Search

We test here the prediction capabilities of the new generation of deep learning predictors in the more challenging situation of multistate multidomain proteins by using as a case study a coiled-coil family of Nucleotide-binding Oligomerization Domain-like (NOD-like) receptors from A. thaliana and a few extra examples for reference. Results reveal a truly remarkable ability of these platforms to correctly predict the 3D structure of modules that fold in well-established topologies. A lower performance is noticed in modeling morphing regions of these proteins, such as the coiled coils. Predictors also display a good sensitivity to local sequence drifts upon the modeling solution of the overall modular configuration. In multivalued 1D to 3D mappings, the platforms display a marked tendency to model proteins in the most compact configuration and must be retrained by information filtering to drive modeling toward the sparser ones. Bias toward order and compactness is seen at the secondary structure level as well. All in all, using AI predictors for modeling multidomain multistate proteins when global templates are at hand is fruitful, but the above challenges have to be taken into account. In the absence of global templates, a piecewise modeling approach with experimentally constrained reconstruction of the global architecture might give more realistic results. [ABSTRACT FROM AUTHOR]

In the wake of recent advancements in the field of AI, this paper investigates the impact of recommender systems and generative models on human decisional and creative autonomy. For this purpose, we adopt Dennett’s conception of autonomy as self-control. We show that recommender systems can play a double role in relation to decisional autonomy: as information filter, they can augment self-control in decision-making, but also act as mechanisms of remote control that clamp degrees of freedom. As for generative models in AI, we show that they can be seen as a powerful system of selection and suggestion (similar to standard recommender systems) but also as an instrument for information production. We suggest that the latter perspective opens new possibilities in terms of creative autonomy. Additionally, for both systems we propose a distinction between “extrinsic” and “intrinsic” mechanisms and effects. Through Dennett’s theory of self-control, this paper offers new insights into the relation between AI and human autonomy by framing it in terms of remote or self-control and by addressing the impact of generative models on creative autonomy. [ABSTRACT FROM AUTHOR]

The human brain continuously integrates information across its two hemispheres to construct a coherent representation of the perceptual world. Characterizing how visual information is represented in each hemisphere over time is crucial for understanding how hemispheric transfer contributes to perception. Here, we investigated information processing within each hemisphere over time and the degree to which it is distinct or duplicated across hemispheres. We presented participants with object images lateralized to the left or right visual fields while measuring their brain activity with electroencephalography. Stimulus coding was more robust and emerged earlier in the contralateral than the ipsilateral hemisphere. Presentation of two stimuli, one to each hemifield, reduced the fidelity of representations in both hemispheres relative to one stimulus alone, signifying hemispheric interference. Last, we found that processing within the contralateral, but not ipsilateral, hemisphere was biased to image-related over concept-related information. Together, these results suggest that hemispheric transfer operates to filter irrelevant information and efficiently prioritize processing of meaning. [ABSTRACT FROM AUTHOR]

Frequency-domain adaptive filter (FDAF) algorithms have been widely used in many fields in virtue of its fast convergence and low computational complexity. However, FDAF algorithms with fixed step-size cannot balance convergence rate and steady-state misadjustment. In this paper, we propose the switching step-size based FDAF (SSS-FDAF) algorithm that selects the optimal step-size at each iteration for the FDAF update by comparing the mean-square deviation (MSD) trends with different step-sizes, to obtain fast convergence and low steady-state misadjustment at the same time. Furthermore, a novel reset strategy is designed for guaranteeing the tracking capability of the proposed algorithm. Computer simulations of colored signals and real-world signals have demonstrated the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

Clothing design plays an important role in personal image expression and social and cultural transmission. The traditional fashion design method has many problems, such as low efficiency and large design error, and it is difficult to bring users better wearing experience. In order to meet different users' Design needs, reduce design errors, and improve users' satisfaction with design results, this paper combined with intelligent sensing technology, conducted in-depth research on digital automation analysis of clothing design CAD (Computer Aided Design). Aiming at the clothing design process, this paper first constructed a brand-new clothing design CAD system, using the depth transducer to solve the 3D information of the relevant feature points, and realized the accurate acquisition of the human body feature size information. Through the registration of adjacent frame point data, the 3D human body modeling was carried out. Then, according to the user's physical characteristics and related information collected by the sensor, the paper compared the user's characteristic information to filter out the user's preferences, and used the recommendation algorithm to calculate the corresponding parameters to realize the intelligent choice of clothing styles. Finally, through the measurement of each index by the sensor, the size adjustment of the garment and the specific design of the garment were realized. In order to verify the effect of clothing design CAD system based on intelligent sensing technology, this paper conducted system tests. The results showed that in terms of clothing comfort, clothing quality and clothing functionality, the number of users satisfied and very satisfied reached 50.4%, 47.9% and 51.3%, respectively. From the overall survey results, the system has a high degree of user satisfaction. The research conclusion of this paper shows that the digital automatic analysis of clothing design CAD based on intelligent sensing technology can effectively meet the needs of users, improve their wearing experience, and promote the intelligent development of clothing design. [ABSTRACT FROM AUTHOR]

This study proposes a voltage‐retention circuit (VRC) for a low‐power phase‐locked loop (PLL) designed for mobile interfaces. The PLL, incorporating the proposed scheme, supports the sleep mode to achieve low power consumption and fast switching between the sleep and active modes. To facilitate rapid switching between these modes, the proposed VRC stores the filter information from the previous input during sleep mode, ensuring quick settling upon reactivation. The VRC comprises a resistor‐steering digital‐to‐analog converter (DAC), a comparator, and a counter. During the active mode, the circuit adjusts the DAC using the comparator and counter to track the loop‐filter voltage, and it holds the tracked voltage value during the sleep mode. The proposed circuit, designed using a 65‐nm CMOS process, demonstrates 54% improved settling time compared to conventional circuits. Additionally, it reduces power consumption during sleep mode by 88%. [ABSTRACT FROM AUTHOR]

Early wildfire smoke detection faces challenges such as limited datasets, small target sizes, and interference from smoke-like objects. To address these issues, we propose a novel approach leveraging Efficient Channel and Dilated Convolution Spatial Attention (EDA). Specifically, we develop an experimental dataset, Smoke-Exp, consisting of 6016 images, including real-world and Cycle-GAN-generated synthetic wildfire smoke images. Additionally, we introduce M-YOLO, an enhanced YOLOv5-based model with a 4× downsampling detection head, and MEDA-YOLO, which incorporates the EDA mechanism to filter irrelevant information and suppress interference. Experimental results on Smoke-Exp demonstrate that M-YOLO achieves a mean Average Precision (mAP) of 96.74%, outperforming YOLOv5 and Faster R-CNN by 1.32% and 3.26%, respectively. MEDA-YOLO further improves performance, achieving an mAP of 97.58%, a 2.16% increase over YOLOv5. These results highlight the potential of the proposed models for precise and real-time early wildfire smoke detection. [ABSTRACT FROM AUTHOR]

With the rapid advancement of mobile interaction technology, teaching methodologies in higher education are increasingly moving toward personalization and intelligence. The use of mobile interaction technology for adaptive recommendation of teaching content has become a critical topic for enhancing educational effectiveness. Existing research in content recommendation, primarily based on collaborative filtering algorithms, often relies on single-dimensional data applications and lacks comprehensive consideration of both location information and temporal effects. Consequently, these approaches fall short in addressing the complex requirements of dynamic learning environments. This study proposes a multi-dimensional dynamic adaptive recommendation system for teaching content based on mobile interaction technology to address the limitations of existing methods. The research encompasses location-based collaborative filtering for teaching content, time-effect-based collaborative filtering, and an integrated multi-dimensional dynamic recommendation model that considers both location and temporal factors. This study is expected to provide a more precise and dynamically adaptive solution for personalized teaching in higher education. [ABSTRACT FROM AUTHOR]

Three-dimensional object detection is a key task in the field of autonomous driving that is aimed at identifying the position and category of objects in the scene. Due to the 3D nature of data generated by LiDAR, most models use it as input data for detection. However, the low scanning resolution of LiDAR for distant objects has inherent limitations to the method, and multimodal fusion 3D object detection methods have attracted widespread attention, mostly using both LiDAR and camera data as inputs for detection. Certainly, multimodal methods can also lead to many problems, the two main ones being the incomplete utilization of camera features and rough fusion methods. In this study, we proposed a novel multimodal 3D object detection method named VirtualFilter, which uses 3D point clouds and 2D images as inputs. In order to better utilize camera features, VirtualFilter utilizes the image semantic segmentation model to generate image semantic features and uses the semantic information to filter the virtual point cloud data during the virtual point cloud generation process to enhance the data accuracy of the virtual cloud. In addition, VirtualFilter utilizes a better RoI feature fusion strategy named 3D-DGAF (3D Distance-based Grid Attentional Fusion), which employs a attention mechanism based on distance gridding to better fuse the RoI features of the original and virtual point clouds. The experimental results on the authoritative autonomous driving dataset KITTI show that this multimodal 3D object detection method outperforms the baseline method in several evaluation metrics. [ABSTRACT FROM AUTHOR]

This paper addresses the increasing complexity of challenges in the field of continuous nonlinear optimization by proposing an innovative algorithm called information acquisition optimizer (IAO), which is inspired by human information acquisition behaviors and consists of three crucial strategies: information collection, information filtering and evaluation, and information analysis and organization to accommodate diverse optimization requirements. Firstly, comparative assessments of performance are conducted between the IAO and 15 widely recognized algorithms using the standard test function suites from CEC2014, CEC2017, CEC2020, and CEC2022. The results demonstrate that IAO is robustly competitive regarding convergence rate, solution accuracy, and stability. Additionally, the outcomes of the Wilcoxon signed rank test and Friedman mean ranking strongly validate the effectiveness and reliability of IAO. Moreover, the time comparison analysis experiments indicate its high efficiency. Finally, comparative tests on five real-world optimization difficulties affirm the remarkable applicability of IAO in handling complex issues with unknown search spaces. The code for the IAO algorithm is available at https://ww2.mathworks.cn/matlabcentral/fileexchange/169331-information-acquisition-optimizer. [ABSTRACT FROM AUTHOR]

Active control in adaptive structures allows for reducing the structural weight of a building and thus to drastically decrease the construction sector's global impact. For an active control, it is necessary to estimate the state. Especially for large structures, decentralized approaches are particularly advantageous. However, the choice of the individual decentralized models, the substructuring, is important. This work considers decentralized state estimation for different substructure layouts obtained by the Relative Gain Array (RGA) for an adaptive high-rise structure. The estimators are realized using Information Filters (IF) based on reduced models derived from the full model via SEREP-Guyan and modal reduction. Different degrees of interconnection (none, sparse, full) are investigated w. r. t. estimation accuracy and robustness towards communication failure. For more substructures the estimation error increases. Depending on the layout, communicating is beneficial, but a full interconnection is not necessary for a sufficient estimation. In case of a failed information exchange, communicating estimators should adapt to the fault. [ABSTRACT FROM AUTHOR]

The non-redescending convex functions degrade the filtering robustness, whereas the redescending non-convex functions improve filtering robustness, but they tend to converge towards local minima. This work investigates the properties of convex and non-convex cost functions from robustness and stability perspectives, respectively. To improve filtering robustness and stability to the high level of non-Gaussian noise, a sequential mixed convex and non-convex cost strategy is presented. To avoid the matrix singularity induced by applying the non-convex function, the M-estimation type Kalman filter is transformed into its information filtering form. Further, to address the problem of the estimation consistency in the iterated unscented Kalman filter, the iterated sigma point filtering framework is adopted using the statistical linear regression method. The simulation results show that, under different levels of heavy-tailed non-Gaussian noise, the mixed cost strategy can avoid the non-convex function-based filters falling into the local minimum, and further can improve the robustness of the convex function-based filter. Therefore, the mixed cost strategy provides a comprehensive improvement in the efficiency of the robust iterated filter. [ABSTRACT FROM AUTHOR]

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

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

This paper introduces EIF-SlideWindow, a novel enhancement of the Extended Information Filter (EIF) algorithm for Simultaneous Localization and Mapping (SLAM). Traditional EIF-SLAM, while effective in many scenarios, struggles with inaccuracies in highly non-linear systems or environments characterized by significant non-Gaussian noise. Moreover, the computational complexity of EIF/EKF-SLAM scales with the size of the environment, often resulting in performance bottlenecks. Our proposed EIF-SlideWindow approach addresses these limitations by maintaining a fixed-size information matrix and vector, ensuring constant-time processing per robot step, regardless of trajectory length. This is achieved through a sliding window mechanism centered on the robot's pose, where older landmarks are systematically replaced by newer ones. We assess the effectiveness of EIF-SlideWindow using simulated data and demonstrate that it outperforms standard EIF/EKF-SLAM in both accuracy and efficiency. Additionally, our implementation leverages PyTorch for matrix operations, enabling efficient execution on both CPU and GPU. Additionally, the code for this approach is made available for further exploration and development. [ABSTRACT FROM AUTHOR]

The exponential increase in digital data has increased the amount of available online information. This complicates the user's decision-making. Most online merchants and service providers utilize recommendation systems to solve this problem and meet customer needs. The traditional collaborative filtering based approach faces enormous challenges in providing potential personalized recommendation results. The demographic information of users may improve personalized recommendation results. This research proposes an improved recommendation approach based on users' demographic information. Compared with traditional collaborative filtering-based approaches, this approach provides improved results. The experimental results show the enhanced prediction accuracy of the proposed approach and significantly lower errors when experimenting with the MovieLens dataset. [ABSTRACT FROM AUTHOR]

This article aims to provide a coherent and comprehensive theoretical framework of the main socio-epistemic features of social media. The first part consists of a concise discussion of the main epistemic consequences of personalised information filtering, with a focus on echo chambers and their many different implications. The middle section instead hosts an analytical investigation of the cognitive and epistemic environments of these platforms aimed at establishing whether, and to what extent, they allow their users to be epistemically vigilant with respect to their sources and the content recommended to them. Finally, in the last part, of a more exquisitely normative nature, some strategies are proposed and discussed that, by reducing the epistemic opacity of social media, could contribute to greater epistemic justice within social media and, concurrently, to augmenting the epistemic autonomy of users. [ABSTRACT FROM AUTHOR]

In recent years, recommendation explanation methods have received widespread attention due to their potentials to enhance user experience and streamline transactions. In scenarios where auxiliary information such as text and attributes are lacking, counterfactual explanation has emerged as a crucial technique for explaining recommendations. However, existing counterfactual explanation methods encounter two primary challenges. First, a substantial bias indeed exists in the calculation of the group impact function, leading to the inaccurate predictions as the counterfactual explanation group expands. In addition, the importance of collaborative filtering as a counterfactual explanation is overlooked, which results in lengthy, narrow, and inaccurate explanations. To address such issues, we propose a counterfactual explanation method based on Modified Group Influence Function for recommendation. In particular, via a rigorous formula derivation, we demonstrate that a simple summation of individual influence functions cannot reflect the group impact in recommendations. After that, building upon the improved influence function, we construct the counterfactual groups by iteratively incorporating the individuals from the training samples, which possess the greatest influence on the recommended results, and continuously adjusting the parameters to ensure accuracy. Finally, we expand the scope of searching for counterfactual groups by incorporating the collaborative filtering information from different users. To evaluate the effectiveness of our method, we employ it to explain the recommendations generated by two common recommendation models, i.e., Matrix Factorization and Neural Collaborative Filtering, on two publicly available datasets. The evaluation of the proposed counterfactual explanation method showcases its superior performance in providing counterfactual explanations. In the most significant case, our proposed method achieves a 17% lead in terms of Counterfactual precision compared to the best baseline explanation method. [ABSTRACT FROM AUTHOR]

Filter pruning has been used on a large scale to compress and accelerate convolutional neural networks. The goal of filter pruning is to find the optimal network substructure from the unpruned network. Most previous pruning methods directly remove the redundant filters from the network or set them to zero. It is not reasonable because these redundant filters still contain information. If these filters are removed directly, the performance of the model may be drastically reduced. To solve this problem, this paper proposes a new filter pruning method, namely Filter Pruning via Annealing Decaying (FPAD), for a fast and efficient search of the optimal substructure. Our proposed FPAD effectively preserves the pre-trained information of filters in the pruning process. In addition, FPAD can improve the convergence speed of the model to achieve the compression target faster. We introduce an annealing function to control the amount of filter decay during the pruning process. To demonstrate the validity of our method, we apply FPAD to three image classification benchmarks. The results show that FPAD outperforms the state-of-the-art pruning methods. In particular, on ILSVRC-2012, our FPAD reduces 42.2% FLOPs in ResNet-50 with 0.17% loss of top-1 accuracy and with only 0.03% loss of top-5 accuracy. [ABSTRACT FROM AUTHOR]

Existing segmentation-based text detection methods generally face the problems of insufficient receptive fields, insufficient text information filtering, and difficulty in balancing detection accuracy and speed, limiting their ability to detect arbitrary-shaped text in complex backgrounds. To address these problems, we propose a new text detection method fusing the pure ConvNet model InceptionNeXt and the multi-scale attention mechanism. Firstly, we propose a text information reinforcement module to fully extract effective text information from features of different scales while preserving spatial position information. Secondly, we construct the InceptionNeXt Block module to compensate for insufficient receptive fields without significantly reducing speed. Finally, the INA-DBNet network structure is designed to fuse local and global features and achieve the balance of accuracy and speed. Experimental results demonstrate the efficacy of our method. Particularly, on the MSRA-TD500 and Total-text datasets, INA-DBNet achieves 91.3% and 86.7% F-measure while maintaining real-time inference speed. Code is available at: https://github.com/yuyu678/INANET. [ABSTRACT FROM AUTHOR]

Keywords are used to provide a concise summary of the text, enabling the quick understanding of core information and assisting in filtering out irrelevant content. In this paper, an improved TextRank keyword extraction algorithm based on word vectors and multi-feature weighting (IWF-TextRank) is proposed to improve the accuracy of keyword extraction by comprehensively considering multiple features of words. The key innovation is demonstrated through the application of a backpropagation neural network, combined with sequential relationship analysis, to calculate the comprehensive weight of words. Additionally, word vectors trained using Word2Vec are utilised to enhance the model's semantic understanding. Finally, the effectiveness of the algorithm is verified from various aspects using traffic accident causation data. The results show that this algorithm demonstrates a significant optimisation effect in keyword extraction. Compared with the traditional model, the IWF-TextRank algorithm shows significant improvement in accuracy (p-value), recall (R-value), and F-value. [ABSTRACT FROM AUTHOR]

Most research on movie recommender systems has been conducted with Collaborative Filtering (CF) methods. The lack of sufficient information about users' interests in bootstrapping is one of the most critical problems of the CF method. Using a content-based filtering method can mitigate some of these problems. On the other hand, recent research has proven that utilising contextual information about the movie, such as genre, actors, and cast, can increase the efficiency of the recommender system. This paper uses a combined Genetic Algorithm (GA) and content-based filtering to find the best combination of genre, cast, and crew weights. We first convert each movie's contextual information into a descriptive vector, including cast, crew, and genre. Then, we calculate the distance between each pair of sentence vectors using two separate approaches, fully connected and metadata-based. Finally, with GA, we tune the weight of each of the contextual information of movies to maximise the recommender system's efficiency. Performance evaluation on the well-known MovieLens dataset shows that GA can improve the Precision@k criterion by producing fewer, more accurate recommendations. Weight adjustment by GA improves the F-Measure metric by approximately 58%. This, in turn, can improve Precision and Recall metrics. Also, the GA offers a higher correct recommendation rate than other methods. [ABSTRACT FROM AUTHOR]

Recent Transformer-based works can generate high-quality captions for remote sensing images (RSIs). However, these methods generally feed global or grid visual features to a Transformer-based captioning model for associating cross-modal information, which limits performance. In this work, we investigate unexplored ideas for remote sensing image captioning task, using a novel patch-level region-aware module with a multi-label framework. Due to an overhead perspective and a significantly larger scale in RSIs, a patch-level region-aware module is designed to filter the redundant information in the RSI scene, which benefits the Transformer-based decoder by attaining improved image perception. Technically, the trainable multi-label classifier capitalizes on semantic features as supplementary to the region-aware features. Moreover, modeling the inner relations of inputs is essential for understanding the RSI. Thus, we introduce region-oriented attention, which associates region features and semantic labels, omits the irrelevant regions to highlight relevant regions, and learns related semantic information. Extensive qualitative and quantitative experimental results show the superiority of our approach on the RSICD, UCM-Captions, and Sydney-Captions. The code for our method will be publicly available. [ABSTRACT FROM AUTHOR]

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

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

For blade damage detection under variable rotational speeds of centrifugal fans, transfer learning under working conditions appears to be more effective than deep learning. However, damage detection models with small samples and single-source domain transfer are still characterized by insufficiencies, such as negative transfer and poor accuracy. Therefore, in this paper, a quantitative blade damage detection method based on multisource domain and multistage joint transfer is proposed. First, an anchor adapter is constructed using linear discriminant analysis projection combined with a feature similarity index metric to acquire the weight matrix of multisource domain-target domain data. Second, a multisource domain feature extractor based on the fusion of vibroacoustic information is established, obtaining the feature set of the target domain data. Then, the feature set is filtered through information gain and max-relevance and min-redundancy to remove the negative transfer features and is combined with an improved supervised locally linear embedding to build a subspace structure preservation model for the alignment between the source and target domain feature distributions. Finally, the classifier is fine-tuned with small sample data for quantitative damage detection of blades with variable rotational speeds. The proposed method is verified using experimental data from two centrifugal fans. The results show that the detection accuracy of the proposed model is significantly higher than that of any comparison model with a single source domain or single stage. Compared with other transfer models, the proposed method is characterized by higher detection accuracy and generalization performance. [ABSTRACT FROM AUTHOR]

Text classification, as an important research area of text mining, can quickly and effectively extract valuable information to address the challenges of organizing and managing large-scale text data in the era of big data. Currently, the related research on text classification tends to focus on the application in fields such as information filtering, information retrieval, public opinion monitoring, and library and information, with few studies applying text classification methods to the field of tourist attractions. In light of this, a corpus of tourist attraction description texts is constructed using web crawler technology in this paper. We propose a novel text representation method that combines Word2Vec word embeddings with TF-IDF-CRF-POS weighting, optimizing traditional TF-IDF by incorporating total relative term frequency, category discriminability, and part-of-speech information. Subsequently, the proposed algorithm respectively combines seven commonly used classifiers (DT, SVM, LR, NB, MLP, RF, and KNN), known for their good performance, to achieve multi-class text classification for six subcategories of national A-level tourist attractions. The effectiveness and superiority of this algorithm are validated by comparing the overall performance, specific category performance, and model stability against several commonly used text representation methods. The results demonstrate that the newly proposed algorithm achieves higher accuracy and F1-measure on this type of professional dataset, and even outperforms the high-performance BERT classification model currently favored by the industry. Acc, marco-F1, and mirco-F1 values are respectively 2.29%, 5.55%, and 2.90% higher. Moreover, the algorithm can identify rare categories in the imbalanced dataset and exhibit better stability across datasets of different sizes. Overall, the algorithm presented in this paper exhibits superior classification performance and robustness. In addition, the conclusions obtained by the predicted value and the true value are consistent, indicating that this algorithm is practical. The professional domain text dataset used in this paper poses higher challenges due to its complexity (uneven text length, relatively imbalanced categories), and a high degree of similarity between categories. However, this proposed algorithm can efficiently implement the classification of multiple subcategories of this type of text set, which is a beneficial exploration of the application research of complex Chinese text datasets in specific fields, and provides a useful reference for the vector expression and classification of text datasets with similar content. [ABSTRACT FROM AUTHOR]

In the era of vast information, individuals are immersed in choices when purchasing goods and services. Recommender systems (RS) have emerged as vital tools to navigate these excess options. However, these systems encounter challenges like data sparsity, impairing their effectiveness. This paper proposes a novel approach to address this issue and enhance RS performance. By integrating user demographic data, singular value decomposition (SVD) clustering, and semantic similarity in collaborative filtering (CF), we introduce the UDIS method. This method amalgamates four prediction types—user-based CF (U), demographic-similarity-based (D), item-based CF (I), and semantic-similarity-based (S). UDIS generates separate predictions for each category and evaluates four different merging techniques—the average, max, weighted sum, and Shambour methods—to integrate these predictions. Among these, the average method proved most effective, offering a balanced approach that significantly improved precision and accuracy on the MovieLens dataset compared to alternative methods. [ABSTRACT FROM AUTHOR]

This research aims to explore the impact of cultural shock experienced by Santri while interacting with social media in the Pondok Pesantren environment to understand the crucial implications of media literacy in countering hoaxes. The underlying theoretical framework for this study encompasses cultural shock theory and the concept of media literacy. The research methodology employed is the content analysis approach, which will delve into cultural shock experiences among Santri, identify common themes of hoaxes, and assess their impact on the Santri community. The findings of this research reveal that Santri are becoming increasingly aware of how cultural shock influences their level of media literacy, as well as the mechanisms of hoax dissemination. Furthermore, the Santri develop media literacy strategies to combat hoaxes and strive to find solutions to mitigate the negative consequences resulting from the challenges of filtering information acquired through social media. [ABSTRACT FROM AUTHOR]

Interrupt-driven programs are widely used in embedded systems with high security requirements. However, uncertain interleaving execution of tasks and interrupts may cause concurrency bugs, with data races being a significant factor in threatening security. Most of the previous research has focused on detecting data races in multi-threaded programs. And existing static analysis methods for interrupt-related data race detection often produce many false positives. This paper presents IntRace, an accurate and efficient static detection technique for interrupt data race. IntRace eliminates false data race by analyzing potential concurrency relationships and path reachability. It first identifies all race candidate pairs using access interleaving pattern matching. Then for each pair of operational accesses, IntRace analyzes potential concurrency relationships, including the special case of interrupt nesting, and uses this information to filter out access pairs that cannot concurrently access the same location. Finally, it checks the feasibility of events in the access pairs by constructing path constraints, which effectively eliminating infeasible paths in concurrent contexts. In addition, IntRace was evaluated on benchmark tests and 9 real embedded programs. The experimental results show that IntRace reduces the false positive rate by 73.2% compared to recent studies. [ABSTRACT FROM AUTHOR]

The recommendation system is a filtering system. It filters a collection of things based on the historical behavior of a user, it also tries to make predictions based on user preferences and make recommendations that interest customers. While incredibly useful, they can face various challenges affecting their performance and utility. Some common problems are, for example, when the number of users and items grows, the computational complexity of generating recommendations increases, which can increase the accuracy and precision of recommendations. So, for this purpose and to improve recommendation system results, we propose a recommendation system combining the demographic approach with collaborative filtering, our approach is based on users' demographic information such as gender, age, zip code, occupation, and historical ratings of the users. We cluster the users based on their demographic data using the k-means algorithm and then apply collaborative filtering to the specific user cluster for recommendations. The proposed approach improves the results of the collaborative filtering recommendation system in terms of precision and recommends diverse items to users. [ABSTRACT FROM AUTHOR]

Filter pruning is a compression and acceleration method for deep convolutional neural network models that operates at a large scale. Many researchers have studied this approach and made significant progress, but the problem remains an open research topic. In this paper, we propose a DCNN structure optimization method for filter order–information structure similarity graph clustering with global pruning rate control, which considers the mapping strength distribution of convolution kernels in filters and the influence of equivalent convolution kernels on filter similarity. In this method, the relative strengths of the mappings between different convolution kernels in a filter determine the overall type of information combined in the output channel through the superposition filtering of information extracted from different input channels. The structural differences between the equivalent convolution kernels of different filters reflect the differences between the types of information extracted from the same input channel in the convolutional layer. By combining these two factors, we construct a measure of filter order–information structure similarity and then construct a filter similarity graph for the convolutional layer. For the pruning strategy, we establish a convolutional layer filter number allocation model with global pruning rate control using the scaling factors of batch normalization (BN) layers in sparse network. Then, in the filter similarity graph, we perform filter pruning by clustering subgraphs according to the given filter number allocation model for each convolutional layer. This yields an optimized structure for the pruned DCNN model. The experimental results and analysis demonstrate that our proposed method achieves effective pruning. In particular, on the ImageNet dataset, when pruning ResNet-50, the acceleration ratio and compression ratio of the model are 5.31x and 3.78x, respectively, while the model's classification accuracy decreases only slightly. Our method outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Accelerated by technological advancements, while online platforms equipped with recommendation algorithms offer convenience to obtain information, it also brought algorithm bias, shaping the norms and behaviors of their users. The filter bubble, conceived as a negative consequence of algorithm bias, means the reduction of the diversity of users' information consumption, garnering extensive attention. Previous research on filter bubbles typically used users' self-reported or behavioral data independently. However, existing studies have disputed whether filter bubbles exist on the platform, possibly owing to variations in measurement methods. In our study, we took content category diversity to measure the filter bubbles and innovatively used a combination of participants' self-reported and website behavioral data, examining filter bubbles on a single online video platform (Bilibili). We conducted a questionnaire survey among 337 college students and collected 3,22,324 browsing records with their informed authorization, constituting the dataset for research analysis. The existence of filter bubbles on Bilibli is found, such that diversity will decrease when viewing Game videos increases. Furthermore, we considered the factors that influence filter bubbles from the perspective of demographics and user behavior. In demographics, female and non-member users are more likely to be trapped in filter bubbles. In user behavior, results of feature importance analysis indicate that the diversity of information consumption of heavy users is higher than others, and both activity and fragmentation have an impact on the formation of filter bubbles, but in different directions. Finally, we discuss the reasons for these results and a theoretical explanation that the filter bubbles effect may be lower than we thought for both heavy and normal users on online platforms. Our conclusions provide valuable insights for understanding filter bubbles and platform management. [ABSTRACT FROM AUTHOR]

In the context of upcoming large-scale surveys like Euclid, the necessity for the automation of strong lens detection is essential. While existing machine learning pipelines heavily rely on the classification probability (P), this study intends to address the importance of integrating additional metrics, such as Information Content (IC) and the number of pixels above the segmentation threshold (⁠|$\rm {\mathit{n}_{s}}$|⁠), to alleviate the false positive rate in unbalanced data-sets. In this work, we introduce a segmentation algorithm (U-Net) as a supplementary step in the established strong gravitational lens identification pipeline (Denselens), which primarily utilizes |$\rm {\mathit{P}_{mean}}$| and |$\rm {IC_{mean}}$| parameters for the detection and ranking. The results demonstrate that the inclusion of segmentation enables significant reduction of false positives by approximately 25 per cent in the final sample extracted from DenseLens, without compromising the identification of strong lenses. The main objective of this study is to automate the strong lens detection process by integrating these three metrics. To achieve this, a decision tree-based selection process is introduced, applied to the Kilo Degree Survey (KiDS) data. This process involves rank-ordering based on classification scores (⁠|$\rm {\mathit{P}_{mean}}$|⁠), filtering based on Information Content (⁠|$\rm {IC_{mean}}$|⁠), and segmentation score (⁠|$\rm {n_{s}}$|⁠). Additionally, the study presents 14 newly discovered strong lensing candidates identified by the U-Denselens network using the KiDS DR4 data. [ABSTRACT FROM AUTHOR]

Most of the existing research on video watermarking schemes focus on improving the robustness of watermarking. However, in application scenarios such as judicial forensics and telemedicine, the distortion caused by watermark embedding on the original video is unacceptable. To solve this problem, this paper proposes a robust reversible watermarking (RRW)scheme based on multi-layer embedding in the video compression domain. Firstly, the watermarking data are divided into several sub-secrets by using Shamir's (t, n)-threshold secret sharing. After that, the chroma sub-block with more complex texture information is filtered out in the I-frame of each group of pictures (GOP), and the sub-secret is embedded in that frame by modifying the discrete cosine transform (DCT) coefficients within the sub-block. Finally, the auxiliary information required to recover the coefficients is embedded into the motion vector of the P-frame of each GOP by a reversible steganography algorithm. In the absence of an attack, the receiver can recover the DCT coefficients by extracting the auxiliary information in the vectors, ultimately recovering the video correctly. The watermarking scheme demonstrates strong robustness even when it suffers from malicious attacks such as recompression attacks and requantization attacks. The experimental results demonstrate that the watermarking scheme proposed in this paper exhibits reversibility and high visual quality. Moreover, the scheme surpasses other comparable methods in the robustness test session. [ABSTRACT FROM AUTHOR]

With the wide application of the intelligent news algorithm in the news industry, its recommendation mechanism has become the primary way for news consumers to obtain information. This study explores the intelligent news algorithm recommendation mechanism’s risk management measures and optimization schemes. Thus, people can get transparent news information more efficiently. Firstly, the study classifies and analyzes the risks of information filtering bias, information cocoon effect, and information bubble in intelligent news algorithm recommendation mechanism and collects and introduces large-scale news data as a data source. Secondly, the intelligent news algorithm recommendation model based on the convolutional neural network is constructed. The model uses word embedding technology to transform news articles into vector representations and trains the model to learn the feature representations of news articles and the correlation between them. Moreover, the loss function and weight of the model are adjusted to improve the diversity and balance of the recommendation results. Finally, simulation experiments are carried out to evaluate the model’s performance. The results reveal that the information diversity of the system model in this study is increased by 15%, and user satisfaction and the information quality index are increased by 10% and 7%. It proves the importance of diversified data sources, algorithm transparency and explainability, user feedback and participation, and balanced recommendation strategies to reduce risk and improve the performance of recommendation mechanisms. Therefore, the research results guide the practical application of the intelligent news algorithm recommendation mechanism and provide a reference for further improvement and optimization of the recommendation algorithm. [ABSTRACT FROM AUTHOR]

Educational dashboards are increasingly prevalent visualising technologies that display data from educational processes to help learners and educators track learning pathways, alert for deviations, and make interventions. This study contributes to critical studies on data visualisations in education by examining dashboards in higher distance education. Inspired by science and technology studies (STS), it investigates several modes of relating to educational dashboards at one distance university, focusing on their production and deployment. Ethnographic findings show how dashboards are produced through public-private, interdisciplinary collaboration and (made to) align with predominant techno-pedagogical ideas, often by persuading university students to use technologies correctly. When deployed, students learn to filter relevant information, practice self-monitoring, and (re)examine dashboard usage. The case exemplifies a ‘dashboarding of learning’ and ‘learning to dashboard’, indicating that dashboards not only enter educational practices but also encourage actors – sometimes unsuccessfully – to understand and realise their education in line with specific techno-pedagogical ideas. [ABSTRACT FROM AUTHOR]

The Remote Sensing Image Change Captioning (RSICC) has recently emerged in the field of remote sensing image interpretation; it aims to automatically predict natural language captions of significant semantic changes in bi-temporal remote sensing images. Recent studies of RSICC have improved the accuracy of change captions of bi-temporal remote sensing images to a large extent. Nevertheless, there still remain challenges in multi-scale perception of ground objects and feature enhancement of bi-temporal remote sensing images. To address these challenges and further improve the accuracy of RSICC, a novel deep learning–based end-to-end scale-wised feature enhancement network (SFEN) is proposed in this paper. SFEN integrates four efficient blocks: 1) the siamese backbone network (SBN) to extract initial features of bi-temporal remote sensing images, 2) the siamese receptive field fusion (SRFF) block to explicitly capture multi-scale semantic information of ground objects in bi-temporal feature maps, 3) the siamese global feature enhancement (SGFE) block to adaptively enhance key information and filtering redundant features of bi-temporal feature maps in both channel and spatial dimensions, 4) the change caption decoder (CCD) to map bi-temporal feature maps into natural language. The SFEN aims to precisely capture significant semantic information of ground objects in bi-temporal remote sensing images and predict accurate change captions. Experimental results on LEVIR-CC dataset demonstrate our SFEN outperforms recent state-of-the-art (SOTA) approach in RSICC by 5.2% on CIDEr-D and achieves a new SOTA. [ABSTRACT FROM AUTHOR]

Many exceptional deep learning networks have demonstrated remarkable proficiency in general object detection tasks. However, the challenge of detecting ships in synthetic aperture radar (SAR) imagery increases due to the complex and various nature of these scenes. Moreover, sophisticated large-scale models necessitate substantial computational resources and hardware expenses. To address these issues, a new framework is proposed called a stepwise attention-guided multiscale feature fusion network (SAFN). Specifically, we introduce a stepwise attention mechanism designed to selectively emphasize relevant information and filter out irrelevant details of objects in a step-by-step manner. Firstly, a novel LGA-FasterNet is proposed, which incorporates a lightweight backbone FasterNet with lightweight global attention (LGA) to realize expressive feature extraction while reducing the model's parameters. To effectively mitigate the impact of scale and complex background variations, a deformable attention bidirectional fusion network (DA-BFNet) is proposed, which introduces a novel deformable location attention (DLA) block and a novel deformable recognition attention (DRA) block, strategically integrating through bidirectional connections to achieve enhanced features fusion. Finally, we have substantiated the robustness of the new framework through extensive testing on the publicly accessible SAR datasets, HRSID and SSDD. The experimental outcomes demonstrate the competitive performance of our approach, showing a significant enhancement in ship detection accuracy compared to some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Heterogeneous graph embedding models based on non-contrastive learning (NCL) do not rely on negative sampling to learn the intrinsic features and patterns, which may cause the model fail to efficiently learn the differences between vertexes. This paper proposed a heterogeneous graph embedding model based on cross-view prototype non-contrastive learning (XPNCL), which learnt better node representations for downstream tasks by finding additional positive samples with more contextual information, and reconsidered the similarity between positive samples. The model firstly designed a tree structure based on random walks in heterogeneous graph. This directed filtering tree (DFT) about positive samples contained rich neighboring and semantic information by filtering out random walk paths that satisfied local structural constraints. Secondly, to achieve the alignment of similar samples in terms of numerical and quantitative from multiple dimensions, XP-NCL defined the cross-view prototype index (ISDR) and peak operator based on the characteristics of heterogeneous graphs. Furthermore, the model trained using stop-gradient updating. Finally, experiments verify the classification and clustering performance of the node on ACM, DBLP and freebase datasets, and the results show that even without the negative samples, the XP-NCL representation can achieve superior performance in many cases compared to other homogeneous and heterogeneous graph baselines. [ABSTRACT FROM AUTHOR]

Field trips enrich learning programs with out-of-school activities that can bring gains in students' academic content knowledge and personal growth. However, they are a source of anxiety for teachers because of the bureaucracy, pedagogy, etc., risks they imply. To address this issue, we propose FieldTripOrganizer, a field trip planner based on the mixed-initiative approach aimed at increasing teachers' autonomy and motivation in designing educational tours. The key aspects of our application are (i) the simultaneous provision of information filtering and automated scheduling support while the user designs the field trip, and (ii) the visual annotation of places and activities to show whether they can be included in the itinerary without violating its time constraints. Different from current tour planners, these functions enable the user to be in full control of the design process, delegating the system to manage difficult and burdensome tasks such as consistency checks and itinerary optimization. We evaluated FieldTripOrganizer in the use case of organizing a science field trip. In a preliminary user study involving 18 science teachers, our application turned up to be superior to a baseline tour planner in both usability and user experience. Moreover, the teachers declared that it was helpful, motivated them, and reduced their anxiety during the design of the field trips. [ABSTRACT FROM AUTHOR]

In a large-scale distributed network, a naming service is used to achieve location transparency and provide effective content discovery. However, fast and accurate name retrieval in the massive name set is laborious. Approximate set membership data structures, such as Bloom filter and Cuckoo filter, are very popular in distributed information systems. They obtain high query performance and reduce memory requirements through the abstract representation of information, but at the cost of introducing query error rates, which will ultimately affect content service quality. In this paper, in order to obtain higher space utilization and a lower query false positive rate, we propose a flexible fingerprint cuckoo filter (FFCF) for information storage and retrieval, which can change the length and type of fingerprints adaptively. In our scheme, FFCF uses longer fingerprints under low occupancy and has the ability to correct errors by changing the type of stored fingerprints. Moreover, we give a theoretical proof and evaluate the performance of FFCF by experimental simulations with synthetic data sets and real network packets. The results demonstrate that FFCF can improve memory utilization, significantly reduce false positive errors by nearly 90 % at 50 % occupancy and outperform Cuckoo filter in the full range of occupancy. [ABSTRACT FROM AUTHOR]

Firms and other entities provide category-level product attribute information via attribute filters and other tools to aid consumers in filtering, evaluating, comparing, and choosing products. This research examines how displaying this information as a range with or without the distribution of values systematically affects judgments involving attribute value comparisons. Specifically, distributions draw attention away from attribute values, reducing the importance of attribute value differences. With this reduced importance, consumers are less sensitive to attribute value differences; thus, consumers evaluate individual products more positively as they seem more similar to the best available option. Likewise, wider bands of attribute values are selected when filtering product options, as the minimum and maximum values chosen seem less different. Reduced sensitivity to differences also has implications for choices involving tradeoffs between attributes. Importantly, the presence of a distribution itself is the primary driver of this effect, more so than distribution type, as the effect is largely independent of the type of distribution displayed (e.g. normal, bimodal, skewed, uniform). Across six main and seven supplemental experiments , this research highlights a novel consideration for how consumers filter options, form preferences, and choose products. These findings have practical implications and highlight important topics for future research. [ABSTRACT FROM AUTHOR]

This paper addresses the lower limits of encoding and processing the information acquired through interactions between an internal system (robot algorithms or software) and an external system (robot body and its environment) in terms of action and observation histories. Both are modeled as transition systems. We want to know the weakest internal system that is sufficient for achieving passive (filtering) and active (planning) tasks. We introduce the notion of an information transition system (ITS) for the internal system which is a transition system over a space of information states that reflect a robot's or other observer's perspective based on limited sensing, memory, computation, and actuation. An ITS is viewed as a filter and a policy or plan is viewed as a function that labels the states of this ITS. Regardless of whether internal systems are obtained by learning algorithms, planning algorithms, or human insight, we want to know the limits of feasibility for given robot hardware and tasks. We establish, in a general setting, that minimal information transition systems (ITSs) exist up to reasonable equivalence assumptions, and are unique under some general conditions. We then apply the theory to generate new insights into several problems, including optimal sensor fusion/filtering, solving basic planning tasks, and finding minimal representations for modeling a system given input-output relations. [ABSTRACT FROM AUTHOR]

The scientific community has reacted to the COVID-19 outbreak by producing a high number of literary works that are helping us to understand a variety of topics related to the pandemic from different perspectives. Dealing with this large amount of information can be challenging, especially when researchers need to find answers to complex questions about specific topics. We present an Information Retrieval System that uses latent information to select relevant works related to specific concepts. By applying Latent Dirichlet Allocation (LDA) models to documents, we can identify key concepts related to a specific query and a corpus. Our method is iterative in that, from an initial input query defined by the user, the original query is expanded for each subsequent iteration. In addition, our method is able to work with a limited amount of information per article. We have tested the performance of our proposal using human validation and two evaluation strategies, achieving good results in both of them. Concerning the first strategy, we performed two surveys to determine the performance of our model. For all the categories that were studied, precision was always greater than 0.6, while accuracy was always greater than 0.8. The second strategy also showed good results, achieving a precision of 1.0 for one category and scoring over 0.7 points overall. [ABSTRACT FROM AUTHOR]

A core issue in presupposition theory concerns the potential role of linear order for projection. This paper presents experimental evidence that conjunction and disjunction differ precisely in this regard. Presuppositions project asymmetrically from conjunction: a presupposition in the first conjunct projects regardless of any information in the second conjunct that could be used to satisfy the presupposition, while a presupposition in the second conjunct can be 'filtered' by material in the first, so that it doesn't project. We find no such asymmetry for disjunction, where presuppositions in both the first and the second disjunct can be filtered by information in the other disjunct. Theoretically, these results pose a challenge to traditional dynamic accounts, and also strongly argue against accounts that take all projection and filtering to be uniformly determined by linear order across connectives. Instead, they call for an account of projection that can differentiate between conjunction and disjunction by modulating the effects of linear order through proper consideration of the underlying truth conditions of each connective. [ABSTRACT FROM AUTHOR]

Most existing RGB-D salient object detection (SOD) methods tend to achieve higher performance by integrating additional modules, such as feature enhancement and edge generation. There is no doubt that these modules will inevitably produce feature redundancy and performance degradation. To this end, we exquisitely design a cross-modal fusion and progressive decoding network (termed CPNet) to achieve RGB-D SOD tasks. The designed network structure only includes three indispensable parts: feature encoding, feature fusion and feature decoding. Specifically, in the feature encoding part, we adopt a two-stream Swin Transformer encoder to extract multi-level and multi-scale features from RGB images and depth images respectively to model global information. In the feature fusion part, we design a cross-modal attention fusion module, which can leverage the attention mechanism to fuse multi-modality and multi-level features. In the feature decoding part, we design a progressive decoder to gradually fuse low-level features and filter noise information to accurately predict salient objects. Extensive experimental results on 6 benchmarks demonstrated that our network surpasses 12 state-of-the-art methods in terms of four metrics. In addition, it is also verified that for the RGB-D SOD task, the addition of the feature enhancement module and the edge generation module is not conducive to improving the detection performance under this framework, which provides new insights into the salient object detection task. Our codes are available at https://github.com/hu-xh/CPNet. [ABSTRACT FROM AUTHOR]

Washington policy research analysts (WAs) monitor political developments and produce research to interpret the impact of these events. We find institutional clients channel more commissions to brokerages providing policy research and commission-allocating institutional clients generate superior returns on their politically sensitive trades. We find that WA policy research reports are associated with significant price and volume reactions. Finally, we find sell-side analysts with access to WA issue superior stock recommendations on politically sensitive stocks. These effects are particularly acute during periods of high political uncertainty. Overall, we uncover a unique and an important conduit through which political information filters into asset prices. This paper was accepted by David Sraer, finance. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2023.4919. [ABSTRACT FROM AUTHOR]