Search

Hot-rolled strip products have diverse applications, and enhancing the detection, diagnostics, and prognostics of product quality during hot rolling is essential. Nevertheless, the multivariable, strong coupling, nonlinear, and time-varying nature of the production process poses a rigorous challenge for accurate hot-rolled prognostics. This paper implements a progressive layered extraction (PLE) multi-task learning (MTL) framework to simultaneously estimate multiple quality indicators, such as strip crown, center line deviation, exit temperature, wedge, width, and symmetry flatness. Additionally, the paper proposes the implements of Hybrid Bayesian Neural Network (HBNN) experts and a gating network with attention mechanism to integrate private and shared task features. It also puts forth an auxiliary task involving a Variational Autoencoder with Generative Adversarial Networks (VAE-GAN) to extract latent states from the original sequence. Moreover, an adaptive joint loss optimization is employed to update the weight of individual task losses for MTL training problems, and three sets of field hot-rolled datasets are used for model evaluation. In the experimental validation, considering the noisy field data and limited conditions in the real hot rolled production, comparative experiments are conducted to demonstrate the improved generalization and robustness of the proposed MTL approach. These experiments involve different percentages of the total data, ranging from 5% to 20%, and various prediction horizons ranging from 1 to 50 steps for model establishment. In addition, the paper discusses the interpretation of the model and strategies for further enhancing model performance. [ABSTRACT FROM AUTHOR]

Text recognition in scene images is still considered as a challenging task for the computer vision and pattern recognition community. For text images affected by multiple adverse factors, such as occlusion (due to obstacles) and poor quality (due to blur and low resolution), the performance of the state-of-the-art scene text recognition methods degrades. The key reason is that the existing encoder–decoder framework follows fixed left-to-right decoding order, which lacks sufficient contextual information. In this paper, we present a novel decoding order where good-quality characters can first be decoded followed by low-quality characters, which preserves the contextual information irrespective of the aforementioned difficult scenarios. Our method, named NDOrder, extracts visual features with a ViT encoder and then decodes with the Random Order Generation module (ROG) for learning to decode with random decoding orders and the Vision-Content-Position module (VCP) for exploiting the connections among visual information, content and position. In addition, a new dataset named OLQT (Occluded and Low-Quality Text) is created by manually collecting text images that suffer from occlusion or low-quality from several standard text recognition datasets. The dataset is now available at https://github.com/djzhong1/OLQT. Experiments on OLQT and public scene text recognition benchmarks show that the proposed method achieves state-of-the-art performance. • The NDOrder can recognize text images with occluded and low-quality characters. • The ROG module ensures the method work with a novel decoding order. • The VCP module constructs a robust connection among image, content and position. • We contribute to a new scene text dataset OLQT with 245 text instances. [ABSTRACT FROM AUTHOR]

Epilepsy is a severe neurological disorder that causes seizures. It is detected by analyzing the electrical impulses of the human brain. Monitoring the brain is commonly done using an electroencephalogram (EEG). Seizure detection from the large recorded EEG dataset is a demanding task. However, numerous machine learning classifiers and the appropriate features can detect seizures. The Hjorth and statistical parameters are used in this study to provide an effective method for field programmable gate array (FPGA) realization of epileptic seizure detectors from EEG signals. Mobility, interquartile range (IQR), median absolute deviation (MAD), energy, non-linear energy, and simple square integral (SSI) are the various features analyzed in this work. The hardware architecture of the seizure detection system is captured in Verilog hardware descriptive language and realized on the Artix-7 FPGA. This paper presents three separate seizure detection models designed by pairing three different features with the Quadratic discriminant analysis (QDA) classifier. Among these three models, the energy and non-linear energy-based seizure detection system offers better performance than existing seizure detection systems because it possesses the lowest dynamic power consumption (0.116 µW), the highest design accuracy (99.4 %), and the highest sensitivity (100 %), which makes it the best seizure detection system for real-time applications. [ABSTRACT FROM AUTHOR]

Automatic humor detection has compelling use cases in modern technologies, such as humanoid robots, chatbots, and virtual assistants. In this paper, we propose a novel approach for detecting and rating humor in short texts based on a popular linguistic theory of humor. The proposed technical method initiates by separating sentences of the given text and utilizing the BERT model to generate embeddings for each one. The embeddings are fed to a neural network as parallel lines of hidden layers in order to determine the congruity and other latent relationships between the sentences, and eventually, predict humor in the text. We accompany the paper with a novel dataset consisting of 200,000 short texts, labeled for the binary task of humor detection. In addition to evaluating our work on the novel dataset, we participated in a live machine-learning competition to rate humor in Spanish tweets. The proposed model obtained F1 scores of 0.982 and 0.869 in the performed experiments which outperform general and state-of-the-art models. The evaluation results confirm the model's strength and robustness and suggest two important factors in achieving high accuracy in the current task: (1) usage of sentence embeddings and (2) utilizing the linguistic structure of humor in designing the proposed model. • A novel method for humor detection and rating based on a general linguistic theory of humor. • Introduced a very large novel dataset with 200k short texts for humor detection. • Achieved 98% accuracy and outperformed five strong baselines on the new dataset. • Demonstrated accuracy and robustness in a data science competition for Spanish texts. • The novel approach and dataset contributed to tens of research projects. [ABSTRACT FROM AUTHOR]

Disruptions occurring at an urban rail transit (URT) system can severely affect its normal operations, and an effective bus bridging service (BBS) is able to help to reduce the negative effects. Transit operators usually arrange BBS to depart from the disrupted stations to evacuate the stranded passengers. However, the overload of passengers at the disrupted stations, especially at turnover and transfer stations, may incur the secondary operation disruptions such as stampede accidents. To mitigate the negative effects of disruptions and reduce the number of passengers stranded at the disrupted stations, the strategy based on the passenger guidance and extended BBS (E-BBS) is introduced in this paper. Different from the widely applied standard BBS running within the disrupted links, E-BBS runs among the normal operating stations or between the normal operating stations and the disrupted stations. A mixed integer linear programming model is developed in this paper to guide the stranded passengers and design an optimal E-BBS solution to transport them. Considering the bi-directional running trains along the disrupted links, a dynamic decision framework is developed to manage the disruptions. Given the impacts of the high uncertainty on bus running time which could affect the performance of E-BBS, a robust model is proposed to obtain more reliable travel guidance and E-BBS schemes. Numerical experiments based on Chengdu subway system in China are conducted. The results indicate that the proposed model can obtain optimal travel guidance and E-BBS solutions in a timely manner. When the uncertainty on bus running time is ignored, the total travel cost for affected passengers is reduced 14.20 % on average with the aid of the optimal travel guidance and E-BBS solutions. Moreover, the number of passengers gathering at the disrupted stations decreases by 36.80 %. The robust model can obtain more reliable travel guidance and E-BBS schemes in consideration of uncertain bus running time. The proposed model shows great potential to effectively mitigate the negative effects of disruptions and help to enhance the capability of a URT system to respond to disruptions. [ABSTRACT FROM AUTHOR]

• The 2S attack matrix on the actual time sequence with the two loopings. • The precise forensics' timeline on the real case attack. • The in-depth technical details of the attacks within the energy sector. • The insight into the attacker's behaviors for network admins. • The protection begins with a clear understanding of the ransomware attack pattern. Due to the Coronavirus pandemic (COVID-19) throughout 2020–22, remote working has played an important part in organizations, businesses, and agencies worldwide. This situation makes the various cybersecurity threats the Internet poses, especially ransomware. Ransomware will remain the top cybersecurity threat, and the energy sector is the prime target. Previously, research papers only focused on the analytical and protection frameworks. These papers rarely provide real evidence and detailed digital forensics. Interestingly, the ransomware gangs developed new methods but still used similar attack patterns. The authors envisage that a precise understanding of the ransomware attack characteristics is a starting point for the correct detection process. This paper presents a true case study demonstrating the actual occurrence of digital forensics and in-depth technical details of the attacks within the energy sector. The significant attack patterns, which have never been emphasized in research papers, can be proposed for the two loops. The results led to a novel ransomware attack matrix with two loop patterns (dwell time factor) applicable to other ransomware gangs for the detection stage of the NIST. [ABSTRACT FROM AUTHOR]

Smart vehicles have a rising demand for computation resources, and recently vehicular edge computing has been recognized as an effective solution. Edge servers deployed in roadside units are capable of accomplishing tasks beyond the capacity which is embedded inside the vehicles. However, the main challenge is to carefully select the tasks to be offloaded considering the deadlines, and in order to reduce energy consumption, while delivering a good performance. In this paper, we consider a vehicular edge computing network in which multiple cars are moving at non-constant speed and produce tasks at each time slot. Then, we propose a task offloading algorithm, aware of the vehicle's direction, based on Rainbow, a deep Q-learning algorithm combining several independent improvements to the deep Q-network algorithm. This is to overcome the conventional limits and to reach an optimal offloading policy, by effectively incorporating the computation resources of edge servers to jointly minimize average delay and energy consumption. Real-world traffic data is used to evaluate the performance of the proposed approach compared to other algorithms, in particular deep Q-network, double deep Q-network, and deep recurrent Q-network. Results of the experiments show an average reduction of 18% and 15% in energy consumption and delay, respectively, when using the proposed Rainbow deep Q-network based algorithm in comparison to the state-of-the-art. Moreover, the stability and convergence of the learning process have significantly improved by adopting the Rainbow algorithm. • We propose a Rainbow-based task offloading algorithm for vehicular networks. • The proposed algorithm aims to jointly minimize average delay and energy consumption. • The performance of the proposed approach is evaluated using real-world traffic data. • Experiments demonstrate significant improvement achieved by the proposed algorithm. [ABSTRACT FROM AUTHOR]

The transformer architecture with its attention mechanism is the state-of-the-art deep learning method for sequence learning tasks and has achieved superior results in many areas such as NLP. Utilizing the transformer architecture for the prediction of sequential time series such as financial time series has hardly been investigated in previous studies. In this research paper, the transformer architecture with time embeddings is used in foreign exchange (FX) trading, the world's largest financial market, and tests its suitability. A systematic comparison is made between transformer and benchmark models. It also examined which influence multivariate, cross-sectional input data have on the forecasting performance of the various models. The goal of the paper is to contribute to the empirical literature on FX forecasting by introducing a transformer with time embeddings to the forecasting community and assessing the accuracy of corresponding models by forecasting exchange rate movements. Empirical results indicate the suitability of transformer models for FX-Spot forecasting in general but also evidence the need for transformer models for multivariate, cross-sectional input data to outperform other state-of-the-art neural networks such as LSTM. [ABSTRACT FROM AUTHOR]

The open-source nature of Android, along with its coarse-grained permission management and widespread use, has heightened its vulnerability to malware threats. However, many traditional approaches face limitations in extracting comprehensive features, which hinders accurate and efficient Android malware detection. In this paper, we propose an effective hybrid approach combining an improved multi-scale convolutional neural network (MSCNN) with residual networks (ResNet) to defend against Android malware. The approach comprises an enhanced feature extraction network and a detection network. Initially, we introduce MSCNN, a novel deep learning model for comprehensive feature extraction. The MSCNN extends into three branches at distinct levels, concatenating features from low to high dimensions. This multilevel structure preserves rich semantic features while avoiding complex feature selection and analysis. Further, ResNet is employed as the detection network, and the hybrid models' performance is evaluated by comparison with a single ResNet. Finally, we validate the effectiveness of our approach by comparing our experimental results with state-of-the-arts. The experimental results show our approach effectively detects Android malware with high accuracy (99.20%) and precision (99.49%), and utilizing MSCNN as a multilevel feature extraction network significantly enhances the performance of the hybrid models, particularly, the F1-Score of MSCNN+ResNet18 increases by 4.8%. • Propose an improved MSCNN model extracting features from various data levels. • Design hybrid models combining MSCNN with GRU, ResNet18, ResNet34 and ResNet50. • MSCNN acts as upper feature extraction layer. • GRU, ResNet18, ResNet34 and ResNet50 as detection network, respectively. • Our approach detects Android malware, and enhances the hybrid model performance. [ABSTRACT FROM AUTHOR]

The main difficulties in semantic segmentation of remote sensing images include the effect of shadows, the blurring of feature differences between categories, and loss of small-scale category features during processing. To deal with these challenges, we propose a semantic segmentation network for RSI based on multi-scale features and global information modeling. A skillfully designed two-branch fusion attention based on an adaptive fusion converter is added to the multilevel cascaded HRNet structure to better combine multiscale features and global modeling information. Prior to this, "Coordinate attention" was combined with "Spatial attention" designed in this paper to form a Feed-forward Attention Layer (FAL) to encode finer feature information cues. Meanwhile, a more refined multilayer decoder is designed to obtain better image category recovery. Various experiments were conducted on four different scenarios and types of datasets including WHDLD, Potsdam, Vaihingen, and LoveDa, and in terms of the significant evaluation metric MIOU, with dividing the training, validation, and test sets in the ratio of 6:2:2, the performance of our model on the above four datasets was obtained with 61.79%, 70.79%, 81.15%, and 52.55%.In addition, a comparison with other excellent works is made and the results show that our designed model has better performance. [ABSTRACT FROM AUTHOR]

Similarity is a vital component for neighborhood-based collaborative filtering (CF). To improve the quality of recommendation, many similarity methods have been proposed and analyzed in recent decades. However, nearly all traditional similarity methods and many advanced similarity methods only utilize corated items among users to compute their similarity, which provides limited information in cold-start/sparse scenarios and yields misleading results. In addition, although a few advanced hybrid similarity models consider items beyond corated items, which can partly mitigate the above limitation, they still have drawbacks, such as disregarding penalizing noncorated items that have many disadvantages. In this paper, we explore a new robust hybrid similarity model, namely Wasserstein distance-based CF (WCF) model, for mitigating the cold-start problem of CF in sparse data. Specifically, we measure item similarity via the Wasserstein distance, which can help circumvent the drawbacks in the Bhattacharyya coefficient and KL divergence that are used in the literature, and is thus more robust in a cold-start/sparse scenario. Besides, we further design a new multiplicative user similarity formula which identifies all noncorated items as a whole to prioritize the importance of corated items and impair the negative effects of noncorated items, which will also play an important role in a cold-start/sparse scenario. In addition, we also propose two novel heuristic similarity factors to impair the negative effects of popular users and items as supplements. We conduct extensive experiments on five real-world benchmark recommendation datasets to test WCF. The experimental results show the superiority of WCF over other existing similarity methods in cold-start/sparse scenarios. • A novel formula is proposed to compute user similarity. • The Wasserstein distance is adopted to compute item similarity. • Two novel factors are proposed to enhance the reliability of user similarity. • Results show that our proposed model outperforms existing similarity methods. [ABSTRACT FROM AUTHOR]

This research paper presents a comprehensive experimental and statistical approach for the analysis of vibration amplitudes in a high-speed rotating shaft employing a squeeze film damper (SFD). The research combines a comprehensive analysis that connects input parameters and response parameters, with a special emphasis on vibration amplitudes along the X and Z axes. This research utilizes the rigorous procedures of Response Surface Methodology (RSM) together with a Box-Behnken design and harnesses the capabilities of Artificial Neural Network (ANN) optimization techniques. The variables under scrutiny encompass critical factors such as shaft rotational speed, extending up to 8000 rpm, oil pressure, with a range extending up to 100 bar, and various oil mix ratios, spanning from 10 % to 50 %. Various statistical measures are computed to assess the errors and coefficients of determination of the projected models. The artificial neural network (ANN) model has shown somewhat reduced prediction errors and a greater coefficient of determination compared to the Response Surface Methodology (RSM) for both the x and z axes of vibration amplitude. The values of mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R-squared) are found for both x and z axes from RSM (3.50, 3.77), (4.50, 4.72), and (0.81, 0.79), (1.88, 1.70), (2.41, 2.12), and (0.94, 0.95), respectively, using the ANN model. The overall mean absolute percentage error (MAPE) from the ANN model of both the x and z axes (9.73 %, 9.38 %) is found to be lower compared to the RSM model (18.18 %–20.50 %). The conclusive research reveals that the artificial neural network (ANN) prediction model outperforms the regression model based on Response Surface Methodology (RSM), exhibiting superior accuracy in predicting vibration amplitudes. The ANN approach is an excellent option for calculating vibration amplitudes in high-speed rotating shafts. Additionally, it provides significant benefits in terms of effectiveness and time economy. This research provides valuable new insights into the most efficient modeling approaches for vibration management and highlights the benefits of using Artificial Neural Networks (ANN) for predictive assessments in this context. Particle Swarm Optimization is used to minimize the vibration amplitude of the shaft along the x and z axes using experimental data. [ABSTRACT FROM AUTHOR]

Nowadays, cloud organizations face challenges in managing huge count of data with various resources due to the prompt expansion of cloud computing (CC) environments with customers ranging from individual users to large commercial organisations. Ineffective resource management can reduce the cloud computing performance. Consequently, it is imperative to distribute resources fairly among various stakeholders while maintaining the organizations profitability and user satisfaction levels. It is not acceptable to indefinitely reject a client's request simply, because basic resources are not available to all. Therefore, the Resource Allocation with Efficient Task Scheduling in Cloud Computing Using Hierarchical Auto-associative Polynomial Convolutional Neural Network (RA-HAPCNN-CC) approach is proposed in this paper to address the mentioned issues. The features of proposed RA-HAPCNN-CC approach are: (i) Starling Murmuration Optimizer (SMO)-based short scheduler decreases the make-span time and increases throughput for task scheduling, (ii) Hierarchical Auto-associative Polynomial Convolutional Neural Network (HAPCNN) for effective resource allocation under various design constraints, like bandwidth, resource load, (iii) Fractional Discrete Meixner Moments Encryption (FDMME) is considered for data encryption to offer protection for data storage, (iv) RA-HAPCNN-CC approach is analyzed to the state-of-art methods to verify the efficiency. The outcomes of resource utilization, energy consumption, response time demonstrate that the RA-HAPCNN-CC method is better than existing one. The performance of the proposed method attains 27.5 %, 10.32 %, 16.65 % lower energy consumption, 30.93 %, 11.14 %, 15.3 % higher throughput compared with existing models. [ABSTRACT FROM AUTHOR]

In the process of medical robot assisted bone milling surgery, the accuracy of recognition of milling state is crucial for surgical safety. However, previous studies have rarely used neural networks for signal analysis and processing, and not included attention mechanisms in neural networks to distinguish the weights of different signal features. In this paper a tactile-auditory attention model for milling state recognition is proposed. The model combines attention mechanism with fully connected neural networks. First, the milling state is divided into four types: idling, cortical bone, cancellous bone, and muscle. The acceleration and sound pressure information are extracted in 13 dimensions each, including 3-dimensional time-domain features and 10-dimensional frequency-domain features. Second, a milling state classification network with attention mechanism was established, including pre-connected attention mechanism (Pre-AT) and embedded attention mechanism (Emb-AT). The experimental results showed greater performance than other traditional methods, with test set accuracy of 94.57% and 95.29%, respectively. Afterwards, the impact of single signal and fused signal on recognition results was explored. From the experimental results, fused tactile-auditory signals had higher accuracy than single signal recognition. The accuracy rates of the test set using fused signals and acceleration and sound pressure signals were 95.29%, 92.09% and 90.07%. In addition, attention vectors are visualized to identify the degree of emphasis on different signals during the recognition process. [ABSTRACT FROM AUTHOR]

Feature selection facilitates uncertainty disposal and information mining, and it has received widespread research interests. Divergence-based fuzzy rough sets (Div-FRSs), a new kind of fuzzy rough sets, have been applied to feature selection and induced two efficient algorithms, FS-AFS and FS-RFS. Nevertheless, FS-AFS and FS-RFS still have advancement space, because the dependency functions only focus on lower approximation and ignore the uncertainty in upper approximation, which will certainly undermine the algorithmic evaluation effects. To this end, this paper introduces the upper approximation and fuses it with lower approximation via class-specific pattern and Spearman coefficient to construct a new information measurement for metric perfection, called Spearman-based self-information. Relying on this new measurement, a novel feature selection algorithm SPESI is established to improve FS-AFS and FS-RFS. At first, Spearman coefficient is introduced and upper approximation is defined. Second, class-driven precision and roughness are built by incorporating Spearman coefficient-based class-specific weight vectors with class-driven lower and upper approximations. Meanwhile, the granulation monotonicity of newly-defined measurements is also explored. Then, the core measurement Spearman-based self-information is firstly given and its feature significance motivates a feature selection algorithm SPESI with heuristic search. Finally, data experiments are implemented to validate the effectiveness of SPESI, and a conclusion can be drawn that SPESI outperforms FS-AFS and FS-RFS to acquire better classification performances with fewer feature numbers and less running time. • Upper approximation is first defined in Div-FRSs to induce measurement. • Class-specific information of D s enriches decision analysis. • Spearman correlation coefficient reveals the relevance between classes. • Algorithm SPESI outperforms FS-AFS and FS-RFS to offer better classification performances. [ABSTRACT FROM AUTHOR]

Multi-band image fusion is a vital image processing technique used to combine data from multiple images or sensor bands, particularly in scenarios where a wide range of spectral information is available. Its primary objective is to create a single, comprehensive image that not only visually enhances the scene but also preserves critical details and characteristics present in each source. This paper proposes a novel image fusion technique that combines the useful features from a set of source images to provide a quick visualization of the scene. The approach is highly beneficial for multi-band images, including a large number of bands acquired by sampling the wavelength spectrum at narrow intervals. The fusion process depends on a multi-objective cost function, which optimizes the resultant fused image according to specific desired characteristics. By solving this optimization framework, an optimal set of weights is obtained using a novel Fusion-Driven Atom Search Optimization with Crossover (FASO-C) algorithm for the fusion of the image bands. Crossover operation enhances the exploitation capability of ASO, enabling the global optimal solution to be achieved quickly. To further validate the effectiveness of the proposed fusion model, various experiments were conducted to assess its performance using both subjective and objective metrics, as well as analyze its convergence. [ABSTRACT FROM AUTHOR]

The commercialization of Fuel Cell Systems (FCSs) faces a key obstacle in the form of limited cell lifespan and resultant cell degradation. This paper introduces a new approach, leveraging an artificial intelligence-based 2DOF control system to regulate the Oxygen Excess Ratio (OER) with two main goals: mitigating cell degradation due to oxygen starvation and optimizing net power output. The proposed control system incorporates a data-driven feedforward controller in conjunction with a feedback controller, facilitating the tracking of desired OER values generated by a data-driven reference generator. We develop fuzzy models and neural networks as the reference generator and feedforward controller to capture the complex FCS behavior by processing the stack current w/wo the temperature of FCS (i.e. Single input or Double input models). By exploring the effects of the structural settings of the models, this study provides a comprehensive understanding of their impact on the representation performance of the FCS characteristics. Although the fitting performances of all models are quite satisfactory, their actual performance gain is evaluated on a realistic FCS model at various operation points. The findings and comparative analysis emphasize the efficacy of incorporating stack temperature in fuzzy-model-based 2DOF control systems, showcasing their potential to maximize net power output through enhanced OER control loop performance while also extending the lifespan of FCSs, as confirmed by results from a developed degradation model. • Improved net output power through the integration of AI in a 2DOF control system. • Reduction of degradation using a data-driven 2DOF control system. • Development of data-driven reference generators and feedforward controllers. • Comparative performance evaluations of fuzzy models and neural networks. [ABSTRACT FROM AUTHOR]

Portfolio management (PM) is a central subject of finance that presents many unresolved challenges. Although solutions have been proposed since the 1950's, recent advances in machine learning are revolutionizing investments. Whereas supervised paradigms such as regression and classification are established in this direction, emerging research suggests that the learning-to-rank (LtR) paradigm can be more effective. Yet, these works are not many and overlook some important aspects. These aspects include the risk inherent in stocks, feature representation, portfolio cardinality and allocation. Addressing these gaps, this paper presents Stochastic-Aware Bootstrap Ensemble Ranking (SABER), an LtR method that directly minimizes the uncertainty and improves ranking performance. In addition, we propose Merged Bootstrap Selection for dynamic portfolio cardinality optimization. Trained on macroeconomic, fundamental and market indicators, the proposed methods outperform a state-of-the-art LtR approach, reaching annual returns and volatility of 83.48% and 29.89% across 6 years. The former also considers renowned weight allocation methods and achieves Sharpe and Sortino ratios of 2.79 and 5.28 respectively. Finally, the computational complexity of the proposed method is proven comparable to that of current methods. • Comprehensive approach to stock ranking, portfolio cardinality and weight allocation. • Risk-aware stock ranking method based on the learning-to-rank (LtR) paradigm. • Effective integration of market, fundamental and macroeconomic features. • Experiments with five renowned portfolio allocation methods. • The proposed strategy achieved Sharpe and Sortino ratios of 2.79 and 5.28. [ABSTRACT FROM AUTHOR]

In the decade, researchers have proposed many remarkable algorithms in structural design, training modes, etc., in the field of Generative AI. However, with the explosive growth of demand for data and annotation in generative models and the emphasis on data-centric algorithms, improving model performance by improving data-efficiency has become another way for the future development of generative models. In this paper, we propose a new strategy to improve the performance of the generative models inspired by active learning. Through the cognitive feature extractor of generative models (similar oracle in active learning) to complete the annotation of data informativeness. By guiding the generative models to focus on samples in low-feature density region, i.e., with high informativeness, the models can gradually achieve "full-cognition" of the data. We conduct extensive experiments to verify the effectiveness of our strategy and demonstrate its widespread application in generative models and downstream data-driven tasks. [ABSTRACT FROM AUTHOR]

• A transform-based feature reconstruction network is designed for missing modalities. • The model reconstructs missing element features to improve the robustness. • Modality-invariant representation is used in missing modalities. • Modality-invariant temporal representation is used to mitigate heterogeneity. • Experimental results show the superior performance of our proposed method. The investigation of missing modalities aims to extract valuable feature information from missing multi-modal data, it is a focal point in multi-modal learning. Existing missing modalities processing methods primarily focused on multi-modal fusion schemes to achieve optimal performance, but they faced the following two key challenges: (1) how to improve the robustness of incomplete multi-modal sequence representation, (2) how to effectively learn modality-invariant representations to mitigate heterogeneity between modalities. In this paper, we propose a m odality- i nvariant t emporal representation learning-based f eature r econstruction net work called MIT-FRNet for the missing modalities to tackle these challenges. In the MIT-FRNet, we first extract the latent features for each modality considering intra-modality and inter-modality, and then introduce an encoder-decoder framework to address the first challenge, it reconstructs missing element features via taking the incomplete modal sequences as input and implementing the inter-modal and cross-modal attention mechanisms for feature extraction. And then, through treating each timestamp as a single Gaussian distribution, we design a fine-grained similarity constraint based on distribution-level modality-invariant representations to learn effective modality-invariant representations, thereby addressing the second challenge. Finally, the efficiency of proposed model is validated through the classification results after multi-modal fusion that involves using a gate encoder to pass it and followed by a vector fusion to fuse it. Extensive experiments on public benchmark datasets demonstrate that the proposed MIT-FRNet method achieves promising results under varying missing rates while exhibiting good convergence. [ABSTRACT FROM AUTHOR]

In this paper, the distributed Nash equilibrium seeking problem for multi-agent finite games is considered. Considering the locally-informed communication structure, previous centralized game-theoretic learning dynamic methods are not feasible. To this end, we propose a distributed log-linear algorithm by introducing a timestamp-based communication mechanism that enables agents to acquire estimates of the true action profile from their neighborhoods. It is shown that the proposed distributed log-linear algorithm significantly outperforms the existing best response dynamics regarding both effectiveness and reliability. For illustration, a locally-informed multi-player Sudoku puzzle is introduced, where each cell is taken as a player, and each player fills numbers only based on the local information of its neighboring players. The simulation results validate the effectiveness of our algorithm in solving the locally-informed multi-player Sudoku puzzle. Our methodology provides a viable and benchmark approach to address the fully distributed locally-informed multi-agent joint decision-making problem. • A distributed log-linear algorithm is proposed for Nash seeking in finite games. • A locally-informed multiplayer Sudoku puzzle is initialized to evaluate algorithm. • The proposed algorithm is superior in terms of both effectiveness and reliability. [ABSTRACT FROM AUTHOR]

Dynamic constrained optimization problems (DCOPs) are common and important optimization problems in real-world, which have great difficulty to solve. Dynamic constrained evolutionary algorithms (DCEAs) are widely used methods for solving DCOPs. However, existing DCEAs often struggle with convergence, particularly for DCOPs with drastic dynamic changes or intricate constraints. To address this issue, this paper proposes a novel DCEA called DCEA-DQN, which leverages the powerful perception and decision-making capabilities of Deep Q-Network (DQN). DCEA-DQN integrates two DQNs to enhance its performance. The first DQN is designed to adaptively respond to dynamic changes, enabling effective handling of DCOPs with various types and degrees of changes. It provides a high-quality re-initialized population for subsequent static optimization, resulting in faster and improved convergence. The second DQN is introduced to guide the mutation direction during offspring generation. It steers the population towards better feasible regions or directs it towards the optimal individual within the current feasible region. Moreover, a penalty mechanism is employed to handle constraints during offspring generation. To evaluate the performance of DCEA-DQN, comprehensive empirical studies are conducted using a new test suite called C-GMPB and a dynamic flexible job-shop scheduling problem. The experimental results, using two commonly used metrics E B and E O in the field of DCOPs, demonstrate that DCEA-DQN outperforms six state-of-the-art DCEAs and achieved optimal performance on 80% and 75% of all 24 test problems, respectively. The source code for DCEA-DQN is available at https://github.com/CIA-SZU/YRT. • A change response strategy based on DQN is proposed for complex DCOPs. • An offspring generation strategy based on penalty and DQN is proposed for complex DCOPs. • A new complex dynamic constrained test suite C-GMPB is proposed. [ABSTRACT FROM AUTHOR]

Most existing deep learning-based polyp segmentation methods neglect two important aspects of polyps: the geometric orientation information of polyps and the point information of the entire colonoscopy area. In this paper, we introduce a multi-view orientational attention network (MVOA-Net), which incorporates orientation and point awareness to effectively address the issue of intra-class inconsistency resulting from variations in polyp shape, size, and position, as well as the inter-class indistinction caused by the high similarity between polyp lesions and surrounding tissues. To achieve robust orientation awareness, we propose a novel geometric orientation transformer encoder (GOTE) based on horizontal and vertical views. Moreover, To simultaneously capture the global context information of GOTE and emphasize the important local information of the convolution-based attention encoder (CBAE), a global and local cross attention fusion module (CAFM) is also proposed to simultaneously model the long-range dependencies of polyps and pay sufficient attention to the local boundaries of polyps. Additionally, a efficient atrous spatial pyramid pooling (E-ASPP) module is proposed to enhance the semantic representation of high-level features. Finally, a point-based affinity module (PBAM) and a multi-scale fusion module (MSFM) are proposed to distinguish the disguise of polyps, further alleviating inter-class indistinction. The ablation study results demonstrate the effectiveness of each component. Quantitative and qualitative experimental results show that MVOA-Net achieves the best segmentation accuracy across domain polyp datasets and has obvious advantages in segmenting multiple polyp objects. [ABSTRACT FROM AUTHOR]

Rice is a crucial agricultural crop, yet it frequently suffers from various diseases, leading to decreased yields and, in severe cases, crop failure. Diseases significantly affect rice growth and yield, resulting in economic losses and food security challenges. The role of image recognition in identifying rice diseases is critical in agricultural production. It enables automated and efficient detection of rice diseases, which is essential for effective management, ensuring food security and sustainable agriculture. To address issues like background noise and edge blurring in rice disease image capture, as well as challenges in determining the optimal learning rate during the training of traditional rice disease recognition networks, a novel method based on PSOC-DRCNet is proposed for rice disease recognition.. First, tto solve the problem of background interference, Dual Mode Attention (DMA) is proposed to adaptively capture meaningful regions in rice disease images. Second, the Residual Adaptive Block(RAB) is proposed, which utilizes dimensional changes and channel attention to solve edge blur problems. Then, a Cross entropy and regularized mixed Loss function (CerLoss), is proposed to optimize the learning strategy of the model in the process of processing datasets and enhance the performance and generalization ability of the model to avoid overfitting problems. Ultimately, In response to the cumbersome problem of finding the optimal learning rate, we propose using Particle Swarm Optimization Chameleon (PSOC) to find the optimal learning rate and train the PSOC-DRCNet model on our custom dataset and compare it with other existing methods and the final average classification accuracy of PSOC-DRCNet is 93.88% with an F1 score of 0.940. We compare it with other existing methods. It is proved that the average classification accuracy of our model under hyper-parameter unification is 92.65% F1 score is 0.928. We validated the PSOC-DRCNet by conducting comparative analyses with other models and through generalization experiments and module effectiveness tests. Additionally, the practicality of PSOC-DRCNet was confirmed through its application in real-world scenarios. The methods proposed in this paper successfully enable the identification of various diseases in rice leaves, offering a practical solution for incorporating deep learning into the agricultural production process. Furthermore, these findings serve as a valuable reference for disease identification in other crops. [ABSTRACT FROM AUTHOR]

• The equilibrium distribution and dynamic subspace approximation (EDDSA) is proposed. • The double subspace transformation is introduced into EDDSA. • The divergence problem in EDDSA is minimized using dynamical change strategy. Nowadays, big data analysis has become an important approach in social information network. However, the social information may not be distributed independently and identically (i.i.d.), which can be addressed using domain adaptation. However, most of the existing domain adaptation methods are designed to align cross-domain distributions. The label information of the samples in the target domain is completely unavailable. Thus, the class-conditional distribution differences cannot be well measured, and the effect of feature distortion on distribution alignment in the original feature space is difficult to handle. This paper proposes a domain adaptation learning based on the Equilibrium Distribution and Dynamic Subspace Approximation (EDDSA) to alleviate these problems. First, EDDSA learns to project the source and target domains into associated feature spaces, and dynamically approximates two subspaces to overcome the feature distortion problem. Second, the balanced distribution alignment term is introduced to dynamically weight the importance of the conditional and marginal distributions. Through many experiments, EDDSA is superior to most traditional methods. [ABSTRACT FROM AUTHOR]

Social robots are increasingly becoming part of our society. In this sense, such robots' interaction capabilities depend largely on their ability to detect and respond to stimuli in their environment as humans would. This paper describes a bio-inspired exogenous attention-based perception architecture for social robots. Exogenous attention regulates those involuntary attentional processes driven by the salience of perceived stimuli. The architecture incorporates bio-inspired concepts, such as inhibition to return, focus of attention selection and detecting salient stimuli, that have been validated on a real social robot. We have integrated several multimodal mechanisms for recognising salient visual, auditory, and tactile stimuli. Then, the attention architecture's performance was evaluated by comparing it to a ground truth gathered from interactions of 50 users, obtaining comparable responses in real-time. • Exogenous attention deals with information from different modalities. • Exogenous attention enables robots to react naturally to unexpected events. • The robot creates 3D representation of the environment with salient stimuli. • The robots can autonomously decide the exogenous attention focus in real time. [ABSTRACT FROM AUTHOR]

A dual stator winding induction motor (DSWIM) has two isolated three-phase windings in its stator, and its rotor is a usual squirrel cage type. In a sensor-less DSWIM drive, the standard and optimal operating mode in all operating speed ranges is the synchronous mode. Until now, researchers use the asynchronous mode to control it in the low speed range that is not the standard mode. But, this paper proposes a new intelligent model reference adaptive system (IMRAS) to control a DSWIM drive without the speed sensor based on a ten-switch converter in the low speed range. In the proposed intelligent sensor-less DSWIM drive, the rotor speed is estimated via an intelligent model as single and bi-objective functions. In the proposed IMRAS, the second objective increases the speed estimation accuracy at very low speeds. In this idea, the rotor speed error is used as data in the rotor speed estimation process. As a result, the convergence between estimated speed and reference speed in the proposed IMRAS is increased at zero and very low speeds. Also, in this paper, the power losses, the capital cost, and the number of switching elements in the converter are reduced via the concept of flux compensation and using a ten-switch converter. The intelligent proposed sensor-less DSWIM drive, unlike conventional methods, works in its standard operating mode (synchronous mode) and has a suitable performance in the low speed range. Hence, the converter power losses are significantly decreased. The suggested techniques are simulated in MATLAB software. The simulation of the proposed DSWIM drive system is performed under different scenarios of operating conditions and the obtained results approve the assumptions. [ABSTRACT FROM AUTHOR]

Gender identification at the word level in a multi-script environment is challenging due to variations posed by free-style handwriting of individuals and geographical differences in writing styles. This paper presents a new approach, Multi-Orientation-Scale Gabor Response Fusion (MOSGF), for gender identification at the word level using handwritten text. Our method has two steps: (i) word segmentation from unconstrained lines and (ii) gender identification at the word level. In the first step, the method explores the number of zero crossing points and gradient information for word segmentation from handwritten text lines. In the second step, employs Gabor responses at different orientations and scales to detect fine details in female and male handwriting. For each Gabor response, the proposed model estimates the correlation between average templates of all Gabor responses and the individual Gabor response to extract global consistency in writing. To strengthen correlation features, the proposed method uses the Mahalanobis distance measure, which extracts local similarity. Further, the proposed approach fuses correlation coefficient and distance-based features in a novel way. The fused features are then fed to a Neural Network (NN) for gender identification. Experiments on our dataset, which comprises Roman (English), Chinese, Farsi (Persian), Arabic, and Indian scripts, and a benchmark dataset, namely, IAM which includes English text, KHATT which includes Arabic, and QUWI which includes both English and Arabic, show that the proposed system outperforms the existing methods in terms of word segmentation and gender identification. [ABSTRACT FROM AUTHOR]

Efficient routing and scheduling are critical for providing patients with quality health care in their homes, and palliative care involves specific requirements. This paper addresses the Palliative Home Health Care Routing and Scheduling Problem (PHHCRSP) through an integrated mathematical model. Key considerations include caregiver skills, care continuity, and a multi-period planning horizon. Special attention is also given to the case of clustered patients. Five formulations with different objective functions are analyzed and solutions reveal that optimizing only for minimum or maximum workload leads to non-efficient routing. The formulation that balances the total workload and the minimum workload emerges as the most effective, as it manages to obtain good routes while distributing the workload evenly among the caregivers. The results of the computational study on a set of well-known benchmark instances show that it is possible to obtain good patient care while keeping good working conditions for the caregivers. • We address the Palliative Home Health Care Routing and Scheduling Problem (PHHCRSP). • We develop and analyze five formulations with alternative objective functions. • We present valid constraints that improve the problem formulations. • The most effective formulation balances both the total and the minimum workload. • An extensive computational study is conducted on well-known benchmark instances. [ABSTRACT FROM AUTHOR]

In this paper, we propose a technique for hierarchical yoga pose classification (YPC) in a multi-stage multi-tasking framework. We propose a three-stage transfer learning based end-to-end training methodology. Novelty lies in (a) proposed supervised contrastive combined loss function for stage-1 training, (b) proposed Encoder–Decoder network architecture with attention mechanism for stage-3 training, (c) proposed spatial context aware multi-tasking combined loss function for stage-3 training. Firstly, for stage-1 training, we propose the usage of linear combination of three loss functions: cross-entropy, self-supervised contrastive loss and supervised contrastive loss in a multi-tasking manner. We introduce radial and cosine margin into the formulation of self-supervised and supervised contrastive loss to pull feature embeddings of same class closer together compared to feature embeddings of different classes. Weights learned over stage-1 training are subsequently fine-tuned over cross-entropy multi-tasking loss in stage-2. These stage-2 weights are transfer learned and are further fine-tuned in stage-3 training. For stage-3 training, we propose the usage of spatial context aware multi-tasking combined loss function. This loss function leverages on the fine-grained spatial features obtained from HiResCAM. These are processed in parallel with features obtained from XGrad-CAM (sensitivity and conservation axioms satisfying features) to further supervise the learning of hierarchical yoga pose classifier. We exemplify our methodology on the publicly available Yoga-82 large-scale dataset. We report peak Top-1 YPC accuracy of 95.89% over 6 pose classes (Yoga-6), 93.85% over 20 pose classes (Yoga-20) and 90.0% over 82 pose classes (Yoga-82). Our proposed method achieves 6.1% improvement over Top-1 classification accuracy in Yoga-6 hierarchy, 9.3% improvement in Yoga-20 hierarchy and 10.9% improvement in Yoga-82 hierarchy in comparison with state-of-the-art (SOTA) methodology. We achieve the current best Top-1 classification accuracies in all the three YPC hierarchies. [Display omitted] • Novel spatial context aware multi-tasking multi-stage end-to-end training method. • Improved spatial context awareness, evident through improved CAM explanations. • Improved inter class margins and intra class compactness. • Achieved SOTA hierarchical yoga pose classification accuracies on Yoga-82 dataset. [ABSTRACT FROM AUTHOR]

As an increasing number of investors share their opinions on social networks, a critical challenge is to provide advice and assistance in making well-informed investment decisions by considering enormous online sentiments. A typical way is to aggregate investors' sentiments into an investing signal. Most previous studies of sentiment aggregation rely on human-defined rules summarized from experience, which are widely accepted for simplicity and interpretability. However, the relations between investor sentiments and wise investment decisions generated by integrating sentiments could be complex and counter-intuitive, which may not be fully described by human-defined rules and require further investigation. This paper proposes a novel machine learning-based method called FollowAKOInvestor to integrate investors' sentiments more effectively for highly profitable stock recommendations. It divides investors into groups by clustering algorithm or their expertise levels, then extracts sentiment features from each group to train a machine learning model. The outputs are utilized to score stocks and provide investment recommendations. Based on an extensive dataset spanning from January 2017 to December 2019, sourced from StockTwits, we simulate a one-year recommendation procedure to compare and evaluate the performance of the proposed method and baselines. The experimental results support the superiority of machine learning over human-defined rules in making the most of sentiments from various investors for stock recommendations. • A novel machine learning-based method is proposed to aggregate investor sentiments. • Sentiments from various investors matter for the stock recommendation. • Applying machine learning to follow various investors boosts performance. • Comparative results on a real-world dataset corroborate the efficacy of our method. • It provides implications for investment practice and crowd intelligence generation. [ABSTRACT FROM AUTHOR]

• End-to-End learning using a deep hierarchical CNN to identify crack regions. • Precision through Kernel Dynamics that accurately characterise the crack pattern. • Parallel channels that enable learning crack pattern at multiple scales. Structural health monitoring plays a crucial role in assessing the condition of civil structures and ensuring their safety and maintenance. One important aspect of structural assessment is the detection and analysis of cracks, which can occur in various structures such as bridges, buildings, tunnels, dams, monuments, and roadways. Recent advancements in crack classification and segmentation techniques have utilized convolutional neural network (CNN) variations. In this paper, we propose an end-to-end learning approach utilizing a deep hierarchical CNN for crack region identification. The proposed architecture leverages high pass kernels in the early convolutional layers to accurately capture the crack patterns, complemented by learnable filters to facilitate adaptive learning. Furthermore, parallel channels within the network enable the learning of cracks at multiple scales, accommodating the varying severity and characteristics of cracks. The model is trained using data at different scales and levels, ensuring comprehensive learning from the lowest to the highest convolutional layers. To validate the effectiveness of our approach, we conducted experimental evaluations using end-to-end training on the Concrete Crack Images for Classification dataset, Asphalt Crack Dataset, and SDNET2018 dataset for crack classification. The results demonstrate the robustness and efficacy of the proposed methodology in accurately identifying crack regions across different datasets. [ABSTRACT FROM AUTHOR]

Deep Non-Negative Matrix Factorization (DNMF) methods provide an efficient low-dimensional representation of given data through their layered architecture. A limitation of such methods is that they cannot effectively preserve the local and global geometric structures of the data in each layer. Consequently, a significant amount of the geometrical information within the data, present in each layer of the employed deep framework, can be overlooked by the model. This can lead to an information loss and a subsequent drop in performance. In this paper, we propose a novel deep non-negative matrix factorization method, D eep N on- N egative M atrix F actorization with Joint G lobal and L ocal Structure Preservation (dubbed Dn2MFGL), that ensures the preservation of both global and local structures within the data space. Dn2MFGL performs representation learning through a sequential embedding procedure which involves both the global data structure by accounting for the data variance, and the local data relationships by utilizing information from neighboring data points. Moreover, a regularization term that promotes sparsity by utilizing the concept of the inner product is applied to the matrices representing the lower dimensions. This aims to retain the fundamental data structure while discarding less crucial features. Simultaneously, the residual matrix of Dn2MFGL is subjected to the L 2 , 1 norm, which ensures the robustness of the model against noisy data samples. An effective and multiplicative updating process also facilitates Dn2MFGL in solving the employed objective function. The clustering performance of the proposed deep NMF method is explored across various benchmarks of face datasets. The results point to Dn2MFGL outperforming several existing classical and state-of-the-art NMF methods. The source code is available at https://github.com/FaridSaberi/Dn2MFGO.git. • Dn2MFGL preserves global/local data structures at each layer. • Dn2MFGL uses the L 2 , 1 norm for robust factorization outcome. • Dn2MFGL employs inner product sparsity for coefficient matrices. [ABSTRACT FROM AUTHOR]

In this paper, a generalized interval vector space is investigated and defined as an ordered relation in the form of a bijective linear transformation of its onto a real vector space. The ordered relation is utilized to formulate an interval optimization problem in the same manner as a classical multi-objective programming problem. A methodology that addresses the existence of efficient solutions for the multi-objective interval optimization problem has also been discussed. Various numerical examples are described to illustrate and substantiate all developed concepts. Furthermore, the multi-objective portfolio rebalancing problem for a time horizon is designed based on the developed interval vector optimization. An algorithm using exhaustive solution technology has been proposed to achieve an efficient investment strategy. Finally, its applicability and efficacy are analyzed using Bombay Stock Exchange India data sets. • Bijective relation for an interval is created using interval vector space. • The solution technique is developed for interval optimization. • Introduction and existence of the interval vector optimization problem. • The Multi-objective Interval Portfolio Rebalancing Problem is designed. • Evaluating the model's applicability and efficacy using historical data. [ABSTRACT FROM AUTHOR]

This paper proposes a dynamic agent-based model (TRANSOPE) to simulate outsourcing among transport companies where, for the first time, accumulated knowledge is included as a variable to select service providers. The model consists of two main procedures. Firstly, the model simulates the decision-making of the professionals that contract transport service providers and the formation of outsourcing chains. Secondly, the model simulates the direct learning of participating companies and the transfer of knowledge towards their environment. Imperfect competition is replicated in three different scenarios, which involve the demand for transport services, regional distances and the intensity of knowledge transfer. The model is based on expert consultations and a survey conducted in an environment with a high concentration of transport companies in the Basque Country, Spain. The results indicate significant imbalances in the distribution of outsourcing, particularly in situations of low transport service demand, where 30% of transport companies do not secure any contracts. However, such situations led to strong regional interdependence. The dynamics of outsourcing reveals that over 75% of the contracted companies participate in all simulated scenarios from the first day. A strong hierarchy is also observed in the network, where certain transport companies act as connector hubs (with z-score values higher than 2.5 and participation coefficient values between 0.3 and 0.75), indicating a greater capacity for interaction and leadership in the transfer of knowledge. This feature allows the collaboration network to be identified as a scale-free network. The model has a low computational cost since the distances between agents remain constant. Finally, the formalisation of outsourcing decision-making in the model underpins its validity in forecasting the conduct of a freight transport system under shifting scenarios. [ABSTRACT FROM AUTHOR]

In this paper we present the SPRF (Sensorised Pen with Real time Feedback) platform that aims to objectively detect handwriting-related graphomotor disorders in children with Special Educational Needs (SEN), and to treat them through game-guided intervention plans performed with the same sensorised system. We have developed two sensorised devices (wristband and pen) for the SPRF to be able to quantify relevant physical parameters as children perform both diagnostic activities and the subsequent intervention plans. This way, SPRF differentiates from traditional methodologies commonly adopted in non-technologically assisted approaches where well-known graphomotor variables (directly related to the abovementioned physical parameters) are observed by diverse professionals with different criteria, which undoubtedly leads to an undesirable subjectivity. The novelty of SPRF relates to: (i) the ability to suggest tailored intervention plans for each child, based on objective parameter measurement, and (ii) the possibility to instantaneously correct children as they perform that custom-made plan thanks to an intuitive interface (similar to traffic lights) through which therapists can easily identify skills achieved, in progress or failed. The approach has been validated with a real group of SEN children from Ecuador, showing that, in terms of graphomotor skills, children who received on-the-fly feedback during the therapeutic intervention outperformed children not exposed to such real-time corrections. [ABSTRACT FROM AUTHOR]

This paper presents a novel deep learning model called Self-Attention Layer within a Convolutional Neural Network (SACNN), specifically designed for detecting acoustic data in extensive datasets containing emergency vehicle sirens and road noise. SACNN leverages a combination of EfficientNet and One Dimensional Convolutional Neural Networks (1D_CNN) to improve the precision and efficiency of detection. The dataset comprises 3-second WAV-format audio files categorized into Emergency Vehicles (Ambulance and Firetruck sirens) and Traffic (plain traffic sounds), with each category having 200 sound files and their corresponding 200 spectrogram images per audio file. Experimental results demonstrate SACNN's superior performance across various metrics, including accuracy, precision, recall, and F1 score, while also achieving notable advancements in computational efficiency. The research addresses the need for more effective solutions in the domain of emergency vehicle siren and road noise detection by introducing SACNN as a cutting-edge solution. By integrating EfficientNet and 1D_CNN, SACNN surpasses existing models in accuracy and computational efficiency. Comparative analysis with EfficientNet and 1D_CNN using a large-scale dataset validates SACNN's superior performance, with an average accuracy, precision, recall, and F1 score of 1.00. Additionally, SACNN exhibits the highest computational efficiency, averaging 0.20883 s per sample. These findings highlight SACNN's efficacy in detecting and classifying emergency vehicle sirens and road noise in large-scale datasets, with implications for traffic management, public safety, and noise pollution monitoring. SACNN offers the potential for constructing real-time acoustic data detection systems. [ABSTRACT FROM AUTHOR]

Counterfeit coins pose a significant challenge in various real-world applications, from vending machines to currency exchange systems, making their reliable detection a matter of utmost importance. This research presents a novel framework designed to tackle this issue by harnessing the power of image-mining techniques. Our proposed framework is developed in two modules. In the first module, a method to detect the region of interest (ROIs) is applied that focuses on blob detection. In the second module, image mining is applied to find image patterns present in coin images using fuzzy association rules mining. The enhancement lies in utilizing Particle Swarm Optimization (PSO) within the image mining module. PSO refines the threshold parameters, thereby improving the efficiency of the fuzzy association rules mining process. This integration allows for the automatic determination of optimal values, contributing to the overall robustness of the counterfeit coin detection system. Comprising two modules, this framework offers a unique advantage as a compress, serving as a knowledge attainment tool. By harnessing the full power of fuzzy association rule mining, this paper introduces pruning methods to reduce redundant and insignificant rules. Moreover, we propose a novel algorithm for feature selection and a pruned-based fuzzy associative classifier to establish a robust counterfeit coin detection system. Comparative analysis with other methods using the same dataset showcases the superiority of our framework, exhibiting lower feature dimensions, smoother boundaries, and maintaining satisfactory accuracy. The generality of this study's problem formulation offers a common framework for addressing similar challenges across various domains. [ABSTRACT FROM AUTHOR]

Facial beauty prediction (FBP) aims to develop a system to assess facial attractiveness automatically. Through prior research and our own observations, it has become evident that attribute information, such as gender and race, is a key factor leading to the distribution discrepancy in the FBP data. Such distribution discrepancy hinders current conventional FBP models from generalizing effectively to unseen attribute domain data, thereby discounting further performance improvement. To address this problem, in this paper, we exploit the attribute information to guide the training of convolutional neural networks (CNNs), with the final purpose of implicit feature alignment across various attribute domain data. To this end, we introduce the attribute information into convolution layer and batch normalization (BN) layer, respectively, as they are the most crucial parts for representation learning in CNNs. Specifically, our method includes: 1) Attribute-guided convolution (AgConv) that dynamically updates convolutional filters based on attributes by parameter tuning or parameter rebirth; 2) Attribute-guided batch normalization (AgBN) is developed to compute the attribute-specific statistics through an attribute guided batch sampling strategy; 3) To benefit from both approaches, we construct an integrated framework by combining AgConv and AgBN to achieve a more thorough feature alignment across different attribute domains. Extensive qualitative and quantitative experiments have been conducted on the SCUT-FBP, SCUT-FBP5500 and HotOrNot benchmark datasets. The results show that AgConv significantly improves the attribute-guided representation learning capacity and AgBN provides more stable optimization. Owing to the combination of AgConv and AgBN, the proposed framework (Ag-Net) achieves further performance improvement and is superior to other state-of-the-art approaches for FBP. • Deep learning techniques for facial beauty prediction. • Learning feature alignment across multiple attribute domain data. • Learning attribute-guided feature representation for better feature alignment. • Attribute-guided convolution to dynamically adjusts convolutional parameters. • Attribute-guided batch normalization to compute attribute-specific statistics. [ABSTRACT FROM AUTHOR]

With the continuous evolution and refinement of urban functional spaces, the escalating reliance of commuters on public transportation for work-related travel has surged with time. This paper offers a multidimensional overview of research pertaining to identifying, analyzing, and forecasting of urban public transportation commuting patterns. Initially, emphasis is placed on the identification of commuting patterns. We delineate the characteristics of four data sources, summarize the establishing of travel chains, and classify the approaches involved in identifying commuting patterns. Subsequent to this, we delve into the type of determinants influencing commuters, exploring the ramifications of spatial–temporal heterogeneities. Thereafter, we classify and expound upon forecasting methodologies for commuter flow, elucidating principles behind predictive algorithms and composite models grounded in statistical and time-series analyses, discrete choice modeling, conventional machine learning, and advanced deep learning techniques. Concurrently, a comparative assessment of the strengths, limitations, and applicability of each method is presented. Concluding our exposition, predicated on current research landscapes and inherent challenges, prospective trajectories for future exploration are proposed, including multi-source data fusion, real-time commuting pattern detection, precise public transit for commuting, and commuting travel under shared transportation. [ABSTRACT FROM AUTHOR]

Presently, traffic safety analysis is mainly based on accident-based indicators, but they are incidental and small probability events, making safety analysis based on accident-related data difficult to achieve a comprehensive application in network size, and to realize risk assessment before accidents occur. To this end, this study innovatively develops a metric named Traffic Dynamic Operation Risk (TDOR) based on aggressive driving behaviors (ADBs) and traffic flow data for traffic safety evaluation. And Non-Negative Matrix Factorization (NMF) is adopted to explore the quantitative risk under the coupling of multiple risk factors. The results show that: 1) segments with high TDOR are always concentrated in a certain area and in a spatial distribution of Gaussian, and the peaks of these distributions are almost the assesses of transportation hubs or complex intersections; 2) traffic volume and coefficient of speed variation are the significant risk factors at ordinary sections and branches, while traffic volume and speed difference between upstream are the largest contributions at intersections; 3) roads with more accidents are associated with a higher TDOR, but the relationship between the two is not completely linearly correlated. The experimental results show that it is reasonable and feasible to use ADBs and traffic flow parameters to quantify traffic safety risks. Compared with other matrix factorization methods, the importance of variables based on NMF is more interpretable and more consistent with the change pattern of risk variables. The method proposed in this paper can change the previous traffic risk assessment pattern based on accident-related indicators and provide a basis for pre-accident risk prevention. [ABSTRACT FROM AUTHOR]

This paper presents a comfort-level trading mechanism for thermostatically controlled loads (TCLs), aiming to incentivize customers to provide more frequency regulation service for smart grid. This mechanism firstly divides aggregators composed of TCLs into the leader layer and the follower layer according to comfort adjustment level produced by the fuzzy neural network controller (FNC). The aggregator at leader layer has a low regulation level, while aggregators at follower layer are high. Then we establish a Stackelberg game between leader layer and follower layer, which can optimize the customer utility. Meanwhile, we build a noncooperative game model among aggregators at follower layer, which can maximize the customer utility while supplying regulation capacity for leader layer. Finally, simulation results validate the effectiveness of FNC and the feasibility of trading mechanism. The FNC can improve tracking accuracy to 2.05%, reduce absolute tracking error to 208.4 kW, and decrease average switching times to 9 per hour. The trading mechanism can make the temperature setpoints of aggregators within their comfort range and improve the customer satisfaction. [ABSTRACT FROM AUTHOR]

Largely inspired by the practice that both the brand name supplier and the platform motivate to encroach on the online retailing market, this paper investigates the optimal encroaching decisions in an online retailing marketplace that is currently owned by multiple online retailers. Depending on whether and who will encroach on, this paper conducts three different encroaching scenarios including the benchmark without encroaching, the brand name supplier encroaching, and the platform encroaching. A Stackelberg game model is then developed to capture competitions among three parties and thus address equilibria in this paper. With analytical studies and numerical experiments, several key findings are derived. For example, but not limited to, the optimal commission set by the platform is contingent largely upon the encroaching scenarios and the number of online retailers. Interestingly, the optimal commission tends to be consistent when there are as many online retailers as possible, regardless of whether and who will encroach. This paper also analytically reveals that the encroaching cost, the product inherent (the fraction of product cost over its market potential), and the optimal commission, induce key impacts on the individuals' retailing encroaching decisions. A free rider effect incurred by the retailing encroaching is found and examined in this platform supply chain. The results derived in our paper shed lights on operational and encroaching decisions for the platform supply chain. • Develop a game theoretical model in an E-commerce platform supply chain with multiple online retailers. • Explore an endogenous commission set by the platform across different encroaching scenarios. • Investigate the optimal retailing encroaching decisions for two potential entrants. • Reveal impacts of retailing encroaching on individual profits and find a free ride effect incurred by the encroaching. [ABSTRACT FROM AUTHOR]

Effective intelligent driving test and evaluation methods can improve the development and deployment process of autonomous vehicles (AVs). However, due to the extreme complexity and high dimensionality of driving behavior, how to objectively and efficiently evaluate the multi-dimensional performance of AVs in simulation and real-world environments is a long-standing problem. This paper proposes an objective multi-dimensional comprehensive evaluation (OMDCE) method that divides the intelligent driving test into four modules: test scenarios, scenario complexity model, simulation test platform, and automated evaluation system. The scenario complexity model is proposed to bridge the gap between the test scenarios and the automated evaluation system, thus enabling adaptive scaling of the evaluation scale for test scenarios with different difficulty levels. Besides, based on the existing four evaluation metrics for ego performance, altruism performance evaluation is first proposed to comprehensively portray AVs' intelligence degree. The OMDCE method was evaluated by testing two different intelligent driving algorithms and conducting real vehicle testing. The experimental results demonstrated that the OMDCE method can effectively evaluate AVs in various scenarios and quantitatively measure their multi-dimensional performance. The proposed method reduces the subjectivity of manual evaluation and speeds up the evaluation. Moreover, it improves the universality and scalability of the evaluation metrics system. • Scenario complexity model is built as a scaling metric to reduce scoring variance. • Altruism performance evaluation is first proposed to portray AVs' intelligence. • MEREC and MARCOS combining complexity model are proposed to quantify performance. • Simulation and field testing are conducted to validate the proposed method. • The method enables a fully automated evaluation of the performance of AVs. [ABSTRACT FROM AUTHOR]

Organic polymers (OPs), including conjugated polymers, conjugated microporous polymers, and conjugated organic frameworks, have garnered increasing attention in recent years due to their exceptional photocatalytic performance and recombinable molecular building blocks. The intramolecular charge transfer (ICT) within OPs is instrumental in achieving efficient photocatalysis. Moreover, the intermolecular electron donor-acceptor (D-A) structure is aimed at optimizing ICT, which could be accomplished by molecular modification. In this paper, we outline the comprehensive approaches for constructing D-A structure through molecular modification, and discuss the fundamental principles of enhancing the photocatalytic activity of D-A OPs in detail. Furthermore, we summarize the application of modified D-A OPs in resolving prevalent environmental and energy problems. This method is widely recognized as a promising solution to address the current bottleneck in photocatalysis. Thus, this review aims to enhance the fundamental comprehension of D-A OPs created through molecular modification and explore innovative strategies for addressing existing environmental challenges. [Display omitted] • The benefits of molecular modification (MMF) compared with others were discussed. • The crucial factors for organic polymers (OPs) in MMF were elucidated. • The advantages of donor-acceptor structure in optimizing OPs were explored. • The potential challenge and future of MMF were put forward. [ABSTRACT FROM AUTHOR]

• Rational Krylov approximation (RKFIT) was implemented to convert ACE-formatted cross-sections into multipole parameters. • Rational Krylov fitting was used to generate poles and residues without converting resonance parameters. • The auto optimized number of poles in RKFIT leads to faster conversion performance. • Cross sections produced by RKFIT are compared with ACE-formatted data. An effective way to perform on-the-fly Doppler broadening of nuclear cross-section data is the windowed multipole method. It has the potential for be a key in achieving high-fidelity multi-physics core calculations with Monte Carlo methods. In the recent years, promising progress in multipole method and its applicability has been made but it has not reached its maturity yet. There is no cohesive method for obtaining multipole parameters for all nuclides necessary for reactor calculations. Previous methods for obtaining such parameters, as partial decomposition and Vector-Fitting based techniques successfully generate multipole library but they are just limited to ENDF/B-VII.1 data set. In this paper a new method for acquiring multipole parameters was investigated. In this study Rational Krylov approximation (RKFIT) method was used for converting commonly ACE (A Compact ENDF) format data to multipole parameters. In comparison with other fitting techniques, initial poles and total number of poles are not required since both are calculated during the fitting process, requiring no user predetermination. Besides, the proposed algorithm is able to convert not only light nuclides but also heavy isotopes cross-section data. This algorithm makes it possible to convert all nuclides of ENDF (Evaluated Nuclear Data File) file effortlessly and independent from resonance representation scheme or existence of background data. Several light and heavy nuclides were tested and cross-section and multipole parameters derived from the algorithm were within acceptable accuracy. [ABSTRACT FROM AUTHOR]

One of the main tasks in nuclear safeguards is regular inspections of Spent Nuclear Fuel (SNF) assemblies to detect possible diversions of special nuclear material such as 235U and 239Pu. In these inspections, characteristic signatures of SNF such as emissions of neutrons and gamma rays from the radioactive decay, are measured and their consistency with the declared assemblies is verified to ensure that no fuel pins have been removed. Research in this field is focused on both the development of detection equipment and methods for the analysis of the acquired measurement data. In this paper, the use of the neutron flux gradient, which is not considered in regular SNF verification, is investigated in combination with the scalar neutron flux as input to artificial neural network models for the quantification of fuel pins in SNF assemblies. The training and testing of these ANN models rely on a synthetic dataset that is generated from Monte Carlo simulations of a typical intact pressurized water reactor assembly and with different patterns of fuel pins replaced by dummy pins. The dataset consists of unique scenarios so that the ANN can be assessed over "unknown" cases that are not part of the learning phase. Results show that the neutron flux gradient is advantageous for a more accurate reconstruction of diversions within SNF assemblies. [ABSTRACT FROM AUTHOR]

This work covers the operational use of the Aerojet General Nucleonics Model 201 Reactor (AGN-201M) at the University of New Mexico (UNM) in Albuquerque, New Mexico. The AGN-201M is a research and test reactor that operates at 5-watts (thermal) and utilizes HALEU fuel encased in polyethylene fuel disks. Operational usage in hours and watt-hours for the 2021 and 2022 fiscal year is provided, as well as licensing data (including training usage), notable research projects, outreach, and educational use in the Nuclear Engineering program at UNM. All research projects described herein have published conference papers, journal articles, or in-progress conference papers, journal articles and benchmarks. [ABSTRACT FROM AUTHOR]

• Study of nuclear heating of structural materials during their irradiation in the reactor. • Computational modeling of nuclear heating of structural materials. • Experimental study of nuclear heating of structural materials in the IGR. When conducting in-pile studies at the Impulse Graphite Reactor (IGR), it is necessary to have an information of the thermal state of the structural elements of the experimental device to ensure the safety of the experiment as well as to obtain the detailed data about the experiment predicted parameters. This paper presents the developed approach of the computer simulation to determine the nuclear heating value of the structural materials during their irradiation in reactor facility. The detailed neutronic and thermohydraulic calculations have been done to determine the main parameters of the irradiated samples of various structural materials used in nuclear industry. The validation of the calculated values of the temperature change of the samples with the experimentally obtained data at the IGR reactor has been carried out. [ABSTRACT FROM AUTHOR]

• An analysis program for the Brayton cycle system of the small helium-xenon cooled nuclear reactor was developed independently. • Analyzed the factors that limit system power and final parameter, and concluded that system require larger size air cooler. • The effects of different reactivity insertion ways on the transient response characteristics of the system are compared and analyzed. • The influence of constant compressor inlet temperature on system transient response characteristics is compared and analyzed. The helium-xenon cold nuclear reactor system has a good prospect in aviation power because of its simple system, small size and lightweight. In this paper, based on the Modelica language, we independently developed a Brayton cycle system analysis program for a small helium-xenon cooled nuclear reactor, and verified the key models. Firstly, a design analysis was conducted on the flow and heat transfer enhancement of the reactor coolant channel, and the factors limiting the system power and final parameters were analyzed through simulation calculations. Then, the transient operating conditions of the system under different reactivity introduction methods and controlling the constant inlet temperature of the compressor were simulated, and the dynamic operating characteristics of the system and the coupling effects of the main equipment were studied. The simulation results show that the main factor limiting the power increase and final parameter reduction of the system is that the low density of air at high altitude cannot provide sufficient low-temperature cooling air to take away a lot of waste heat. Increasing flight speed and reducing flight altitude can increase the cooling power of the air cooler and reduce the final system parameters. By introducing the same reactivity through different reactivity insertion ways, the ultimate steady-state operating state of the system is the same. By controlling the compressor inlet temperature to be constant, the system output power can be improved. The relevant system analysis results provide a reference for the design of aeronautic electric propulsion system of helium-xenon cooled nuclear reactor. [ABSTRACT FROM AUTHOR]