Search

This paper focuses on both voltage transients and short-duration RMS variations, and presents a unique and heterogeneous approach to their assessment by applying AI tools. The database consists of both real (obtained from Lithuanian PQ monitoring campaigns) and synthetic data (obtained from the simulation and literature review). Firstly, this paper investigates the fundamental grid component and its harmonics filtering with an IIR shelving filter. Secondly, in a key part, both SVM and KNN are used to classify PQ events by their primary cause in the voltage–duration plane as well as by the type of short circuit in the three-dimensional voltage space. Thirdly, since it seemed to be difficult to interpret the results in the three-dimensional space, the new method, based on Clarke transformation, is developed to convert it to two-dimensional space. The method shows an outstanding performance by avoiding the loss of important information. In addition, a geometric analysis of the fault voltage in both two-dimensional and three-dimensional spaces revealed certain geometric patterns that are undoubtedly important for PQ classification. Finally, based on the results of a PQ monitoring campaign in the Lithuanian distribution grid, this paper presents a unique discussion regarding PQ assessment gaps that need to be solved in anticipation of a great leap forward and refers them to PQ legislation. [ABSTRACT FROM AUTHOR]

Cryptographic technology can effectively defend against malicious attackers to attack sensitive and private information. The core of cryptographic technology is cryptographic algorithm, and the cryptographic algorithm identification is the premise of in-depth analysis of cryptography. In the cryptanalysis of unknown cryptographic algorithm, the primary task is to identify the cryptographic algorithm used in the encryption and then carry out targeted analysis. With the rapid growth of Internet data, the increasing complexity of communication environment, and the increasing number of cryptographic algorithms, the single-layer identification scheme of cryptographic algorithm faces great challenges in terms of identification ability and stability. To solve these problems, on the basis of existing identification schemes, this paper proposes a new cluster division scheme CMSSBAM-cluster, and then proposes a multi-layer composite identification scheme of cryptographic algorithm using a composite structure. The scheme adopts the method of cluster division and single division to identify various cryptographic algorithms. Based on the idea of ensemble, the scheme uses the hybrid random forest and logistic regression (HRFLR) model for training, and conducts research on a data set consisting of 1700 ciphertext files encrypted by 17 cryptographic algorithms. In addition, two ensemble learning models, hybrid gradient boosting decision tree and logistic regression (HGBDTLR) model and hybrid k-neighbors and random forest (HKNNRF) model are used as controls to conduct controlled experiments in this paper. The experimental results show that multi-layer composite identification scheme of cryptographic algorithm based on HRFLR model has an accuracy rate close to 100% in the cluster division stage, and the identification results are higher than those of the other two models in both the cluster division and single division stages. In the last layer of cluster division, the identification accuracy of ECB and CBC encryption modes in block cryptosystem is significantly higher than that of the other two classification models by 35.2% and 36.1%. In single division, the identification accuracy is higher than HGBDTLR with a maximum of 9.8%, and higher than HKNNRF with a maximum of 7.5%. At the same time, the scheme proposed in this paper has significantly improved the identification effect compared with the single division identification accuracy of 17 cryptosystem directly and the 17 classification accuracy of 5.9% compared with random classification, which indicates that multi-layer composite identification scheme of cryptographic algorithm based on HRFLR model has significant advantages in the accuracy of identifying multiple cryptographic algorithms. [ABSTRACT FROM AUTHOR]

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform. [ABSTRACT FROM AUTHOR]

Battery voltage is a pivotal parameter for evaluating battery health and safety. The precise prediction of battery voltage and the implementation of anomaly detection are imperative for ensuring the secure and dependable operation of battery systems. Nevertheless, during the actual operation of electric vehicles, battery performance is subject to the influence of the vehicle's operational state and battery characteristic parameters, introducing challenges to safety alerts. In order to address these challenges and achieve precise battery voltage prediction, this paper comprehensively considers the battery characteristics and driving behavior of electric vehicles in both charging and operational states. Mathematical processing, including averaging and variance calculation, is applied to the battery characteristic parameter data and driving behavior data. By integrating historical voltage data and employing a modified gradient boosting decision tree algorithm (GBDT), a fast and accurate online voltage prediction method is proposed. Hyperparameter optimization is employed to minimize prediction voltage errors. The accuracy and timeliness of the predictions are validated through a comprehensive evaluation and comparison of the forecasted voltages. To diagnose anomalies in battery voltage, the paper proposes a fault diagnosis method that combines the Isolation Forest and Boxplot techniques. Finally, utilizing authentic electric vehicle data for validation, the research underscores the capability of the proposed method to achieve accurate voltage predictions six minutes in advance and provide effective fault diagnosis. This investigation carries substantial practical implications for fortifying battery management and optimizing the performance of electric vehicles. [ABSTRACT FROM AUTHOR]

With the continuous breakthrough of natural language processing, the application of intelligent question-answering technology in electric power systems has attracted wide attention. However, at present, the traditional question-answering system has poor performance and is difficult to apply in engineering practice. This paper proposes an improved BERTserini algorithm for the intelligent answering of electric power regulations based on a BERT model. The proposed algorithm is implemented in two stages. The first stage is the text-segmentation stage, where a multi-document long text preprocessing technique is utilized that accommodates the rules and regulations text, and then Anserini is used to extract paragraphs with high relevance to the given question. The second stage is the answer-generation and source-retrieval stage, where a two-step fine-tuning based on the Chinese BERT model is applied to generate precise answers based on given questions, while the information regarding documents, chapters, and page numbers of these answers are also output simultaneously. The algorithm proposed in this paper eliminates the necessity for the manual organization of professional question–answer pairs, thereby effectively reducing the manual labor cost compared to traditional question-answering systems. Additionally, this algorithm exhibits a higher degree of exact match rate and a faster response time for providing answers. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Grid-based Non-uniform Probability Density Sampling Probabilistic Roadmap algorithm (GN-PRM) in response to the challenges of difficult sampling in narrow passages and low-probability map generation in traditional Probabilistic Roadmap algorithms (PRM). The improved algorithm incorporates grid-based processing for map segmentation, employing non-uniform probability density sampling based on the different attributes of each block to enhance sampling probability in narrow passages. Additionally, considering the computational cost and frequent ineffective searches in traditional PRM algorithms during pathfinding, this paper optimizes the time required for query route planning by altering connection strategies to improve the algorithm's runtime. Finally, the simulation results indicate that, with a reduction of over 50% in undirected line segments and a reduction of over 85% in runtime, the GN-PRM algorithm achieves a 100% success rate in complex planning scenarios with a sampling point value of K = 500. In comparison, the traditional PRM algorithm has a success rate of no more than 10%, with a sampling point value of K = 500. [ABSTRACT FROM AUTHOR]

Existing Decision-Making Trial and Evaluation Laboratory (DEMATEL) methods are mostly suitable for simple systems with fewer factors, and lack effective integration of expert knowledge and experience from large-scale group populations, resulting in a potential compromise of the quality of the initial direct relation (IDR) matrix. To make DEMATEL better suited for the identification of critical factors in complex systems, this paper proposes a hierarchical DEMATEL method for large-scale group decision-making. Considering the limitations of expert knowledge and experience, a method based on expert consistency network for constructing the expert weight matrix is designed. The expert consistency network is constructed for different elements, and the weights of experts in different elements are determined using the clustering coefficient. Following the principles of the classic DEMATEL method, the steps for identifying key elements in complex systems using the large-scale group-hierarchical DEMATEL method are summarized. To objectively test the effectiveness and superiority of the decision algorithm, the robustness of the algorithm is analyzed in an interference environment. Finally, the superiority of the proposed method and algorithm is verified through a case study, which demonstrating that the proposed decision-making method is suitable for group decision-making in complex systems, with high algorithm stability and low algorithm deviation. [ABSTRACT FROM AUTHOR]

The vehicle's power battery is composed of a large number of battery cells series or in parallel. Due to the manufacturing process error and the different use environments, there are differences between the battery cells, and the battery pack will have inconsistency problems, which will increase the safety hazard. Therefore, it is of great practical significance to identify and warn about the inconsistency of power batteries. Based on the data of the internet of vehicles platform, this paper proposes an improved isolated forest power battery abnormal monomer identification and early warning method, which uses the sliding window (SW) to segment the dataset and update the data of the diagnosis model in real‐time. The scores of normal battery cells and abnormal battery cells were analyzed, and then the fault threshold was determined to be 0.75. The results show that the recall ratio and precision ratio of the algorithm are 0.91 and 0.95, respectively, which is more suitable for inconsistent battery cell identification than other methods. If the SW size is 15, the warning effect is the best. Before the vehicle alarm occurs, the algorithm can realize early fault warnings, thus effectively avoiding the safety problems caused by inconsistency faults. [ABSTRACT FROM AUTHOR]

In this paper, an analysis of a mathematical model of the coronavirus is carried out by using two fractal-fractional parameters. This dangerous virus infects a person through the mouth, eyes, nose or hands. This makes it so dangerous that no one can get rid of it. One of the main factors contributing to increasing infections of this deadly virus is crowding. We believe that it is necessary to model this effect mathematically to predict the possible outcomes. Hence, the study of neural network-based models related to the spread of this virus can yield new results. This paper also introduces the use of artificial neural networks (ANNs) to approximate the solutions, which is a significant contribution in this regard. We suggest employing this new method to solve a system of integral equations that explain the dynamics of infectious diseases instead of the classical numerical methods. Our study shows that, compared to the Adams-Bashforth algorithm, the ANN is a reliable candidate for solving the problems. [ABSTRACT FROM AUTHOR]

Sleep monitoring has become a prevalent area of research where body position and physiological data, such as heart rate and respiratory rate, are monitored. Numerous critical health problems are associated with poor sleep, such as pressure sore development, sleep disorders, and low sleep quality, which can lead to an increased risk of falls, cardiovascular diseases, and obesity. Current monitoring systems can be costly, laborious, and taxing on hospital resources. This paper reviews the most recent solutions for contactless textile technology in the form of bed sheets or mats to monitor body positions, vital signs, and sleep, both commercially and in the literature. This paper is organized into four categories: body position and movement monitoring, physiological monitoring, sleep monitoring, and commercial products. A detailed performance evaluation was carried out, considering the detection accuracy as well as the sensor types and algorithms used. The areas that need further research and the challenges for each category are discussed in detail. [ABSTRACT FROM AUTHOR]

Due to the complicated and changing circumstances of the sea environment, path planning technology is essential for unmanned surface vehicles (USVs) to fulfill search tasks. In most cases, the location of the underwater target is unknown, so it is necessary to completely cover the search area. In this paper, the global static path is planned using a parallel line scan search. When encountering unknown obstacles, the improved Bug algorithm is used for local dynamic path planning according to the sensor detection information. This paper first sets up the safe expansion area to ensure the safety of the USV during the obstacle avoidance process and optimizes the movement direction considering the operation and behavior characteristics of the USV. To meet the requirement of USV steering, the Bezier curve is used to smooth the path points, which greatly improves the smoothness of the path. In this paper, the multi-mode switching strategy of the Bug algorithm based on obstacle boundary width obtained by the sensor is proposed, which ensures no area omissions and meets the requirement of search area coverage during the process of bypassing obstacles. The simulation results show that the improved Bug algorithm can maintain a safe distance along the obstacle boundary to bypass the obstacle. Moreover, the improved Bug algorithm effectively improves the path oscillation phenomenon of traditional Bug and shortens the path length and operating time. Finally, through the global search path planning simulation and comparison experiments, the effectiveness of the proposed method is verified. [ABSTRACT FROM AUTHOR]

With the increasingly maturing technology of unmanned surface vehicles (USVs), their applications are becoming more and more widespread. In order to meet operational requirements in complex scenarios, the real-time interaction and linkage of a large amount of information is required between USVs, between USVs and mother ships, and between USVs and shore-based monitoring systems. Visual images are the main perceptual information gathered from USVs, and their efficient transmission and recognition directly affect the real-time performance of information exchange. However, poor maritime communication signals, strong channel interference, and low bandwidth pose great challenges to efficient image transmission. Traditional image transmission methods have difficulty meeting the real-time and image quality requirements of visual image transmissions from USVs. Therefore, this paper proposes an efficient method for visual image transmission from USVs based on semantic communication. A self-encoder network for semantic encoding which compresses the image into low-dimensional latent semantics through the encoding end, thereby preserving semantic information while greatly reducing the amount of data transmitted, is designed. On the other hand, a generative adversarial network is designed for semantic decoding. The decoding end decodes and reconstructs high-quality images from the semantic information transmitted through the channel, thereby improving the efficiency of image transmission. The experimental results show that the performance of the algorithm is significantly superior to traditional image transmission methods, achieving the best image quality while transmitting the minimum amount of data. Compared with the typical BPG algorithm, when the compression ratio of the proposed algorithm is 51.6% of that of the BPG algorithm, the PSNR and SSIM values are 7.6% and 5.7% higher than the BPG algorithm, respectively. And the average total time of the proposed algorithm is only 59.4% of that of the BPG algorithm. [ABSTRACT FROM AUTHOR]

The real-time path planning of unmanned aerial vehicles (UAVs) in dynamic environments with moving threats is a difficult problem. To solve this problem, this paper proposes a time-based rapidly exploring random tree (time-based RRT*) algorithm, called the hierarchical rapidly exploring random tree algorithm based on potential function lazy planning and low-cost optimization (HPO-RRT*). The HPO-RRT* algorithm can guarantee path homotopy optimality and high planning efficiency. This algorithm uses a hierarchical architecture comprising a UAV perception system, path planner, and path optimizer. After the UAV perception system predicts moving threats and updates world information, the path planner obtains the heuristic path. First, the path planner uses the bias sampling method based on the artificial potential field function proposed in this paper to guide sampling to improve the efficiency and quality of sampling. Then, the tree is efficiently extended by the improved time-based lazy collision checking RRT* algorithm to obtain the heuristic path. Finally, a low-cost path optimizer quickly optimizes the heuristic path directly to optimize the path while avoiding additional calculations. Simulation results show that the proposed algorithm outperforms the three existing advanced algorithms in terms of addressing the real-time path-planning problem of UAVs in a dynamic environment. [ABSTRACT FROM AUTHOR]

Link prediction is a crucial area of study within complex networks research. Mapping nodes to low-dimensional vectors through network embeddings is a vital technique for link prediction. Most of the existing methods employ "node–edge"-structured networks to model the data and learn node embeddings. In this paper, we initially introduce the Clique structure to enhance the existing model and investigate the impact of introducing two Clique structures (LECON: Learning Embedding based on Clique Of the Network) and nine motifs (LEMON: Learning Embedding based on Motif Of the Network), respectively, on experimental performance. Subsequently, we introduce a hypergraph to model the network and reconfigure the network by mapping hypermotifs to two structures: open hypermotif and closed hypermotif, respectively. Then, we introduce hypermotifs as supernodes to capture the structural similarity between nodes in the network (HMRLH: HyperMotif Representation Learning on Hypergraph). After that, taking into account the connectivity and structural similarity of the involved nodes, we propose the Depth and Breadth Motif Random Walk method to acquire node sequences. We then apply this method to the LEMON (LEMON-DB: LEMON-Depth and Breadth Motif Random Walk) and HMRLH (HMRLH-DB: HMRLH-Depth and Breadth Motif Random Walk) algorithms. The experimental results on four different datasets indicate that, compared with the LEMON method, the LECON method improves experimental performance while reducing time complexity. The HMRLH method, utilizing hypernetwork modeling, proves more effective in extracting node features. The LEMON-DB and HMRLH-DB methods, incorporating new random walk approaches, outperform the original methods in the field of link prediction. Compared with state-of-the-art baselines, the proposed approach in this paper effectively enhances link prediction accuracy, demonstrating a certain level of superiority. [ABSTRACT FROM AUTHOR]

A series of recent papers raises worries about the manipulative potential of algorithmic transparency (to wit, making visible the factors that influence an algorithm’s output). But while the concern is apt and relevant, it is based on a fraught understanding of manipulation. Therefore, this paper draws attention to the ‘indifference view’ of manipulation, which explains better than the ‘vulnerability view’ why algorithmic transparency has manipulative potential. The paper also raises pertinent research questions for future studies of manipulation in the context of algorithmic transparency. [ABSTRACT FROM AUTHOR]

Introduction This Special Issue of Algorithms is of a different nature than other Special Issue in the journal, which are usually dedicated to a particular subjects in the area of algorithms. Algorithms Editorial 2020 Selected Papers from Algorithms' Editorial Board Members Frank Werner Citation: Werner, F. 2020 Selected Papers from Algorithms' Editorial Board Members. Algorithms 2021,14, 32. https://doi.org/10.3390/a14020032 https://www.mdpi.com/journal/algorithms Algorithms 2021,14, 32 2 of 2 The paper [5] deals with parsing which has applications in many branches of computer science, e.g., in compilers or formal language theory. [Extracted from the article]

A supply chain is an order of activities engaged which circulates, assembles and handles the products to move the benefits from a dealer under the control of the last customer. It is an interconnected compound network controlled by supply and demand. Cyber security in SCM is one of the segment of its estimates of protection which primarily gives attention in managing the essential virtual protection which comprises of system software of information technology. In the existing system, cloud services must need extra applications and assistances to locate, govern and protect data which initiate extra supply chain contributors. The manufacturing process data will mislead the manufacturing process in this system based on errors which are done manually. To Store and Maintain data in a protected manner, most algorithms such as DES (Data Encryption Standard) algorithm has disadvantages and threats which seems to be an upper hand for the hackers who are working to steal the data all around. In this paper, for securing the private and secret data, we applied and executed AES (Advanced Encryption Standard) algorithm and MD5 (Message-Digest algorithm 5) in supply chain management. We apply PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyzes) approach in domain of supply chain management, data security, and cyber security to screen the various methods and algorithms which are published in various journal papers and to select a unique and best approach to be used in supply chain management and its security. This method is basically a kind of literature survey to select a best topic for doing a project or a research paper. [ABSTRACT FROM AUTHOR]

The deep model is widely used and has been demonstrated to have more hidden security risks. An adversarial attack can bypass the traditional means of defense. By modifying the input data, the attack on the deep model is realized, and it is imperceptible to humans. The existing adversarial example generation methods mainly attack the whole image. The optimization iterative direction is easy to predict, and the attack flexibility is low. For more complex scenarios, this paper proposes an edge-restricted adversarial example generation algorithm (Re-AEG) based on semantic segmentation. The algorithm can attack one or more specific objects in the image so that the detector cannot detect the objects. First, the algorithm automatically locates the attack objects according to the application requirements. Through the semantic segmentation algorithm, the attacked object is separated and the mask matrix for the object is generated. The algorithm proposed in this paper can attack the object in the region, converge quickly and successfully deceive the deep detection model. The algorithm only hides some sensitive objects in the image, rather than completely invalidating the detection model and causing reported errors, so it has higher concealment than the previous adversarial example generation algorithms. In this paper, a comparative experiment is carried out on ImageNet and coco2017 datasets, and the attack success rate is higher than 92%. [ABSTRACT FROM AUTHOR]

Nearly thirty years ago, it was shown that \(\Omega (\sqrt {n})\) read/write registers are needed to solve randomized wait-free consensus among n processes. This lower bound was improved to n registers in 2018, which exactly matches known algorithms. The \(\Omega (\sqrt {n})\) space complexity lower bound actually applies to a class of objects called historyless objects, which includes registers, test-and-set objects, and readable swap objects. However, every known n-process obstruction-free consensus algorithm from historyless objects uses Ω (n) objects. In this paper, we give the first Ω (n) space complexity lower bounds on consensus algorithms for two kinds of historyless objects. First, we show that any obstruction-free consensus algorithm from swap objects uses at least n-1 objects. More generally, we prove that any obstruction-free k-set agreement algorithm from swap objects uses at least \(\lceil \frac{n}{k}\rceil - 1\) objects. The k-set agreement problem is a generalization of consensus in which processes agree on no more than k different output values. This is the first non-constant lower bound on the space complexity of solving k-set agreement with swap objects when k > 1. We also present an obstruction-free k-set agreement algorithm from n-k swap objects, which exactly matches our lower bound when k=1. Second, we show that any obstruction-free binary consensus algorithm from readable swap objects with domain size b uses at least \(\frac{n-2}{3b+1}\) objects. When b is a constant, this asymptotically matches the best known obstruction-free consensus algorithms from readable swap objects with unbounded domains. Since any historyless object can be simulated by a readable swap object with the same domain, our results imply that any obstruction-free consensus algorithm from historyless objects with domain size b uses at least \(\frac{n-2}{3b+1}\) objects. For b = 2, we show a slightly better lower bound of n-2. There is an obstruction-free binary consensus algorithm using 2n-1 readable swap objects with domain size 2, asymptotically matching our lower bound. [ABSTRACT FROM AUTHOR]

A paper manufacturing plant minimizes its production cost by using long production runs that combine the demands from its various customers. As jobs are completed, they are released to distribution for delivery. Deliveries are made by railcars, each of which is dedicated to one customer. Long production runs imply that maximizing railcar utilization requires holding the cars over several days or holding completed jobs within the loading facility. Each of these methods imposes a cost onto the distribution function. We find how distribution can minimize its cost, given production's schedule. We then consider the problem of minimizing the company's overall cost of both production and distribution. A computational study using general data illustrates that the distribution cost is reduced by 25.80% through our proposed scheme, and that the overall cost is reduced an additional 4.40% through our coordination mechanism. An optimal algorithm is derived for a specific plant's operations. [ABSTRACT FROM AUTHOR]

In order to better solve the problem of automatic identification of quality control line and detection line in the detection of gold standard test strip, this paper proposes to collect the image information of gold standard test strip after color rendering through CMOS sensor, preprocess the obtained information, transform RGB image into gray image, build cloud model in the CIELAB/HSV/HSL space, and apply the improved AdaBoost algorithm to determine the position of detection line and quality control line Place. Compared with the traditional template matching method, it improves the accuracy and accuracy of recognition. [ABSTRACT FROM AUTHOR]

Machine learning (ML), a form of artificial intelligence (AI), is being increasingly employed in neurology. Reported performance metrics often match or exceed the efficiency of average clinicians. The neurologist is easily baffled by the underlying concepts and terminologies associated with ML studies. The superlative performance metrics of ML algorithms often hide the opaque nature of its inner workings. Questions regarding ML model's interpretability and reproducibility of its results in real-world scenarios, need emphasis. Given an abundance of time and information, the expert clinician should be able to deliver comparable predictions to ML models, a useful benchmark while evaluating its performance. Predictive performance metrics of ML models should not be confused with causal inference between its input and output. ML and clinical gestalt should compete in a randomized controlled trial before they can complement each other for screening, triaging, providing second opinions and modifying treatment. [ABSTRACT FROM AUTHOR]

This document discusses the importance of optimization in various fields such as statistics, biology, finance, economics, and control. It highlights the advancements made in optimization theory and methods, including first-order methods and augmented Lagrangian methods. The document also introduces a special issue on "Symmetry in Optimization Theory, Algorithms and Applications," which features five papers on topics such as ensemble learning, ant colony system algorithms, subspace algorithms, consensus problems in multi-agent systems, and dynamic conditional correlation models. The authors express their gratitude to the contributors and reviewers of the special issue. [Extracted from the article]

Intelligent agriculture has become the development trend of agriculture in the future, and it has a wide range of research and application scenarios. Using machine learning to complete basic tasks for people has become a reality, and this ability is also used in machine vision. In order to save the time in the fruit picking process and reduce the cost of labor, the robot is used to achieve the automatic picking in the orchard environment. Cherry target detection algorithms based on deep learning are proposed to identify and pick cherries. However, most of the existing methods are aimed at relatively sparse fruits and cannot solve the detection problem of small and dense fruits. In this paper, we propose a cherry detection model based on YOLOv5s. First, the shallow feature information is enhanced by convolving the feature maps sampled by two times down in BackBone layer of the original network model to the input end of the second and third CSP modules. In addition, the depth of CSP module is adjusted and RFB module is added in feature extraction stage to enhance feature extraction capability. Finally, Soft- Non-Maximum Suppression (Soft-NMS) is used to minimize the target loss caused by occlusion. We test the performance of the model, and the results show that the improved YOLOv5s-cherry model has the best detection performance for small and dense cherry detection, which is conducive to intelligent picking. [ABSTRACT FROM AUTHOR]

In the model (m:n), to improve the autonomous collaborative interception capability for air vehicle, a new autonomous cross-collaborative interception algorithm based on GTSMC (Global Terminal Sliding Mode Control) and real-time virtual geometry is proposed in this paper. Firstly, the conception of an autonomous cross-collaboration is defined and the multi-air vehicle for the multi- object interception problem is formulated. Then, this paper presents the dynamic situation assessment function, which considers the real-time flight status and cooperative status of the air vehicle during the interception of the object. At the same time, this paper states the condition of whether the air vehicle is in a cooperative state and proves it. After completing the dynamic situation assessment, and considering the dynamic of the air vehicles, a new controller is designed by using GTSMC and the idea of backstepping method. Simultaneously, this paper gives a stability analysis of the closed-loop system by using Lyapunov theory. Finally, to demonstrate the effectiveness of the proposed algorithm, several simulation cases which consider different interception scenarios are given. The simulation results show that the new collaborative interception algorithm can provide better autonomous cross-collaborative interception capability and higher accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a road crack detection algorithm based on an improved SparseInst network, called the SparseInst-CDSM algorithm, aimed at solving the problems of low recognition accuracy and poor real-time detection of existing algorithms. The algorithm introduces the CBAM module, DCNv2 convolution, SPM strip pooling module, MPM mixed pooling module, etc., effectively improving the integrity and accuracy of crack recognition. At the same time, the central axis skeleton of the crack is extracted using the central axis method, and the length and maximum width of the crack are calculated. In the experimental comparison under the self-built crack dataset, SparseInst-CDSM has an accuracy of 93.66%, a precision of 67.35%, a recall of 66.72%, and an IoU of 84.74%, all higher than mainstream segmentation models such as Mask-RCNN and SOLO that were compared, reflecting the superiority of the algorithm proposed in this paper. The comparison results of actual measurements show that the algorithm error is within 10%, indicating that it has high effectiveness and practicality. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

Fragile watermarking is embedding a watermark in a media (an image in this paper) such that even small changes, called tamper, can be detected or even recovered to prevent unauthorized alteration. A well-known category of spatial fragile watermarking methods is based on embedding the watermark in the least significant bits of the image to preserve the quality. In addition, Hamming code is a coding algorithm in communication that transmits the data bits by augmenting some check bits to detect and recover single-bit modifications precisely. This property was previously used to detect and perfectly recover the images modified by small tampers less than a quarter of the image in diameter. To achieve this goal, the Hamming code is applied on a distributed pixel, bits of which are gathered from sufficient far pixels in the image. It guarantees that such tampers can toggle at most one bit of each distributed Hamming code that is recoverable. It was the only guaranteed perfect reconstruction method of small tampers, based on our knowledge. In this paper, the method has been extended to support distortion in two bits of a Hamming code by the use of common structures of distributed codes. It guarantees the recovery of tampers less than half of the image in width and height. According to the experimental results, the proposed method achieved better performance, in terms of recovering the tampered areas, in comparison to state-of-the-art. [ABSTRACT FROM AUTHOR]

Every year, the number of women affected by breast tumors is increasing worldwide. Hence, detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The conventional methods obtained low sensitivity and specificity with cancer region segmentation accuracy. The high-resolution standard mammogram images were supported by conventional methods as one of the main drawbacks. The conventional methods mostly segmented the cancer regions in mammogram images concerning their exterior pixel boundaries. These drawbacks are resolved by the proposed cancer region detection methods stated in this paper. The mammogram images are classified into normal, benign, and malignant types using the Adaptive Neuro- Fuzzy Inference System (ANFIS) approach in this paper. This mammogram classification process consists of a noise filtering module, spatial-frequency transformation module, feature computation module, and classification module. The Gaussian Filtering Algorithm (GFA) is used as the pixel smooth filtering method and the Ridgelet transform is used as the spatial-frequency transformation module. The statistical Ridgelet feature metrics are computed from the transformed coefficients and these values are classified by theANFIS technique in this paper. Finally, Probability Histogram Segmentation Algorithm (PHSA) is proposed in this work to compute and segment the tumor pixels in the abnormal mammogram images. This proposed breast cancer detection approach is evaluated on the mammogram images in MIAS and DDSM datasets. From the extensive analysis of the proposed tumor detection methods stated in this work with other works, the proposed work significantly achieves a higher performance. The methodologies proposed in this paper can be used in breast cancer detection hospitals to assist the breast surgeon to detect and segment the cancer regions. [ABSTRACT FROM AUTHOR]

The detection of salient objects in foggy scenes is an important research component in many practical applications such as action recognition, target tracking and pedestrian re-identification. To facilitate saliency detection in foggy scenes, this paper explores two issues. The construction of dataset for foggy weather conditions and implementation scheme for foggy weather saliency detection. Firstly, a foggy sky image synthesis method is designed based on the atmospheric scattering model, and a saliency detection dataset applicable to foggy sky is constructed. Secondly, we compare the current classification networks and adopt resnet50, which has the highest classification accuracy, as the backbone network of the classification module, and classify the foggy sky images into three levels, namely fogless, light fog and dense fog, according to different concentrations. Then, Residual Refinement Network (R2Net) was selected to train and test the classified images. Horizontal and vertical flipping and image cropping were used to enhance the training set to relieve over-fitting. The accuracy of the network model was improved by using Adam as the optimizer. Experimental results show that for the detection of fogless images, our method is almost on par with state-of-the-art, and performs well for both light and dense fog images. Our method has good adaptability, accuracy and robustness. [ABSTRACT FROM AUTHOR]

The hyperspectral anomaly detection algorithm based on collaborative representation does not fully utilize the two-dimensional spatial features in hyperspectral images. It also has the problem that anomalous pixels will pollute the background dictionary and induce bad detection performance. Based on these, this paper proposes a hyperspectral anomaly detection algorithm based on multiple feature joint trilateral filtering and collaborative representation. The algorithm first introduces an improved trilateral filtering algorithm, which utilizes the spatial features of hyperspectral images. The preliminary positions of possible abnormal objects are determined. On this basis, abnormal removal and background filling are performed to obtain a purified background. Finally, the purified background and the original hyperspectral image are used for joint collaborative representation to complete the detection. Experimental results show that the detection accuracy of the algorithm proposed in this paper was efficiently improved by introducing multiple feature joint trilateral filtering, where multiple spatial spectrum features are utilized. [ABSTRACT FROM AUTHOR]

Author-supplied citations are a fraction of the related literature for a paper. The "related citations" on PubMed is typically dozens or hundreds of results long, and does not offer hints why these results are related. Using noun phrases derived from the sentences of the paper, we show it is possible to more transparently navigate to PubMed updates through search terms that can associate a paper with its citations. The algorithm to generate these search terms involved automatically extracting noun phrases from the paper using natural language processing tools, and ranking them by the number of occurrences in the paper compared to the number of occurrences on the web. We define search queries having at least one instance of overlap between the author-supplied citations of the paper and the top 20 search results as citation validated (CV). When the overlapping citations were written by same authors as the paper itself, we define it as CV-S and different authors is defined as CV-D. For a systematic sample of 883 papers on PubMed Central, at least one of the search terms for 86% of the papers is CV-D versus 65% for the top 20 PubMed "related citations." We hypothesize these quantities computed for the 20 million papers on PubMed to differ within 5% of these percentages. Averaged across all 883 papers, 5 search terms are CVD, and 10 search terms are CV-S, and 6 unique citations validate these searches. Potentially related literature uncovered by citation-validated searches (either CV-S or CV-D) are on the order of ten per paper - many more if the remaining searches that are not citation-validated are taken into account. The significance and relationship of each search result to the paper can only be vetted and explained by a researcher with knowledge of or interest in that paper. [ABSTRACT FROM AUTHOR]

At present, PPF-based point cloud recognition algorithms can perform better matching than competitors and be verified in the case of severe occlusion and stacking. However, including certain superfluous feature point pairs in the global model description would significantly lower the algorithm's efficiency. As a result, this paper delves into the Point Pair Feature (PPF) algorithm and proposes a 6D pose estimation method based on Keypoint Pair Feature (K-PPF) voting. The K-PPF algorithm is based on the PPF algorithm and proposes an improved algorithm for the sampling point part. The sample points are retrieved using a combination of curvature-adaptive and grid ISS, and the angle-adaptive judgment is performed on the sampling points to extract the keypoints, therefore improving the point pair feature difference and matching accuracy. To verify the effectiveness of the method, we analyze the experimental results in scenes with different occlusion and complexity levels under the evaluation metrics of ADD-S, Recall, Precision, and Overlap rate. The results show that the algorithm in this paper reduces redundant point pairs and improves recognition efficiency and robustness compared with PPF. Compared with FPFH, CSHOT, SHOT and SI algorithms, this paper improves the recall rate by more than 12.5%. [ABSTRACT FROM AUTHOR]

This paper proposes a new algorithm composition network from the perspective of machine learning, based on an in-depth study of related literature. At the same time, this paper examines the characteristics of music and develops a model for recognising musical emotions. Using the model's information entropy of pitch and intensity to extract the main melody track, note features are extracted from bar features. Finally, the cosine of the vector included angle is used to judge the similarity between feature vectors of several adjacent sections, allowing the music to be divided into several independent segments. The emotional model of music is used to analyze each segment's emotion. By quantifying music features, this paper classifies and quantifies music emotion based on the mapping relationship between music features and emotion. Music emotion can be accurately identified by the model. The model's emotion recognition accuracy is up to 93.78 percent, and the algorithm's recall rate is up to 96.3 percent, according to simulation results. The recognition method used in this paper has a higher recognition ability than other methods, and the emotion recognition result is more reliable. This paper can not only meet the composer's auxiliary creative needs, but it can also help intelligent music services. [ABSTRACT FROM AUTHOR]

This Special Issue contains four papers focused on hyperspectral data analysis. The authors use multivariate data analysis to establish a quantitative relationship between the obtained spectral information of the kidney and its reference TWC values. The present Special Issue covers a range of algorithms and techniques for hyperspectral data analysis. [Extracted from the article]

This paper proposes and evaluates two robust sheet tension estimation algorithms based on unwind and rewind variables, respectively. The proper sheet tension estimation is guaranteed by a continuous monitoring of the differences between the actual estimated values and the values predicted from the last calibration of the estimation parameters. The evaluation was performed with the aid of a developed winder emulator that allowed the offline testing in a real-time field environment, including the initial setting of the estimation constants, and evaluation of both four- and six-shipping-roll cycles. The sheet tension estimation results confirm the precise and stable operation of the proposed robust estimation algorithms, in tests conducted with signals from a winder model, and with tests involving actual field signals from an operational winder. [ABSTRACT FROM AUTHOR]

Copyright of Canadian Journal of Chemical Engineering is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

An algorithm for retrieval of vertical profiles from ground-based spectra in the near IR is described and tested. Known as GFIT2, the algorithm is primarily intended for CO2, and is used exclusively for CO2 in this paper. Retrieval of CO2 vertical profiles from ground-based spectra is theoretically possible, would be very beneficial for carbon cycle studies and the validation of satellite measurements, and has been the focus of much research in recent years. GFIT2 is tested by application both to synthetic spectra, and to measurements at two TCCON sites. We demonstrate that there are approximately 3° of freedom for the CO2 profile, and the algorithm performs as expected on synthetic spectra. We show that the accuracy of retrievals of CO2 from measurements in the 1.6μ spectral band is limited by small uncertainties in calculation of the atmospheric spectrum. We investigate several techniques to minimize the effect of these uncertainties in calculation of the spectrum. These techniques are somewhat effective, but to date have not been demonstrated to produce CO2 profile retrievals superior to existing techniques for retrieval of column abundance. We finish by discussing on-going research which may allow CO2 profile retrievals with sufficient accuracy to significantly improve on the results of column retrievals, both in total column abundance and in profile shape. [ABSTRACT FROM AUTHOR]

To satisfy the requirement of quality control in printing and packaging industry, a sheet counting apparatus is developed, which adopts a line-scan camera to image the fringes of sheet stack and is able to provide a real-time and noncontact measurement of their quantity. With a brief introduction of the system architecture, our main work focuses on the sheet counting algorithms. The basic principle is to identify each sheet profile from the 1-D image with a robust ridge strength measurement. First, a multiscale bi-Gaussian ridge likelihood measurement and a ridge-valley descriptor are utilized to improve adjacent objects detection by increasing local contrast around sheet fringes. Then, a sheet recognition scheme, which integrates a peak detection algorithm and the ridge region criteria for verification, is proposed to discriminate true sheets from the obtained ridgeness measure. According to experiments and tests in real production lines, our apparatus can reach a very high measuring accuracy for printing papers or cards with a thickness not <0.2 mm. [ABSTRACT FROM PUBLISHER]

Polynomial multiplication is the most computationally expensive part of the lattice-based cryptography algorithm. However, the existing acceleration schemes have problems, such as low performance and high hardware resource overhead. Based on the polynomial multiplication of number theoretic transformation (NTT), this paper proposed a simple element of Montgomery module reduction with pipeline structure to realize fast module multiplication. In order to improve the throughput of the NTT module, the block storage technology is used in the NTT hardware module to enable the computing unit to read and write data alternately. Based on the NTT hardware module, a precalculated parameter storage and real-time calculation method suitable for the hardware architecture of this paper is also proposed. Finally, the hardware of polynomial multiplier based on NTT module is implemented, and its function simulation and performance evaluation are carried out. The results show that the proposed hardware accelerator can have excellent computing performance while using fewer hardware resources, thus meeting the requirements of lattice cipher algorithms in security chips. Compared with the existing studies, the computing performance of the polynomial multiplier designed in this paper is improved by approximately 1 to 3 times, and the slice resources and storage resources used are reduced by approximately 60% and 17%, respectively. [ABSTRACT FROM AUTHOR]

The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper. [ABSTRACT FROM AUTHOR]

Aiming at the problem of motion blur in the inspection image of wind power generation equipment, an improved fast motion blur removal method based on deblurganv2 is proposed in this paper. Firstly, according to the characteristics of disparate local motion blur degrees and different global motion blur directions of the wind power inspection image, the real wind power fuzzy image data set is collected and produced. Secondly, according to the characteristics of the single background of the wind power inspection image and the requirements of fast and effective processing, the lightweight network Ghostnet is redesigned as the backbone network of the Deblurganv2 generator to reduce the number of network parameters and calculations. Finally, five SE channel attention mechanism layers are added to GhostNet to strengthen feature extraction, and the upsampling process is optimized through bilinear interpolation, to improve the deblurring performance of the wind power inspection image. The experimental results show that compared with other algorithms, the proposed algorithm has a higher peak signal‐to‐noise ratio and structural similarity, the network model parameters are compressed to 6.1 MB, and the reasoning speed is improved to 0.42 s. [ABSTRACT FROM AUTHOR]

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer's global modeling ability and convolutional neural network's local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. [ABSTRACT FROM AUTHOR]

With the advent of Mobile Edge Computing (MEC), shifting data processing from cloud centers to the network edge presents an advanced computational paradigm for addressing latency-sensitive applications. Specifically, in radar systems, the real-time processing and prediction of radar echo data pose significant challenges in dynamic and resource-constrained environments. MEC, by processing data near its source, not only significantly reduces communication latency and enhances bandwidth utilization but also diminishes the necessity of transmitting large volumes of data to the cloud, which is crucial for improving the timeliness and efficiency of radar data processing. To meet this demand, this paper proposes a model that integrates a spatiotemporal Attention Module (STAM) with a Long Short-Term Memory Gated Recurrent Unit (ST-ConvLSGRU) to enhance the accuracy of radar echo prediction while leveraging the advantages of MEC. STAM, by extending the spatiotemporal receptive field of the prediction units, effectively captures key inter-frame motion information, while optimizations to the convolutional structure and loss function further boost the model's predictive performance. Experimental results demonstrate that our approach significantly improves the accuracy of short-term weather forecasting in a mobile edge computing environment, showcasing an efficient and practical solution for processing radar echo data under dynamic, resource-limited conditions. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

In addressing the challenge of ships being prone to occlusion in multi‐target situations during ship target detection, leading to missed and false detections, this paper proposes an enhanced ship detection algorithm for YOLOv7‐tiny. The proposed method incorporates several key modifications. Firstly, it introduces the Convolutional Block Attention Module in the Backbone section of the original model, emphasizing position information while attending to channel features to enhance the network's ability to extract crucial information. Secondly, it replaces standard convolution with GSConv convolution in the Neck section, preserving detailed information and reducing computational load. Subsequently, the lightweight operator Content‐Aware ReAssembly of Features is employed to replace the original nearest‐neighbour interpolation, mitigating the loss of feature information during the up‐sampling process. Finally, the localization loss function, SIOU Loss, is utilized to calculate loss, expedite training convergence, and enhance detection accuracy. The research results indicate that the precision of the improved model is 91.2%, mAP@0.5 is 94.5%, and the F1‐score is 90.7%. These values are 3.7%, 5.5%, and 4.2% higher than those of the original YOLOv7‐tiny model, respectively. The improved model effectively enhances detection accuracy. Additionally, the improved model achieves an FPS of 145.4, meeting real‐time requirements. [ABSTRACT FROM AUTHOR]

Communication security has become particularly crucial with the rapid development of the Internet of Things (IoT). Frequency hopping spread spectrum (FHSS) technology, a prevalent method in wireless communication, has a wide range of applications in the Internet of Things. Enhancing the security of frequency hopping sequences is an essential means to improve the security of frequency hopping communication in the Internet of Things, as the performance of frequency hopping sequences plays a crucial role in frequency hopping systems. This paper proposes constructing secure adaptive frequency hopping sequence sets based on the advanced encryption standard (AES) algorithm. As a block cipher algorithm with superior security, the AES algorithm can provide a fundamental guarantee for the security of the proposed frequency hopping sequences. The mapping methods from ciphertext sequences to frequency hopping sequences proposed in this paper can achieve the construction of frequency hopping sequences of any frequency set size to meet the requirements of adaptive frequency hopping. In addition, we also model and analyse the problem of overlapping spectrum band of the IoT groups in the industrial, scientific, and medical (ISM) band, aiming to achieve better packet transmission performance by adjusting the frequency set size. [ABSTRACT FROM AUTHOR]

This project will study a fast retrieval method for music humming speech recognition based on sentence features and deep learning. The method proposed in this paper can realize the fast extraction of songs. According to the characteristics of the natural pause mode of the song, the song database and the song fragments provided by the user are divided into different sentences. The deep learning algorithm of BDTW is used to calculate the similarity of the song's pitch, and users can set matching conditions according to their preferences. It can identify the most significant differences between music fragments and the order of queries in the database. Then, a retrieval method of a music database based on DIS is proposed. It can shorten the acquisition time. Experiments show that the algorithm can recognize humming songs quickly and efficiently. [ABSTRACT FROM AUTHOR]