Search

Over the past four decades, the prophecy from computer pundits and prognosticators pointed to the looming arrival of the paperless office era. However, forty years later, physical paper documents are still playing a significant role due to the ease of use, superior readability, and availability. The drawbacks of paper sheets are that they are hard to modify and retrieve, have limited space, and are environmentally unfriendly. Augmenting paper documents with digital information from mobile devices extends the two-dimensional space of physical paper documents. Various camera-based recognition and detection devices have been proposed to augment paper documents with digital information. However, there are still some limitations that exist in these systems. This paper presents a novel, low cost, spatially aware, mobile system called Ultrasonic PhoneLens. The Ultrasonic PhoneLens adopts two-dimensional dynamic image presentation and ultrasonic sound positioning techniques. It consists of two ultrasonic sound sensors, one Arduino mini-controller board, and one android mobile device. Based on the location of the mobile device over the physical paper, Ultrasonic PhoneLens can retrieve pre-saved digital information from a mobile database for the object (such as a text, a paragraph, or an image) in a paper document. An empirical study was conducted to evaluate the system performance. The results indicate that our system has a better performance in tasks such as browsing multivalent documents and sharing digital information than the Wiimote PhoneLens system.

Class imbalance, as a phenomenon of asymmetry, has an adverse effect on the performance of most machine learning and overlap is another important factor that affects the classification performance of machine learning algorithms. This paper deals with the two factors simultaneously, addressing the class overlap under imbalanced distribution. In this paper, a theoretical analysis is firstly conducted on the existing class overlap metrics. Then, an improved method and the corresponding metrics to evaluate the class overlap under imbalance distributions are proposed based on the theoretical analysis. A well-known collection of the imbalanced datasets is used to compare the performance of different metrics and the performance is evaluated based on the Pearson correlation coefficient and the ξ correlation coefficient. The experimental results demonstrate that the proposed class overlap metrics outperform other compared metrics for the imbalanced datasets and the Pearson correlation coefficient with the AUC metric of eight algorithms can be improved by 34.7488% in average.

To beat competition and obtain valuable information, decision-makers must conduct in-depth machine learning or data mining for data analytics. Traditionally, clustering and classification are two common methods used in machine mining. For clustering, data are divided into various groups according to the similarity or common features. On the other hand, classification refers to building a model by given training data, where the target class or label is predicted for the test data. In recent years, many researchers focus on the hybrid of clustering and classification. These techniques have admirable achievements, but there is still room to ameliorate performances, such as distributed process. Therefore, we propose clustering and classification based on distributed automatic feature engineering (AFE) for customer segmentation in this paper. In the proposed algorithm, AFE uses artificial bee colony (ABC) to select valuable features of input data, and then RFM provides the basic data analytics. In AFE, it first initializes the number of cluster k. Moreover, the clustering methods of k-means, Wald method, and fuzzy c-means (FCM) are processed to cluster the examples in variant groups. Finally, the classification method of an improved fuzzy decision tree classifies the target data and generates decision rules for explaining the detail situations. AFE also determines the value of the split number in the improved fuzzy decision tree to increase classification accuracy. The proposed clustering and classification based on automatic feature engineering is distributed, performed in Apache Spark platform. The topic of this paper is about solving the problem of clustering and classification for machine learning. From the results, the corresponding classification accuracy outperforms other approaches. Moreover, we also provide useful strategies and decision rules from data analytics for decision-makers.

This paper presents a novel approach for an Intrusion Detection System (IDS) based on one kind of asymmetric optimization which use any three already well-known IDS algorithms and Triple Modular Redundancy (TMR) algorithm together. Namely, a variable threshold which indicates an attack on an observed and protected network is determined by using all three values obtained with three known IDS algorithms i.e., on previously recorded data by making a decision by majority. For these algorithms authors used algorithm of k-nearest neighbors, cumulative sum algorithm, and algorithm of exponentially weighted moving average. Using a proposed method we can get a threshold that is more precisely determined than in the case of any method individual. Practically, using TMR we obtain a dynamically threshold adjustment of IDS software, which reduces the existence of false alarms and undetected attacks, so the efficiency of such IDS software is notably higher and can get better results. Today, Denial of Service attacks (DoS) are one of the most present type of attacks and the reason for the special attention paid to them in this paper. In addition, the authors of the proposed method for IDS software used a known CIC-DDoS2019 dataset, which contains various data recordings of such attacks. Obtained results with the proposed solution showed better characteristics than each individual used algorithm in this solution. IDS software with the proposed method worked precisely and timely, which means alarms were triggered properly and efficiently.

This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrusion detection, they exhibit inferior performance towards adversarial examples. Noise introduction, to some degree, to the original data could lead adversarial examples to be misclassified by deep neural networks, even though they can still be deemed as normal by humans. In this paper, a robust diversity adversarial training method against adversarial attacks was demonstrated. In this approach, the target model is more robust to unknown adversarial examples, as it trains various adversarial samples. During the experiment, Tensorflow was employed as our deep learning framework, while MNIST and Fashion-MNIST were used as experimental datasets. Results revealed that the diversity training method has lowered the attack success rate by an average of 27.2 and 24.3% for various adversarial examples, while maintaining the 98.7 and 91.5% accuracy rates regarding the original data of MNIST and Fashion-MNIST.

Autonomous (unmanned) combat systems will become an integral part of modern defense systems. However, limited operational capabilities, the need for coordination, and dynamic battlefield environments with the requirement of timeless in decision-making are peculiar difficulties to be solved in order to realize intelligent systems control. In this paper, we explore the application of Learning Classifier System and Artificial Immune models for coordinated self-learning air defense systems. In particular, this paper presents a scheme that implements an autonomous cooperative threat evaluation and weapon assignment learning approach. Taking into account uncertainties in a successful interception, target characteristics, weapon type and characteristics, closed-loop coordinated behaviors, we adopt a hierarchical multi-agent approach to coordinate multiple combat platforms to achieve optimal performance. Based on the combined strengths of learning classifier system and artificial immune-based algorithms, the proposed scheme consists of two categories of agents; a strategy generation agent inspired by learning classifier system, and strategy coordination inspired by Artificial Immune System mechanisms. An experiment in a realistic environment shows that the adopted hybrid approach can be used to learn weapon-target assignment for multiple unmanned combat systems to successfully defend against coordinated attacks. The presented results show the potential for hybrid approaches for an intelligent system enabling adaptable and collaborative systems.

Artificial Neural Networks (ANNs) were created inspired by the neural networks in the human brain and have been widely applied in speech processing. The application areas of ANN include: Speech recognition, speech emotion recognition, language identification, speech enhancement, and speech separation, amongst others. Likewise, given that speech processing performed by humans involves complex cognitive processes known as auditory attention, there has been a growing amount of papers proposing ANNs supported by deep learning algorithms in conjunction with some mechanism to achieve symmetry with the human attention process. However, while these ANN approaches include attention, there is no categorization of attention integrated into the deep learning algorithms and their relation with human auditory attention. Therefore, we consider it necessary to have a review of the different ANN approaches inspired in attention to show both academic and industry experts the available models for a wide variety of applications. Based on the PRISMA methodology, we present a systematic review of the literature published since 2000, in which deep learning algorithms are applied to diverse problems related to speech processing. In this paper 133 research works are selected and the following aspects are described: (i) Most relevant features, (ii) ways in which attention has been implemented, (iii) their hypothetical relationship with human attention, and (iv) the evaluation metrics used. Additionally, the four publications most related with human attention were analyzed and their strengths and weaknesses were determined.

Mass media not only reflect the activities of state bodies but also shape the informational context, sentiment, depth, and significance level attributed to certain state initiatives and social events. Multilateral and quantitative (to the practicable extent) assessment of media activity is important for understanding their objectivity, role, focus, and, ultimately, the quality of the society’s “fourth power”. The paper proposes a method for evaluating the media in several modalities (topics, evaluation criteria/properties, classes), combining topic modeling of the text corpora and multiple-criteria decision making. The evaluation is based on an analysis of the corpora as follows: the conditional probability distribution of media by topics, properties, and classes is calculated after the formation of the topic model of the corpora. Several approaches are used to obtain weights that describe how each topic relates to each evaluation criterion/property and to each class described in the paper, including manual high-level labeling, a multi-corpora approach, and an automatic approach. The proposed multi-corpora approach suggests assessment of corpora topical asymmetry to obtain the weights describing each topic’s relationship to a certain criterion/property. These weights, combined with the topic model, can be applied to evaluate each document in the corpora according to each of the considered criteria and classes. The proposed method was applied to a corpus of 804,829 news publications from 40 Kazakhstani sources published from 01 January 2018 to 31 December 2019, to classify negative information on socially significant topics. A BigARTM model was derived (200 topics) and the proposed model was applied, including to fill a table of the analytical hierarchical process (AHP) and all of the necessary high-level labeling procedures. Experiments confirm the general possibility of evaluating the media using the topic model of the text corpora, because an area under receiver operating characteristics curve (ROC AUC) score of 0.81 was achieved in the classification task, which is comparable with results obtained for the same task by applying the BERT (Bidirectional Encoder Representations from Transformers) model.

This paper mainly formulates the problem of predicting context-aware smartphone apps usage based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the user-centric context and device-centric context. In the area of artificial intelligence and machine learning, decision tree model is one of the most popular approaches for predicting context-aware smartphone usage. However, real-life smartphone apps usage data may contain higher dimensions of contexts, which may cause several issues such as increases model complexity, may arise over-fitting problem, and consequently decreases the prediction accuracy of the context-aware model. In order to address these issues, in this paper, we present an effective principal component analysis (PCA) based context-aware smartphone apps prediction model, &ldquo, ContextPCA&rdquo, using decision tree machine learning classification technique. PCA is an unsupervised machine learning technique that can be used to separate symmetric and asymmetric components, and has been adopted in our &ldquo, model, in order to reduce the context dimensions of the original data set. The experimental results on smartphone apps usage datasets show that &ldquo, model effectively predicts context-aware smartphone apps in terms of precision, recall, f-score and ROC values in various test cases.

Low-rank tensor factorization can not only mine the implicit relationships between data but also fill in the missing data when working with complex data. Compared with the traditional collaborative filtering (CF) algorithm, the changes are essentially proposed, from traditional matrix analysis to three-dimensional spatial analysis. Based on low-rank tensor factorization, this paper proposes a recommendation model that comprehensively considers local information and global information, in other words, combining the similarity between trust users and low-rank tensor factorization. First, the similarity between trusted users is measured to capture local information between users by trusting similar preferences of users when selecting items. Then, the users&rsquo, similarity is integrated into the tensor, and the low-rank tensor factorization is used to better maintain and describe the internal structure of the data to obtain global information. Furthermore, based on the idea of the alternating least squares method, the conjugate gradient (CG) optimization algorithm for the model of this paper is designed. The local and global information is used to generate the optimal expected result in an iterative process. Finally, we conducted a large number of comparative experiments on the Ciao dataset and the FilmTrust dataset. Experimental results show that the algorithm has less precision loss under the data set with lower density. Thus, not only can a perfect compromise between accuracy and coverage be achieved, but also the computational complexity can be reduced to meet the need for real-time results.

With the development of multimedia technology, the secure image retrieval scheme has become a hot research topic. However, how to further improve algorithm performance in the ciphertext needs to be further explored. In this paper, we propose a secure image retrieval scheme based on a deep hash algorithm for index encryption and an improved 4-Dimensional(4-D)hyperchaotic system. The main contributions of this paper are as follows: (1) A novel secure retrieval scheme is proposed to control data transmission. (2) An improved 4-D hyperchaotic system is proposed to preserve privacy. (3) We propose an improved deep pairwise-supervised hashing (DPSH) algorithm and secure kNN to perform index encryption and propose an improved loss function to train the network model. (4) A secure access control scheme is shown, which aims to achieve secure access for users. The experimental results show that the proposed scheme has better retrieval efficiency and better security.

Service fulfillment for clients increasingly involves cooperation between information technology (IT) systems. Designing such solutions requires an architectural approach that ensures symmetry between the communicating parties. For the design of such systems, the author introduces the 1+5 architectural views model. The model contains three new architectural views. For business process modeling, it ensures the integrated processes view. Integration aspects cover two additional views: integrated services, and contracts. Moreover, new stereotypes and tagged values have been added to the unified modeling language (UML). The author has introduced two profiles: UML profile for integration flows, and UML profile for distributed ledger deployment. Communication between systems requires flows that arrange mediation mechanisms. The paper describes an integration flow diagram that extends a UML activity diagram. In the case of blockchain, the author has proposed the smart contract design pattern. The paper describes three case studies that have employed the model to design various solutions. The 1+5 model has proven to be well suited for designing both centralized integration environments with enterprise service bus (ESB) and distributed blockchain solutions with peer-to-peer (P2P) connections.

Text, voice, images and videos can express some intentions and facts in daily life. By understanding these contents, people can identify and analyze some behaviors. This paper focuses on the commodity trade declaration process and identifies the commodity categories based on text information on customs declarations. Although the technology of text recognition is mature in many application fields, there are few studies on the classification and recognition of customs declaration goods. In this paper, we proposed a classification framework based on machine learning (ML) models for commodity trade declaration that reaches a high rate of accuracy. This paper also proposed a symmetrical decision fusion method for this task based on convolutional neural network (CNN) and transformer. The experimental results show that the fusion model can make up for the shortcomings of the two original models and some improvements have been made. In the two datasets used in this paper, the accuracy can reach 88% and 99%, respectively. To promote the development of study of customs declaration business and Chinese text recognition, we also exposed the proprietary datasets used in this study.

This paper proposes a critical analysis of the literature addressed to modelling and simulations of human crowds with the aim of selecting the most appropriate scale out of the microscopic (individual based), mesoscopic (kinetic), and macroscopic (hydrodynamical) approaches. The selection is made focusing on possible applications of the model. In particular, model validation and safety problems, where validation consists of studying the ability of models to depict empirical data and observed emerging behaviors. The contents of the paper look forward to computational applications related to the flow crowds on the Jamarat bridge.

A major development in the field of access control is the dominant role-based access control (RBAC) scheme. The fascination of RBAC lies in its enhanced security along with the concept of roles. In addition, attribute-based access control (ABAC) is added to the access control models, which is famous for its dynamic behavior. Separation of duty (SOD) is used for enforcing least privilege concept in RBAC and ABAC. Moreover, SOD is a powerful tool that is used to protect an organization from internal security attacks and threats. Different problems have been found in the implementation of SOD at the role level. This paper discusses that the implementation of SOD on the level of roles is not a good option. Therefore, this paper proposes a hybrid access control model to implement SOD on the basis of permissions. The first part of the proposed model is based on the addition of attributes with dynamic characteristics in the RBAC model, whereas the second part of the model implements the permission-based SOD in dynamic RBAC model. Moreover, in comparison with previous models, performance and feature analysis are performed to show the strength of dynamic RBAC model. This model improves the performance of the RBAC model in terms of time, dynamicity, and automatic permissions and roles assignment. At the same time, this model also reduces the administrator&rsquo, s load and provides a flexible, dynamic, and secure access control model.

Using expert samples to improve the performance of reinforcement learning (RL) algorithms has become one of the focuses of research nowadays. However, in different application scenarios, it is hard to guarantee both the quantity and quality of expert samples, which prohibits the practical application and performance of such algorithms. In this paper, a novel RL decision optimization method is proposed. The proposed method is capable of reducing the dependence on expert samples via incorporating the decision-making evaluation mechanism. By introducing supervised learning (SL), our method optimizes the decision making of the RL algorithm by using demonstrations or expert samples. Experiments are conducted in Pendulum and Puckworld scenarios to test the proposed method, and we use representative algorithms such as deep Q-network (DQN) and Double DQN (DDQN) as benchmarks. The results demonstrate that the method adopted in this paper can effectively improve the decision-making performance of agents even when the expert samples are not available.

Business information required for applications and business processes is extracted using systems like business rule engines. Since the advent of Big Data, such rule engines are producing rules in a big quantity whereas more rules lead to more complexity in semantic analysis and understanding. This paper introduces a method to handle semantic complexity in rules and support automated generation of Resource Description Framework (RDF) metadata model of rules and such model is used to assist in querying and analysing Big Data. Practically, the dynamic changes in rules can be a source of conflict in rules stored in a repository. It is identified during the literature review that there is a need of a method that can semantically analyse rules and help business analysts in testing and validating the rules once a change is made in a rule. This paper presents a robust method that not only supports semantic analysis of rules but also generates RDF metadata model of rules and provide support of querying for the sake of semantic interpretation of the rules. The results of the experiments manifest that consistency checking of a set of big data rules is possible through automated tools.

Evaluating the reputation of higher institutions is important as a benchmark for the continuous development of universities. In multi-criteria decision-making (MCDM), the estimation of the criteria weight is significant in improving the accuracy of the evaluation results. However, criteria weights assigned by decision makers (DMs) can be inaccurate when not measured from the orientations from which the DMs pursue their decision goals. This paper combines the grey system theory (GST) and regulatory focus theory (RFT) in estimating the weights of criteria by measuring the promotional and prevention focus orientations of the DMs and representing it as grey numbers. In this paper, we showed not all weight measurements from the DMs are symmetrical. In essence, to improve the accuracy of the MCDM weights, the grey regulatory focus theory (GRFT) weighting method is proposed to estimate the weights of an MCDM problem as well as aggregating the weights of the group DMs, thereby overcoming the limitation of a single orientation measurement. Furthermore, the GRFT weighting method is applied in ranking four universities in Xi’an city of China from a sample data from 1,200 students. The most reputable university is consistent with the other ranking indexes in the literature.

Digital signature with proxy delegation, which is a secure ownership enforcement tool, allows an original signer to delegate signature rights to a third party called proxy, so that the proxy can sign messages on behalf of the original signer. Many real-world applications make use of this secure mechanism, e.g., digital property transfer. A traditional digital signature mechanism is required to bind a message and its signature together for verification. This may yield extra cost in bandwidth while the sizes of message and signature are relatively huge. Message recovery signature, enabling to reduce the cost of bandwidth, embeds a message into the corresponding signature; therefore, only the signature will be transmitted to the verifier and the message can further be recovered from the signature. In this paper, we, for the first time, propose a novel digital signature scheme in the identity-based context with proxy delegation and message recovery features and, more importantly, our scheme is quantum resistant, in a particular lattice-based signature. Our scheme achieves delegation information and signature existential unforgeability against adaptive chosen warrant and identity. Compared with the seminal lattice-based message recovery signature, our scheme is independent from public key infrastructure, realizes delegation transfer of signature rights, and compresses signature length ulteriorly. To the best of our knowledge, this paper is the first of its type.

Typical fire monitoring and warning systems use a single smoke detector that is connected to a fire management system to give early warnings before the fire spreads out up to a damaging level. However, it is found that only smoke detector-based fire monitoring systems are not efficient and intelligent since they generate false warnings in case of a person is smoking, etc. There is need of a multi-sensor based intelligent and smart fire monitoring system that employs various parameters, such as presence of flame, temperature of the room, smoke, etc. To achieve such a smart solution, a multi-sensor solution is required that can intelligently use the data of sensors and generate true warnings for further fire control and management. This paper presents an intelligent Fire Monitoring and Warning System (FMWS) that is based on Fuzzy Logic to identify the true existence of dangerous fire and send alert to Fire Management System (FMS). This paper discusses design and application of a Fuzzy Logic Fire Monitoring and Warning System that also sends an alert message using Global System for Mobile Communication (GSM) technology. The system is based on tiny, low cost, and very small in size sensors to ensure that the solution is reproduceable. Simulation work is done in MATLAB ver. 7.1 (The MathWorks, Natick, MA, USA) and the results of the experiments are satisfactory.

The modeling of free-form engineering complex curves is an important subject in product modeling, graphics, and computer aided design/computer aided manufacturing (CAD/CAM). In this paper, we propose a novel method to construct free-form complex curves using shape-adjustable generalized B&eacute, zier (or SG-B&eacute, zier, for short) curves with constraints of geometric continuities. In order to overcome the difficulty that most of the composite curves in engineering cannot often be constructed by using only a single curve, we propose the necessary and sufficient conditions for G1 and G2 continuity between two adjacent SG-B&eacute, zier curves. Furthermore, the detailed steps of smooth continuity for two SG-B&eacute, zier curves, and the influence rules of shape parameters on the composite curves, are studied. We also give some important applications of SG-B&eacute, zier curves. The modeling examples show that our methods in this paper are very effective, can easily be performed, and can provide an alternative powerful strategy for the design of complex curves.

Clustering is more popular than the expert knowledge approach in Interval Fuzzy Type-2 membership function construction because it can construct membership function automatically with less time consumption. Most research proposed a two-fuzzifier fuzzy C-Means clustering method to construct Interval Fuzzy Type-2 membership function which mainly focused on producing Gaussian membership function. The other two important membership functions, triangular and trapezoidal, are constructed using the grid partitioning method. However, the method suffers a drawback of not being able to represent actual data composition in the underlying dataset. Some research proposed triangular and trapezoidal membership functions construction using readily formed Fuzzy Type-1 membership functions, which means it remains unclear how the membership functions are heuristically constructed using fuzzy C-Means outputs. The triangular and trapezoidal membership functions are important because previous works have shown that they may produce superior performance than Gaussian membership function in some applications. Therefore, this paper presents a structured literature review on generating triangular and trapezoidal Interval Fuzzy Type-2 membership functions using fuzzy C-Means. Initially, 110 related manuscripts were collected from Web of Science, Scopus, and Google Scholar. These manuscripts went through the identification, screening, eligibility, and inclusion processes, and as a result, 21 manuscripts were reviewed and discussed in this paper. To ensure that the review also covers the important components of fuzzy logic, this paper also reviews and discusses another 49 manuscripts on fuzzy calculation and operation. Furthermore, this paper also discusses the contributions of the conducted review to the body of knowledge, future research directions and challenges, with the aim to motivate the future works of constructing the methods to generate Interval Fuzzy Type-2 triangular and trapezoidal membership functions using fuzzy C-Means. The methods imply flexibility in choosing membership function type, hence increasing the effectiveness of fuzzy applications through leveraging the advantages that each of the three membership function types could provide.

The complexity of a mathematical expression is a measure that can be used to compare the expression with other mathematical expressions and judge which one is simpler. In the paper, we analyze three effect factors for the complexity of a mathematical expression: representational length, computational time, and intelligibility. Mainly, the paper introduces a binary-lambda-calculus based calculation method for representational complexity and a rule based calculation method for algebraic computation complexity. In the process of calculating the representation complexity of mathematical expressions, we transform the de bruijn notation into the binary lambda calculus of mathematical expressions that is inspired by compressing symmetry strings in Kolmogorov complexity theorem. Furthermore, the application of complexity of mathematical expressions in MACP, a mathematics answer checking protocol, is also addressed. MACP can be used in a computer aided assessment system in order to compute correct answers, verify equivalence of expressions, check user answers whether in a simplification form, and give automatic partial grades.

This paper analyzed the locomotion of a snake robot in narrow spaces such as a pipe or channel. We developed a unique experimental snake robot with one revolute and one linear joint on each module, with the ability to perform planar motion. The designed locomotion pattern was simulated in MATLAB R2015b and subsequently verified by the experimental snake robot. The locomotion of the developed snake robot was also experimentally analyzed on dry and viscous surfaces. The paper further describes the investigation of locomotion stability by three symmetrical curves used to anchor static modules between the walls of the pipe. The stability was experimentally analyzed by digital image correlation using a Q-450 Dantec Dynamics high-speed correlation system. The paper presents some input symmetrical elements of locomotion and describes their influence on the results of locomotion. The results of simulations and experiments show possibilities of snake robot locomotion in a pipe. Web of Science 12 6 art. no. 939

In modern recommender systems, matrix factorization has been widely used to decompose the user&ndash, item matrix into user and item latent factors. However, the inner product in matrix factorization does not satisfy the triangle inequality, and the problem of sparse data is also encountered. In this paper, we propose a novel recommendation model, namely, metric factorization with item cooccurrence for recommendation (MFIC), which uses the Euclidean distance to jointly decompose the user&ndash, item interaction matrix and the item&ndash, item cooccurrence with shared latent factors. The item cooccurrence matrix is obtained from the colike matrix through the calculation of pointwise mutual information. The main contributions of this paper are as follows: (1) The MFIC model is not only suitable for rating prediction and item ranking, but can also well overcome the problem of sparse data. (2) This model incorporates the item cooccurrence matrix into metric learning so it can better learn the spatial positions of users and items. (3) Extensive experiments on a number of real-world datasets show that the proposed method substantially outperforms the compared algorithm in both rating prediction and item ranking.

The intelligent satellite, iSAT, is a concept based on software-defined satellites. Earth observation is one of the important applications of intelligent satellites. With the increasing demand for rapid satellite response and observation tasks, intelligent satellite in-orbit task planning has become an inevitable trend. In this paper, a mixed integer programming model for observation tasks is established, and a heuristic search algorithm based on a symmetric recurrent neural network is proposed. The configurable probability of the observation task is obtained by constructing a structural symmetric recurrent neural network, and finally, the optimal task planning scheme is obtained. The experimental results are compared with several typical heuristic search algorithms, which have certain advantages, and the validity of the paper is verified. Finally, future application prospects of the method are discussed.

The issues of identity authentication and privacy protection of individuals in body area network (BAN) systems have raised much concern in past few years. To address the challenges of privacy protection in wireless BAN, an image encryption algorithm has been proposed recently by Wang et al. The encryption algorithm utilized two 1D chaotic maps to generate sub-chaotic matrices which are combined to perform encryption. The algorithm has good statistical encryption performance. However, a cautious inquiry finds that it has some underlying security defects. This paper evaluates the security of the Wang et al. encryption algorithm to show that it is totally breakable under proposed cryptanalysis and hence infeasible for privacy protection in BAN. It has been shown that the plain-image data can be recovered without any prior knowledge of secret key and plain-text. Furthermore, this paper also suggests an improved encryption scheme using secure hash algorithm SHA-512 for one-time keys and a 4D hyperchaotic system to subdue the security insufficiencies of the algorithm under study. The simulation results and analysis demonstrate that the improved image encryption scheme has excellent encryption quality, plain-image sensitivity, and resistance to possible cryptanalytic attacks.

An effective and reliable fusion method for conflicting information is proposed in this paper. Compared with a single-sensor system, a multi-sensor fusion system can comprehensively combine the redundancy and complementarity of multi-sensor information to obtain better system performance. Hence, the multi-sensor fusion system has become one of the research hotspots. However, due to lack knowledge about the measurement environment and limited sensor accuracy, the multi-sensor system inevitably appears to have imperfect, uncertain and inconsistent information. To solve the problem, we introduce one powerful uncertainty reasoning method: Dempster–Shafer theory (DS theory). With convincing measurement and a forceful combination of uncertain information, DS theory is widely applied in various fields, like decision-making, expert systems, target tracking, monitoring systems, etc. Nevertheless, DS theory will produce counter-intuitive fusion results when the pieces of evidence are highly conflicting. To address this issue, we raise an improved DS combination method for conflicting information fusion in this paper. First of all, the modified Minkowski distance function and the betting-commitment distance function are separately employed to revise potentially conflicting pieces of evidence. The procedure availably solves the conflicting situations caused by unreliable and imprecise evidence sources, which enhances the consistency among pieces of evidence. Then, based on two revised pieces of evidence, a conflicting redistribution strategy based on locally conflicting analyses is put forward. The approach dexterously combines two revised pieces of evidence to avoid conflicting situations caused by compulsive normalization, which further improves the accuracy and convergence speed of the multi-sensor fusion system. Finally, two experimental analyses with consistent information and conflicting information reveal the remarkable effectiveness and priority of the proposed algorithm for the multi-sensor fusion system. Consequently, this paper has certain value for the multi-sensor fusion system.

This study proposes a method of effectively creating mobile virtual reality scenes centered at events for the purpose of providing new experiences in virtual reality environment to users. For this purpose, this paper uses Prim’s maze generation algorithm to automatically create maze environments that have different patterns every time and to compute mazes with finite paths. This paper designs a scheme of creating virtual reality scenes based on event-centered mazes to maximize users’ tension and immersion. Here, event components that are appropriate for the maze environment are defined and maze patterns are created centered at the event point where events that are appropriate for the maze pattern are automatically created. Finally, the paper analyzes whether the proposed virtual reality scene based on event-centered mazes is helpful in enhancing users’ immersion and arousing their interest through diverse experiments.

The European standard on transport logistics and services in public passenger transport EN 13816 is based on a relationship between the perception of users and transport carriers throughout the groups of criteria taken as a basis for observation in this paper. The constant development and improvement of services in order to achieve sustainability of passenger transport is an imperative on the one hand and a challenge on the other. This is highly evident in persons with disabilities who are faced with many physical and social barriers related to access to rail transport. In this paper, a new model for the selection of criteria for the quality of passenger service in rail transport, from the perspective of persons with disabilities as the main category of passengers, has been created. The survey has covered 168 criteria classified in several groups and the entire territory of Serbia. In order to select the most important criteria, a new model that implies the integration of Full Consistency Method and a Rough Power Heronian aggregator has been developed. The development of a new aggregator enables more accurate decision-making in the process of group decision-making. The results obtained in this paper show that the most important criteria according to importance are Accessibility, Availability, Security, Time, Customer care, Information, Comfort, Environmental impact. Based on the criteria obtained for the service quality of rail transport for persons with disabilities, railway carriers will be able to change and improve the existing services, content, characteristics, equipment of railway stations and vehicles.

Three-dimensional (3D) origami, which can generate a structure through folding a crease pattern on a flat sheet of paper, has received considerable attention in art, mathematics, and engineering. With consideration of symmetry, the user can efficiently generate a rational crease pattern and make the fabricated shape stable. In this paper, we focus on a category of axisymmetric origami consisting of triangular facets and edit the origami in 3D space for expanding its variations. However, it is difficult to retain the developability, which requires the sum of the angles around each interior vertex needing to equal 360 degrees, for designing origami. Intersections occur between crease lines when such a value is larger than 360 degrees. On the other hand, blank spaces (unfolded areas) emerge in the crease pattern when the value is less than 360 degrees. The former case is difficult to generate a realizable shape due to the crease lines are intersected with each other. For the latter case, however, blank spaces can be filled with crease lines and become a part of the origami through tucking. Here, we propose a computational method to add flaps or tucks on the 3D shape, which contains non-developable interior vertices, for achieving the resulting origami. Finally, on the application side, we describe a load-bearing experiment on a stool shape-like origami to demonstrate the potential usage.

Mobile communication security techniques are employed to guard the communication between the network entities. Mobile communication cellular systems have become one of the most important communication systems in recent times and are used by millions of people around the world. Since the 1990s, considerable efforts have been taken to improve both the communication and security features of the mobile communications systems. However, these improvements divide the mobile communications field into different generations according to the communication and security techniques such as A3, A5 and A8 algorithms for 2G-GSM cellular system, 3G-authentication and key agreement (AKA), evolved packet system-authentication and key agreement (EPS-AKA), and long term evolution-authentication and key agreement (LTE-AKA) algorithms for 3rd generation partnership project (3GPP) systems. Furthermore, these generations have many vulnerabilities, and huge security work is involved to solve such problems. Some of them are in the field of the public key cryptography (PKC) which requires a high computational cost and more network flexibility to be achieved. As such, the public key infrastructure (PKI) is more compatible with the modern generations due to the superior communications features. This paper surveys the latest proposed works on the security of GSM, CDMA, and LTE cellular systems using PKI. Firstly, we present the security issues for each generation of mobile communication systems, then we study and analyze the latest proposed schemes and give some comparisons. Finally, we introduce some new directions for the future scope. This paper classifies the mobile communication security schemes according to the techniques used for each cellular system and covers some of the PKI-based security techniques such as authentication, key agreement, and privacy preserving.

Images crowdsourcing of mobile devices can be applied to many real-life application scenarios. However, this type of scenario application often faces issues such as the limitation of bandwidth, insufficient storage space, and the processing capability of CPU. These lead to only a few photos that can be crowdsourced. Therefore, it is a great challenge to use a limited number of resources to select photos and make it possible to cover the target area maximally. In this paper, the geographic and geometric information of the photo called data-unit is used to cover the target area as much as possible. Compared with traditional content-based image delivery methods, the network delay and computational costs can be greatly reduced. In the case of resource constraints, this paper uses the utility of photos to measure the coverage of the target area, and improves a photo utility calculation method based on data-unit. In the meantime, this paper proposes the minimum selection problem of images under the coverage requirements, and designs a selection algorithm based on greedy strategies. Compared with other traditional random selection algorithms, the results prove the effectiveness and superiority of the minimum selection algorithm.

This paper proposes an image authentication scheme for mobile devices. The proposed scheme generates an image watermark by using discrete cosine transform (DCT) and hides the watermark in the spatial pixels for image authentication and tamper detection. The hiding operator used in this paper is very simple in a mobile environment allowing high-speed authentication using a low-power mobile device. The quality of the stego-image and the recovered image becomes excellent as a result of the proposed scheme.

Future communication networks would be required to deliver data on a far greater scale than is known to us today, thus mandating the maximal utilization of the available radio spectrum using cognitive radios. In this paper, we have proposed a novel cooperative spectrum sensing approach for cognitive radios. In cooperative spectrum sensing, the fusion center relies on reports of the cognitive users to make a global decision. The global decision is obtained by assigning weights to the reports received from cognitive users. Computation of such weights requires prior information of the probability of detection and the probability of false alarms, which are not readily available in real scenarios. Further, the cognitive users are divided into reliable and unreliable categories based on their weighted energy by using some empirical threshold. In this paper, we propose a method to classify the cognitive users into reliable, neutral and unreliable categories without using any pre-defined or empirically-obtained threshold. Moreover, the computation of weights does not require the detection, or false alarm probabilities, or an estimate of these probabilities. Reliable cognitive users are assigned the highest weights, neutral cognitive users are assigned medium weights (less than the reliable and higher than the unreliable cognitive users’ weights), and unreliable users are assigned the least weights. We show the performance improvement of our proposed method through simulations by comparing it with the conventional cooperative spectrum sensing scheme through different metrics, like receiver operating characteristic (ROC) curve and mean square error. For clarity, we also show the effect of malicious users on detection probability and false alarm probability individually through simulations.

Speculative multithreading (SpMT) is a thread-level automatic parallelization technique that can accelerate sequential programs, especially for irregular applications that are hard to be parallelized by conventional approaches. Thread partition plays a critical role in SpMT. Conventional machine learning-based thread partition approaches applied machine learning to offline guide partition, but could not explicitly explore the law between partition and performance. In this paper, we build a parametric model (Qinling) with a multiple regression method to discover the inherent law between thread partition and performance. The paper firstly extracts unpredictable parameters that determine the performance of thread partition in SpMT; secondly, we build a parametric model Qinling with extracted parameters and speedups, and train Qinling offline, as well as apply it to predict the theoretical speedups of unseen applications. Finally, validation is done. Prophet, which consists of an automatic parallelization compiler and a multi-core simulator, is used to obtain real speedups of the input programs. Olden and SPEC2000 benchmarks are used to train and validate the parametric model. Experiments show that Qinling delivers a good performance to predict speedups of unseen programs, and provides feedback guidance for Prophet to obtain the optimal partition parameters.

Both distributed healthcare systems and the Internet of Things (IoT) are currently hot topics. The latter is a new computing paradigm to enable advanced capabilities in engineering various applications, including those for healthcare. For such systems, the core social requirement is the privacy/security of the patient information along with the technical requirements (e.g., energy consumption) and capabilities for adaptability and personalization. Typically, the functionality of the systems is predefined by the patient’s data collected using sensor networks along with medical instrumentation; then, the data is transferred through the Internet for treatment and decision-making. Therefore, systems creation is indeed challenging. In this paper, we propose a model-driven framework to develop the IoT-based prototype and its reference architecture for personalized health monitoring (PHM) applications. The framework contains a multi-layered structure with feature-based modeling and feature model transformations at the top and the application software generation at the bottom. We have validated the framework using available tools and developed an experimental PHM to test some aspects of the functionality of the reference architecture in real time. The main contribution of the paper is the development of the model-driven computational framework with emphasis on the synergistic effect of security and energy issues.

In this paper, we proposed not only an extraction methodology of multiple feature vectors from ultrasound images for carotid arteries (CAs) and heart rate variability (HRV) of electrocardiogram signal, but also a suitable and reliable prediction model useful in the diagnosis of cardiovascular disease (CVD). For inventing the multiple feature vectors, we extract a candidate feature vector through image processing and measurement of the thickness of carotid intima-media (IMT). As a complementary way, the linear and/or nonlinear feature vectors are also extracted from HRV, a main index for cardiac disorder. The significance of the multiple feature vectors is tested with several machine learning methods, namely Neural Networks, Support Vector Machine (SVM), Classification based on Multiple Association Rule (CMAR), Decision tree induction and Bayesian classifier. As a result, multiple feature vectors extracted from both CAs and HRV (CA+HRV) showed higher accuracy than the separative feature vectors of CAs and HRV. Furthermore, the SVM and CMAR showed about 89.51% and 89.46%, respectively, in terms of diagnosing accuracy rate after evaluating the diagnosis or prediction methods using the finally chosen multiple feature vectors. Therefore, the multiple feature vectors devised in this paper can be effective diagnostic indicators of CVD. In addition, the feature vector analysis and prediction techniques are expected to be helpful tools in the decisions of cardiologists.

Smart Home Architecture is suitable for progressive and symmetric urbanization. Data being generated in smart home appliances using internet of things should be stored in cloud where computing resources can analyze the data and generate the decisive pattern within no time. This additional requirement of storage, majorly, comprising of unfiltered data escalates requirement of host machines which carries with itself extra overhead of energy consumption; thus, extra cost has to be beard by service providers. Various static algorithms are already proposed to improve energy management of cloud data centers by reducing number of active bins. These algorithms are not able to cater to the needs of present heterogeneous requests generated in cloud machines by people of diversified work environment with adhering to the requirements of quality parameters. Therefore, the paper has proposed and implemented dynamic bin-packing approaches for smart architecture that can significantly reduce energy consumption without compromising upon makespan, resource utilization and Quality of Service (QoS) parameters. The novelty of the proposed dynamic approaches in comparison to the existing static approaches is that the proposed approach dynamically creates and dissolves virtual machines as per incoming and completed requests which is a dire need of present computing paradigms via attachment of time-frame with each virtual machine. The simulations have been performed on JAVA platform and dynamic energy utilized-best fit decreasing bin packing technique has produced better results in maximum runs.

Over the last two decades (2000–2020), the Internet has rapidly evolved, resulting in symmetrical and asymmetrical Internet consumption patterns and billions of users worldwide. With the immense rise of the Internet, attacks and malicious behaviors pose a huge threat to our computing environment. Brute-force attack is among the most prominent and commonly used attacks, achieved out using password-attack tools, a wordlist dictionary, and a usernames list—obtained through a so-called an enumeration attack. In this paper, we investigate username enumeration attack detection on SSH protocol by using machine-learning classifiers. We apply four asymmetrical classifiers on our generated dataset collected from a closed-environment network to build machine-learning-based models for attack detection. The use of several machine-learners offers a wider investigation spectrum of the classifiers’ ability in attack detection. Additionally, we investigate how beneficial it is to include or exclude network ports information as features-set in the process of learning. We evaluated and compared the performances of machine-learning models for both cases. The models used are k-nearest neighbor (K-NN), naïve Bayes (NB), random forest (RF) and decision tree (DT) with and without ports information. Our results show that machine-learning approaches to detect SSH username enumeration attacks were quite successful, with KNN having an accuracy of 99.93%, NB 95.70%, RF 99.92%, and DT 99.88%. Furthermore, the results improve when using ports information.

This paper presents a robust nonlinear control scheme with time-varying output constraint for the electro-hydraulic force control system (EHFCS). Two typical double-rod symmetrical hydraulic cylinders are employed to simulate force environments in the EHFCS. Therefore, in order to improve the performance of the EHFCS, firstly, the model of the EHFCS is established with taking external disturbances, parameter uncertainties as well as structural vibrations into consideration. Secondly, in order to estimate external disturbances, parameter uncertainties and structural vibrations in the EHFCS and compensate them in the following robust controller design, two disturbance observers (DOs) are designed according to the nonlinear system model. Thirdly, with two estimation values from two DOs, a time-varying constraint-based robust controller (TVCRC) is presented in detail. Moreover, the stability of the proposed controller is analyzed by defining a proper Lyapunov functions. Finally, in order to validate the performance of the proposed controller, a series of simulation studies are conducted using the MATLAB/Simulink software. These simulation results give a fine proof of the efficiency of the proposed controller. What’s more, an experimental setup of the EHFCS is established to further validate the performance. Comparative experimental results show that the proposed controller exhibits better performance than the TVCRC without two DOs and a conventional proportional integral (PI) controller.

The electricity distribution system is the coupling point between the utility and the end-user. Typically, these systems have unbalanced feeders due to the variety of customers’ behaviors. Some significant problems occur, the unbalanced loads increase the operational cost and system investment. In radial distribution systems, swapping loads between the three phases is the most effective method for phase balancing. It is performed manually and subjected to load flow equations, capacity, and voltage constraints. Recently, due to smart grids and automated networks, dynamic phase balancing received more attention, thus swapping the loads between the three phases automatically when unbalance exceeds permissible limits by using a remote-controlled phase switch selector/controller. Automatic feeder reconfiguration and phase balancing eliminates the service interruption, enhances energy restoration, and minimize losses. In this paper, a case study from the Irbid district electricity company (IDECO) is presented. Optimal reconfiguration of phase balancing using three techniques: feed-forward back-propagation neural network (FFBPNN), radial basis function neural network (RBFNN), and a hybrid are proposed to control the switching sequence for each connected load. The comparison shows that the hybrid technique yields the best performance. This work is simulated using MATLAB and C programming language.

In 2002, Agrawal and Kiernan defined six basic requirements, including preventing illegal watermark embedding and authentication, reversibility, robustness, and others, which must be satisfied when a reversible watermark is designed for relational databases. To meet these requirements, in this paper, a lossless watermarking scheme for a categorical relational database called LRW-CRDB (lossless robust watermarking for categorical relational databases) is proposed. In our LRW-CRDB scheme, the database owner needs to generate two secret embedding keys, K1 and K2, in advance. Then, two reference sets are generated based on two different secret embedding keys and a symmetry-based data hiding strategy, and then these are used for the watermark embedding phases. Experimental results confirmed that our LRW-CRDB scheme successfully detects 100% of hidden watermarks, even when more than 95% of the watermarked relational database has been deleted. In other words, the robustness of our proposed LRW-CRDB scheme outperforms other existing schemes under a variety of possible attacks, such as alteration, sorting, deletion, and mix-match attacks.

Expert systems, a form of artificial intelligence (AI), are typically designed to solve many real-world problems by reasoning through knowledge, which is primarily represented as IF–THEN rules, with the information acquired from humans or domain experts. However, to assume such rules for personalized decision-making in an intelligent, context-aware mobile application is a challenging issue. The reason is that different mobile users may behave differently in various day-to-day situations, i.e., not identical, and thus the rules for personalized services must be reflected according to their symmetrical or asymmetrical behavioral activities. Therefore, our key focus is to solve this issue through adding personalized decision-making intelligence to develop powerful mobile applications to assist the end-users. To achieve our goal, in this paper, we explore on “Mobile Expert System”, where we take into account machine-learning rules as knowledge-base rather than traditional handcrafted static rules. Thus, the concept of a mobile expert system enables the computing and decision-making processes more actionable and intelligent than traditional ones in the domain of mobile analytics and applications. Our experiment section shows that the context-aware machine learning rules discovered from users’ mobile phone data can contribute in building a mobile expert system to solve a particular problem, through making personalized decisions in various context-aware test cases.

Decision support systems (DSS) are currently developing rapidly and are increasingly used in various fields. More often, those systems are inseparable from information-based systems and computer systems. Therefore, from a methodical point of view, the algorithms implemented in the DSS play a critical role. In this aspect, multi-criteria decision support (MCDA) methods are widely used. As research progresses, many MCDA methods and algorithms for the objective identification of the significance of individual criteria of the MCDA models were developed. In this paper, an analysis of available objective methods for criteria weighting is presented. Additionally, the authors presented the implementation of the system that provides easy and accessible weight calculations for any decision matrix with the possibility of comparing results of different weighting methods. The results of weighting methods were compared using carefully selected similarity coefficients to emphasise the correlation of the resulting weights. The performed research shows that every method should provide distinctive weights considering input data, emphasising the importance of choosing the correct method for a given multi-criteria decision support model and DSS.

The energy manufacturers are required to produce an accurate amount of energy by meeting the energy requirements at the end-user side. Consequently, energy prediction becomes an essential role in the electric industrial zone. In this paper, we propose the hybrid ensemble deep learning model, which combines multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and hybrid CNN-LSTM to improve the forecasting performance. These DL architectures are more popular and better than other machine learning (ML) models for time series electrical load prediction. Therefore, hourly-based energy data are collected from Jeju Island, South Korea, and applied for forecasting. We considered external features associated with meteorological conditions affecting energy. Two-year training and one-year testing data are preprocessed and arranged to reform the times series, which are then trained in each DL model. The forecasting results of the proposed ensemble model are evaluated by using mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Error metrics are compared with DL stand-alone models such as MLP, CNN, LSTM, and CNN-LSTM. Our ensemble model provides better performance than other forecasting models, providing minimum MAPE at 0.75%, and was proven to be inherently symmetric for forecasting time-series energy and demand data, which is of utmost concern to the power system sector.

The information technique has developed rapidly. The technique of QR codes is widely applied in our daily life, and the mechanism is suitable to share data. A QR code uses symmetric encryption to store and retrieve data efficiently. However, the security issues of QR codes are seldom discussed by the wider community. Moreover, if the sender wishes only the authorized participant to attain the private data which are shared, the data must be encrypted. Furthermore, we do not know who should be censured when problems arise. In view of this, to maintain the integrity and the confidentiality of information security, this paper proposed a new puzzle-based data sharing scheme to share the private information safely. Firstly, we generated the digital signature of the information, then applied the random grids algorithm to obtain the shares. Then, we disarrayed the shares which contain the information and the digital signature with a puzzle-based encoding method. Afterwards, we concealed them into the cover QR codes. With the QR code mechanism of error correction, the marked QR code remain meaningful. Finally, we could send marked QR codes via transmission. The receiver could use XOR operation to obtain the private information after solving the puzzles and verify whether it was tampered with by the digital signature. The proposed system can recover the lossless data and protect them from being divulged. To deal with the potential hazard of transmission in a public environment, there are more and more studies on data hiding and image authentication.

Public Key Infrastructure (PKI) is the fundamental of secure digital communications. It provides a secure means to authenticate identities over the Internet. Symmetric or asymmetric encryption schemes are widely used in identity authentication in any kind of PKI. The conventional PKI has several drawbacks due to the centralized and non-transparent design. Several recent research works utilize blockchain technology to overcome the limitations of conventional implementations of PKI. Blockchain-based PKI integrates blockchain technology with PKI to form a new type of decentralized PKI (DPKI). Several works utilize the currency property in blockchains to implement the reward-and-punishment mechanism. In this paper, we propose a smart contract-based PKI which utilizes the Ethereum smart contract to build a new type of blockchain-based PKI with the reward-and-punishment mechanism using ERC-20 tokens. It has several advantages over previous implementations of similar research that use Ethereum’s main currency—Ether.

In this paper, we propose a novel method for plant leaves recognition by incorporating an unsupervised convolutional auto-encoder (CAE) and Siamese neural network in a unified framework by considering Siamese as an alternative to the conventional loss of CAE. Rather than the conventional exploitation of CAE and Siamese, in our case we have proposed to extend CAE for a novel supervised scenario by considering it as one-class learning classifier. For each class, CAE is trained to reconstruct its positive and negative examples and Siamese is trained to distinguish the similarity and the dissimilarity of the obtained examples. On the contrary and asymmetric to the related hierarchical classification schemes which require pre-knowledge on the dataset being recognized, we propose a hierarchical classification scheme that doesn’t require such a pre-knowledge and can be employed by non-experts automatically. We cluster the dataset to assemble similar classes together. A test image is first assigned to the nearest cluster, then matched to one class from the classes that fall under the determined cluster using our novel one-class learning classifier. The proposed method has been evaluated on the ImageCLEF2012 dataset. Experimental results have proved the superiority of our method compared to several state-of-the art methods.

Deep neural networks (DNNs) have become the de facto standard for image recognition tasks, and their applications with respect to plant diseases have also obtained remarkable results. However, the large number of parameters and high computational complexities of these network models make them difficult to deploy on farms in remote areas. In this paper, focusing on the problems of resource constraints and plant diseases, we propose a DNN-based compression method. In order to reduce computational burden, this method uses lightweight fully connected layers to accelerate reasoning, pruning to remove redundant parameters and reduce multiply–accumulate operations, knowledge distillation instead of retraining to restore the lost accuracy, and then quantization to compress the size of the model further. After compressing the mainstream VGGNet and AlexNet models, the compressed versions are applied to the Plant Village dataset of plant disease images, and a performance comparison of the models before and after compression is obtained to verify the proposed method. The results show that the model can be compressed to 0.04 Mb with an accuracy of 97.09%. This experiment also proves the effectiveness of knowledge distillation during the pruning process, and compressed models are more efficient than prevalent lightweight models.