Search

The stratospheric airship, as a near-space vehicle, is increasingly utilized in scientific exploration and Earth observation due to its long endurance and regional observation capabilities. However, due to the complex characteristics of the stratospheric wind field environment, trajectory planning for stratospheric airships is a significant challenge. Unlike lower atmospheric levels, the stratosphere presents a wind field characterized by significant variability in wind speed and direction, which can drastically affect the stability of the airship's trajectory. Recent advances in deep reinforcement learning (DRL) have presented promising avenues for trajectory planning. DRL algorithms have demonstrated the ability to learn complex control strategies autonomously by interacting with the environment. In particular, the proximal policy optimization (PPO) algorithm has shown effectiveness in continuous control tasks and is well suited to the non-linear, high-dimensional problem of trajectory planning in dynamic environments. This paper proposes a trajectory planning method for stratospheric airships based on the PPO algorithm. The primary contributions of this paper include establishing a continuous action space model for stratospheric airship motion; enabling more precise control and adjustments across a broader range of actions; integrating time-varying wind field data into the reinforcement learning environment; enhancing the policy network's adaptability and generalization to various environmental conditions; and enabling the algorithm to automatically adjust and optimize flight paths in real time using wind speed information, reducing the need for human intervention. Experimental results show that, within its wind resistance capability, the airship can achieve long-duration regional station-keeping, with a maximum station-keeping time ratio (STR) of up to 0.997. [ABSTRACT FROM AUTHOR]

Hole detection is an important means of crack detection for aero-engine blades, and the current technology still mainly relies on manual operation, which may cause safety hazards for visual reasons. To address this problem, this paper proposes a deep learning-based, aero-engine blade crack detection model. First, the K-means++ algorithm is used to recalculate the anchor points, which reduces the influence of the anchor frame on the accuracy; second, the backbone network of YOLOv5s is replaced with Mobilenetv3 for a lightweight design; then, the slim-neck module is embedded into the neck part, and the activation function is replaced with Hard Sigmoid for redesign, which improves the accuracy and the convergence speed. Finally, in order to improve the learning ability for small targets, the SimAM attention mechanism is embedded in the head. A large number of ablation tests are conducted in real engine blade data, and the results show that the average precision of the improved model is 93.1%, which is 29.3% higher; the number of parameters of the model is 12.58 MB, which is 52.96% less, and the Frames Per Second (FPS) can be up to 95. The proposed algorithm meets the practical needs and is suitable for hole detection. [ABSTRACT FROM AUTHOR]

Salient object detection (SOD) aims to identify the most visually striking objects in a scene, simulating the function of the biological visual attention system. The attention mechanism in deep learning is commonly used as an enhancement strategy which enables the neural network to concentrate on the relevant parts when processing input data, effectively improving the model's learning and prediction abilities. Existing saliency object detection methods based on RGB deep learning typically treat all regions equally by using the extracted features, overlooking the fact that different regions have varying contributions to the final predictions. Based on the U2Net algorithm, this paper incorporates the split coordinate channel attention (SCCA) mechanism into the feature extraction stage. SCCA conducts spatial transformation in width and height dimensions to efficiently extract the location information of the target to be detected. While pixel-level semantic segmentation based on annotation has been successful, it assigns the same weight to each pixel which leads to poor performance in detecting the boundary of objects. In this paper, the Canny edge detection loss is incorporated into the loss calculation stage to improve the model's ability to detect object edges. Based on the DUTS and HKU-IS datasets, experiments confirm that the proposed strategies effectively enhance the model's detection performance, resulting in a 0.8% and 0.7% increase in the F1-score of U2Net. This paper also compares the traditional attention modules with the newly proposed attention, and the SCCA attention module achieves a top-three performance in prediction time, mean absolute error (MAE), F1-score, and model size on both experimental datasets. [ABSTRACT FROM AUTHOR]

This paper aims to develop a new model of Project-Based Instructional Taxonomy (PBIT) that provides a tool of course design that facilitates Computational Thinking (CT) development as creative action in solving real-life problems. Theoretically, PBIT is built on an integrative framework bringing together with studies on CT education, creativity, Bloom's Taxonomy, and Project-Based Instruction (PBI). This guides the course design to make alignment between diverse elements including education objectives, categories of CT, levels of learning ability, process of project facilitation, and methods of grading. A case will be discussed that focuses on a course Deep Learning and Technologies in AI bachelor program at Northeastern University (NEU) in China. It also shows how PBIT is applied in teaching practice that benefits students' CT development. As the conclusion indicates, this paper has contributions to future research on creativity, PBI, CT, and AI education. [ABSTRACT FROM AUTHOR]

As globalization accelerates, the linguistic diversity and semantic complexity of in-vehicle communication is increasing. In order to meet the needs of different language speakers, this paper proposes an interactive attention-based contrastive learning framework (IABCL) for the field of in-vehicle dialogue, aiming to effectively enhance cross-lingual natural language understanding (NLU). The proposed framework aims to address the challenges of cross-lingual interaction in in-vehicle dialogue systems and provide an effective solution. IABCL is based on a contrastive learning and attention mechanism. First, contrastive learning is applied in the encoder stage. Positive and negative samples are used to allow the model to learn different linguistic expressions of similar meanings. Its main role is to improve the cross-lingual learning ability of the model. Second, the attention mechanism is applied in the decoder stage. By articulating slots and intents with each other, it allows the model to learn the relationship between the two, thus improving the ability of natural language understanding in languages of the same language family. In addition, this paper constructed a multilingual in-vehicle dialogue (MIvD) dataset for experimental evaluation to demonstrate the effectiveness and accuracy of the IABCL framework in cross-lingual dialogue. With the framework studied in this paper, IABCL improves by 2.42% in intent, 1.43% in slot, and 2.67% in overall when compared with the latest model. [ABSTRACT FROM AUTHOR]

In steel production, defect detection is crucial for preventing safety risks, and improving the accuracy of steel defect detection in industrial environments remains challenging due to the variable types of defects, cluttered backgrounds, low contrast, and noise interference. Therefore, this paper introduces a steel surface defect detection model, DBCW-YOLO, based on YOLOv5. Firstly, a new feature fusion strategy is proposed to optimize the feature map fusion pair model using the BiFPN method to fuse information at multiple scales, and CARAFE up-sampling is introduced to expand the sensory field of the network and make more effective use of the surrounding information. Secondly, the WIoU uses a dynamic non-monotonic focusing mechanism introduced in the loss function part to optimize the loss function and solve the problem of accuracy degradation due to sample inhomogeneity. This approach improves the learning ability of small target steel defects and accelerates network convergence. Finally, we use the dynamic heads in the network prediction phase. This improves the scale-aware, spatial-aware, and task-aware performance of the algorithm. Experimental results on the NEU-DET dataset show that the average detection accuracy is 81.1, which is about (YOLOv5) 6% higher than the original model and satisfies real-time detection. Therefore, DBCW-YOLO has good overall performance in the steel surface defect detection task. [ABSTRACT FROM AUTHOR]

In this era of intelligence, the learning methods of learners have substantially changed. Many learners choose to learn through online education platforms. Although learners may enjoy more high-quality educational resources, when they are faced with an abundance of resource information, they are prone to become lost in knowledge, among other problems. To solve this problem, a multi-algorithm collaborative, personalized, learning path recommendation model is proposed to provide learning guidance for learners of online learning platforms. First, the learner model is constructed from four perspectives: cognitive level, learning ability, learning style, and learning intensity. Second, the association rule algorithm is employed to generate a sequence of knowledge points and to plan the learning sequence of knowledge points for learners. Last, the swarm intelligence algorithm is utilized to ensure that each knowledge point is matched with personalized learning resources with a higher degree of adaptability so that learners can learn using a more targeted approach. The experimental results show that the research results of this paper can, to a certain extent, recommend ideal learning paths to target users, effectively improve the accuracy of recommended resources, and thus improve the learning quality and learning effect of users. [ABSTRACT FROM AUTHOR]

Driver distraction detection not only helps to improve road safety and prevent traffic accidents, but also promotes the development of intelligent transportation systems, which is of great significance for creating a safer and more efficient transportation environment. Since deep learning algorithms have very strong feature learning abilities, more and more deep learning-based driver distraction detection methods have emerged in recent years. However, the majority of existing deep learning-based methods are optimized only through the constraint of classification loss, making it difficult to obtain features with high discrimination, so the performance of these methods is very limited. In this paper, to improve the discrimination between features of different classes of samples, we propose a high-discrimination feature learning strategy and design a driver distraction detection model based on Swin Transformer and the highly discriminative feature learning strategy (ST-HDFL). Firstly, the features of input samples are extracted through the powerful feature learning ability of Swin Transformer. Then, the intra-class distance of samples of the same class in the feature space is reduced through the constraint of sample center distance loss (SC loss), and the inter-class distance of samples of different classes is increased through the center vector shift strategy, which can greatly improve the discrimination of different class samples in the feature space. Finally, we have conducted extensive experiments on two publicly available datasets, AUC-DD and State-Farm, to demonstrate the effectiveness of the proposed method. The experimental results show that our method can achieve better performance than many state-of-the-art methods, such as Drive-Net, MobileVGG, Vanilla CNN, and so on. [ABSTRACT FROM AUTHOR]

This paper contributes to the dialogue around how to increase inclusion in higher education, taking the lecturer perspective as the point of departure. Theoretically, disability is understood as an interaction, which means that lecturers partake in the constitution of dis/ability in learning situations. Two qualitative interviews were conducted with an interdisciplinary lecturer employed in an institution of higher education in Norway. These data are used for this single case study to illustrate and reflect on the challenges of diversity in learning situations. Findings suggest that the lecturer struggles to encounter an increasingly diverse student population inclusively. Overall, her experiences unpack the outcome of a structural lack of prioritization to ensure accessibility for disabled students at an institutional level at the university where she is employed. This article emphasizes that the responsibility to ensure an inclusive teaching practice in higher education must be recognized and treated as an institutional obligation. To signal its priority, all institutions of higher education should make inclusive training obligatory for lecturers, as well as assigning hours to work on enhancing the development of inclusive skills in this group. [ABSTRACT FROM AUTHOR]

Personalized education aims to provide cooperative and exploratory courses for students by using computer and network technology to construct a more effective cooperative learning mode, thus improving students' cooperation ability and lifelong learning ability. Based on students' interests, this paper proposes an effective student grouping strategy and group-oriented course recommendation method, comprehensively considering characteristics of students and courses both from a statistical dimension and a semantic dimension. First, this paper combines term frequency–inverse document frequency and Word2Vec to preferably extract student characteristics. Then, an improved K-means algorithm is used to divide students into different interest-based study groups. Finally, the group-oriented course recommendation method recommends appropriate and quality courses according to the similarity and expert score. Based on real data provided by junior high school students, a series of experiments are conducted to recommend proper social practical courses, which verified the feasibility and effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

Bio-controllers inspired by the characteristics of the human lower limb play an important role in the study of lower limb rehabilitation robots (LLRRs). However, the inverse dynamics modeling of robots for human lower limb rehabilitation remains a challenging issue due to the non-linear and strong coupling characteristics of the bio-controller. To further improve the inverse dynamics model's accuracy, this paper proposes the use of a non-parametric modeling approach in order to learn it. In detail, the main idea is to use the motion data of the main joints of the lower limbs of healthy people as an input and the corresponding joint moments as an output, which are learned through the training of a neural network. To ensure that the learned model can be used on LLRRs, all data collected in this paper are real data from human lower limbs. In addition, since the type of data collected is time series, this paper proposes the use of the long short-term memory (LSTM) and gated recurrent unit (GRU) networks to learn the inverse dynamics model of the robot-like human lower limb and to compare the learning effects of the two networks. The evaluation metric for both network models is the root mean square error (RMSE). The experimental results show that both networks have sound learning effects, and that the GRU network has a more significant learning ability than the LSTM network. [ABSTRACT FROM AUTHOR]

As one of the advanced automotive chassis technologies, the steer-by-wire system offers a high level of precision, responsiveness, and controllability in the driving experience. It can also adjust and optimize parameters to adapt to the preferences of different drivers. However, when faced with the steer-by-wire system, both experienced drivers and novice drivers are in the novice stage, exhibiting learning or adaptation behaviors when using this steering system. In this paper, a small-scale pilot evaluation was conducted by means of a questionnaire survey and driving-simulator experiment, and the learning behavior and adaptability of four experienced and four novice drivers to the steer-by-wire system were analyzed when using the traditional steering system. The study found that experienced drivers show significant changes in their adaptation to the steering system, mainly due to their habitual driving with traditional steering systems. In contrast, novice drivers show no significant changes in their adaptation to the steering system, which is attributed to their lack of driving experience and skills, resulting in less sensitivity to changes in the steering system. Additionally, the study found that novice drivers under the steer-by-wire system grasp control over speed and steering-wheel angle more quickly. This research provides a reference for improving drivers' learning and adaptation abilities to the steer-by-wire system and optimizing the design of the steer-by-wire system. [ABSTRACT FROM AUTHOR]

A long-standing research goal is to develop computing technologies that mimic the brain's capabilities by implementing computation in electronic systems directly inspired by its structure, function, and operational mechanisms, using low-power, spike-based neural networks. The Loihi neuromorphic processor provides a low-power, large-scale network of programmable silicon neurons for brain-inspired artificial intelligence applications. This paper exploits the Loihi processors and a theory-guided methodology to enable unsupervised learning of spike patterns. Our method ensures efficient and rapid selection of the network's hyperparameters, enabling the neuromorphic processor to generate attractor states through real-time unsupervised learning. Precisely, we follow a fast design process in which we fine-tune network parameters using mean-field theory. Moreover, we measure the network's learning ability regarding its error correction and pattern completion aptitude. Finally, we observe the dynamic energy consumption of the neuron cores for each millisecond of simulation equal to 23 μ J/time step during the learning and recall phase for four attractors composed of 512 excitatory neurons and 256 shared inhibitory neurons. This study showcases how large-scale, low-power digital neuromorphic processors can be quickly programmed to enable the autonomous generation of attractor states. These attractors are fundamental computational primitives that theoretical analysis and experimental evidence indicate as versatile and reusable components suitable for a wide range of cognitive tasks. [ABSTRACT FROM AUTHOR]

Accurately capturing children's word learning abilities is critical for advancing our understanding of language development. Researchers have demonstrated that utilizing more complex statistical methods, such as mixed-effects regression and hierarchical linear modeling, can lead to a more complete understanding of the variability observed within children's word learning abilities. In the current paper, we demonstrate how a person-centered approach to data analysis can provide additional insights into the heterogeneity of word learning ability among children while also aiding researchers' efforts to draw individual-level conclusions. Using previously published data with 32 typically developing and 32 late-talking infants who completed a novel noun generalization (NNG) task to assess word learning biases (i.e., shape and material biases), we compare this person-centered method to three traditional statistical approaches: (1) a t-test against chance, (2) an analysis of variance (ANOVA), and (3) a mixed-effects regression. With each comparison, we present a novel question raised by the person-centered approach and show how results from the corresponding analyses can lead to greater nuance in our understanding of children's word learning capabilities. Person-centered methods, then, are shown to be valuable tools that should be added to the growing body of sophisticated statistical procedures used by modern researchers. [ABSTRACT FROM AUTHOR]

In order to solve the problem of the slow transmission rate of high-frequency information in smart grid and improve the efficiency of information transmission, a research method of high-frequency information transmission in smart grids based on the CNN-LSTM model is proposed. It effectively combines the superiority of the CNN algorithm for high-frequency information feature extraction and the learning ability of the LSTM algorithm for global features of high-frequency information. Meanwhile, the client buffer is divided by the VLAN area division method, which avoids the buffer being too large due to line congestion. The intelligent control module is adopted to change the traditional control concept. In addition, the neural network optimization control module is used for intelligent control, which ensures the feedback speed of the control terminal and avoids the problem of increasing the buffer area caused by the feedback time difference. The experimental results show that via the method in this paper, the total efficiency of single-channel transmission reaches 96% and the transmission rate reaches 46 bit/s; the total efficiency of multiplex transmission is 89% and the transmission rate reaches 75 bit/s. It is verified that the method proposed in this paper has a fast transmission rate and high efficiency. [ABSTRACT FROM AUTHOR]

At present, substation operation ticket system is developed based on an expert system, which has some problems such as knowledge base redundancy, intelligence deficiency and automatic learning ability. To solve this problem, this paper proposes an operation sequence reasoning model based on the knowledge base of the Neo4j knowledge graph and DuelingDQN (Dueling Deep Q Network) algorithm. Firstly, the diagram structure model of substation main wiring was established using the Neo4j knowledge graph. Based on the diagram structure model, the operable equipment set of the operation task was searched to form the task space, action space and action selection model of DuelingDQN. The reward and punishment function was designed based on the "five defense" rules and the state change of equipment. Make DuelingDQN model and Neo4j model interact in real time, and automatically learn the operation sequence. The test results show that the method proposed in this paper can automatically deduce the correct operation steps under different wiring modes and realize the transfer within the station, which is of great significance to the intellectualization of the operation ticket system. [ABSTRACT FROM AUTHOR]

The primary sight control system of a tank gunner has image stabilization as one of its primary functions. The image stabilization deviation in the aiming line is a key indicator for evaluating the operational status of Gunner's Primary Sight control system. Employing image detection technology to measure image stabilization deviation enhances the effectiveness and accuracy of the detection process and allows for the evaluation of image stabilization functionality. Hence, this paper proposes an image detection method aimed at the Gunner's Primary Sight control system of a specific tank which utilizes an enhanced You Only Look Once version 5 (YOLOv5) sight-stabilizing deviation algorithm. At first, a dynamic weight factor is integrated into SCYLLA-IoU (SIOU), creating δ-SIOU, which replaces Complete IoU (CIoU) as the loss function of YOLOv5. After that, the Spatial Pyramid Pool module of YOLOv5 was enhanced to improve the multi-scale feature fusion ability of the model, thereby elevating the performance of the detection model. Finally, the C3CA module was created by embedding the Coordinate Attention (CA) attention mechanism into the CSK-MOD-C3 (C3) module. The Bi-directional Feature Pyramid (BiFPN) network structure was also incorporated into the Neck network of YOLOv5 to improve the model's ability to learn target location information and image detection accuracy. Based on data collected by a mirror control test platform, experimental results indicate an improvement in the detection accuracy of the model by 2.1%. These findings offer valuable insights into measuring the image stabilization deviation in the aiming line and facilitating the development of the parameter measurement system for Gunner's Primary Sight control system. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) technology is significant for human–computer interaction, and this paper studies the features and modeling of SER. Mel-spectrogram is introduced and utilized as the feature of speech, and the theory and extraction process of mel-spectrogram are presented in detail. A deep residual shrinkage network with bi-directional gated recurrent unit (DRSN-BiGRU) is proposed in this paper, which is composed of convolution network, residual shrinkage network, bi-directional recurrent unit, and fully-connected network. Through the self-attention mechanism, DRSN-BiGRU can automatically ignore noisy information and improve the ability to learn effective features. Network optimization, verification experiment is carried out in three emotional datasets (CASIA, IEMOCAP, and MELD), and the accuracy of DRSN-BiGRU are 86.03%, 86.07%, and 70.57%, respectively. The results are also analyzed and compared with DCNN-LSTM, CNN-BiLSTM, and DRN-BiGRU, which verified the superior performance of DRSN-BiGRU. [ABSTRACT FROM AUTHOR]

As a result of the Internet of Things (IoT), smart city infrastructure has been able to advance, enhancing efficiency and enabling remote management. Despite this, this interconnectivity poses significant security and privacy concerns, as cyberthreats are rapidly adapting to exploit IoT vulnerabilities. In order to safeguard privacy and ensure secure IoT operations, robust security strategies are necessary. To detect anomalies effectively, intrusion detection systems (IDSs) must employ sophisticated algorithms capable of handling complex and voluminous datasets. A novel approach to IoT security is presented in this paper, which focuses on safeguarding smart vertical networks (SVNs) integral to sector-specific IoT implementations. It is proposed that a deep learning-based method employing a stacking deep ensemble model be used, selected for its superior performance in managing large datasets and its ability to learn intricate patterns indicative of cyberattacks. Experimental results indicate that the model is exceptionally accurate in identifying cyberthreats, exceeding other models, with a 99.8% detection rate for the ToN-IoT dataset and 99.6% for the InSDN dataset. The paper aims not only to introduce a robust algorithm for IoT security, but also to demonstrate its efficacy through comprehensive testing. We selected a deep learning ensemble model due to its proven track record in similar applications and its ability to maintain the integrity of IoT systems in smart cities. [ABSTRACT FROM AUTHOR]

Climate change has increased the frequency of various types of meteorological disasters in recent years. Finding the primary factors that limit the emergency response capability of meteorological disasters through the evaluation of that capability and proposing corresponding improvement measures in order to increase that capability is of great practical importance. The evaluation of meteorological disaster emergency response capability still has some issues. The majority of research methods use qualitative analysis, which makes it challenging to deal with fuzzy factors, leading to conclusions that are subjective and insufficiently rigorous. The evaluation models themselves are also complex and challenging to simulate and analyze, making it challenging to promote and use them in practice. Deep learning techniques have made it easier to collect and process large amounts of data, which has opened new avenues for advancement in the emergency management of weather-related disasters. In this paper, we suggest a Recurrent Neural Network (RNN)-based dynamic capability feature extraction method. The process of evaluation content determination and index selection is used to build a meteorological disaster emergency response capability evaluation index system before an encoder, based on the encoder–decoder architecture, is built for dynamic feature extraction. The RNN autoencoder deep learning ability dynamic rating method used in this paper has been shown through a series of experiments to be able to not only efficiently extract ability features from time series data and reduce the dimensionality of ability features, but also to reduce the focus of the ability evaluation model on simple and abnormal samples, concentrate the model learning on difficult samples, and have a higher accuracy. As a result, it is more suitable for the problem situation at evaluation of the disaster capability. [ABSTRACT FROM AUTHOR]

In response to the issues of low model recognition accuracy and weak generalization in mechanical equipment fault diagnosis due to scarce data, this paper proposes an innovative solution, a cross-device secondary transfer-learning method based on EGRUN (efficient gated recurrent unit network). This method utilizes continuous wavelet transform (CWT) to transform source domain data into images. The EGRUN model is initially trained, and shallow layer weights are frozen. Subsequently, random overlapping sampling is applied to the target domain data to enhance data and perform secondary transfer learning. The experimental results demonstrate that this method not only significantly improves the model's ability to learn fault features but also enhances its classification accuracy and generalization performance. Compared to current state-of-the-art algorithms, the model proposed in this study shows faster convergence speed, higher diagnostic accuracy, and superior robustness and generalization, providing an effective approach to address the challenges arising from scarce data and varying operating conditions in practical engineering scenarios. [ABSTRACT FROM AUTHOR]

Multi-view clustering requires simultaneous attention to both consistency and the diversity of information between views. Deep learning techniques have shown impressive abilities to learn complex features when working with extensive datasets; however, existing deep multi-view clustering methods often focus only on either consistency information or diversity information, making it difficult to balance both aspects. Therefore, this paper proposes a view-driven multi-view clustering using the contrastive double-learning method (VMC-CD), aiming to generate better clustering results. This method first adopts a view-driven approach to consider information from other views to encourage diversity, thus guiding feature learning. Additionally, it presents the idea of dual contrastive learning to enhance the alignment of views at both the clustering and feature levels. The VMC-CD method's superiority over various cutting-edge methods is substantiated by experimental findings across three datasets, affirming its effectiveness. [ABSTRACT FROM AUTHOR]

This paper presents the findings from a systematic review of 29 websites and 13 frameworks that provide STEM (Science, Technology, Engineering, Mathematics) educational resources for parents, educators, and children (birth–8 years of age). Our theoretical approach is rooted within a social semiotic perspective that has indicated that multimodality enables children to use different types of expression to communicate a message or share an idea. Using the PRISMA methodology and the narrative document analysis approach, the themes that emerged included how the content and resources available on the websites addressed whether multimodality supported STEM engagement in an inclusive manner. The findings revealed that there were scarce multimodal resources that engaged children with fun, interactive, and meaningful opportunities to be autonomous learners (e.g., children had agency) (n = 11 out of 29), moving between the digital and hands-on physical spaces (n = 8 out of 29), employing gamification for deep learning (n = 4 out of 29), and piquing children's imagination, inquiry, and creativity, and links to everyday STEM scenarios were hardly present (n = 10 out of 29). The implications lie in addressing early STEM engagement by considering children's learning abilities and agency, bearing in mind parents/educators' sociocultural backgrounds, confidence in STEM awareness, and multimodal avenues for communicating STEM learning and inquiry. [ABSTRACT FROM AUTHOR]

Dongba characters are ancient ideographic scripts with abstract expressions that differ greatly from modern Chinese characters; directly applying existing methods cannot achieve the font style transfer of Dongba characters. This paper proposes an Attention-based Font style transfer Generative Adversarial Network (AFGAN) method. Based on the characteristics of Dongba character images, two core modules are set up in the proposed AFGAN, namely void constraint and font stroke constraint. In addition, in order to enhance the feature learning ability of the network and improve the style transfer effect, the Convolutional Block Attention Module (CBAM) mechanism is added in the down-sampling stage to help the network better adapt to input font images with different styles. The quantitative and qualitative analyses of the generated font and the real font were conducted by consulting with professional artists based on the newly built small seal script, slender gold script, and Dongba character dataset, and the styles of the small seal script and slender gold script were transferred to Dongba characters. The results indicate that the proposed AFGAN method has advantages in evaluation indexes and visual quality compared to existing networks. At the same time, this method can effectively learn the style features of small seal script and slender gold script, and transfer them to Dongba characters, indicating the effectiveness of this method. [ABSTRACT FROM AUTHOR]

In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development. [ABSTRACT FROM AUTHOR]

The quadrotor aircraft has the characteristics of simple structure, high attitude maintenance performance and strong maneuverability, and is widely used in air surveillance, post−disaster search and rescue, target tracking and military industry. In this paper, a robust control scheme based on linear active disturbance rejection is proposed to solve the problem that the quadrotor is susceptible to various disturbances during the take−off process of non−horizontal planes and strong disturbances. Linear Active Disturbance Rejection Control (LADRC) is a product of a tracking differentiator (TD), a linear extended state observer (LESO) and an error feedback control law (PD) and is a control technique for estimating compensation for uncertainty. Radial Basis Function Neural Networks (RBFNN) is a well−performing forward network with best approximation, simple training, fast learning convergence and the ability to overcome local minima problems. Combined with the advantages and disadvantages of LADRC, Adaptive Control and Neural Network, the coupling force between each channel, gust crosswind disturbance and additional resistance of offshore platform jitter in the flight state of the quadrotor are optimized. In the control, the RBF neural network is designed, the nonlinear control signal is wirelessly approximated and the uncertain disturbance to the quadrotor is identified online. Finally, the real−time estimation and compensation are performed by LESO to realize the full−attitude take−off of the quadrotor. In addition, this paper uses adaptive control to optimize the parameters of LADRC to reduce the problem of many LADRC parameters and difficulty to integrate. Finally, the robust control system mentioned in this paper is simulated and verified, and the simulation results show that the control scheme has the advantages of simple parameter adjustment and stronger robustness. [ABSTRACT FROM AUTHOR]

Filter optimization problems involve time-consuming simulations and many variables in the design. These problems require a large amount of computation. This paper proposes an adaptive online updating 1D convolutional autoencoders (AOU-1D-CAE) surrogate model for solving this computationally expensive problem. In the optimization process, an adaptive update surrogate mapping between input variables and output objectives is constructed within the surrogate model AOU-1D-CAE framework. AOU-1D-CAE can replace electromagnetic (EM) simulation software for data collection, and select and automatically use the accumulated data as training samples to train the AOU-1D-CAE surrogate model. With more and more training samples, the learning ability of the surrogate model is also becoming stronger and stronger. The experimental results show that the data collection efficiency of AOU-1D-CAE is greatly improved, and the automatic update of the sample set improves the prediction performance of the surrogate model. In this paper, the optimization framework is AOU-1D-CAE-assisted particle swarm optimization (PSO), and the surrogate model assists PSO to find the global optimal solution. In the PSO stage, PSO automatically updates and saves the optimal solution, and takes the optimal solution of each stage as the initial solution of the next optimization stage to avoid falling into the local optimal solution. The optimization time is greatly saved and the optimization efficiency is improved. The continuous iteration of PSO also improves the prediction accuracy of the surrogate model. The efficiency of the proposed surrogate model is demonstrated by using two cavity filters as examples. [ABSTRACT FROM AUTHOR]

Diabetes is a widely spread disease that significantly affects people's lives. The leading cause is uncontrolled levels of blood glucose, which develop eye defects over time, including Diabetic Retinopathy (DR), which results in severe visual loss. The primary factor causing blindness is considered to be DR in diabetic patients. DR treatment tries to control the disease's severity, as it is irreversible. The primary goal of this effort is to create a reliable method for automatically detecting the severity of DR. This paper proposes a new automated system (DR-NASNet) to detect and classify DR severity using an improved pretrained NASNet Model. To develop the DR-NASNet system, we first utilized a preprocessing technique that takes advantage of Ben Graham and CLAHE to lessen noise, emphasize lesions, and ultimately improve DR classification performance. Taking into account the imbalance between classes in the dataset, data augmentation procedures were conducted to control overfitting. Next, we have integrated dense blocks into the NASNet architecture to improve the effectiveness of classification results for five severity levels of DR. In practice, the DR-NASNet model achieves state-of-the-art results with a smaller model size and lower complexity. To test the performance of the DR-NASNet system, a combination of various datasets is used in this paper. To learn effective features from DR images, we used a pretrained model on the dataset. The last step is to put the image into one of five categories: No DR, Mild, Moderate, Proliferate, or Severe. To carry this out, the classifier layer of a linear SVM with a linear activation function must be added. The DR-NASNet system was tested using six different experiments. The system achieves 96.05% accuracy with the challenging DR dataset. The results and comparisons demonstrate that the DR-NASNet system improves a model's performance and learning ability. As a result, the DR-NASNet system provides assistance to ophthalmologists by describing an effective system for classifying early-stage levels of DR. [ABSTRACT FROM AUTHOR]

Compared with traditional machine learning algorithms, the convolutional neural network (CNN) has an excellent automatic feature learning ability and can complete the nonlinear representation from original data input to output by itself. However, the CNN does not sufficiently mine the tool wear information contained in the multi-sensor data due to disregard of the differences in the contribution of different features when extracting features. In this paper, a tool wear prediction method based on a multi-scale convolutional neural network with attention fusion is proposed, which fuses the tool wear degradation information collected by different types of sensors. In the multi-scale convolution module, convolution kernels with different sizes are used to extract the degradation information of different scales in the wear information, and then the attention fusion module is constructed to fuse the multi-scale feature information. Finally, the mapping between tool wear and multi-sensor data is realized through the feature information obtained by residual connection and full connection layer. By comparing the multi-scale convolutional neural network with different attention mechanisms, the experiments demonstrated the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Fitness is important in people's lives. Good fitness habits can improve cardiopulmonary capacity, increase concentration, prevent obesity, and effectively reduce the risk of death. Home fitness does not require large equipment but uses dumbbells, yoga mats, and horizontal bars to complete fitness exercises and can effectively avoid contact with people, so it is deeply loved by people. People who work out at home use social media to obtain fitness knowledge, but learning ability is limited. Incomplete fitness is likely to lead to injury, and a cheap, timely, and accurate fitness detection system can reduce the risk of fitness injuries and can effectively improve people's fitness awareness. In the past, many studies have engaged in the detection of fitness movements, among which the detection of fitness movements based on wearable devices, body nodes, and image deep learning has achieved better performance. However, a wearable device cannot detect a variety of fitness movements, may hinder the exercise of the fitness user, and has a high cost. Both body-node-based and image-deep-learning-based methods have lower costs, but each has some drawbacks. Therefore, this paper used a method based on deep transfer learning to establish a fitness database. After that, a deep neural network was trained to detect the type and completeness of fitness movements. We used Yolov4 and Mediapipe to instantly detect fitness movements and stored the 1D fitness signal of movement to build a database. Finally, MLP was used to classify the 1D signal waveform of fitness. In the performance of the classification of fitness movement types, the mAP was 99.71%, accuracy was 98.56%, precision was 97.9%, recall was 98.56%, and the F1-score was 98.23%, which is quite a high performance. In the performance of fitness movement completeness classification, accuracy was 92.84%, precision was 92.85, recall was 92.84%, and the F1-score was 92.83%. The average FPS in detection was 17.5. Experimental results show that our method achieves higher accuracy compared to other methods. [ABSTRACT FROM AUTHOR]

The echo state network (ESN) is a recurrent neural network that has yielded state-of-the-art results in many areas owing to its rapid learning ability and the fact that the weights of input neurons and hidden neurons are fixed throughout the learning process. However, the setting procedure for initializing the ESN's recurrent structure may lead to difficulties in designing a sound reservoir that matches a specific task. This paper proposes an improved pre-training method to adjust the model's parameters and topology to obtain an adaptive reservoir for a given application. Two strategies, namely global random selection and ensemble training, are introduced to pre-train the randomly initialized ESN model. Specifically, particle swarm optimization is applied to optimize chosen fixed and global weight values within the network, and the reliability and stability of the pre-trained model are enhanced by employing the ensemble training strategy. In addition, we test the feasibility of the model for time series prediction on six benchmarks and two real-life datasets. The experimental results show a clear enhancement in the ESN learning results. Furthermore, the proposed global random selection and ensemble training strategies are also applied to pre-train the extreme learning machine (ELM), which has a similar training process to the ESN model. Numerical experiments are subsequently carried out on the above-mentioned eight datasets. The experimental findings consistently show that the performance of the proposed pre-trained ELM model is also improved significantly. The suggested two strategies can thus enhance the ESN and ELM models' prediction accuracy and adaptability. [ABSTRACT FROM AUTHOR]

Vehicle-mounted ground-penetrating radar (GPR) technology is an effective means of detecting railway subgrade diseases. However, existing methods of GPR data interpretation largely rely on manual identification, which is not only inefficient but also highly subjective. This paper proposes a semi-supervised deep learning method to identify railway subgrade diseases. This method addresses the sample imbalance problem in the defect dataset by utilizing a data augmentation method based on a generative adversarial network model. An initial network model for disease identification is obtained by training the YOLOv5 network with a small number of existing samples. The intelligently extended samples are then labeled to achieve a balance in the disease samples. The network is trained to improve the recognition accuracy of the intelligent model using a more complete dataset. The experimental results show that the accuracy of the proposed method can reach up to 94.53%, which is 23.85% higher than that of the supervised learning model without an extended dataset. This has strong industrial application value for railway subgrade disease detection as the potential learning ability of the model can be explored to a greater extent, thereby improving the recognition accuracy of subgrade diseases. [ABSTRACT FROM AUTHOR]

This paper introduces an FPGA-based implementation of a smart switch designed to avoid inrush currents occurring during the connection of single-phase transformers utilized in grid-connected photovoltaic (PV) systems. The magnitude of inrush currents is notably impacted by the residual flux within the transformer core and the precise moment of energization relative to the wave cycle. Alternative methods frequently hinge on intricate procedures to estimate residual flux. This challenge is adeptly circumvented by the innovative smart control system proposed herein, rendering it a cost-effective solution for grid-connected PV systems. The proposed solution for mitigating inrush current remains effective, even in the face of challenges with current and voltage sensors. This resilience arises from the system's ability to learn and adapt by leveraging information acquired from the network. [ABSTRACT FROM AUTHOR]

Artifacts are the main cause of degradation in CT image quality and diagnostic accuracy. Because of the complex texture of CT images, it is a challenging task to automatically detect artifacts from limited image samples. Recently, graph convolutional networks (GCNs) have achieved great success and shown promising results in medical imaging due to their powerful learning ability. However, GCNs do not take the attention mechanism into consideration. To overcome their limitations, we propose a novel Regional–Temporal Graph Attention Network for motion artifact detection from computed tomography images (RT-GAT). In this paper, head CT images are viewed as a heterogeneous graph by taking regional and temporal information into consideration, and the graph attention network is utilized to extract the features of the constructed graph. Then, the feature vector is input into the classifier to detect the motion artifacts. The experimental results demonstrate that our proposed RT-GAT method outperforms the state-of-the-art methods on a real-world CT dataset. [ABSTRACT FROM AUTHOR]

Accurately and effectively measuring the breaking quality of harvested corn kernels is a critical step in the intelligent development of corn harvesters. The detection of broken corn kernels is complicated during the harvesting process due to turbulent corn kernel movement, uneven lighting, and interference from numerous external factors. This paper develops a deep learning-based detection method in real time for broken corn kernels in response to these issues. The system uses an image acquisition device to continuously acquire high-quality corn kernel image data and cooperates with a deep learning model to realize the rapid and accurate recognition of broken corn kernels. First, we defined the range of broken corn kernels based on image characteristics captured by the acquisition device and prepared the corn kernel datasets. The corn kernels in the acquired image were densely distributed, and the highly similar features of broken and whole corn kernels brough challenges to the system for visual recognition. To address this problem, we propose an improved model called BCK-YOLOv7, which is based on YOLOv7. We fine-tuned the model's positive sample matching strategy and added a transformer encoder block module and coordinate attention mechanism, among other strategies. Ablation experiments demonstrate that our approach improves the BCK-YOLOv7 model's ability to learn effectively broken corn kernel features, even when high-density features are similar. The improved model achieved a precision rate of 96.9%, a recall rate of 97.5%, and a mAP of 99.1%, representing respective improvements of 3.7%, 4.3%, and 2.8% over the original YOLOv7 model. To optimize and deploy the BCK-YOLOv7 model to the edge device (NVIDIA Jetson Nano), TensorRT was utilized, resulting in an impressive inference speed of 33 FPS. Finally, the simulation system experiment for corn kernel broken rate detection was performed. The results demonstrate that the system's mean absolute deviation is merely 0.35 percent compared to that of manual statistical results. The main contribution of this work is the fact that this is the first time that a set of deep learning model improvement strategies and methods are proposed to deal with the problem of rapid and accurate corn kernel detection under the conditions of high density and similar features. [ABSTRACT FROM AUTHOR]

Although convolutional neural networks (CNNs) have produced great achievements in various fields, many scholars are still exploring better network models, since CNNs have an inherent limitation—that is, the remote modeling ability of convolutional kernels is limited. On the contrary, the transformer has been applied by many scholars to the field of vision, and although it has a strong global modeling capability, its close-range modeling capability is mediocre. While the foreground information to be segmented in medical images is usually clustered in a small interval in the image, the distance between different categories of foreground information is uncertain. Therefore, in order to obtain a perfect medical segmentation prediction graph, the network should not only have a strong learning ability for local details, but also have a certain distance modeling ability. To solve these problems, a remote feature exploration (RFE) module is proposed in this paper. The most important feature of this module is that remote elements can be used to assist in the generation of local features. In addition, in order to better verify the feasibility of the innovation in this paper, a new multi-organ segmentation dataset (MOD) was manually created. While both the MOD and Synapse datasets label eight categories of organs, there are some images in the Synapse dataset that label only a few categories of organs. The proposed method achieved 79.77% and 75.12% DSC on the Synapse and MOD datasets, respectively. Meanwhile, the HD95 (mm) scores were 21.75 on Synapse and 7.43 on the MOD dataset. [ABSTRACT FROM AUTHOR]

The weigh-in-motion (WIM) system weighs the entire vehicle by identifying the dynamic forces of each axle of the vehicle on the road. The load of each axle is very important to detect the total weight of the vehicle. Different drivers have different driving behaviors, and when large trucks pass through the weighing detection area, the driving state of the trucks may affect the weighing accuracy of the system. This paper proposes YOLOv3 network model as the basis for this algorithm, which uses the feature pyramid network (FPN) idea to achieve multi-scale prediction and the deep residual network (ResNet) idea to extract image features, so as to achieve a balance between detection speed and detection accuracy. In the paper, spatial pyramid pooling (SPP) network and cross stage partial (CSP) network are added to the original network model to improve the learning ability of the convolutional neural network and make the original network more lightweight. Then the detection-based target tracking method with Kalman filtering + RTS (rauch–tung–striebel) smoothing is used to extract the truck driving status information (vehicle trajectory and speed). Finally, the effective size of the vehicle in different driving states on the weighing accuracy is statistically analyzed. The experimental results show that the method has high accuracy and real-time performance in truck driving state extraction, can be used to analyze the influence of weighing accuracy, and provides theoretical support for personalized accuracy correction of WIM system. At the same time, it is beneficial for WIM system to assist the existing traffic system more accurately and provide a highway health management and effective decision making by providing reliable monitoring data. [ABSTRACT FROM AUTHOR]

Fine-grained image recognition, as a significant branch of computer vision, has become prevalent in various applications in the real world. However, this image recognition is more challenging than general image recognition due to the highly localized and subtle differences in special parts. Up to now, many classic models, including Bilinear Convolutional Neural Networks (Bilinear CNNs), Destruction and Construction Learning (DCL), etc., have emerged to make corresponding improvements. This paper focuses on optimizing the Navigator-Teacher-Scrutinizer Network (NTS-Net). The structure of NTS-Net determines its strong ability to capture subtle information areas. However, research finds that this advantage will lead to a bottleneck of the model's learning ability. During the training process, the loss value of the training set approaches zero prematurely, which is not conducive to later model learning. Therefore, this paper proposes the INTS-Net model, in which the Stochastic Partial Swap (SPS) method is flexibly added to the feature extractor of NTS-Net. By injecting noise into the model during training, neurons are activated in a more balanced and efficient manner. In addition, we obtain a speedup of about 4.5% in test time by fusing batch normalization and convolution. Experiments conducted on CUB-200-2011 and Stanford cars demonstrate the superiority of INTS-Net. [ABSTRACT FROM AUTHOR]

Wireless traffic prediction is critical to the intelligent operation of cellular networks, such as load balancing, congestion control, value-added service promotion, etc. However, the BTS data in each region has certain differences and privacy, and centralized prediction needs to transmit a large amount of traffic data, which will not only cause bandwidth consumption, but may also cause privacy leakage. Federated learning is a kind of distributed learning method with multi-client joint training and no sharing between clients. Based on existing related research, this paper proposes a gradient similarity-based federated aggregation algorithm for wireless traffic prediction (Gradient Similarity-based Federated Aggregation for Wireless Traffic Prediction) (FedGSA). First of all, this method uses a global sharing enhanced data strategy to overcome the data heterogeneity challenge of multi-client collaborative training in federated learning. Secondly, the sliding window scheme is used to construct the dual channel training data to improve the feature learning ability of the model; In addition, to improve the generalization ability of the final global model, a two-layer aggregation scheme based on gradient similarity is proposed. The personalized model is generated by comparing the gradient similarity of each client model, and the central server aggregates the personalized model to finally generate the global model. Finally, the FedGSA algorithm is applied to wireless network traffic prediction. Experiments are conducted on two real traffic datasets. Compared with the mainstream Federated Averaging (FedAvg) algorithm, FedGSA performs better on both datasets and obtains better prediction results on the premise of ensuring the privacy of client traffic data. [ABSTRACT FROM AUTHOR]

The theme of this paper is that the SP Theory of Intelligence (SPTI), and its realisation in the SP Computer Model, is a promising foundation for the development of artificial intelligence at the level of people or higher, also known as 'artificial general intelligence' (AGI). The SPTI, and alternatives to the SPTI chosen to be representative of potential foundations for the development of AGI, are considered and compared. A key principle in the SPTI and its development is the importance of information compression (IC) in human learning, perception, and cognition. More specifically, IC in the SPTI is achieved via the powerful concept of SP-multiple-alignment, the key to the versatility of the SPTI in diverse aspects of intelligence, and thus a favourable combination of Simplicity with descriptive and explanatory Power. Since there are many uncertainties between where we are now and, far into the future, anything that might qualify as an AGI, a multi-pronged attack on the problem is needed. The SPTI qualifies as the basis for one of those prongs. Although it will take time to achieve AGI, there is potential along the road for many useful benefits and applications of the research. [ABSTRACT FROM AUTHOR]

The ability to learn continuously is crucial for a robot to achieve a high level of intelligence and autonomy. In this paper, we consider continual reinforcement learning (RL) for quadruped robots, which includes the ability to continuously learn sub-sequential tasks (plasticity) and maintain performance on previous tasks (stability). The policy obtained by the proposed method enables robots to learn multiple tasks sequentially, while overcoming both catastrophic forgetting and loss of plasticity. At the same time, it achieves the above goals with as little modification to the original RL learning process as possible. The proposed method uses the Piggyback algorithm to select protected parameters for each task, and reinitializes the unused parameters to increase plasticity. Meanwhile, we encourage the policy network exploring by encouraging the entropy of the soft network of the policy network. Our experiments show that traditional continual learning algorithms cannot perform well on robot locomotion problems, and our algorithm is more stable and less disruptive to the RL training progress. Several robot locomotion experiments validate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

The growing need for effective object detection models on mobile devices makes it essential to design models that are both accurate and have fewer parameters. In this paper, we introduce a YOLOv8 Res2Net Extended Network (YOLOv8-CGRNet) approach that achieves enhanced precision under standards suitable for lightweight mobile devices. Firstly, we merge YOLOv8 with the Context GuidedNet (CGNet) and Residual Network with multiple branches (Res2Net) structures, augmenting the model's ability to learn deep Res2Net features without adding to its complexity or computational demands. CGNet effectively captures local features and contextual surroundings, utilizing spatial dependencies and context information to improve accuracy. By reducing the number of parameters and saving on memory usage, it adheres to a 'deep yet slim' principle, lessening channel numbers between stages. Secondly, we explore an improved pyramid network (FPN) combination and employ the Stage Partial Spatial Pyramid Pooling Fast (SimPPFCSPC) structure to further strengthen the network's capability in processing the FPN. Using a dynamic non-monotonic focusing mechanism (FM) gradient gain distribution strategy based on Wise-IoU (WIoU) in an anchor-free context, this method effectively manages low-quality examples. It enhances the overall performance of the detector. Thirdly, we introduce Unifying Object Detection Heads with Attention, adapting to various input scenarios and increasing the model's flexibility. Experimental datasets include the commonly used detection datasets: VOC2007, VOC2012, and VisDrone. The experimental results demonstrate a 4.3% improvement in detection performance by the proposed framework, affirming superior performance over the original YOLOv8 model in terms of accuracy and robustness and providing insights for future practical applications. [ABSTRACT FROM AUTHOR]

The growing utilization of web-based search engines for learning purposes has led to increased studies on searching as learning (SAL). In order to achieve the desired learning outcomes, web learners have to carefully plan their learning objectives. Previous SAL research has proposed the significant influence of task planning quality on learning outcomes. Therefore, accurately predicting web-based learners' task planning abilities, particularly in the context of SAL, is of paramount importance for both web-based search engines and recommendation systems. To solve this problem, this paper proposes a method for predicting the ability of task planning for web learners. Specifically, we first introduced a tree-based representation method to capture how learners plan their learning tasks. Subsequently, we proposed a method based on the deep learning technique to accurately predict the SAL task planning ability for web learners. Experimental results indicate that, compared to baseline approaches, our proposed method can provide a more effective representation of learners' task planning and deliver more accurate predictions of learners' task planning abilities in SAL. [ABSTRACT FROM AUTHOR]

Finding all the roots of a nonlinear equation is an important and difficult task that arises naturally in numerous scientific and engineering applications. Sequential iterative algorithms frequently use a deflating strategy to compute all the roots of the nonlinear equation, as rounding errors have the potential to produce inaccurate results. On the other hand, simultaneous iterative parallel techniques require an accurate initial estimation of the roots to converge effectively. In this paper, we propose a new class of global neural network-based root-finding algorithms for locating real and complex polynomial roots, which exploits the ability of machine learning techniques to learn from data and make accurate predictions. The approximations computed by the neural network are used to initialize two efficient fractional Caputo-inverse simultaneous algorithms of convergence orders ς + 2 and 2 ς + 4 , respectively. The results of our numerical experiments on selected engineering applications show that the new inverse parallel fractional schemes have the potential to outperform other state-of-the-art nonlinear root-finding methods in terms of both accuracy and elapsed solution time. [ABSTRACT FROM AUTHOR]

Object detection based on wood defects involves using bounding boxes to label defects in the surface image of the wood. This step is crucial before the transformation of wood products. Due to the small size and diverse shape of wood defects, most previous object detection models are unable to filter out critical features effectively. Consequently, they have faced challenges in generating adequate contextual information to detect defects accurately. In this paper, we proposed a YOLOv5 model based on a Semi-Global Network (SGN) to detect wood defects. Unlike previous models, firstly, a lightweight SGN is introduced in the backbone to model the global context, which can improve the accuracy and reduce the complexity of the network at the same time; the backbone is embedded with the Extended Efficient Layer Aggregation Network (E-ELAN), which continuously enhances the learning ability of the network; and finally, the Efficient Intersection and Merger (EIOU) loss is used to solve the problems of slow convergence speed and inaccurate regression results. Experimental results on public wood defect datasets demonstrated that our approach outperformed existing target detection models. The mAP value was 86.4%, a 3.1% improvement over the baseline network model, a 7.1% improvement over SSD, and a 13.6% improvement over Faster R-CNN. These results show the effectiveness of our proposed methodology. [ABSTRACT FROM AUTHOR]

The existing techniques for detecting defects in photovoltaic (PV) components have some drawbacks, such as few samples, low detection accuracy, and poor real-time performance. This paper presents a cloud-edge collaborative technique for detecting the defects in PV components, based on transfer learning. The proposed cloud model is based on the YOLO v3-tiny algorithm. To increase the detection effect of small targets, we produced a third prediction layer by fusing the shallow feature information with the stitching layer in the second detection scale and introducing a residual module to achieve improvement of the YOLO v3-tiny algorithm. In order to further increase the ability of the network model to extract target features, the residual module was introduced in the YOLO v3-tiny backbone network to increase network depth and learning ability. Finally, through the model's transfer learning and edge collaboration, the adaptability of the defect-detection algorithm to personalized applications and real-time defect detection was enhanced. The experimental results showed that the average accuracy and recall rates of the improved YOLO v3-tiny for detecting defects in PV components were 95.5% and 93.7%, respectively. The time-consumption of single panoramic image detection is 6.3 ms, whereas the consumption of the model's memory is 64 MB. After cloud-edge learning migration, the training time for a local sample model was improved by 66%, and the accuracy reached 99.78%. [ABSTRACT FROM AUTHOR]

Time series forecasting provides a vital basis for the control and management of various systems. The time series data in the real world are usually strongly nonstationary and nonlinear, which increases the difficulty of reliable forecasting. To fully utilize the learning capability of machine learning in time series forecasting, an adaptive broad echo state network (ABESN) is proposed in this paper. Firstly, the broad learning system (BLS) is used as a framework, and the reservoir pools in the echo state network (ESN) are introduced to form the broad echo state network (BESN). Secondly, for the problem of information redundancy in the reservoir structure in BESN, an adaptive optimization algorithm for the BESN structure based on the pruning algorithm is proposed. Thirdly, an adaptive optimization algorithm of hyperparameters based on the nonstationary test index is proposed. In brief, the structure and hyperparameter optimization algorithms are studied to form the ABESN based on the proposed BESN model in this paper. The ABESN is applied to the data forecasting of air humidity and electric load. The experiments show that the proposed ABESN has a better learning ability for nonstationary time series data and can achieve higher forecasting accuracy. [ABSTRACT FROM AUTHOR]

Transmitting orthogonal waveforms are the basis for giving full play to the advantages of MIMO radar imaging technology, but the commonly used waveforms with the same frequency cannot meet the orthogonality requirement, resulting in serious coupling noise in traditional imaging methods and affecting the imaging effect. In order to effectively suppress the mutual coupling interference caused by non-orthogonal waveforms, a new non-orthogonal waveform MIMO radar imaging method based on deep learning is proposed in this paper: with the powerful nonlinear fitting ability of deep learning, the mapping relationship between the non-orthogonal waveform MIMO radar echo and ideal target image is automatically learned by constructing a deep imaging network and training on a large number of simulated training data. The learned imaging network can effectively suppress the coupling interference between non-ideal orthogonal waveforms and improve the imaging quality of MIMO radar. Finally, the effectiveness of the proposed method is verified by experiments with point scattering model data and electromagnetic scattering calculation data. [ABSTRACT FROM AUTHOR]

Anomaly detection tasks involving time-series signal processing have been important research topics for decades. In many real-world anomaly detection applications, no specific distributions fit the data, and the characteristics of anomalies are different. Under these circumstances, the detection algorithm requires excellent learning ability of the data features. Transformers, which apply the self-attention mechanism, have shown outstanding performances in modelling long-range dependencies. Although Transformer based models have good prediction performance, they may be influenced by noise and ignore some unusual details, which are significant for anomaly detection. In this paper, a novel temporal context fusion framework: Temporal Context Fusion Transformer (TCF-Trans), is proposed for anomaly detection tasks with applications to time series. The original feature transmitting structure in the decoder of Informer is replaced with the proposed feature fusion decoder to fully utilise the features extracted from shallow and deep decoder layers. This strategy prevents the decoder from missing unusual anomaly details while maintaining robustness from noises inside the data. Besides, we propose the temporal context fusion module to adaptively fuse the generated auxiliary predictions. Extensive experiments on public and collected transportation datasets validate that the proposed framework is effective for anomaly detection in time series. Additionally, the ablation study and a series of parameter sensitivity experiments show that the proposed method maintains high performance under various experimental settings. [ABSTRACT FROM AUTHOR]

Learnability in Automated Driving (LiAD) is a neglected research topic, especially when considering the unpredictable and intricate ways humans learn to interact and use automated driving systems (ADS) over the sequence of time. Moreover, there is a scarcity of publications dedicated to LiAD (specifically extended learnability methods) to guide the scientific paradigm. As a result, this generates scientific discord and, thus, leaves many facets of long-term learning effects associated with automated driving in dire need of significant research courtesy. This, we believe, is a constraint to knowledge discovery on quality interaction design phenomena. In a sense, it is imperative to abstract knowledge on how long-term effects and learning effects may affect (negatively and positively) users' learning and mental models. As well as induce changeable behavioural configurations and performances. In view of that, it may be imperative to examine operational concepts that may help researchers envision future scenarios with automation by assessing users' learning ability, how they learn and what they learn over the sequence of time. As well as constructing a theory of effects (from micro, meso and macro perspectives), which may help profile ergonomic quality design aspects that stand the test of time. As a result, we reviewed the literature on learnability, which we mined for LiAD knowledge discovery from the experience perspective of long-term learning effects. Therefore, the paper offers the reader the resulting discussion points formulated under the Learnability Engineering Life Cycle. For instance, firstly, contextualisation of LiAD with emphasis on extended LiAD. Secondly, conceptualisation and operationalisation of the operational mechanics of LiAD as a concept in ergonomic quality engineering (with an introduction of Concepts for Applying Learnability Engineering (CALE) research based on LiAD knowledge discovery). Thirdly, the systemisation of implementable long-term research strategies towards comprehending behaviour modification associated with extended LiAD. As the vehicle industry revolutionises at a rapid pace towards automation and artificially intelligent (AI) systems, this knowledge is useful for illuminating and instructing quality interaction strategies and Quality Automated Driving (QAD). [ABSTRACT FROM AUTHOR]