Search

With the prevalence of artificial intelligence technologies, big data has been utilized to higher extent in many cross-domain fields. This paper concentrates on the digital assessment of vocational education level in some specific areas, and proposes a graph neural network-based assessment model for this purpose. Assume that all vocational colleges inside a specific region are with a social graph, in which each college is a node and the relations among them are the edges. The graph neural network (GNN) model is formulated to capture global structured features of all the nodes together. The GNN is then employed for the sequential modeling pattern, and the evolving characteristics of all the colleges can be captured. Some experiments are also conducted to evaluate the performance of the proposed GNN-VEL. It is compared with two typical forecasting methods under evaluation of two metrics. The results show that it performs better than other two methods. [ABSTRACT FROM AUTHOR]

In this paper, the method for the design automation of a narrow band-pass amplifier, and hence the amplifier tuned oscillator is discussed. A fixator approach is utilized in this method to design the narrow band-pass amplifiers and a reference circuit is required for this process. The fixator–norator pair helps to generate an extra sub-circuit, generally the feedback network; the addition of this sub-circuit in the actual amplifier circuit will modify the frequency response of the amplifier. The amplifier now behaves like an active narrow band-pass filter, which exactly follows the frequency response of the model circuit. This can be turned into an oscillator by providing positive feedback. Such a circuit possesses independent frequency and amplitude control. Hence, the re-designed circuit can be employed as an active filter or an oscillator at the selected center frequency. In addition to the technical merits, the proposed method has pedagogical importance. Few case studies are worked out in this paper to demonstrate the method. [ABSTRACT FROM AUTHOR]

With 3D products being widely applied, more attention has focused on studying stereo image super-resolution (SR). Current stereo image SR studies mainly aim to improve the performance by the additional information from a pair of low-resolution stereo images. However, it is challenging for stereo image SR to fully exploit self-similarity information from its own image and parallax information between stereo image pairs. In line with these challenges, this paper presents a Two-Branch Network (TBNet) to integrate self-similarity information and parallax information for SR. In the TBnet, a stereo parallax transfer module with an encoder–decoder structure was first proposed to sufficiently transfer multi-scale parallax information and preserve the stereo consistency between stereo images. This paper further presented a residual pyramid self-attention module to employ self-similarity information to take advantage of self-predictive power. Finally, extensive experiments demonstrate the superiority of our model over the state-of-the-art performance in terms of objective and perceptual quality and the accuracy of disparity estimation. [ABSTRACT FROM AUTHOR]

Crowdsourcing is an emerging approach in software development, where software is developed by unknown, heterogeneous people around the globe, via an open call by the employer. Crowdsourcing, when used with agile, faces challenges because of the different development methodologies. Agile development methodology has practices that involve face-to-face frequent interaction, whereas crowdsourcing is a distributed development with no or limited face-to-face interaction. Both concepts are actively being used in the software development industry due to their benefits. However, there is a need to explore the integration of both methodologies for an effective and efficient software development. In this regard, the first step is to identify the challenges of integrating crowdsourcing and agile. In this paper, we intend to identify the possible challenges that may be faced while executing agile along with crowdsourcing. For this, we have conducted a Systematic Literature Review. Five main categories of challenges are presented which are: team issues, coordination and communication issues, organizational issues, project-related issues and task-related issues. A list of possible challenges of Agile–Crowd Software Development (ACSD) is presented in this study. [ABSTRACT FROM AUTHOR]

At present, there are many semantic segmentation algorithms with excellent performance for intelligent driving vehicles, but most of them only work well on scenes with good illumination. In order to solve the problem of scene segmentation under low illumination, this paper proposes a novel semantic segmentation algorithm that combines visible and infrared images. In this algorithm, two parallel encoders are designed as the input of the images, and the decoder divides the fused images output from the encoder. The model is based on ResNet algorithm, and the residual attention module is used in each branch to mine and enhance the spatial features of multilevel channels to extract images information. Experiments are carried out on publicly available thermal infrared and visible datasets. The results show that the algorithm proposed in this paper is superior to the algorithm using only visible images in semantic segmentation of traffic environment. [ABSTRACT FROM AUTHOR]

In this paper, we focus on two tasks: semantic segmentation and target detection in the visual semantic understanding of tennis sports images and we optimize the network structure to achieve a more complete location contour information mining of the target. In detail, we focus on a weakly supervised image semantic segmentation method based on null convolution pixel relations. To address the problem of incomplete pixel-level pseudo-labeling, we introduce a cavity convolution unit with multiple cavity rates and a self-attentive mechanism in the classification model to adaptively enhance the target regions and suppress other irrelevant regions while expanding the perceptual field to generate high-quality pixel-level pseudo-labeling and then train the semantic segmentation model. The final experimental results show that the hierarchical fusion algorithm proposed in this paper significantly outperforms other algorithms, and the overall classification accuracy of the tandem cavity neural network algorithm reaches 81% with good overall classification results. The recognition accuracy of static movements is higher than that of dynamic movements. [ABSTRACT FROM AUTHOR]

To address the issues of blurred details and distortion of color in the images recovered by the original AOD-Net dehazing method, this paper proposes a CPAD-Net dehazing network model based on attention mechanism and dense residual blocks. The network is improved on the basis of AOD-Net, which can reduce the errors arising from the separately determined transmittance and atmospheric light values. A new dense residual block structure is designed to replace the traditional convolution method, which effectively improves the detail processing capability and the representation ability of the network model for image feature information. On this basis, the attention module determines how to learn the weights according to the feature importance of distinct channels and distinct pixels, and then obtain the recovery of images in terms of color and texture. The experiments showed that the dehazing efficiency of our method are richer in texture detail information and more natural in color recovery. Compared with other algorithms, the PSNR and SSIM indexes of our method are considerably superior to those listed algorithms, which definitively demonstrates that the dehazing effect of our method is more effective, and the recovered images are more realistic and natural. [ABSTRACT FROM AUTHOR]

Concrete crack detection is essential for infrastructure safety, and its detection efficiency and accuracy are the key issues. An improved YOLOV5 and three measurement algorithms are proposed in this paper, where the original prediction heads are replaced by Transformer Heads (TH) to expose the prediction potential with one self-attention model. Experiments show that the improved YOLOV5 effectively enhances the detection and classification of concrete cracks, and the Mean Average Precision (MAP) value of all classes increases to 99.5%. The first method is more accurate for small cracks, whilst the average width obtained based on the axial traverse correction method is more exact for large cracks. The crack width obtained from the concrete picture sample is the same as that obtained from the manual detection, with a deviation rate of 0–5.5%. This research demonstrates the recognition and classification of concrete cracks by integrating deep learning and machine vision with high precision and high efficiency. It is helpful for the real-time measurement and analysis of concrete cracks with potential safety hazards in bridges, high-rise buildings, etc. [ABSTRACT FROM AUTHOR]

Currently, the prevalence of various Internet intrusion technologies has brought much challenge to the enterprise management. For many core documents, the information leakage may lead to the loss of secrets of enterprises. Therefore, some core official documents in enterprises are in the format of papers, rather than electronic format. As a consequence, it is of significance to develop automatic information processing techniques for official documents in the format of papers, so as to improve the working efficiency of enterprises. In this paper, a novel business scheduling approach for enterprises via vision sensing-based automatic documental information extraction is proposed. For the first stage, the vision sensing-based optical character recognition (OCR) technique is utilized to extract textual information from official documents in the format of papers. For the second stage, the deep neural network is utilized to output business scheduling results on the basis of digital recognition contents from the first stage. Finally, the experimental simulation is also carried out to verify efficiency of the proposal. [ABSTRACT FROM AUTHOR]

This paper mainly discusses the problem of fast fixed-time bipartite synchronization in the complex networks with signed graph that is based on TS fuzzy system. By designing suitable and effective controller, the synchronization of the considered complex networks has been achieved successfully in this paper, whose convergence rate is superior to the great majority of existing results. With the assistance of a comparison system being built and using the theory of Lyapunov stability, this paper has established sufficient criteria successfully that are able to achieve fast fixed-time bipartite synchronization. And a numerical simulation example displays the performance of the obtained new results at the end of this paper. [ABSTRACT FROM AUTHOR]

In this paper, we design a natural scene text detection and recognition model based on deep learning by model construction and in-depth study of wild scene text detection and recognition. This paper proposes a scene text recognition method based on connection time classification and attention mechanism for the situation where natural scene text is challenging to recognize due to the high complexity of text and background. The method converts the text recognition problem in natural scenes into a sequence recognition problem, avoiding the drawback of overall recognition performance degradation due to the difficulty of character segmentation. At the same time, the attention mechanism introduced can reduce the network complexity and improve the recognition accuracy. The performance of the improved PSE-based text detection algorithm in this paper is tested on the curved text datasets SCUT-ctw1500 and ICDAR2017 in natural scenes for comparison. The results show that the proposed algorithm achieves 88.5%, 77%, and 81.3% in the three indexes of accuracy, recall, and F1 value, respectively, without adding the pre-training module. The algorithm can detect text in any direction well without adding the pre-training module; the improved text recognition algorithm based on CRNN in this paper is tested on the natural scene dataset ICDAR2017, and the results show that the accuracy rate reaches 94.5% under the condition of no constraint, which is a good performance. [ABSTRACT FROM AUTHOR]

As information technology expands across industries in the age of deep learning, companies face new changes in their credit assessment methods. One of the difficulties in financing food enterprises stems from the complexity of investment in reviewing enterprises' credit. Therefore, this paper proposes a deep learning-based credit prediction and evaluation model for food enterprises, which performs well on the dataset and achieves 85.73% and 88.56% accuracy in verifying the performance and default test samples, respectively. In addition, the model was confirmed to have good robustness through ablation experiments. Finally, the paper concludes with relevant recommendations for food companies based on the study's findings, offering new methods to improve their corporate credit assessment. [ABSTRACT FROM AUTHOR]

Image defect detection of casting parts is a key part of the production process in the machinery manufacturing industry. The traditional methods are ineffective because traditional computer image processing methods require a large number of manual features to be set artificially, and the detection time is too long. In order to save human resources and improve the efficiency of image defect detection, this paper proposes a deep learning-based defect detection method for automobile parts. This paper selects EfficientNetB0 as the backbone framework of the target detection network, which significantly reduces the memory usage of the model and shortens the model inference time, while improving the model detection accuracy. Facing the problem of small samples of defect image dataset, we analyze the image characteristics of the dataset and introduce shape transformation and scale scaling as the basic online data enhancement method according to the industrial field image projection law. Then, it is expected to combine the traditional image processing algorithms according to the characteristics of casting parts with different depth distribution and multiple morphological changes, and develop a special image defect data enhancement method. This further improves the performance of the model and increases the detection accuracy of the algorithm by 22.3% without increasing the data. [ABSTRACT FROM AUTHOR]

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]

With the rapid development of economic globalization, population, capital and information are rapidly flowing and clustering between regions. As the most important transportation mode in the high-speed transportation systems, airports are playing an increasingly important role in promoting regional economic development, yielding a number of airport economic promotion areas. To boost effective development management of these areas, accurate risk assessment through data analysis is quite important. Thus in this paper, the idea of ensemble learning is utilized to propose a big data-driven assessment model for supply chains in airport economic promotion areas. In particular, we combine two aspects of data from different sources: (1) national economic statistics and enterprise registration data from the Bureau of Industry and Commerce; (2) data from the Civil Aviation Administration of China and other multi-source data. On this basis, an integrated ensemble learning method is constructed to quantitatively analyze the supply chain security characteristics in domestic airport economic area, providing important support for the security of supply chains in airport economic area. Finally, some experiments are conducted on synthetic data to evaluate the method investigated in this paper, which has proved its efficiency and practice. [ABSTRACT FROM AUTHOR]

Due to the open-source and versatility of the Android operating system, Android malware has exploded, and the malware detection of Android IoT devices has become a research hotspot in recent years. Static analysis technology cannot effectively analyze obfuscated malware. Without decomposing, the existing detection methods are mainly based on grayscale images and single files without analyzing and verifying their anti-obfuscation performance. In addition, the current detection of Android malware using deep learning is concentrated in the field of binary classification. This paper proposes a multi-classification method of the Android malware family based on multi-class feature files and RGB images to solve these problems. The method proposed in this paper does not need to decompile the Android APK installation package. However, it extracts the DEX file and XML file in batch from the APK installation package. Then, it converts the file into an RGB image using the conversion algorithm that converts Android software into images. Finally, the deep neural network automatically obtains the RGB image texture features to realize the multiple classifications of the Android malware family. Experimental data show that the proposed method has high detection performance, and the accuracy of multiple classifications of the Android malware family is as high as 99.84%. In addition, the method based on RGB image is better than the grayscale image in detection accuracy, and the effect of RGB image combined with DEX and XML is better than that of separate DEX file image and separate XML file image. Therefore, the method proposed in this paper can effectively detect the obfuscated Android malware, and the detection accuracy of 99.23% can be achieved for the obfuscated sample data. Furthermore, this method has good anti-obfuscation ability. The proposed method is compared with those based on Multi-Layer Perceptron, Long Short-Term Memory, bidirectional Long Short-Term Memory and Deep Belief Network. The experimental results show the proposed method's effectiveness and high generalization performance. [ABSTRACT FROM AUTHOR]

Depression is a serious mood disorder that can significantly impact a person's ability to live a normal life. In severe cases, it can even lead to suicidal thoughts. As such, accurate detection of depression is crucial for effective management and treatment. This paper presents a facial expression-based approach for depression detection, which is composed of two steps. First, static features are extracted using Local Binary Pattern (LBP), Histogram of Oriented Gradients (HOG), and Bag of Words (BOW). Second, dynamic features are obtained by applying LBPs on Three Orthogonal Planes (LBP-TOP) and Eight Vertices LBP (EVLBP) frame by frame. Next, the static and dynamic features are combined to create a 1377-dimensional vector for each video. Finally, Gradient Boosting Regression is used to predict depression scores. The experimental results on the AVEC 2014 depression dataset (RMSE = 8. 6 5 , MAE = 6. 9 1) demonstrate the effectiveness of the proposed method. These results indicate that the low-dimensional vectors extracted by the proposed method can effectively capture the facial motion of individuals with depression, and also suggest that hand-crafted methods could have potential in depression detection. [ABSTRACT FROM AUTHOR]

Twin delayed deep deterministic (TD3) policy gradient has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment, due to the complexity of the robot path planning task, the rate of convergence of TD3 algorithm is slow and the rate of collision is high. To address this problem, deep dense dueling twin delayed deep deterministic (D3-TD3) architecture is proposed, a method that preserves important information from cross-layer inputs through dense connections and divides the network into a value function and a dominance function, thus, allowing for faster convergence when solving complex tasks. Finally, a spatial model based on three-dimension (3D) point cloud is built, and simulation experimental results show that in static environment, the algorithm proposed in the paper has 40.6% fewer collisions compared to TD3, 30% fewer collisions compared to TD3-BC, 19.2% fewer collisions compared to Dueling TD3 and 17.4% fewer collisions compared to deep dense TD3. In dynamic and static environment, the algorithm proposed in the paper has 34.4% fewer collisions compared to TD3, 24% fewer collisions compared to TD3-BC, 6% fewer collisions compared to Dueling TD3 and 25% fewer collisions compared to deep dense TD3. [ABSTRACT FROM AUTHOR]

In this paper, a method based on deep learning to detect abnormal traffic of IoTs in edge computing environment is proposed. Firstly, the data are preprocessed by data cleaning, normalization, oversampling and undersampling, and data set segmentation to obtain a data set with balanced data distribution. Secondly, a method of calculating feature information based on data increment is adopted, which can accurately extract feature information from the dynamic data flow. Finally, the convolution neural network (CNN) is used to extract the local features of the data, and the bi-directional gated loop unit (BiGRU) is used to extract the long sequence correlation of the data. The two networks work together to extract data features. The self-focus mechanism is introduced to deal with redundant data. Experiments show that the accuracy, recall and F 1 value of the proposed method are 97.36%, 98.38% and 97.16%, respectively, in the normal class, which are higher than the comparison algorithm. [ABSTRACT FROM AUTHOR]

The quantitative evaluation for communicable events has been a significant demand in digital society management. This paper takes the 2022 Winter Olympic Games as the object and proposes a quantitative evaluation method for the communication impact of sporting events based on the SIR dynamic diffusion model. Specifically, this study combinesa long short-term memory (LSTM) neural network, wavelet packet decomposition, and other techniques to propose a digital evaluation approach for the quantification of communication impact. Among these, the transfer probability is quantified and calculated by the user node reputation value algorithm. In the experimental simulation, the effects of different mechanisms of joining consensus nodes and blockchain on the propagation probability in the model are discussed, respectively. Some simulation experiments are conducted on the real-world scenes of social networks, and the simulation results show that the number of nodes spreading false information is reduced by 9.89% compared with baseline methods. Finally, a sports event communication effect evaluation index system was constructed, and the data characteristics of indicators at all levels were analyzed to preliminarily predict the communication effect, after which the fuzzy hierarchical comprehensive evaluation method, combined with the expert survey method, was used to empirically evaluate, and test the communication effect of its events. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth research analysis on the evaluation of the development quality of regional economy through an improved convolutional neural network algorithm, and uses it to design a fuzzy comprehensive evaluation model for the practical process. Based on the measured indices of different variables, a spatial econometric model is constructed and provincial panel data are selected to empirically analyze the impact and spatial spillover effects of financial agglomeration and technological innovation on regional economic quality development from both static and dynamic aspects and to examine the spatial correlation of the factors. A new serial data flow model is adopted, which optimizes the control of data flow in convolutional computation, reduces the percentage of clock cycles used to read memory data, and increases the computational efficiency. At the same time, with dynamic data caching, a convolutional computation can be completed in one clock cycle, reducing the memory capacity required for caching intermediate data. The effectiveness of the evaluation system constructed in this paper is further tested. Most of the indicators have a significant positive or negative impact on the quality level of economic development, and the direction of the impact is consistent with the positive and negative attributes of the indicators in this study, which verifies the validity of the evaluation indicator system constructed in this paper. In summary of the study, effective suggestions are made in terms of human capital investment, reasonable allocation of fiscal expenditure, enhancing regional greening development and improving risk prevention measures. [ABSTRACT FROM AUTHOR]

Aiming at the low accuracy of the track signal intrusion detection (IDe) algorithm in the traditional cloud-side collaborative computing environment, this paper proposes a deep learning (D-L)-based track signal IDe method in the cloud edge collaborative computing environment. First, the main framework of the IDe method is constructed by comprehensively considering the backbone network, network transmission and ground equipment, and edge computing (EC) is introduced to cloud services. Then, the The CNN (Convolutional Neural Networks)-attention-based BiLSTM (Bi-directional Long Short-Term Memory) neural network is used in the cloud center layer of the system to train the historical data, a D-L method is proposed. Finally, a pooling layer and a dropout layer are introduced into the model to effectively prevent the overfitting of the model and achieve accurate detection of track signal intrusion. The purpose of introducing the pooling layer is to accelerate the model convergence, remove the redundancy and reduce the feature dimension, and the purpose of introducing the dropout layer is to prevent the overfitting of the model. Through simulation experiments, the proposed IDe method and the other three methods are compared and analyzed under the same conditions. The results show that the F1 value of the method proposed in this paper is optimal under four different types of sample data. The F1 value is the lowest of 0.948 and the highest of 0.963. The performance of the algorithm is better than the other three comparison algorithms. The method proposed in this paper is important for solving the IDe signal in the cloud-edge cooperative environment, and also provides a theoretical basis for tracking the signal IDe direction. [ABSTRACT FROM AUTHOR]

The real-time monitoring and detection of the fruit carrying for monorail transporter in the mountain orchard are significant for the transporter scheduling and safety. In this paper, we present a fruit carrying monitoring system, including the pan-tilt camera platform, AI edge computing platform, improved detection algorithm and the web client. The system used a pan-tilt camera to capture images of the truck body of the monorail transporter, realizing monitoring of fruit carrying. Besides, we present an improved fruit carrying detection algorithm based on YOLOv5s, taking the "basket", "orange" and "fullbasket" as the object. We introduced the improved attention mechanism E-CBAM (Efficient-Convolutional Block Attention Module) based on CBAM, into the C3 module in the neck network of YOLOv5s. Focal loss was introduced to improve the classification and confidence loss to improve detection accuracy; to deploy the model on the embedded platform better, we compressed the model through the EagleEye pruning algorithm to reduce the parameters and improve the detection speed. The experiment was performed on the custom fruit-carrying datasets, the mAP was 91.5%, which was 9.6%, 9.9% and 12.0% higher than that of Faster-RCNN, RetinaNet-Res50 and YOLOv3-tiny, respectively, and detection speed at Jetson Nano was 72 ms/img. The monitoring system and detection algorithm proposed in the paper can provide technical support for the safe transportation of monorail transporter and scheduling transportation equipment more efficiently. [ABSTRACT FROM AUTHOR]

In the Internet of Things (IoT) era, an immense amount of sensing devices are obtained and produce various sensory data over time for a wide range of disciplines and applications. These devices will result in significant, fast, and real-time data streams based on the utilization characteristics. Utilizing analytics over such data streams to identify new information, model future insights, and make control decisions is a necessary process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. This paper presents a study of digital agriculture and its significance in terms of the application of an IoT-based device — a two-wheeled self-balancing robot — followed by a thorough procedural explanation of the development of the device, which begins with the mathematical modeling of the system through the Euler–Lagrange method to obtain the equations of motion for the same and linearize the equation to define the control method to be used to balance the robot structure, all based on the concept of the inverted pendulum. Then paper discusses the suitable and the most efficient control method, which is the linear quadratic regulator (LQR), for these robots. Then deep learning-based LQR (DL-LQR) method is implemented in the robots performing the algorithm to balance it successfully. [ABSTRACT FROM AUTHOR]

The development of young people's physique and health is the core element of national manpower reserves, which is related to the rise and fall of national power in the future. In recent years, a large-scale physical fitness test for students has been carried out by the state every year; thus, abundant data have been accumulated. However, for a long time, the collection, integration, analysis and utilization of these data resources have been seriously insufficient; thus, it is difficult to meet the needs of student health services. Wireless devices are emerging rapidly due to their sensing, computing and communication capabilities and are gradually being applied to physique and health research. This is expected to improve the traditional service model. Personalized physique and health information of students can be obtained via wearable devices. However, to effectively analyze and utilize these data and improve the effectiveness of corresponding health management decisions, intelligent analysis methods are needed. Machine learning, as the core of artificial intelligence technology, can learn from big data and mine the potential value of data in order to predict events and propose countermeasures. This paper aims to collect and transmit various kinds of physique and health data of students through wireless communication technology and to realize intelligent analysis and management of these data based on a machine learning algorithm. [ABSTRACT FROM AUTHOR]

With the rapid development of Internet technology, people can learn all kinds of travel information anytime and anywhere. However, the serious information overload causes travelers to be unable to make accurate and reasonable travel routes that meet tourists' tastes for a while, thus reducing the quality of travel. The recommendation system as the mainstream solution to the information explosion of two means has received the attention of the majority of scholars and industry. Based on the research theory of tourist route recommendation, this paper analyzes the characteristics of attractions, factors affecting travelers' travel experience when touring attractions and factors affecting travelers' travel experience along tourist routes. Furthermore, we propose a tourist route recommendation model that meets tourists' preferences. Then, this paper uses the graph neural network (GNN) algorithm to build a framework for tourist route recommendations based on the GNN using the relationship of preference and commonality existing among groups, tourists and attractions. The GNN algorithm is optimized and improved using multiple graphs and an attention mechanism. Finally, the effectiveness of this paper's algorithm is verified by conducting experiments on different data sets. [ABSTRACT FROM AUTHOR]

Digital notch filters are useful for removing sinusoidal signals with a single frequency or multi-frequencies. For some applications, the sinusoidal signals being processed may change frequencies, and thus the notch filter must also have a variable notch frequency. Such a digital filter with a variable notch-frequency (VNF) is called variable notch-frequency (VNF) digital filter. Generally speaking, a VNF filter has the ability to change its notch frequency continuously, and can remove sinusoidal signals with variable frequencies. To design a recursive VNF filter, guaranteeing its stability is the top-priority issue. In this paper, a recursive VNF filter is designed by utilizing the least Lp-norm criterion, and the stability is guaranteed through adopting the stability-guarantee methodology based on parameter transformations. To perform the parameter transformations, a function that meets a special condition is required, and such a function is called unity-bounded function. In this paper, various unity-bounded functions are developed for the parameter-transformation-based stability guarantee. The unity-bounded functions play a crucial role in the stability guarantee. This paper details how to design a stable VNF filter by incorporating the parameter transformations employing the unity-bounded functions into the Lp-norm minimization of the magnitude response. Theoretically, the stability of the recursive VNF filter resulting from the design is definitely guaranteed. Moreover, since the coefficients of the designed VNF are variable, changing the filter coefficients enables the user to get a VNF filter with updated notch frequency. [ABSTRACT FROM AUTHOR]

Sense amplifier is a key element of memory and a CMOS-based spin hybrid circuit. Magnetic tunnel junction (MTJ) is a key spintronic device used in spin-based memory and hybrid circuits. This paper presents a design of a voltage-controlled magnetic anisotropy MTJ-based sense amplifier (VCMA-SA) that offers better reliability, power efficiency and high-speed performance. MTJ switching between different resistive states in this paper takes place through the faster and energy-efficient voltage-controlled magnetic anisotropy (VCMA) scheme rather than the traditional spin-transfer torque (STT)-based magnetization switching. This paper demonstrates that SA based on VCMA-MTJ switching is faster, reliable and more energy-efficient compared with iPMA-based STT switching. [ABSTRACT FROM AUTHOR]

In this paper, an improved voltage-mode constant on-time (COT) control DC–DC buck converter is designed, which makes the DC–DC buck converter have good stability. Firstly, an improved compensation scheme is introduced through the analysis and derivation of the traditional voltage-mode COT controlled buck converter model. Then, according to the application requirements of the design, Simplis software modeling is used to verify the correctness of the theoretical analysis. The 0.13 μ m BCD technology is used to tape out the DC–DC converter of the improved voltage mode COT. The input voltage is 3.7–5.5 V and the output voltage is 3.3 V. The chip test mainly includes heavy-load condition in CCM operation, light-load condition in DCM operation, and load transient response. The test results show that the chip can remain stable under heavy-load and light-load conditions. The overshoot and undershoot in transient response can be quickly restored to steady state during the recovery process. Finally, compared with chips of the same type, it shows that the DC–DC chip for portable electronic equipment designed in this paper adopts an internal compensation structure, which has good stability, simple design, small main chip area, simple peripheral equipment, and good application value. [ABSTRACT FROM AUTHOR]

In this paper, the fuzzy neural network model is studied, the real-time regulation model of physical training intensity is analyzed and a real-time regulation system based on a fuzzy neural network is designed. The real-time, accurate and effective regulation of the physiological load intensity in the body of the exerciser is consistent with the predetermined goals of the training program. In this paper, we propose an RBF neural network, combined with the plan and demand of physical training operation situation sensing, and considering that most of the biological training operation data is fuzzy, this paper connects a fuzzy logic inference system and a neural network and proposes a network operation situation sensing model based on an RBF neural network structure. The RBF neural network and the traditional fuzzy neural network are compared. The experiments prove that this paper's fuzzy neural network model has a faster training speed. In this paper, we use time-realistic control equipment to monitor the physical training process of athletes so that we can grasp the training situation of athletes in real-time and ensure that athletes can achieve better training results by changing training methods and changing training loads in time for those athletes who cannot reach their sports goals. In the process of physical fitness training monitoring, an effective monitoring of training, time-accurate regulation monitoring has the advantage of timely feedback on the training situation. This model has a better convergence effect during exercise and a higher accuracy of posture prediction during testing. [ABSTRACT FROM AUTHOR]

A single-inductor multiple-input multiple-output converter is proposed in this paper that can be used in low-power systems due to low output current and voltage. This converter is implemented discretely, and only one microcontroller is employed to control the system. The unique zero-current switching (ZCS) technique considered in this paper is such that only by reading the inductor's left-side voltage the optimal value of the inductor discharge duty cycle is determined. This method can be generalized to low-power and high-power converters, whether implemented and designed as discrete or integrated. This converter works in discontinuous conduction mode. It uses pulse width modulation control and the time-multiplexing control method, which makes the system have high efficiency and makes the cross-regulation problem between the converter's outputs tiny. The control algorithm considered in this converter is digital, which determines the optimal charge and discharge duty cycles. Also, the switching frequency of this converter is constant, relatively low, and equal to 5 kHz. The efficiency of this converter has reached 91.6% by using the ZCS technique and other mentioned control methods. [ABSTRACT FROM AUTHOR]

In the electricity business, power evacuation from source to load is a challenging task when there is contingency and agencies have to swirl around for solutions in terms of rescheduling generator dispatch, load slashing, adding of network, etc. The more challenging scenario arises when the independent operator wants to re-dispatch a generator during the contingent situation. So, in this paper, we focus on a new generator rescheduling technique with congestion price and transmission security as an intervention. The significant intention of this paper involves restricting the load thereby dispatching a particular generator or a set of generators with low cost and secure transmission line. In addition to this, the network jamming is unpredictable and does not follow any pattern, but power supply in some zones is disrupted due to hidden reasons. Therefore, a macroscopic or holistic approach is adopted for congestion forecasting through demand schedule, gathering, minimum as well as maximum drawls. Here, two significant factors namely the transmission utilization charges as well as transmission congestion charges for predicting the congestion of a transmission line are evaluated. Finally, the experimental analysis to determine transmission utilization charges, transmission congestion charges, cost function and generation supply as well as demand balance with congestion optimization. [ABSTRACT FROM AUTHOR]

Considering the continuous development of the film industry and the improvement of the living standard among people, movies have gradually come to the civilians. A good movie poster can effectively reflect the content of the movie, attract the audience, stimulate the demand and achieve a good publicity effect. The current movie poster design work is mainly carried out by professional designers, which requires a lot of time and labor cost. In this paper, we propose a context-aware image generation method for assisted design of movie posters using generative adversarial network (named as MPAD-CIP for short). First, the basic information and visual contents of the movie are perceived, and the representative images are extracted, with the use of convolution operations. Then, a backbone network of deep convolutional generative neural network is formulated to generate images for summary of movies. The backbone network is composed of two components: a generator and a discriminator. Their combination realizes the computer-assisted movie poster design by sensing visual context. In the experimental part, the proposed MPAD-CIP method is compared with several benchmark models to demonstrate that the posters generated by this paper are more realistic and versatile, and some of the generated posters are exhibited. [ABSTRACT FROM AUTHOR]

The object of this paper is to introduce a new CMOS differential input single output (DISO) transconductor (realizable from eight MOSFETs operating in saturation) and a dual input dual output (DIDO) transconductor (realizable with 16 MOSFETs operating in saturation) and their applications in realizing grounded/ floating, positive/ negative, electronically controllable resistors and inductors. The workability of all the prepositions has been demostrated by SPICE simulations using TSMC 0.18 μ m CMOS technology parameters. The paper, thus, adds a number of useful electronically-controllable circuits to the existing repertoire of CMOS analog circuits for signal processing. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) faces many security and privacy risks due to the large number of devices accessing the network while providing convenience to the current society. At present, the management of IoT devices is centralized. All terminal devices are managed in a centralized manner, and the data accessing IoT devices can only be connected to the network with the permission of the centralized nodes. In this scenario, the increase in the amount of equipment can cause central node overload or single node failure. Moreover, flexible expansion requirements are difficult to achieve in such a centralized architecture. This paper proposes a safe and efficient IoT device recognition and management scheme based on blockchain and edge computing, DRMT. This scheme realizes feature extraction, clustering, and learning of IoT devices' traffic based on the characteristics of distributed deployment of edge servers. In this process, the recognition model can be continuously updated. The scheme also has an advantage that it is possible to enhance the management efficiency and scalability of the system by establishing a blockchain network between edge servers to share identification information and automate deployment security. This paper also verifies the scheme's effectiveness by building an experimental network and a blockchain system. The results showed that DRMT would help realize the effective management of large-scale IoT devices in smart cities. [ABSTRACT FROM AUTHOR]

The prevention and control of communicable diseases such as COVID-19 has been a worldwide problem, especially in terms of mining towards latent spreading paths. Although some communication models have been proposed from the perspective of spreading mechanism, it remains hard to describe spreading mechanism anytime. Because real-world communication scenarios of disease spreading are always dynamic, which cannot be described by time-invariant model parameters, to remedy such gap, this paper explores the utilization of big data analysis into this area, so as to replace mechanism-driven methods with big data-driven methods. In modern society with high digital level, the increasingly growing amount of data in various fields also provide much convenience for this purpose. Therefore, this paper proposes an intelligent knowledge discovery method for critical spreading paths based on epidemic big data. For the major roadmap, a directional acyclic graph of epidemic spread was constructed with each province and city in mainland China as nodes, all features of the same node are dimension-reduced, and a composite score is evaluated for each city per day by processing the features after principal component analysis. Then, the typical machine learning model named XGBoost carries out processing of feature importance ranking to discriminate latent candidate spreading paths. Finally, the shortest path algorithm is used as the basis to find the critical path of epidemic spreading between two nodes. Besides, some simulative experiments are implemented with use of realistic social network data. [ABSTRACT FROM AUTHOR]

Nowadays, almost all of the enterprises are facing resources and materials with multimodal format. For example, textual information can be mixed with visual scenes, and visual information can be also mixed with textual scenarios. As a result, such information fusion among multimodal materials costs a large amount of human labors in daily management affairs. To deal with such issue, this paper introduces deep learning to characterize gap between vision and texts, and proposes a deep learning-based multimodal resource reconstruction scheme via awareness of table document, so as to facilitate digital enterprise management. A deep neural network is developed to construct a method to automatically extract table texts from images, so that multimodal information fusion can be realized. This can reduce much human labor in recognizing textual characteristics from visual scenarios, which can further facilitate the resource dispatching activities in the process of digital enterprise management. Some experiments are also conducted upon the basis of real-world data set, and proper results are obtained to prove that the proposal is endowed with considerable efficiency. [ABSTRACT FROM AUTHOR]

There are problems of low model detection accuracy, low detection speed and difficulty in deploying online inspection in industrial surface defect detection relying on deep learning object detection algorithms. In order to effectively solve this problem, an efficient channel attention-enhanced lightweight neural network model named as EMV2-YOLOX is proposed in this paper. The algorithm incorporates the ECA module into the lightweight backbone extraction network MobileNetV2 to achieve adaptive adjustment of channel information weights, which can improve the extraction capability of the algorithm. The YOLOX model is also introduced to enhance the model's identification and localization of tiny defects. The improved algorithm can guarantee the model's accuracy and improve the model detection performance, as well as the carrying capacity of hardware devices. The experimental results show that the highest accuracy is achieved on the GCT10 and NEU public defect datasets with mean Average Precision values of 0.86 and 0.68, respectively, which is higher than the accuracy of the EMV2yoloV4 model. The parametric model number is only 10.24 M in size, and the detection rate is 54.25 f/s, which is the highest performance in embedded devices. EMV2-YOLOX, combined with the attention mechanism, can efficiently extract the location and semantic information of hard-to-detect defects and plays a vital role in the intelligent detection methods. [ABSTRACT FROM AUTHOR]

With the development of emerging information technology, the traditional management methods of marine fishes are slowly replaced by new methods due to high cost, time-consumption and inaccurate management. The update of marine fishes management technology is also a great help for the creation of smart cities. However, some new methods have been studied that are too specific, which are not applicable for the other marine fishes, and the accuracy of identification is generally low. Therefore, this paper proposes an ecological Internet of Things (IoT) framework, in which a lightweight Deep Neural Networks model is implemented as a image recognition model for marine fishes, which is recorded as Fish-CNN. In this study, multi-training and evaluation of Fish-CNN is accomplished, and the accuracy of the final classification can be fixed to 89.89%–99.83%. Moreover, the final evaluation compared with Rem-CNN, Linear Regression and Multilayer Perceptron also verify the stability and advantage of our method. [ABSTRACT FROM AUTHOR]

Microwave hyperthermia is a new method of treating cancer, where the therapeutic effect is determined by the heating temperature. Traditional active temperature sensors are interfered by high frequency so that the accuracy of temperature measurement cannot be guaranteed. It is of great significance to study the high-precision fluorescent optical fiber temperature sensor with complete insulation. This paper has realized a compact and practical fluorescent optical fiber temperature sensor after studying the optical path, circuit, data processing algorithm. In order to improve the accuracy of the system, the weighted linear least-squares fitting algorithm is improved in this paper. Through experimental tests, compared with the standard linear least-squares fitting algorithm and the unimproved weighted linear least-squares fitting algorithm, the accuracy of the algorithm is improved by about 98% and 65.5%, respectively. In addition, the response time is reduced by about 36.5%, compared with the unimproved weighted linear least-squares fitting algorithm. This algorithm fully meets the precision requirements of microwave hyperthermia. [ABSTRACT FROM AUTHOR]

This paper proposes a novel hybrid technique for enhancing power quality (PQ) in distributed generation (DG) systems by deploying a unified power quality conditioner (UPQC). Here, the proposed hybrid method is the joint execution of white shark optimizer (WSO) and recalling-enhanced recurrent neural network (RERNN), called the WSO-RERNN technique. The primary objective of this novel approach is to effectively mitigate voltage sag and reduce voltage harmonics under varying load conditions. It is important to investigate the voltage sag, swell and harmonic distortion of the system to obtain an enhanced PQ of the energy supply. Therefore, this paper shows the brief impact of PQ in DG utilizing the proposed unified PQ conditioner controller. The WSO-RERNN control technique enhances the performance of the UPQC controller by providing the optimal control signal. By then, the efficiency of the proposed approach is done in MATLAB, and the performance is compared with those of existing optimization techniques, including Ant Lion Optimizer (ALO), Grey wolf optimization (GWO) and Salp swarm algorithm (SSA) methods. [ABSTRACT FROM AUTHOR]

As a widely used equation in electrostatics, the Poisson equation has significant research value in numerical solution. The basic principle of existing methods is to divide the solution domain into various grids and solve the numerical solutions at each grid node. Therefore, the accuracy of the solution is strongly correlated with the grid density divided. Based on this, this paper proposes a grid-free numerical calculation method that requires far fewer model parameters than traditional methods, and can ignore the order of the equation to solve high-dimensional Poisson equations. Given a Poisson equation, which has a certain type of boundary condition. A certain number of coordinate points are selected on the solution space and its boundary to construct a dataset. Using automatic differentiation technique to fit the differential operator in the equation, a loss function is constructed by incorporating the given boundary conditions or initial conditions, and the final numerical solution is obtained through iterative optimization algorithms. In the numerical experiment section, the algorithm proposed in this paper was used to solve the two-dimensional and three-dimensional Poisson equations with given exact solutions. The relative errors between the numerical solution and the true solution were 8. 5 3 e − 4 and 6. 4 0 e − 2 , which are within the acceptable range. This proves that the proposed algorithm is feasible for solving the two-dimensional and three-dimensional Poisson equations with precise solutions. Secondly, the proposed algorithm is used to solve the four-dimensional Poisson equation with first-type boundary conditions, and the relative error range of the solution was within [0,0.56], which successfully extends the algorithm to solve high-dimensional Poisson equations and verifies its feasibility and efficiency in solving high-dimensional Poisson equations regardless of the dimension restriction. [ABSTRACT FROM AUTHOR]

The widespread adoption of e-commerce has rendered online reviews an indispensable source for acquiring knowledge about product features. The Kano model serves as a classic framework for categorizing customer requirements. It was proposed by the Japanese scholar Noriaki Kano in 1984 as a tool primarily used to help businesses better understand and categorize customer needs, guiding product development and service quality improvement. However, existing research on mining online review information often relies predominantly on static analysis, lacking comprehensive categorization of user demands. To address this gap, this paper introduces an enhanced Kano model for the identification and dynamic analysis of user demands. This model classifies review data based on emotional polarity and user attention, leveraging the characteristics inherent in online reviews. Furthermore, it constructs a user demand evolution model using time series analysis and utilizes SnowNLP for emotional calculations. By conducting word frequency statistics and employing LDA models to analyze product features, this paper identifies the evolving trends in user demands. Additionally, the exponential smoothing method is used to forecast the trend in users’ emotional values towards the product. The findings demonstrate that this model effectively extracts valuable insights regarding product feature information from user reviews, thereby offering novel perspectives and methodologies for related fields. Consequently, this contributes significantly to advancing the identification and dynamic analysis of user demands. [ABSTRACT FROM AUTHOR]

This paper takes the wind turbine of the new energy pumping unit as the study subject, which mainly analyzes realistic wind speed estimation on the windward side of the wind turbine and then proposes a wind turbine speed control method based on wind speed estimation. The support vector regression (SVR) model is built first in this study, and the parameters of the SVR model are optimized by the particle swarm algorithm. The SVR II wind speed prediction model is constructed and the working characteristic curve of the wind turbine is generated by gathering wind speed and output power data from the wind turbine at the assigned test location. The prediction model can compensate for the disturbance of system inertia and make the output wind speed more accurate. The effective wind speed acting on the turbine surface can be obtained by substituting the predicted wind speed into the optimal blade tip velocity ratio equation. Suppose the wind turbine is in maximum power tracking control. In that case, the optimal speed can be given directly by the model SCR III, and the speed can be tracked in real-time by the controller to accomplish the largest wind power capture. The optimal speed tracking control uses the calculated effective wind speed if the wind turbine is under constant power output control. In this paper, 14,000 sets of characteristic samples were extracted within the range of wind speed variation of 4–20 m/s, and model verification was carried out for models SVR-I, SVR-II and SVR-III. Finally, the predicted effective wind speed value and the actual value are within ±0.3 m/s of each other. In practical engineering applications, the forecasted effective wind speed value can entirely substitute the actual value. This work put forward a maximum power tracking control approach that can satisfy new energy pumping units' energy conservation needs. [ABSTRACT FROM AUTHOR]

This paper proposes a new dielectrically modulated (DM) twin cavity nanotube biosensor and its sensitivity evaluation suitability by the transit time (τ) and device efficiency (g m / I ds ). In addition, the vertical structure of the device also helps the uniform spreading of biomolecules within the nanogap cavity region. The inner cavity of the proposed biosensor offers more space for the stabilization of biomolecules and uses the benefits of material solubility. In this paper, the sensing ability of the biosensor is examined in terms of τ and g m / I ds for five neutral biomolecules. Furthermore, the charged biomolecule and deoxyribonucleic acid (DNA) are separately investigated for positive as well as negative charge densities. Also, various optimizations on the device are analyzed for different biomolecules in this paper. [ABSTRACT FROM AUTHOR]

In this paper, the linear active disturbance rejection control (LADRC) is applied to the position control of a dicing saw chuck table, which is used to improve the steady-state accuracy and anti-interference ability of the control system. Aiming at the problem that LADRC parameters are difficult to adjust, a parameter adjustment method based on an improved sand cat swarm algorithm is proposed. The nonlinear convergence factor strategy and multiple chaotic map optimization strategy are used to improve the algorithm. In order to verify the performance of the proposed method, the improved sand cat swarm optimization algorithm is compared with the standard sand cat swarm optimization algorithm, grey wolf optimization algorithm and salp swarm optimization algorithm. The final experimental results show that using the improved sand cat swarm optimization algorithm to optimize the LADRC controller has higher steady-state accuracy, stronger anti-interference ability, and better optimization results. [ABSTRACT FROM AUTHOR]

In this paper, an example of an intelligent security system based on deep learning approach has been analyzed and described. Security is an important element in many aspects of human life. Depending on customer requirements, different levels of security may be required and implemented. Nowadays, artificial intelligence is becoming an indispensable part in many areas of human life and accordingly security systems are also based on the new achievements in this field. In this paper, an intelligent security system based on two methods for identifying persons, gait recognition and face recognition, was described. The two methods mentioned above can be used to give persons access to different buildings, facilities, institutions, etc. or to different indoor or outdoor areas. In light of the above, the aforementioned system uses face and gait recognition to identify persons who should be granted access to a facility or a specific area within the facility. Accordingly, two deep learning models for gait and face recognition have been developed and described. The analysis, the settings defined and the results obtained in relation to the models developed were also described. [ABSTRACT FROM AUTHOR]

The increasing demand for low voltage, power efficient, high-speed analog-to-digital converters (ADCs) results in the improvement of speed and power of regenerative dynamic comparator. In this paper, a dual-tail dynamic comparator is used with two extra transistors in the latch stage. These extra transistors help in the increase of transconductance of the latch stage, which helps decrease the delay of the proposed comparator. Mathematical analysis is done for the proposed architecture; this gives the idea of reducing the delay of the comparator with an increase in the transconductance of the comparator. The simulation and layout of the proposed comparator are done on the Cadence software with 90 nm CMOS technology. This proposed design is simulated with a 2 GHz clock frequency at supply voltage of 1 V. The proposed architecture consumes a power of 39.19 μ W and a delay of 143.12 ps at 1 V supply voltage, 5 mV input difference voltage and 0.9 V common mode voltage. The Monte Carlo simulation of the proposed architecture for power, delay, power delay product (PDP) and offset is also demonstrated in this paper. Process corner analysis is done for power, delay and PDP. [ABSTRACT FROM AUTHOR]

Due to the complex underground environment of coal mines, the unsafe behaviors of miners are likely to lead safety accidents. Therefore, research on underground abnormal behavior recognition methods based on video images is gradually gaining attention. This paper proposes an underground abnormal behavior recognition method based on an optimized Alphapose-ST-GCN. First, an image set captured in underground monitoring video is defogged and enhanced by the CycleGAN. Second, the Alphapose target detection is optimized using the LTWOA-Tiny-YOLOv3 model. Third, the ST-GCN is used for abnormal behavior recognition. The image quality of the dataset before and after a CycleGAN enhancement is compared, the convergence curves of LTWOA under four test functions are compared, and the mean average accuracy mAP of the LTWOA-Tiny-YOLOv3 model is evaluated. Finally, the performance of the proposed method is compared with other detection algorithms. The results show that CycleGAN significantly improves the quality of the dataset images. The whale optimization algorithm improved by the logistic-tent chaos mapping has a more significant convergence effect than the other optimization algorithms, and the LTWOA-Tiny-YOLOv3 model has a better recognition accuracy of 9.1% in mAP compared with the unoptimized model. The underground abnormal detection model proposed in this paper achieves an 82.3% accuracy on the coal mine underground behavior dataset. [ABSTRACT FROM AUTHOR]