Search

This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The image forming method called the rising paper chromatography is utilized in preparing the images of Memecik varieties of green olives for CNN. In the rising chromatography method, 20, 30, and 40% sample concentrations were determined as the suitable concentrations for both organic and conventional olives. The concentrations of AgNO3 and FeSO4 were determined as 0.25, 0.5, 0.75 and 1% for both conventional and organic samples. The visual differences used for differentiation of different types of Memecik green olives are usually determined according to the regional color differences, the vivid color occurrence, the width and the frequency of bowl occurrence, the thin line, and the picks at drop zone by the expert assessors. The testing results in this study verified the effectiveness of the CNN methodology in differentiating between the organically and conventionally cultivated Memecik green olives. The newly designed neural network achieved 100% accuracy. Furthermore, this high accuracy achieved by CNN might suggest that it can be effectively used in place of the expert assessors. [ABSTRACT FROM AUTHOR]

This paper investigates the art design of user interaction experience in mobile systems through the methods of contextual perception and machine learning. The theoretical foundations for the design of intangible cultural heritage interactive display resources include digital display theory, intangible cultural heritage education theory, embodied cognition theory, and gamification design theory. Based on the modelling and analysis of the theoretical foundations, the design principles are derived, including the heritage education principle, the somatic interaction design principle, and the content design principle. In this paper, we use ontologies to construct user knowledge models, fuse multi-situational similarity metrics, screen out candidate neighbour sets through preliminary screening, then combine the user's activity to construct time-based weight tensor scores, use tensor decomposition to obtain recommendation evaluation values, and finally use the recommendation evaluation values to make artistic recommendations. The experimental results show that the algorithm can still obtain a good recommendation implementation in the case of extremely sparse data. The analysis of the fit between augmented reality and folk art appreciation class, as well as the reference to relevant application cases, make design and practice of augmented reality application in folk art appreciation class, try to solve the common problems in folk art appreciation class, analyse the feedback effect and make a summary and outlook. [ABSTRACT FROM AUTHOR]

Experimental results on five public gene expression profile datasets verify that the proposed algorithm outperforms other methods in terms of diversity, distribution stability, and quality of generated samples. The fifth paper by I Tingyu Ye i et al. on "Artificial bee colony algorithm with an adaptive search manner and dimension perturbation" proposes a modified artificial bee colony (ABC) algorithm with an adaptive search manner and dimension perturbation (ASDABC). The tenth paper by I Fei Han i et al. on "Gene-CWGAN: A Data Enhancement Method for Gene Expression Profile Based on Improved CWGAN-GP" tackles the problem of high dimension and small sample size of gene expression profile data classification. [Extracted from the article]

Traditional sentiment analysis focuses on text-level sentiment mining, transforming sentiment mining into classification or regression problems, resulting in a sentiment analysis low accuracy rate. Sentiment analysis refers to the use of natural language processing, text analysis, and computational linguistics to systematically identify, extract, quantify, and study sentimental states. Therefore, more scholars have begun to focus on speech recognition and facial expression recognition research, and extracting and analysing people's sentiment tendencies can improve sentiment recognition accuracy. Traditional single-modal sentiment analysis can no longer meet people's needs. Therefore, this paper proposes a multimodal sentiment analysis method based on the multimodal sentiment analysis method that can obtain more sentimental information sources and help people make better decisions. The experimental results in this paper show that the highest recognition rates of CNN-SVM, RNN-SVM, and CRNN-SVM were 76.8%, 71.2%, and 93.5%, respectively. It can be seen that CRNN-SVM has the highest sentiment tendency recognition rate in deep learning, so it is suitable to apply CRNN-SVM to sentiment tendency analysis system design in this paper. The average accuracy rate of the system designed in this paper was 91%, and the stability was also very strong, which shows that the system designed in this paper is meaningful. The main contribution of this paper is based on the limitations of single-mode emotion analysis. It proposes a multimode emotion analysis method and introduces a convolutional neural network to help people obtain more emotional information sources to meet their needs. [ABSTRACT FROM AUTHOR]

This paper introduces a diagnostic model that effectively diagnoses in fourteen different stages, by fusing functional magnetic resonance imaging (fMRI) and structural MRI (sMRI) information. Georgios Theodoridis and Athanasios Tsadiras from the Aristotle University of Thessaloniki, Greece, have authored the seventh paper which is entitled "Applying machine learning techniques to predict and explain subscriber churn of an online drug information platform." Machine learning (ML) and more specifically deep learning (DL) algorithms are considered among the most paramount technologies of both artificial intelligence (AI) and 4 SP th sp industrial revolution. This paper provides an in-depth comparison of various machine learning (ML) techniques and advanced preprocessing methods, in an effort to successfully perform online subscriber churn prediction. [Extracted from the article]

The massive number of research articles on the Web makes it troublesome for researchers to identify related works that could meet their preferences and interests. Consequently, various network representation learning-based models have been proposed to produce citation recommendations. Nevertheless, these models do not exploit semantic relations and contextual information between the objects of bibliographic papers' networks, which can result in inadequate citation recommendations. Moreover, existing citation recommendation methods face problems such as lack of personalization, cold-start, and network sparsity. To mitigate such problems and produce individualized citation recommendations, we propose a heterogeneous network embedding model that jointly learns node representations by exploiting semantics corresponding to the author, time, context, field of study, citations, and topics. Compared to baseline models, the results produced by the proposed model over the DBLP datasets prove 10% and 12% improvement on mean average precision (MAP) and normalized discounted cumulative gain (nDCG@10) metrics, respectively. Also, the effectiveness of our model is analyzed on the cold-start papers and network sparsity problems, where it gains 12% and 9% better MAP and recall@10 scores, respectively. [ABSTRACT FROM AUTHOR]

In big data era, multi-source heterogeneous data become the biggest obstacle to data sharing due to its high dimension and inconsistent structure. Using text classification to solve the ontology construction and mapping problem of multi-source heterogeneous data can not only reduce manual operation, but also improve the accuracy and efficiency. This paper proposes an ontology construction and mapping scheme based on hybrid neural network and autoencoder. Firstly, the proposed text classification method uses the multi-core convolutional neural network to capture local features and uses the improved Bidirectional Long Short-Term Memory network to compensate for the shortcomings of the convolutional neural network that cannot obtain context-related information. Secondly, a similarity matching method is used for ontology mapping, which integrate autoencoder to improve anti-interference ability. We have carried out several sets of experiments to test the validity of the proposed ontology construction and mapping scheme. [ABSTRACT FROM AUTHOR]

This editorial briefly analyses, describes, and provides a short summary of a set of selected papers published in a special issue focused on deep learning methods and architectures and their application to several domains and research areas. The set of selected and published articles covers several aspects related to two basic aspects in deep learning (DL) methods, efficiency of the models and effectiveness of the architectures These papers revolve around different interesting application domains such as health (e.g. cancer, polyps, melanoma, mental health), wearable technologies solar irradiance, social networks, cloud computing, wind turbines, object detection, music, and electricity, among others. This editorial provides a short description of each published article and a brief analysis of their main contributions. [ABSTRACT FROM AUTHOR]

This cannot be achieved only through conventional Machine Learning (ML) frameworks and technologies. The technological advancement in recent years has seen a great shift leading to a greater magnitude of data storage, communication and subsequent processing with reduced size and cost of the systems. The thirteen paper "A Novel Emergency Situation Awareness Machine Learning Approach to Assess Flood Disaster Risk based on Chinese Weibo" is authored by Bai Hua, Yu Hualong, Yu Guang and Huang Xing. [Extracted from the article]

This Special Issue presents extended versions of the best papers presented at the International Conference on Digital Image Computing: Techniques and Applications (DICTA) which is the flagship Australian Conference on computer vision, image processing, pattern recognition, and related areas. DICTA is technically cosponsored by the Institute of Electrical and Electronics Engineers (IEEE) and the Australian Pattern Recognition Society (APRS). [Extracted from the article]

With the development of informatization, traditional industries have been seriously impacted by cross-border e-commerce (CBEC), and the financial management mode no longer meets the needs of CBEC users. As cross-border electronic trading platforms face enormous financial data challenges, they need financial supervision and effective network risk protection. Artificial intelligence (AI) can effectively improve the financial accounting ability and resource integration of platforms. However, at present, the underdeveloped financial management system of CBEC platforms and problems, such as the running records of platform funds have seriously hindered the development of the financial standardization of platforms because the financial management system affects managers' statistical analysis of financial data. Therefore, this paper analyzes the financial risks, the management problems and the causes of these problems of CBEC platforms and then uses AI to study the financial operation of CBEC platforms. Subsequently, this paper uses a machine learning (ML) algorithm to analyze the financial data clustering center and the security factor of the financial model. Finally, this paper proposes some corresponding strategies for financial model optimization and construction that can improve the information security and capital management of CBEC finance and promote the long-term development of CBEC platforms. The experimental results show that the classifier value and the safety factor of the financial model of CBEC platforms gradually increase under the ML algorithm. The mean value of the classifier value is approximately 1.14, and the mean value of the safety factor is approximately 1.37. Overall, the initial value of the classifier value of the platform financial model is 0.85, which increases to 1.41 on the seventh day, while the whole process increases by 0.56. The initial value of the safety factor of the platform financial model is 1.10, which increases to 1.64 on the seventh day, while the whole process increases by 0.54. The transaction information security and financial accounting accuracy of the CBEC platform financial model is better than that of the original financial model. The transaction information security is 10.4% higher than that of the original financial model, and the financial accounting accuracy is 10% higher than that of the original financial model. In other words, both AI and ML can promote the financial accounting standards and long-term development of CBEC platforms. [ABSTRACT FROM AUTHOR]

The deep fusion of sports and machine vision has become a research hot spot in sports video target detection, athlete state recovery and sports promotion. On the basis of in-depth study, it can detect a large number of sports videos, complete the drawing and analysis of human body detection model, and detect and evaluate the posture of corresponding athletes in the video, which can save a lot of costs and maximize the more professional training of athletes. In order to solve the above problems, this paper innovatively completes the automatic language description of sports video based on time-sharing memory algorithm. Its principle is to realize the accurate decomposition of athletes' sports data through the mapping relationship between the corresponding letter sequence and video sequence in time-sharing memory. In order to capture the key posture of athletes' sports video, this paper innovatively proposes an object extraction algorithm based on athletes' skeleton motion enhancement. In practical application, based on the key pose capture, it is necessary to train the depth selection network in time to extract the key pose of the skeleton. Based on this network, it can enhance the key posture of bone information and accurately express its related features. After extracting the actual athlete's bone information, we need to fine-tune the training network to realize the accurate recognition of key features. Based on the above key algorithms, this paper designs a sports video athlete detection system based on deep learning and makes an experimental research on the related sports video. The experimental results show that the detection accuracy of athletes' sports video is improved by nearly 10% compared with the traditional convolution network recognition algorithm, so the algorithm has obvious advantages in recognition accuracy. [ABSTRACT FROM AUTHOR]

The spread of Covid-19 misinformation on social media had significant real-world consequences, and it raised fears among internet users since the pandemic has begun. Researchers from all over the world have shown an interest in developing deception classification methods to reduce the issue. Despite numerous obstacles that can thwart the efforts, the researchers aim to create an automated, stable, accurate, and effective mechanism for misinformation classification. In this paper, a systematic literature review is conducted to analyse the state-of-the-art related to the classification of misinformation on social media. IEEE Xplore, SpringerLink, ScienceDirect, Scopus, Taylor & Francis, Wiley, Google Scholar are used as databases to find relevant papers since 2018–2021. Firstly, the study begins by reviewing the history of the issues surrounding Covid-19 misinformation and its effects on social media users. Secondly, various neuro-fuzzy and neural network classification methods are identified. Thirdly, the strength, limitations, and challenges of neuro-fuzzy and neural network approaches are verified for the classification misinformation specially in case of Covid-19. Finally, the most efficient hybrid method of neuro-fuzzy and neural networks in terms of performance accuracy is discovered. This study is wrapped up by suggesting a hybrid ANFIS-DNN model for improving Covid-19 misinformation classification. The results of this study can be served as a roadmap for future research on misinformation classification. [ABSTRACT FROM AUTHOR]

Today's factories are considered as smart ecosystems with humans, machines and devices interacting with each other for efficient manufacturing of products. Industry 4.0 is a suite of enabler technologies for such smart ecosystems that allow transformation of industrial processes. When implemented, Industry 4.0 technologies have a huge impact on efficiency, productivity and profitability of businesses. The adoption and implementation of Industry 4.0, however, require to overcome a number of practical challenges, in most cases, due to the lack of modernisation and automation in place with traditional manufacturers. This paper presents a first of its kind case study for moving a traditional food manufacturer, still using the machinery more than one hundred years old, a common occurrence for small- and medium-sized businesses, to adopt the Industry 4.0 technologies. The paper reports the challenges we have encountered during the transformation process and in the development stage. The paper also presents a smart production control system that we have developed by utilising AI, machine learning, Internet of things, big data analytics, cyber-physical systems and cloud computing technologies. The system provides novel data collection, information extraction and intelligent monitoring services, enabling improved efficiency and consistency as well as reduced operational cost. The platform has been developed in real-world settings offered by an Innovate UK-funded project and has been integrated into the company's existing production facilities. In this way, the company has not been required to replace old machinery outright, but rather adapted the existing machinery to an entirely new way of operating. The proposed approach and the lessons outlined can benefit similar food manufacturing industries and other SME industries. [ABSTRACT FROM AUTHOR]

Human distance estimation is essential in many vital applications, specifically, in human localisation-based systems, such as independent living for older adults applications, and making places safe through preventing the transmission of contagious diseases through social distancing alert systems. Previous approaches to estimate the distance between a reference sensing device and human subject relied on visual or high-resolution thermal cameras. However, regular visual cameras have serious concerns about people's privacy in indoor environments, and high-resolution thermal cameras are costly. This paper proposes a novel approach to estimate the distance for indoor human-centred applications using a low-resolution thermal sensor array. The proposed system presents a discrete and adaptive sensor placement continuous distance estimators using classification techniques and artificial neural network, respectively. It also proposes a real-time distance-based field of view classification through a novel image-based feature. Besides, the paper proposes a transfer application to the proposed continuous distance estimator to measure human height. The proposed approach is evaluated in different indoor environments, sensor placements with different participants. This paper shows a median overall error of ± 0.2 m in continuous-based estimation and 96.8 % achieved-accuracy in discrete distance estimation. [ABSTRACT FROM AUTHOR]

Digital image noise may be introduced during acquisition, transmission, or processing and affects readability and image processing effectiveness. The accuracy of established image processing techniques, such as segmentation, recognition, and edge detection, is adversely impacted by noise. There exists an extensive body of work which focuses on circumventing such issues through digital image enhancement and noise reduction, but this work is limited by a number of constraints including the application of non-adaptive parameters, potential loss of edge detail information, and (with supervised approaches) a requirement for clean, labeled, training data. This paper, developed on the principle of Noise2Void, presents a new unsupervised learning approach incorporating a pseudo-siamese network. Our method enables image denoising without the need for clean images or paired noise images, instead requiring only noise images. Two independent branches of the network utilize different filling strategies, namely zero filling and adjacent pixel filling. Then, the network employs a loss function to improve the similarity of the results in the two branches. We also modify the Efficient Channel Attention module to extract more diverse features and improve performance on the basis of global average pooling. Experimental results show that compared with traditional methods, the pseudo-siamese network has a greater improvement on the ADNI dataset in terms of quantitative and qualitative evaluation. Our method therefore has practical utility in cases where clean images are difficult to obtain. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been widely applied to single image super-resolution(SISR). However, the majority of deep learning methods employ the Mean Square Error(MSE) loss as the objective optimization function, and the generated results are frequently too smooth and lack of details. In addition, the high-frequency information of the reconstructed image is severely lost, resulting in a generated image with poor visual effects. In order to address the aforementioned issues, this paper proposes a super-resolution network (RRFDB-GAN) with a receptive field module with a generative adversarial network as the main framework. The network adopts the receptive field block (RFB), which enables it to extract the features in multiple scales and to improve the discriminability. In this paper, the Residual in Residual Dense Block (RRDB) and the Residual of Receptive Field Dense Block (RRFDB) are combined into a new module, called Basic block. This module enhances the capability of feature reconstruction for low-resolution images. During the upsampling stage, a combination of Nearest Neighborhood Interpolation and Sub-pixel convolution is used to reduce the computational complexity and provide additional contextual information for super-resolution reconstruction, while achieving satisfactory performance. Finally, the four Basic blocks are integrated with the upsampling module into a simple end-to-end framework. Extensive experimental results demonstrate that the proposed method in this paper shows more details on the five test sets and outperforms other methods in terms of quantitative metrics and perception assessment. [ABSTRACT FROM AUTHOR]

Handwritten music recognition (HMR) is the technology of transcribing the content of images of music scores. The accurate detection of music objects at the page level is one of the main challenges of HMR. Thus far, the existing methods suffer from the tiny and dense nature of handwritten music notations and realize positive detection accuracy only on snippets. In this paper, we propose a detector that consists of a staff line removal model and a handwritten music object detection model for page-level handwritten music object recognition. First, an end-to-end staff line removal model R_Staff_Net based on residual learning reduces the complexity of page-level detection. Second, we developed an improved YOLO-V4 model for handwritten music object detection. The improvements mainly concern the adoption of a de-coupled detection head and visual attention module in the YOLO-V4, and an adaptive multi-scale feature fusion module AMFFM is used to enhance the textures and features of tiny music symbols in the deep convolution layers, and the gradient harmonized mechanism is utilized to address the inherent imbalance between music objects. We verified the R_Staff_Net and the improved YOLO-V4 model on the ICDAR/GREC staff line removal dataset and the MUSCIMA++ dataset, respectively. The experiments highlight that R_Staff_Net presents outstanding performance with an F-M score of 98.64%, and our improved YOLO-V4 model is superior to other handwritten music symbol detection methods with a mean average precision (mAP) of 91.8% when addressing page-level input. Although the experimental results of the detector show that the R_Staff_Net helps little to the overall mAP, the network is beneficial for symbols that are similar to staff lines or heavily overlap staff lines. [ABSTRACT FROM AUTHOR]

Constructing a personalized learning path is a critical way to solve the problem of cognitive difference and learning disorientation effectively. The construction process of the learning path is closely related to the internal relationship between knowledge and needs to meet different learning scenarios and learning needs. Because of the above requirements, a personalized learning path model based on a knowledge network is proposed in this paper. The algorithm begins by building a knowledge network with learning resource nodes and knowledge points. Following that, the order of the knowledge points was determined using their sequential link. A sequence of learning materials that adhere to user characteristics was eventually acquired by evaluating the learning time limit of various learning contexts. The proposed approach was tested on the data sets of open MOOPer and Python learning platforms. Compared with traditional learning path construction algorithms, the proposed algorithm improves the accuracy and relevance. [ABSTRACT FROM AUTHOR]

With the rapid development of computer technology and artificial intelligence today, human–computer interaction based solely on computer software operations is far from being able to meet human requirements for computer use. People are looking forward to a more convenient and fast human–computer interface. This paper studies the expression dynamic capture and 3D animation generation methods based on deep learning. For facial expression dynamic capture, this paper proposes a facial feature extraction algorithm based on deep learning and uses SVM technology for feature classification. For 3D animation, C++ and OpenGL are used for rendering simulation. The experimental results show that the face detection algorithm proposed in this paper has good performance in both accuracy and speed. It can realize real-time detection of face regions in video images. [ABSTRACT FROM AUTHOR]

It is challenging to use unsupervised machine translation models to generate ancient poems. The current method has solved the problems of Under-translation and Over-translation caused by the huge length difference between the translated sentence pairs. However, the above method lacks guidance in generating intermediate vectors, and the denoising ability of the model is very poor. In this paper, we guide vector space distribution during training to improve the quality of the generated ancient poems and the convergence speed of the model. We also introduce the target language information while adding noise, which effectively avoids the recurrence of the Under-translation problem while improving the model's denoising ability. Experiment results on the VP dataset show that our model obtains state-of-the-art results with faster convergence speed. In addition to the BLEU scores, we also made a comparative analysis of ancient poetry sentences generated by different models. The analysis results show that the optimization method proposed in this paper is indeed helpful for generating high-quality ancient poems. [ABSTRACT FROM AUTHOR]

The popularity of digital cameras and social networks has greatly enriched people's spiritual life, and we can easily obtain massive amounts of digital photos. However, due to the lack of professional guidance and differences in aesthetic appreciation, the photos taken many photographers lack aesthetics. This article is dedicated to the research of image aesthetics, using computers to simulate human perception, and realize the evaluation or beautification of images in line with human aesthetics. In terms of image classification, this article examines the unique perception of human vision on images and proposes new aesthetic features. Combining visual features and semantic features, the SVM algorithm is utilized to build an aesthetic classifier. In the aspect of image optimization, this paper uses the detection of the main image area and the division line of the area and adjusts the main body size and position of the image according to common aesthetic rules, so as to realize the optimization adjustment of the composition of the social image. The experimental results show that the accuracy of social image classification is 97.7%, and the optimized and adjusted images are more aesthetic. [ABSTRACT FROM AUTHOR]

In order to improve the traffic visualization management technology of smart cities, this paper applies machine learning to smart traffic management, and uses machine learning methods to process and analyze traffic data generated in smart cities. Moreover, this paper uses it to understand the distribution law of traffic data and the internal connections between data, excavate traffic characteristics in smart cities, and accurately predict the future traffic situation, so as to solve the problems of traffic congestion and route planning in smart cities. Moreover, this paper combines improved machine learning algorithms to construct a traffic visualization management system, and designs experiments to verify the performance of the system proposed in this paper. It can be seen from the experimental research results that the method proposed in this paper can play an important role in the traffic management of smart cities. [ABSTRACT FROM AUTHOR]

To improve the effect of commercial insurance risk decision, this paper applies neural network algorithms to commercial insurance risk decision under the guidance of machine learning ideas, and selects the neural network algorithm based on the actual situation. Moreover, this paper analyzes the nature of risks of commercial insurance, analyzes the types of risks and risk relevance, constructs a commercial insurance risk decision model based on neural network algorithms, and determines the system process. In addition, this paper uses a combination method of qualitative and quantitative to identify the influencing factors of risk estimation to obtain relevant influencing factors, and verify the model proposed in this paper in combination with experimental research. From the experimental research results, it can be seen that the commercial insurance risk decision system based on neural network algorithm is very good in terms of decision effect. [ABSTRACT FROM AUTHOR]

Broad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent's behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) aims to develop techniques to extract concepts from the agent's: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. CXF is designed to incorporate many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes its decisions. This paper aims to: establish XRL as a distinct branch of XAI; introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper discusses how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI. [ABSTRACT FROM AUTHOR]

Automatic facial expression recognition (AFER), sometimes referred to as emotional recognition, is important for socializing. Automatic methods in the past two years faced challenges due to Covid-19 and the vital wearing of a mask. Machine learning techniques tremendously increase the amount of data processed and achieved good results in such AFER to detect emotions; however, those techniques are not designed for masked faces and thus achieved poor recognition. This paper introduces a hybrid convolutional neural network aided by a local binary pattern to extract features in an accurate way, especially for masked faces. The basic seven emotions classified into anger, happiness, sadness, surprise, contempt, disgust, and fear are to be recognized. The proposed method is applied on two datasets: the first represents CK and CK +, while the second represents M-LFW-FER. Obtained results show that emotion recognition with a face mask achieved an accuracy of 70.76% on three emotions. Results are compared to existing techniques and show significant improvement. [ABSTRACT FROM AUTHOR]

Image white-balancing is an integral part of every camera's processing pipeline. White-balancing is used to remove illumination chromaticity from an image. Most research in this field has been limited to images with a single uniform illuminant. In this paper, we introduce a novel method for illumination estimation for situations where the scene is illuminated by a variable number of different illuminants and where the illumination in the scene can be non-uniform. The proposed method uses a lightweight convolutional neural network that achieves state-of-the-art results. The method performs illumination estimation on a patch-by-patch basis. We use the assumption that only one illuminant affects each patch since they are so small. Unlike other such methods, our method uses features extracted from the entire image to perform patch illumination estimation. The paper also shows how the image features improve method accuracy with a minimal increase in complexity. The proposed method has around 42 k parameters, and it was tested on three different cameras from the Large-Scale Multi-Illuminant dataset. [ABSTRACT FROM AUTHOR]

Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches that improve the chance of success in practical situations. Our search simultaneously optimizes for network accuracy, energy efficiency and memory usage. We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult, we use a random forest model to roughly predict the energy usage of a candidate network. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early stopping to reduce the computational burden. Our search, evaluated on a sound event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint than our baseline MobileNetV1/V2 implementations while slightly improving task accuracy. We also demonstrate how combining a 2D spectrogram with a convolution with many filters causes a computational bottleneck for audio classification and that alternative approaches reduce the computational burden but sacrifice task accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a deep learning-based activity recognition for the Human–Robot Interaction environment. The observations of the object state are acquired from the vision sensor in the real-time scenario. The activity recognition system examined in this paper comprises activities labeled as classes (pour, rotate, drop objects, and open bottles). The image processing unit processes the images and predicts the activity performed by the robot using deep learning methods so that the robot will do the actions (sub-actions) according to the predicted activity. [ABSTRACT FROM AUTHOR]

A continuous monitoring of neurological status can help in reporting the physical and mental health of a person. This can be capitalized for building a healthcare tracking system using a wearable device and a handheld mobile device. In this paper, we have used the non-EEG physiological biosignals dataset which gives practicability among subjects for acquiring data easily from wearable device sensors linearly and comfortably rather than the way of putting the subjects in a cumbersome setup laboratory. This paper proposes a custom fully convolutional-LSTM (FCN-LSTM) network to identify the neurological status of a subject using multivariate time series physiological sensor data. The proposed architecture uses parallel stacks of the convolutional layers and LSTM cells. This combination of different network types is significant for the selected problem as the fully convolutional section of the model extracts the local spatial features in the data, while the LSTM network handles the high-level features and temporal dependencies. The proposed FCN-LSTM model yielded a high accuracy of 98.6% and a precision of 98% on the non-EEG dataset from UT-Dallas. The average accuracy of single-subject results of the dataset using the proposed model was observed to be 99.26%. The results from the proposed model are significantly improved when compared with various state-of-the-art works on this problem. These results strongly suggest that this model, when put on a wearable device, can be effectively used to detect the neurological status or stress that the subject may be going through in real time. [ABSTRACT FROM AUTHOR]

Promoting the development of enterprises is a common task of all countries in the world, and the government has always taken promoting enterprise development as a long-term strategy. With the development for market, as an integral part of the social market economy, enterprises have made great contributions to the rapid of national economy. The enterprises are increasing, but the market competition is becoming increasingly fierce, and the weaknesses of enterprises such as limited scale, lax management and difficult financing are constantly highlighted. The appearance of these problems makes enterprises encounter many bottleneck problems in the process of development. Innovation, as the inexhaustible power of enterprise development, plays a significant role in enterprise growth, it is the key to solving the bottleneck problem of enterprise development. If an enterprise wants to achieve considerable development, it must innovate and enhance its competitiveness through innovation. In this context, how to evaluate enterprise innovation has become an important work. This work proposes an IPSO-ATT-MSCNN network via PSO from swarm optimization algorithm and artificial neural network to evaluate enterprise innovation. First, this work designs a multi-scale convolutional neural network (ATT-MSNN) via attention mechanism. This method uses multi-scale convolution to extract features of different scales, which improves the richness of features. This adds attention mechanisms to enhance useful features and reduce the impact of unwanted features such as noise. Second, in view of the performance degradation caused by the random initialization, this paper uses improved PSO algorithm to optimize the initial parameters. Third, this work proposes a series of strategies for promoting enterprise innovation. Finally, this work carried out a comprehensive and systematic experiment for the designed method, and the experiment verified the superiority of this method. [ABSTRACT FROM AUTHOR]

Cluster analysis is one of the most fundamental methods in data mining, and it has been widely used in economics, social sciences and computer science. However, with the rapid development of Internet technology, the volume of data required for various web applications has grown rapidly, making the traditional clustering analysis methods face technical challenges. How to obtain useful information in a large amount of data quickly and efficiently is an urgent problem in many industrial fields. With the continuous development of cloud computing technology, large amounts of data can be performed quickly and efficiently. Hadoop is an open source distributed cloud computing platform with HDFS (Digital File System) and MapReduce as its core. HDFS provides massive data storage, while MapReduce uses the MapReduce programming model to achieve parallel processing. Compared with the traditional parallel programming model, it contains basic functions such as data partitioning, task scheduling, and parallel processing, making it possible for users to develop distributed applications on their own without understanding the basics of distributed basics, thus facilitating the design of parallel programs. K-means algorithm is a typical clustering analysis method, which is widely used in industry, but the number of iterations will increase significantly due to the growth of data volume, thus reducing the efficiency of computation. In order to better apply to the cluster analysis of large-scale data, this paper firstly implements a parallelization algorithm based on MapReduce on Hadoop platform using the basic idea of MapReduce and improves the K-means algorithm for the problems of blindness and easy to fall into local optimum when selecting randomly in clusters. [ABSTRACT FROM AUTHOR]

According to the coexistence of fuzziness and randomness of risk factors in engineering early warning, this paper proposes a risk early warning model based on a convolutional neural network, which identifies and analyzes the risk points in engineering through engineering site pictures and provides early warning for engineering risk points in time. The risk warning model fully characterizes the fuzziness and randomness of risk, and the warning results are more objective and in line with the actual situation, which provides a more feasible engineering risk warning method. The experiments prove that the method can accurately warn of project risks, and the warning readiness rate reaches 91.3%. [ABSTRACT FROM AUTHOR]

For detecting and resolving the various types of malware, novel techniques are proposed, among which deep learning algorithms play a crucial role. Although there has been a lot of research on the development of DL-based mobile malware detection approaches, they were not reviewed in detail yet. This paper aims to identify, assess, and synthesize the reported articles related to the application of DL techniques for mobile malware detection. A Systematic Literature Review is performed in which we selected 40 journal articles for in-depth analysis. This SLR presents and categorizes these articles based on machine learning categories, data sources, DL algorithms, evaluation parameters & approaches, feature selection techniques, datasets, and DL implementation platforms. The study also highlights the challenges, proposed solutions, and future research directions on the use of DL in mobile malware detection. This study showed that Convolutional Neural Networks and Deep Neural Networks algorithms are the most used DL algorithms. API calls, Permissions, and System Calls are the most dominant features utilized. Keras and Tensorflow are the most popular platforms. Drebin and VirusShare are the most widely used datasets. Supervised learning and static features are the most preferred machine learning and data source categories. [ABSTRACT FROM AUTHOR]

Marine object detection has become increasingly important in intelligent underwater robot. Because of color cast and blur in underwater images, features directly extracted from backbone networks usually lack interesting and discriminative characters, that affects performance on marine object detection. To this end, this paper proposes a novel refined marine object detector with attention-based spatial pyramid pooling networks and bidirectional feature fusion strategy to relieve the weakening of features and address marine object detection issues. Firstly, an attention-based spatial pyramid pooling network named as SA-SPPN is proposed to enrich interesting information and extend receptive field on original features extracted from backbone network. Based on enhanced multiple level features, the bidirectional feature fusion strategy is designed to fuse different level features and generate robust feature maps for detection. Specifically, the top-down connection could transfer semantic information from high-level features to enhance low-level features. The bottom-up pathway could extend resolution of high-level features. Furthermore, the cross-layer connections are integrated into both top-down passway and bottom-up passway to carry out multiple branch fusion. On bounding boxes regression phase, the distance-IoU loss is adopted to improve regression speed and accuracy. Finally, this paper conducts series experiments on underwater image datasets and URPC datasets to detect marine objects. The experimental results reveal that our approach could achieve impressive performance and reach 79.64% mAP on underwater image datasets, 79.31% mAP on URPC2019 datasets and 79.93% mAP on URPC2020 datasets, respectively. For standard object detection, the proposed algorithm also could realize notable performance and get 81.9% mAP on PASCAL VOC datasets. [ABSTRACT FROM AUTHOR]

In the paper titled "A prediction-based cycle life test optimization method for cross-formula batteries using instance transfer and variable-length-input", Ma et al. deal with the prediction of the useful life of lithium-ion power-grade batteries. The practice of maintenance and asset management has been among the key beneficiaries of the industrial transition towards digitalisation. Data-driven machine learning approaches for critical assets can rarely benefit from the availability of data which cover a sufficient range of operating conditions and faults. [Extracted from the article]

Contents of the special issue This special issue contains 8 articles, which were carefully selected from 45 initial submissions to ALA 2020. This special issue features selected papers from the 12th Adaptive and Learning Agents Workshop[1] (ALA 2020), which was held virtually on 9 and 10 May 2020, in conjunction with the 19th International Conference of Autonomous Agents and Multi-Agent Systems (AAMAS 2020). The goal of the Adaptive and Learning Agents (ALA) workshop is to increase awareness of and interest in adaptive agent research, encourage collaboration, and give a representative overview of current research in the area of adaptive and learning agents. [Extracted from the article]

With graph structure data becoming more common in practical problems, graph neural networks have shown their potential for processing graph structure data. Now, a heterogeneous graph containing different types of nodes and edges as a more complex type of graph structure is the hot research area. However, existing studies only focus on supervised methods/semi-supervised methods for heterogeneous graph, which require a lot of labeled data, demanding lots of money and time. In this paper, we propose a novel framework, i.e., the self-supervised contrastive learning for heterogeneous graph based on multi-pretext tasks (HGMT). In our proposed HGMT, considering the essential and inherent properties of heterogeneous graph, we utilize both metapath-based encoder and network schema-based encoder to get two different node representations to construct contrastive samples. And then, we design three complementary pretext tasks, i.e., local–local self-supervised contrastive learning task, local–context self-supervised contrastive learning task and local–global self-supervised contrastive learning task, which can make model have a deeper understanding of the interaction relationships on local, context and global structure information of heterogeneous graph. At last, we view it as multitask learning to train our proposed HGMT model by balancing these three pretext tasks. Empirical results validate the performance of our proposed HGMT compared with the existing state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Chinese calligraphy is an important part of Chinese national culture and art and part of the essence of Chinese national culture. Stone calligraphy is one of the important elements of Chinese calligraphy art. Stone carved calligraphy characters have high cultural and artistic value. Therefore, accurately recognizing stone carved calligraphy characters are of great importance. Stone carved calligraphy can identify hard-to-preserve stone calligraphy paper materials in electronic data that can be preserved for a long time, thereby offering important reference materials for the study of the historical development of Chinese calligraphy art. Moreover, with the development of science and technology and the investment of China in cultural and artistic undertakings, computer-aided calligraphy character recognition technology is also constantly improving, and its application in calligraphy recognition is becoming increasingly extensive. This article aims to study a method of stone inscription calligraphy recognition based on convolutional neural networks. In this paper, we use an image recognition and optimization method consisting of a convolutional neural network to carry out an experiment with stone inscription calligraphy characters. It was concluded that the recognition accuracy of stone calligraphy characters by the convolutional neural network reached 99.2%, indicating that this stone calligraphy character recognition method based on a convolutional neural network has a good ability to recognize stone calligraphy characters. [ABSTRACT FROM AUTHOR]

With the rapid development of information technology, information war is becoming more and more intense. Signal processing plays an increasingly important role in information war, and the application of this technology is becoming more and more extensive. The information signal processed by the traditional frequency hopping communication system is relatively single. When there are a variety of electromagnetic signals, the communication channel environment is complex and there will be signal interference. Therefore, this paper studies the detection, identification, and experimental simulation of quasi-frequency hopping signal under multi-fixed frequency interference. Firstly, this paper uses the short-time Fourier transform and Wigner–Ville time–frequency analysis method to identify and simulate the interference signal of multi-fixed frequency interference. Then, according to the working principle of genetic algorithm, the design steps of radio high frequency (RHF) signal are designed, the signal model is constructed, and the narrowband interference suppression strategy is proposed to suppress the fixed frequency interference signal. According to the simulation of this model in this paper, the suppression effect of time–frequency domain and joint method is more obvious than that of traditional time–frequency domain. If the fixed frequency interference signal only covers a small part or does not cover the quasi random frequency hopping signal, the signal suppression effect of using time–frequency domain to filter the interference signal is better than using non-decimation wavelet packet transform algorithm, and there will be no error impact on the original signal when completely using time–frequency domain to filter the signal. Finally, this paper combines the interference analysis algorithm in time domain and time frequency domain and carries on the simulation analysis. Through the application simulation of multi-target scene, the results show that the complementary code modulation method can estimate the distance and velocity parameters in multi-target scene. Although the velocity measurement range is narrow, this method has the advantages of high velocity measurement accuracy, higher output signal-to-noise ratio and lower computational complexity. [ABSTRACT FROM AUTHOR]

High-resolution remote sensing images have become mainstream remote sensing data, but there is an obvious "salt and pepper phenomenon" in the existing semantic segmentation methods of high-resolution remote sensing images. The purpose of this paper is to propose an improved deep convolutional neural network based on HRNet and PSPNet to segment and realize deep scene analysis and improve the pixel-level semantic segmentation representation of high-resolution remote sensing images. Based on hierarchical multiscale segmentation technology research, the main method is multiband segmentation; the vegetation, buildings, roads, waters and bare land rule sets in the experimental area are established, the classification is extracted, and the category is labeled at each pixel in the image. Using the image classification network structure, different levels of feature vectors can be used to meet the judgment requirements. The HRNet and PSPNet algorithms are used to analyze the scene and obtain the category labels of all pixels in an image. Experiments have shown that artificial intelligence uses the pyramid pooling module in the classification and recognition of CCF satellite images. In the context of integrating different regions, PSPNet affects the region segmentation accuracy. FCN, DeepLab and PSPNet are now the best methods and achieve 98% accuracy. However, the PSPNet object recognition algorithm has better advantages in specific areas. Experiments show that this method has high segmentation accuracy and good generalization ability and can be used in practical engineering. [ABSTRACT FROM AUTHOR]

The automatic reading of pointer meters is significantly important to data monitoring and efficient measurement in the industrial field. However, the existing automatic reading method can not obtain accurate performance in natural scenarios and present no satisfactory application effects in industrial fields (such as power stations and gas stations). In this paper, a novel automatic reading method for pointer meters based on deep learning is proposed, which contains five stages. Stage-1: the object detection algorithm Yolov4 and the feature optimization module IFF are used to locate the target meter. Stage-2: Semantic segmentation model is applied to extract the pointer area based on Anam-Net. Stage-3: the character detection algorithm CRAFT and the text recognition algorithm E2E-MLT are combined and used to recognize the scale text and unit on the meter. Stage-4: the scale area of the meter is converted to the polar coordinate system, and a lightweight convolutional neural network is designed to locate the main scale line. And finally in Stage-5: the reading data are calculated according to the outputs of the above-mentioned deep learning models. The experiment results show that the reading method proposed in this paper has higher accuracy and robustness than those of the existing approaches and obtains satisfactory application effects in the industrial field. [ABSTRACT FROM AUTHOR]

Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters ( ∼ 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis. [ABSTRACT FROM AUTHOR]

Over the past years, a digital multimedia uprising has been experienced in every walk of life, due to which the un-annotated or unstructured multimedia content has always been a key issue for research. The multimedia content is usually created with some intended emotions, which the creator wants to induce in viewers. The affectiveness of the multimedia content can be measured by analyzing elicited emotions of its viewers. In this paper, we present a rigorous study of human cognition using EEG signals while watching a video, to analyze the affectiveness of video content. The analysis presented in this paper is done to establish an effective relationship between video content and the human emotional state. For this, the most effective scalp location and frequency ranges are identified for two categories of videos, i.e., excited and sad. Furthermore, a common affective response (CAR) is extracted for finding the distinguishable features for aforementioned categories of videos. The CAR is calculated and tested on the publicly available dataset "AMIGOS," and the results presented here show the utility of cognitive features on extracted scalp locations and frequency ranges for automatic tagging of video content. The current research explores the innovative applicability of neuro-signals for a mouse-free video tagging based on human excitement level to augment a range of brain–computer interface (BCI)-based devices. It can further aid to automatically retrieve the video content which is exciting and interesting to human viewers. With this analysis, we aimed to provide a thorough analysis which can be used to customize a low-cost and mobile EEG system for automatic analysis and retrieval of videos. [ABSTRACT FROM AUTHOR]

This paper focuses on improving the autonomy and efficiency of fuel-optimal powered landing guidance for reusable rockets considering aerodynamic forces. Deep-learning-based methods are developed to enable online and autonomous operation ability and to avoid the convergence problem encountered by classic indirect and direct optimal control methods. Considering the complex uncertainties of the preceding entry flight and potential unsettling hand-over conditions, a classification network is designed to classify the initial states of landing flights into different categories that correspond to bang–bang or non-bang–bang/singular thrust profiles. Thus, the subsequent online regression network can perform well for a large initial state distribution, and the algorithm adjusts to extensive landing situations. The combined application of classification and regression networks is one of the main contributions of the paper. The offline trained state-action regression networks generate guidance commands according to the real-time rocket state, obtaining a near-optimal landing trajectory. In addition, an online parallel trajectory simulation strategy is proposed to verify the trajectory quality, and an alternative trajectory optimization procedure is embedded into the proposed network-based framework to enhance the safety and accuracy of the guidance algorithm, representing another major contribution. Numerical experiments are presented to evaluate the effectiveness and accuracy of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Energy efficiency is a critical issue in the management and operation of cloud data centers, which form the backbone of cloud computing. Virtual machine (VM) placement has a significant impact on energy-efficiency improvement for virtualized data centers. Among various methods to solve the VM-placement problem, the genetic algorithm (GA) has been well accepted for the quality of its solution. However, GA is also computationally demanding, particularly in the computation of its fitness function. This limits its application in large-scale systems or specific scenarios where a fast VM-placement solution of good quality is required. Our analysis in this paper reveals that the execution time of the standard GA is mostly consumed in the computation of its fitness function. Therefore, this paper designs a data structure extended from a previous study to reduce the complexity of the fitness computation from quadratic to linear one with respect to the input size of the VM-placement problem. Incorporating with this data structure, an alternative fitness function is proposed to reduce the number of instructions significantly, further improving the execution-time performance of GA. Experimental studies show that our approach achieves 11 times acceleration of GA computation for energy-efficient VM placement in large-scale data centers with about 1500 physical machines in size. [ABSTRACT FROM AUTHOR]

With the origin of smart homes, smart cities, and smart everything, smart phones came up as an area of magnificent growth and development. These devices became a part of daily activities of human life. This impact and growth have made these devices more vulnerable to attacks than other devices such as desktops or laptops. Text messages or SMS (Short Text Messages) are a part of smartphones through which attackers target the users. Smishing (SMS Phishing) is an attack targeting smartphone users through the medium of text messages. Though smishing is a type of phishing, it is different from phishing in many aspects like the amount of information available in the SMS, the strategy of attack, etc. Thus, detection of smishing is a challenge in the context of the minimum amount of information shared by the attacker. In the case of smishing, we have short text messages which are often in short forms or in symbolic forms. A single text message contains very few smishing-related features, and it consists of abbreviations and idioms which makes smishing detection more difficult. Detection of smishing is a challenge not only because of features constraint but also due to the scarcity of real smishing datasets. To differentiate spam messages from smishing messages, we are evaluating the legitimacy of the URL (Uniform Resource Locator) in the message. We have extracted the five most efficient features from the text messages to enable the machine learning classification using a limited number of features. In this paper, we have presented a smishing detection model comprising of two phases, Domain Checking Phase and SMS Classification Phase. We have examined the authenticity of the URL in the SMS which is a crucial part of SMS phishing detection. In our system, Domain Checking Phase scrutinizes the authenticity of the URL. SMS Classification Phase examines the text contents of the messages and extracts some efficient features. Finally, the system classifies the messages using Backpropagation Algorithm and compares results with three traditional classifiers. A prototype of the system has been developed and evaluated using SMS datasets. The results of the evaluation achieved an accuracy of 97.93% which shows the proposed method is very efficient for the detection of smishing messages. [ABSTRACT FROM AUTHOR]

In order to improve the effect of college student performance prediction, based on machine learning and neural network algorithms, this paper improves the traditional data processing algorithms and proposes a similarity calculation method for courses. Moreover, this paper uses cosine similarity to calculate the similarity of courses. Simultaneously, this paper proposes an improved hybrid multi-weight improvement algorithm to improve the cold start problem that cannot be solved by traditional algorithms. In addition, this paper combines the neural network structure to construct a model framework structure, sets the functional modules according to actual needs, and analyzes and predicts students' personal performance through student portraits. Finally, this paper designs experiments to analyze the effectiveness of the model proposed in this paper. From the experimental data, it can be seen that the model proposed in this paper basically meets the expected requirements. [ABSTRACT FROM AUTHOR]

In order to improve the diagnosis and classification effect of pituitary tumors, this paper combines the current common machine learning methods and classification prediction methods to improve the traditional machine learning algorithms. Moreover, this paper analyzes the feature algorithm based on the feature extraction requirements of pituitary tumor pictures and compares a variety of commonly used algorithms to select a classification algorithm suitable for the model of this paper through comparison methods. In addition, this paper carries out the calculation of the prediction algorithm and verifies the algorithm according to the actual situation. Finally, based on the neural network algorithm, this paper designs and constructs the algorithm function module and combines the actual needs of pituitary tumors to build the model and verify the performance of the model. The research results show that the model system constructed in this paper meets the expected demand. [ABSTRACT FROM AUTHOR]

Providing connectivity to high-density traffic demand is one of the key promises of future wireless networks. The open radio access network (O-RAN) is one of the critical drivers ensuring such connectivity in heterogeneous networks. Despite intense interest from researchers in this domain, key challenges remain to ensure efficient network resource allocation and utilization. This paper proposes a dynamic traffic forecasting scheme to predict future traffic demand in federated O-RAN. Utilizing information on user demand and network capacity, we propose a fully reconfigurable admission control framework via fuzzy-logic optimization. We also perform detailed analysis on several parameters (user satisfaction level, utilization gain, and fairness) over benchmarks from various papers. The results show that the proposed forecasting and fuzzy-logic-based admission control framework significantly enhances fairness and provides guaranteed quality of experience without sacrificing resource utilization. Moreover, we have proven that the proposed framework can accommodate a large number of devices connected simultaneously in the federated O-RAN. [ABSTRACT FROM AUTHOR]