检索结果-内蒙古大学图书馆

Structural Balance Computation of Signed Hypergraphs via Memetic Algorithm

学校读者我要写书评

暂无评论

Structural Balance Computation of Signed Hypergraphs via Mem...

Data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Xinchu Han Ruijie Xu Lijia Ma Zengyang Shao Yuan Bai Shanfeng Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Laboratory of Data Discovery for Health Limited Hong Kong China School of Electronic Engineering Xidian University Xi'an China

The potential imbalances among entities and connections within complex systems can pose significant threats to their overall functionality. In order to enhance the functional security of these complex systems, it becomes imperative to address and alleviate these underlying imbalances. Structural balance computation has gained attention because of its ability to balance relationships among entities within systems. Traditional methods in structural balance computation aim to minimize imbalances within signed networkss. However, signed networkss have limitations in effectively representing complex data relationships in multi-modal or multi-type data. In order to address this constraint, we propose a novel framework called SHMA (Structural Balance of Signed Hypergraphs based on Memetic Algorithm) which aims to identify and minimize imbalances within signed hypergraphs. More specifically, we formulate the degree of imbalance in signed hypergraphs as an extended energy function, thereby transforming the computation of structural balance of the hypergraphs into an optimization problem. Then, we utilize a multi-level memetic algorithm to optimize the energy function and obtain a solution with the least imbalances. To assess the performance of SHMA, we performed experiments on various real-world datasets and conducted a comparative analysis. The experimental results illustrate that SHMA outperforms the alternative algorithms in terms of structural balance computation of signed hypergraphs. In addition, SHMA exhibits fast convergence, enabling it to reach a balanced state more efficiently.

关键词：

M-CNN-RF: A hybrid deep learning model for accurate pediatric skeletal age estimation using hand bone radiographs

学校读者我要写书评

暂无评论

Alexandria engineering Journal 2025年 129卷 289-301页

作者： Hazrat Bilal Yibin Tian Inam Ullah Sahil Garg Bong Jun Choi Mohammad Mehedi Hassan College of Mechatronics and Control Engineering Shenzhen University Shenzhen 518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Department of Computer Engineering Gachon University Seongnam 13120 Republic of Korea École de Technologie Supérieure Montreal QC H3C1K3 Canada Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India School of Computer Science and Engineering Soongsil University Seoul Republic of Korea Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia

Precise and accurate skeletal age estimation using medical imaging is a pivotal and challenging task in the healthcare sector, particularly for identifying potential bone growth issues in infants and newborns. Therefore, this study addresses the pervasive challenges associated with assessing bone abnormalities in pediatric patients, including injuries and infections. Given the importance of early and precise detection of skeletal development, a novel hybrid model is proposed that integrates a modified convolutional neural network (M-CNN) with a robust machine learning (ML) model, specifically random forest (RF), resulting in the M-CNN-RF framework. This model is designed to enhance pediatric bone health assessment by providing an effective method for skeletal age estimation. The M-CNN-RF model is tailored to accurately evaluate hand bone maturation, overcoming the inherent difficulties in skeletal age assessment. The model utilizes the bone age dataset from the Radiological Society of North America that includes 14,236 left-hand radiological images, focusing on the development of a robust model for a precise evaluation based on hand skeleton guidelines. In addition, to enhance the prediction and generalization of the model, data augmentation techniques were employed to increase the size of the dataset. The M-CNN-RF exhibits exceptional performance using numerous performance measures, achieving an accuracy of 97% and precision and recall exceeding 94%. In addition, the model reaches an F1 score of 97%, highlighting the ability of the model to ensure a balance between precision and recall. Furthermore, low mean absolute error (MAE) and mean square error (MSE) values of 0.0141 and 0.0327, respectively, were computed for the proposed model, which demonstrates its notable efficacy in predicting skeletal age. The findings of this study not only contribute valuable information for clinical applications but also underscore the potential of the adopted approach to address th

关键词： Machine learning Pediatric bone health assessment Bone X-ray images Modified-CNN model Hybrid M-CNN-RF model Skeletal age estimation

A Theoretical Approach to Designing Interactive Robots, Using Restaurant Assistants as an Example

学校读者我要写书评

暂无评论

A Theoretical Approach to Designing Interactive Robots, Usin...

International Conference on Ubiquitous Robots (UR)

作者： Norina Gasteiger Mehdi Hellou Jong Yoon Lim Bruce MacDonald Ho Seok Ahn Department of Electrical Computer and Software Engineering CARES The University of Auckland Auckland New Zealand School of Health Sciences The University of Manchester United Kingdom Department of Computer Science The University of Manchester United Kingdom

Within restaurant settings, robotic assistants are required to interact with different users in different scenarios. Adaptive behavior is essential when providing quality services, facilitating natural interactions, and influencing perceptions on social intelligence, helpfulness, and willingness to accept recommendations. Informed by our previous review on culturalization/localization and personalization in the field of human-robot interaction, this paper exemplifies how to apply relevant knowledge on communication and language, behavior and service, proxemics, and interface design, to propose a design strategy for an adaptable restaurant robot. The prospective robot is intended to be able to adapt its behaviors and speech to different users across different restaurant settings and countries. Specifically, the robot will respond to four common scenarios within restaurant settings: greeting customers, making simple recommendations, providing assistance and giving directions. Technical solutions are also considered and include: 1) mechanical design, 2) navigation and localization system, 3) perception, 4) speech, 5) gestures and 6) additional tools.

关键词：

Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Guangming Wang, Siyuan Wu, Tianci Zhang, Liang School of Computer Science and Technology Xidian University China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province China Xi’an Key Laboratory of Intelligent Software Engineering China

Free-hand sketches are appealing for humans as a universal tool to depict the visual world. Humans can recognize varied sketches of a category easily by identifying the concurrence and layout of the intrinsic semantic components of the category, since humans draw free-hand sketches based a common consensus that which types of semantic components constitute each sketch category. For example, an airplane should at least have a fuselage and wings. Based on this analysis, a semantic component-level memory module is constructed and embedded in the proposed structured sketch recognition network in this paper. The memory keys representing semantic components of each sketch category can be self-learned and enhance the recognition network’s explainability. Our proposed networks can deal with different situations of sketch recognition, i.e., with or without semantic components labels of strokes. Experiments on the SPG and SketchIME datasets demonstrate the memory module’s flexibility and the recognition network’s explainability. The code and data are available at https://***/GuangmingZhu/SketchESC. © 2023, CC BY.

关键词： Semantics

Emergency Transportation and Structural Prediction and Optimization of Goods Based on ARIMA and Multi-objective E-commerce Logistics Network Model

学校读者我要写书评

暂无评论

Emergency Transportation and Structural Prediction and Optim...

Applied Intelligence and Sustainable Computing (ICAISC), International Conference on

作者： Yiyang Nie Xiang Chen Xuanli Wu Zihao Deng School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan China Shcool of Mathematics and Computational Science Hunan University of Science and Technology Xiangtan China

With the development of the internet, online shopping has gradually become a popular way of shopping among the general public, which in turn poses a greater challenge to the e-commerce logistics network. Predicting the volume of goods for each logistics site and route, and establishing a model for quickly adjusting the network in response to sudden situations can save logistics network costs and improve its efficiency. Therefore, this article has done the following work: first, it establishes an effective logistics network volume prediction model; second, for the two scenarios of network structure that cannot be modified and can be modified, it provides a model that can effectively guide the adjustment of the volume of goods on each route when a logistics site is closed; finally, it establishes a logistics network evaluation model to evaluate the importance of logistics sites and routes.

关键词：

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University Bangladesh

Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel perspective of enhancing the robustness of channels in feature maps to domain shifts. We observe that models trained on source domains contain a substantial number of channels that exhibit unstable activations across different domains, which are inclined to capture domain-specific features and behave abnormally when exposed to unseen target domains. To address the issue, we propose a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation. We theoretically prove that our framework could effectively lower the generalization bound. Extensive experiments on several benchmarks indicate that our framework achieves state-of-the-art performance compared to other competing methods. Our code is available at https://***/lingeringlight/DomainDrop. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Quantum-based Feature Selection for Multi-Classification Problem in Complex Systems with Edge Computing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Wenjie Chen, Junxiu Wang, Yuxiang Gao, Peipei Lei, Zhibin Ma, Xu Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China 999077 Hong Kong School of Software Qufu Normal University Shandong273165 China

The complex systems with edge computing require a huge amount of multi-feature data to extract appropriate insights for their decision-making, so it is important to find a feasible feature selection method to improve the computational efficiency and save the resource consumption. In this paper, a quantum-based feature selection algorithm for the multi-classification problem, namely QReliefF, is proposed, which can effectively reduce the complexity of algorithm and improve its computational efficiency. First, all features of each sample are encoded into a quantum state by performing operations CMP and Ry, then the amplitude estimation is applied to calculate the similarity between any two quantum states (i.e., two samples). According to the similarities, the Grover-Long method is utilized to find the nearest k neighbor samples, and then the weight vector is updated. After a certain number of iterations through the above process, the desired features can be selected with regards to the final weight vector and the threshold τ. Compared with the classical ReliefF algorithm, our algorithm reduces the complexity of similarity calculation from O(MN) to O(M), the complexity of finding the nearest neighbor from O(M) to O(√M), and resource consumption from O(MN) to O(MlogN). Meanwhile, compared with the quantum Relief algorithm, our algorithm is superior in finding the nearest neighbor, reducing the complexity from O(M) to O(√M). Finally, in order to verify the feasibility of our algorithm, a simulation experiment based on Rigetti with a simple example is performed. © 2023, CC BY.

关键词： Feature Selection

Multi-View Incongruity Learning for Multimodal Sarcasm Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Diandian Cao, Cong Yuan, Fangfang Liu, Yanbing Zeng, Guangjie Yu, Xiaoyan Peng, Hao Yu, Philip S. Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science University of Illinois Chicago United States

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model’s generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL’s advancement in mitigating the effect of spurious correlation. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Adversarial Guided Gradient Estimation Hashing for Cross-modal Retrieval

学校读者我要写书评

暂无评论

Adversarial Guided Gradient Estimation Hashing for Cross-mod...

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Kangkang Lu Meiyu Liang Zhe Xue Xiaowen Cao Mengran Yin Zehua Zhao Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665456579

Due to low storage cost and fast query speed, deep hashing methods are widely used in cross-modal retrieval. However, the “heterogeneous gap” between multi-modal data is still a challenge. Moreover, a major difficulty in deep hashing lies in the discrete constraints imposed on the network output. Existing solutions usually use relaxation techniques, but this inevitably produces quantization error, leading to sub-optimal hash code. In this paper, we propose Adversarial Guided Gradient Estimation Hashing (AGEH). Firstly, in order to bridge the heterogeneous gap between different modal data, a cross-modal adversarial feature learning network is constructed to learn cross-modal semantic associations. Secondly, to solve the discrete optimization problem of hash code, we propose a hashing optimization strategy based on gradient estimation for sign function, which strictly uses sign function to maintain discrete constraints in forward propagation, while in back propagation, the gradient is directly transmitted to the previous layer and thus avoid quantization error. Extensive experiments conducted on two cross-modal benchmark datasets show that our proposed AGEH outperforms several state-of-the-art methods.

关键词： Representation learning Bridges Backpropagation Training Codes Quantization (signal) Semantics