFNN (with 30 hidden neurons)-based controllers, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a novel healthcare services framework that leverages versatile distributed computing and mobile cloud computing to enhance the delivery of medical care data. The framework is designed to integrate with diverse cloud settings and distributed computing resources, utilizing a Virtual-Dedicated-Server with 5 VCPU and 32 GB storage of RAM to develop a prototype specifically tailored for stroke patients with cardioembolic and cryptogenic subtypes, using Android-based mobile phones as the primary devices. The proposed framework consists of two fundamental application components: flexible usage and server request. By employing a Convolutional Neural Network (CNN) module, the system effectively distinguishes between the two-stroke subtypes. Simultaneously, the server application securely stores patient data, ensuring accessibility, security, and adaptability for stroke patients. The CNN module performs computations using the Stroke dataset, providing valuable insights into subtype classification. Additionally, the GBRF (Gradient boosting random forest) algorithm has been employed for further analysis and accurate predictive modeling within the healthcare system. The research contributions of this work are significant. Firstly, it introduces a unique healthcare mechanism that harnesses the potential of distributed computing and mobile cloud computing in improving healthcare services. Secondly, the paper verifies the exceptional value of stroke-related data collected through smartphones, underscoring the uniqueness and reliability of such data sources. Lastly, the system enables the provision of health status information to patients through a CNN application programming interface (API), facilitating seamless communication and personalized healthcare services. By integrating machine intelligence based technologies, the framework enhances the efficiency and effectiveness of stroke identification and contributing to the overall well-being of patients in a meaningful way. [ABSTRACT FROM AUTHOR]

In recent years, there have been several sports-related injuries and even unexpected fatalities due to the rapid growth of China's sports industry and increasing fitness issues. The prevalence of sports injuries is rapidly rising because of the intense competition among athletes and the increased physical load caused by players' long-term training. The difficulty in the sports' world is the identification and evaluation of risk factors associated with athletes. To address these issues, this paper develops a cognitive evaluation model for risk assessment of injuries in sports using big data to understand and determine the likelihood of injuries. The model is used to prevent the issues faced by running athlete's injury and thereby lowers the risk of overall risk. This paper also analyzes the injury factors while running by establishing an estimation model based on the radial basis function (RBF) neural network and explains how to compare RBF neural networks and risk level evaluation using certain criteria. The estimation model helps to identify and judge the risk factors of athletes. It designs an algorithm for Gaussian distribution, which predicts the output of the model. It discusses how the error may be calculated, which measures the neural network model's overall performance in forecasting sports' injury outcomes using a particular dataset. Finally, it designs the RBF Neural Network Learning algorithm, which generates the leaned network parameters to evaluate the reliability of risk cognitive model for athletes based on big data. The Lagrange and Bayesian models are selected for comparison. The results indicate that this model has a higher evaluation effect and accuracy as compared to other models. For this purpose, the comparison is made using 25 athletes. The proposed model's evaluation time is the lowest in comparison to the existing approaches. After examining the impact of cognitive evaluation, it has been reflected that the proposed model can be utilized to assess the different injury types for different parts of athletes. The highest single injury degree is 38.76%, while the highest composite injury degree is 40.05%. [ABSTRACT FROM AUTHOR]

Parkinson disease (PD) is a neurodegenerative disease that occurs due to insufficient level of dopamine in the human brain. This disease may occur predominantly in elder people. There exists no definite procedure to diagnose PD. It is diagnosed based on the symptoms, clinical trials, and number of laboratory tests. In this research paper, machine learning techniques are used to predict PD and help the medical practitioner to recommend personalized drugs for the patients. In this research paper, appropriate features are selected through rough set theory, and principal component analysis is used for dimensionality reduction. The performance is experimented using deep neural network, random forest, and SVM classifiers. The efficiency of the proposed approach is measured through confusion matrix, accuracy, precision, and recall. [ABSTRACT FROM AUTHOR]

The Analytic hierarchy process (AHP) is a widely used multi-criteria decision theory, and most AHP relies on the judgments of experts to derive priority scales. However, the judgments of experts may be subjective. Using machine learning algorithms for decision-making can be more objective, but machine learning algorithms are strongly related to the collected data and not being flexible enough. This paper tries to combine experts' judgments with algorithmic judgments to improve the bias of experts' judgments while still making decision-making flexible. In this paper, the authors introduce the ordered pair of normalized real numbers (OPNs) into the AHP method for the first time and propose the fuzzy analytic hierarchy process with the OPNs (OFAHP). The OFAHP uses OPNs to combine experts' judgments with those of machine learning algorithms and then make decisions by OPNs. Experiments on real data sets show that the proposed method can get reasonable decision results. Moreover, when the experts' judgments are wrong or invalid, the judgments given by the machine learning algorithm can correct the experts' judgments to obtain a reasonable decision-making result. [ABSTRACT FROM AUTHOR]

Reconstruction of cross-cut shredded text documents (RCCSTD) has important applications for information security and judicial evidence collection. The traditional method of manual construction is a very time-consuming task, so the use of computer-assisted efficient reconstruction is a crucial research topic. Fragment consensus information extraction and fragment pair compatibility measurement are two fundamental processes in RCCSTD. Due to the limitations of the existing classical methods of these two steps, only documents with specific structures or characteristics can be spliced, and pairing error is larger when the cutting is more fine-grained. In order to reconstruct the fragments more effectively, this paper improves the extraction method for consensus information and constructs a new global pairwise compatibility measurement model based on the extreme learning machine algorithm. The purpose of the algorithm's design is to exploit all available information and computationally suggest matches to increase the algorithm's ability to discriminate between data in various complex situations, then find the best neighbor of each fragment for splicing according to pairwise compatibility. The overall performance of our approach in several practical experiments is illustrated. The results indicate that the matching accuracy of the proposed algorithm is better than that of the previously published classical algorithms and still ensures a higher matching accuracy in the noisy datasets, which can provide a feasible method for RCCSTD intelligent systems in real scenarios. [ABSTRACT FROM AUTHOR]

With the rapid development in information and communication technologies, the relationship among the disciplines in various fields has become closer, resulting in many new technologies based on interdisciplinary research. This article considers robot soccer training as a research topic by involving related fields, i.e., interdisciplinary research. Compared with the physical robot, its simulation has the advantages of less cost, shorter experimental period, and is beneficial to the real-life studies in this context. This article discusses the practical application and optimization techniques used for robot soccer matches and training evaluation. The main tasks are as follows. First, we analyze and build a simulation platform for robot soccer matches. The basic principles of this platform are learning, and designing a novel optimized SARSA algorithm, built using the state-of-the-art state–action–reward–state–action (SARSA) algorithm. The optimized SARSA is a reinforcement learning algorithm that uses Q-value for making critical decisions about various parameters involved in the football training. Second, this paper simulates and analyzes the proposed optimized SARSA algorithm in a single-entity environment of robot football training. We compare the two algorithms before and after the improvement in a multi-entity environment. Among the simulation results, it is found that the optimized SARSA has a more powerful performance. The simulation results prove that the robot football training evaluation based on machine learning (optimized SARSA) can better formulate the robot football training strategy after applying the reinforcement learning strategy. [ABSTRACT FROM AUTHOR]

Using machine learning and deep learning methods to analyze text data from social media can effectively explore hidden emotional tendencies and evaluate the psychological state of social media account owners. However, the label noise caused by mislabeling may significantly influence the training and prediction results of traditional supervised models. To resolve this problem, this paper proposes a psychological evaluation method that incorporates a noisy label correction mechanism and designs an evaluation framework that consists of a primary classification model and a noisy label correction mechanism. Firstly, the social media text data are transformed into heterogeneous text graphs, and a classification model combining a pre-trained model with a graph neural network is constructed to extract semantic features and structural features, respectively. After that, the Gaussian mixture model is used to select the samples that are likely to be mislabeled. Then, soft labels are generated for them to enable noisy label correction without prior knowledge of the noise distribution information. Finally, the corrected and clean samples are composed into a new data set and re-input into the primary model for mental state classification. Results of experiments on three real data sets indicate that the proposed method outperforms current advanced models in classification accuracy and noise robustness under different noise ratio settings, and can efficiently explore the potential sentiment tendencies and users' psychological states in social media text data. [ABSTRACT FROM AUTHOR]

This paper aims to generate a universal well-fitted mathematical model to aid global representation of the spread of the coronavirus (COVID-19) disease. The model aims to identify the importance of the measures to be taken in order to stop the spread of the virus. It describes the diffusion of the virus in normal life with and without precaution. It is a data-driven parametric dependent function, for which the parameters are extracted from the data and the exponential function derived using multiplicative calculus. The results of the proposed model are compared to real recorded data from different countries and the performance of this model is investigated using error analysis theory. We stress that all statistics, collected data, etc., included in this study were extracted from official website of the World Health Organization (WHO). Therefore, the obtained results demonstrate its applicability and efficiency. [ABSTRACT FROM AUTHOR]

This paper promotes better life quality and lifestyle for patients. We attain this goal by creating a mobile application that analyses patient's medical records, such as diabetes, hypertension, and chronic kidney diseases. Then, we implement the system to diagnose patients with chronic conditions using machine learning techniques. Machine learning classifiers are used in this paper to decide whether a person has any chronic diseases. The investigated diseases are hypertension, diabetes, and chronic kidney disease. Four datasets were used to build the classifying models. Orange3 from Anaconda-Navigator, a data mining tool, was used to test machine learning algorithms. The study findings revealed the superiority of the tree algorithm with 100% accuracy for hypertension; it was the highest outcome for both males and females using Orange3. The highest precision, which is 100%, is observed by SVM, k-NN, decision trees, logistic regression, and CART for hypertension males' data collection. In comparison, the highest precision is 100% in SVM, MLP, decision tree, random forest, logistic regression, and CART for the female dataset. We conclude that the two datasets for the same diseases share mostly the same algorithm accuracy. For kidneys, the Random Forest algorithm produced 100% accuracy, which is the highest value among other algorithms. For diabetes, neural networks have attested the best accuracy. It was 76.3%, yet the accuracy increased slightly as the kNN algorithm showed 83% accuracy. [ABSTRACT FROM AUTHOR]

The usage of artificial intelligence and machine learning methods on cyberattacks increasing significantly recently. For the defense method of cyberattacks, it is possible to detect and identify the attack event by observing the log data and analyzing whether it has abnormal behavior or not. This paper implemented the ELK Stack network log system (NetFlow Log) to visually analyze log data and present several network attack behavior characteristics for further analysis. Additionally, this system evaluated the extreme gradient enhancement (XGBoost), Recurrent Neural Network (RNN), and Deep Neural Network (DNN) model for machine learning methods. Keras was used as a deep learning framework for building a model to detect the attack event. From the experiments, it can be confirmed that the XGBoost model has an accuracy rate of 96.01% for potential threats. The full attack dataset can achieve 96.26% accuracy, which is better than RNN and DNN models. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the detection and localization of radioactive sources by exploiting supervised machine learning. Machine learning is utilized in a wide variety of applications due to its effectiveness in prediction and autonomous decision-making. However, applying machine learning would only be effective when representative features for the application can be acquired, through which learning algorithms can be trained. Hence, first, we present a feature extraction technique for radioactive source localization, and then propose a parameter estimation method via machine learning. A distributed sensor network is employed to assist in estimating the radioactive source's location and intensity. We propose a feature extraction method that evaluates a feature vector using the reading and position of each sensor located in a region where a radiation source is detected. The feature extraction is based on a data fusion process, where a single feature value is provided to represent both the reading value and position coordinates corresponding to a given sensor. After the feature extraction, we apply the decision tree machine learning method for regression to localize a radioactive source. To examine the effectiveness of the proposed work, a performance comparison is carried out with recent existing methods in terms of the estimation accuracy and the execution time. Experimental results show that the proposed algorithm provides accurate source intensity estimation and achieves a good compromise between localization accuracy and execution time. [ABSTRACT FROM AUTHOR]

At a worldwide scale, artificial intelligence (AI) is now an intrinsic part of various sectors and a significant strategic element in the business agendas of several industries including health care, finance and retail. Machine learning, an statistical paradigm of AI, is one of the most preferred technologies to achieve AI. Machine learning-oriented approaches exploit massive sized, unstructured and complicated dataset instances to learn from previous experiences and find insightful patterns. A range of statistical, probabilistic and optimization approaches are used to achieve this task. Early detection of chronic diseases is critical in the realm of biomedical research and healthcare communities, where it is pivotal to primarily diagnose the particular disease at probabilistically early stage in order to lower the death rate. Pneumonia mainly affects a huge number of people, particularly children and adults, in the developing and undeveloped nations that are characterized as overcrowding, inadequate sanitation, malnutrition, lack of suitable medical services and other risk factors. It is critical to detect pneumonia at its early stage in order to properly treat the infection. This paper presents an approach, i.e. DPUD (Disease Prediction for Unstructured Data). The proposed framework consists of an statistically novel and fine-tuned algorithmic procedure to address certain pain points of categorization problem such as selection of an optimal set of model hyperparameters and attain an improved statistical performance metrics with multichannel shared activation function and cost function. In experimental evaluation, our approach capitulates state-of-the-art computational achievement on Chest X-Ray Images for the Pneumonia Classification dataset, while being considerably much faster at specifically test time. The methodology presented in this chapter has an empirical scope for societal improvement, modernization and progress. [ABSTRACT FROM AUTHOR]

Humans have the ability to quickly identify their own environment, understand, judge and analyze it, which is one of the important reasons why human beings can survive in nature for a long time and gradually develop it into a prosperous society today. The key to human's ability to perceive and understand the environment lies in the ability to accurately find and identify objects, understand and describe visual scenes, and even express emotions on this basis. And if computers can realize automatic and accurate image recognition, and even understand the semantics of images correctly, it will surely improve and facilitate human life. Based on this, the author integrated and optimized the computer image recognition system and applied it in this paper. The core technology of the system is to improve the image algorithm, which can complete the training, testing and classification of target images. The experimental data are available. Choosing this algorithm to improve the learning and training of the data generated by the original image processing is more effective than directly training the original image. [ABSTRACT FROM AUTHOR]

The traditional English part-of-speech analysis model fails to meet people's actual needs due to the fact that the accuracy and other parameters are not up to standard. Facing large-scale English text data, quickly and accurately obtaining the key information needed and improving the efficiency and accuracy of clustering have always been the focus of attention. However, the inherent characteristics of English text make it impossible to accurately calculate the traditional feature weight calculation method, and its part of speech is difficult to recognize. Moreover, in order to obtain a structure closer to the real data, this paper fuses the norm graph and the k-nearest neighbor graph, proposes a new composition framework, and combines it with two common propagation algorithms to complete the classification task. In addition, in order to obtain the improvement effect of the algorithm, the algorithm is tested on the English text classification corpus data set of the natural language processing open platform, and a control experiment is set to analyze the model performance. Finally, this article combines mathematical statistics to process data and draw corresponding charts. [ABSTRACT FROM AUTHOR]

Ethnic villages are an important part of villages, and also the inheritance of ethnic, cultural and spiritual forms. In a certain sense, the overall landscape characteristics of ethnic villages are the epitome of a national culture and image. In this paper, a landscape visualization scheme based on machine learning is proposed by combining the computing form of machine learning with the current visualization system. And use the principle of logistic regression and the principle of support vector calculation to analyze, select the appropriate data set for trend data analysis. Finally, taking the Hlai ethnic village landscape as the research direction in Hainan, the research is carried out in the fields of landscape science and ecology, and the comprehensive analysis is carried out in combination with the national culture, social, ecological and esthetic sensibility, and the Hlai ethnic village's own landscape index system is established. The research shows that the visual system research on the Hlai ethnic village landscape can reflect the Hlai ethnic village cultural landscape to a certain extent and is helpful to the protection and innovation of the Hlai ethnic villages; It is helpful to establish the landscape classification of Hlai ethnic villages and the establishment of future goals; To create their own national cultural landscape for Hlai ethnic villages; At the same time, it helps the sustainable development of Hlai ethnic villages and provides practical methods for the construction of Hlai ethnic villages. [ABSTRACT FROM AUTHOR]

Single-cell ribonucleic acid (RNA) sequencing technology is used to analyze transcriptomes of each cell individually and helps to identify rare cell populations. By using traditional applications, it is difficult to understand and analyze the transcriptomic profiles of cells at the single-cell level. So, to overcome these kinds of issues, machine learning technologies are playing a great role. In this paper, we analyzed single-cell RNA seq data by implementing linear dimensional reduction, identifying highly variable features, clustering the cells, nonlinear dimensional reduction, and identifying gene markers. This type of single-cell RNA sequencing analysis is much needed in identifying transcriptomic profile challenges in cells and heterogeneous characteristics. Our study helps researchers who are doing fundamental research in the field of bioinformatics and computational biology concerning single-cell RNA sequencing data. [ABSTRACT FROM AUTHOR]

Hyperparameter optimization plays a significant role in the overall performance of machine learning algorithms. However, the computational cost of algorithm evaluation can be extremely high for complex algorithm or large dataset. In this paper, we propose a model-based reinforcement learning with experience variable and meta-learning optimization method to speed up the training process of hyperparameter optimization. Specifically, an RL agent is employed to select hyperparameters and treat the k-fold cross-validation result as a reward signal to update the agent. To guide the agent's policy update, we design an embedding representation called "experience variable" and dynamically update it during the training process. Besides, we employ a predictive model to predict the performance of machine learning algorithm with the selected hyperparameters and limit the model rollout in short horizon to reduce the impact of the inaccuracy of the model. Finally, we use the meta-learning technique to pre-train the model for fast adapting to a new task. To prove the advantages of our method, we conduct experiments on 25 real HPO tasks and the experimental results show that with the limited computational resources, the proposed method outperforms the state-of-the-art Bayesian methods and evolution method. [ABSTRACT FROM AUTHOR]

Protecting users' privacy over the Internet is of great importance; however, it becomes harder and harder to maintain due to the increasing complexity of network protocols and components. Therefore, investigating and understanding how data are leaked from the information transmission platforms and protocols can lead us to a more secure environment. In this paper, we propose a framework to systematically find the most vulnerable information fields in a network protocol. To this end, focusing on the transport layer security (TLS) protocol, we perform different machine-learning-based fingerprinting attacks on the collected data from more than 70 domains (websites) to understand how and where this information leakage occurs in the TLS protocol. Then, by employing the interpretation techniques developed in the machine learning community and applying our framework, we find the most vulnerable information fields in the TLS protocol. Our findings demonstrate that the TLS handshake (which is mainly unencrypted), the TLS record length appearing in the TLS application data header, and the IV field are among the most critical leaker parts in this protocol, respectively. [ABSTRACT FROM AUTHOR]

Traditional IT with advent of convolution neural networks and deep learning can lead a trendsetter for healthcare sector, diseases identification and prediction. An essential upsurge during pandemic is virtualization of hospital functional policies and care models. Virtual models are providing solutions for disease detection without consulting a doctor in turn help to enhance patient care and performance. These architectural and operational policies are significant for healthcare domain to enable strategic decision-making for intricate and sensitive environment. The machine learning models will reveal information from the historical, optimize the present and even predict the future performance of the different areas analysed. This paper reveals the challenges of healthcare with automated Cataract Detection and Grading System. The proposed system uses an efficient deep learning model with CNN and LSTM for detecting and classifying healthy eye from cataract eye. The proposed system produced an accuracy of 98.5 for the custom dataset. [ABSTRACT FROM AUTHOR]

The unfluctuating running of on-orbit spacecraft equipment has a decisive impact on the smooth implementation of space exploration mission. However, due to the adverse work conditions and complex running states, it is really a challenge for the online monitoring of aerospace equipment. In this paper, an improved growing neural gas method based on incremental learning is proposed, which is dedicated to solving the problem of online anomaly detection. The learning rate of the proposed method is adaptively adjusted according to the process of model training, ensuring the weights update quickly at the beginning of model construction and converge steady at the end of model training. The optimized insertion mechanisms of neurons ensure that the necessary new neurons are inserted at the right time and location dynamically, while the innovative deletion mechanisms of neurons ensure that the worthless neurons be deleted timely and at the same time guarantee the representation ability of model. The comparison results with the conventional methods on public datasets show that the proposed method achieves the better performance obviously, both in the aspects of detection accuracy and computational efficiency, respectively. At last, as a case study, the proposed method is used for online anomaly detection of a real aerospace device, i.e., a gamma ray detector, and the final F1 score of anomaly detection is as high as 98.78%. The results show that the proposed method can be applied to online detection of aerospace equipment health conditions effectively. [ABSTRACT FROM AUTHOR]