检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Xing Nguyen, Huy Harris, Carl Ho, Nhat Saria, Suchi Department of Computer Science Johns Hopkins University United States Department of Statistics and Data Sciences The University of Texas Austin United States Department of Biomedical Engineering Johns Hopkins University United States

As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models' predictive performance. We introduce "FuseMoE", a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE is effective in managing scenarios with missing modalities and irregularly sampled data trajectories. Theoretically, our unique gating function contributes to enhanced convergence rates, leading to better performance in multiple downstream tasks. The practical utility of FuseMoE in the real world is validated by a diverse set of challenging prediction tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Iterative Methods via Locally Evolving Set Process 38

Iterative Methods via Locally Evolving Set Process

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhou, Baojian Sun, Yifan Harikandeh, Reza Babanezhad Guo, Xingzhi Yang, Deqing Xiao, Yanghua The School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Department of Computer Science Stony Brook University United States Samsung SAIT AI Lab

Given the damping factor α and precision tolerance ϵ, Andersen et al. [2] introduced Approximate Personalized PageRank (APPR), the de facto local method for approximating the PPR vector, with runtime bounded by Θ(1/(αϵ)) independent of the graph size. Recently, Fountoulakis & Yang [12] asked whether faster local algorithms could be developed using Õ(1/(√αϵ)) operations. By noticing that APPR is a local variant of Gauss-Seidel, this paper explores the question of whether standard iterative solvers can be effectively localized. We propose to use the locally evolving set process, a novel framework to characterize the algorithm locality, and demonstrate that many standard solvers can be effectively localized. Let vol(St) and γt be the running average of volume and the residual ratio of active nodes St during the process. We show vol(St)/γt ≤ 1/ϵ and prove APPR admits a new runtime bound Õ(vol(St)/(αγt)) mirroring the actual performance. Furthermore, when the geometric mean of residual reduction is Θ(√α), then there exists c ∈ (0, 2) such that the local Chebyshev method has runtime Õ(vol(St)/(√α(2 − c))) without the monotonicity assumption. Numerical results confirm the efficiency of this novel framework and show up to a hundredfold speedup over corresponding standard solvers on real-world graphs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ontological Knowledge-Based Representation System to Prevent Web Attacks in iMANET's

Ontological Knowledge-Based Representation System to Prevent...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Chandani, Priyanka Gupta, Anand Kumar Manivasagam Noida Institute Of Engineering And Technology Department Of Data Science Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India

ISBN: (纸本)9798350366846

This paper implies securing Internet-based Mobile Ad-hoc Networks (iMANETs) with semantic web techniques. To illustrate safety issues, ontologies will be utilised rather than taxonomies. These ontologies can be added to an intrusion detection system's (IDS) information repository. By employing inference based on semantic relations, intrusion detection systems can identify and incorporate upcoming attacks into their current knowledge base. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Dynamic Optimization-Based Calibration Framework for Agent-Based Financial Market Simulators 13

Evolutionary Dynamic Optimization-Based Calibration Framewor...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Yang, Zhenhua Zhong, Muyao Yang, Peng Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Statistics and Data Science Shenzhen518055 China

ISBN: (纸本)9798350308365

The agent-based financial market simulators serve as an important validation tool for trading strategies. For high-fidelity simulation, it is pivotal to calibrate the parameters of a simulator so that the generated simulation data resembles the observed real market data of interest. In traditional calibration methods, it is typical that the parameters of the simulator are set to be time-invariant. However, the dynamic nature of the real financial market introduces various variability into the behaviors of the market participants over different time intervals, posing in-herent limitations to the traditional methods. A more reasonable approach might involve employing a simulator with time-variant parameters. This suggests that the model parameters can be dynamically adjusted at different stages of the simulation to adapt to the evolving market. Consequently, the calibration problem of the financial market simulators can be treated as a dynamic optimization problem. To dynamically calibrate the simulators, we introduce an Evolutionary Dynamic Optimization (EDO) framework. By monitoring the changes of the best fitness, the whole simulation time interval is adaptively divided into multiple stages. Then the Negatively Correlated Search (NCS) algorithm is employed to effectively adjust the parameters at different simulation stages to better simulate the real financial market. Empirical results on both synthetic and real data verify that our dynamic calibration framework significantly outperforms traditional calibration methods that fixing a parameter for the whole simulation interval. The proposed strategy of detecting dynamic changes is also shown to be more reliable than the naive method of manually segmenting stages. In terms of calibration time, our proposed method significantly improves by nearly 93% compared to the fixed parameter setting, and approximately 61% compared to manual segmentation calibration. © 2024 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Allocation in Edge Computing via Deep Deterministic Policy Gradient Reinforcement Learning 3

Dynamic Resource Allocation in Edge Computing via Deep Deter...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Gopal, Vidhya Surendar, U. Bajulunisha, A. Tamilselvi, M. Sathiyapriya, V. Saranya, N. Sona College of Technology Department of Computer Science and Engineering Salem India Srm institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Kundrathur India Roever Engineering College Department of Computer Science and Engineering Perambalur India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India Karpagam College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798331508456

The difficulty with dynamic and heterogeneous natured edge computing environments is resource provisioning. Reinforcement Learning (RL) can be promising to solve the problems of resource allocation under conditions of dynamics and complexity. This research work presents a novel DDPG-based (Deep Deterministic Policy Gradient) approach for optimizing the dynamics of resource allocation in edge computing environments by exploiting the CRAWDAD KAIST-WIBRO dataset for the proposed model. This approach implements a neural network that learns the optimal policies of allocations with dynamism towards new changes in workloads and resource availabilities. In order to test the performance of this method, conducted several simulations over real-world workload and resource data, mapping the parameters like rewards and variation in episodes. The simulation results indicate that proposed approach performs superior compared to traditional heuristic-based approaches as well as other RL algorithms for resource usage, response time, and energy efficiency. This proposed approach permits optimized resource utilization along with quality of service, of paramount importance in executing complex and demanding applications at the edge computing environment. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Impact of Stuttering Event Representation on Detection Performance 2

The Impact of Stuttering Event Representation on Detection P...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-Banna, Abedal-Kareem Fang, Hui Shubita, Ahmad F. Arafah, Mohammad Eqteeshat, Amani Abuaisheh, Saif B. University Of Petra Department Of Ai And Data Science Jordan Loughborough University Department Of Computer Science United Kingdom University Of Petra Department Of Software Engineering Jordan University Of Petra Department Of Computer Science Jordan Malaya University Department Of Information System Malaysia

ISBN: (纸本)9798350394962

Stuttering or stammering is a common neurogenic, psychogenic fluency disorder wherein people have uncontrolled blocks on the natural flow of speech. Automatic Stuttering Event Detection (SED) is a widely recognised challenge due to the heterogenic and overlapped nature of stuttering speech. Therefore, this comparative study investigates the impact of stuttering event representation on detection performance. The paper evaluates the performance of SED and shows the impact of employing ASR pre-trained feature extractions on each stuttering event. Moreover, the paper provides different groups of experiments that evaluate the impact of three acoustic features, the Zero Crossing Rate (ZCR), the Spectral Flux Onset Strength Envelope (SFO), and Fundamental Frequency (FF) features, on SED performance. The paper demonstrates that the fusion of spectral and ASR features improves SED performance across all stuttering events by 8%. The F1 score of the Block class increased by approximately 10%, from 15% to 25%, while the word repetition and interjection increased by 8%. In addition, our experiments proved that the fusion of temporal features increased the average F1 score of SED by 2% across all stuttering events. The F1 score of the prolongation and sound repetition classes increased by 6% and 3%, respectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Gloss-Free Sign Language Translation using Sign2gpt-Next Technique

Gloss-Free Sign Language Translation using Sign2gpt-Next Tec...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Babisha, A. Umarani Srikanth, G. Angel Kiruba, D.R. Sundar, R. Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering DMI College of Engineering Chennai India Department of Computer Science and Engineering School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331510299

This work proposes a new approach to convert the data from sign language to spoken language without exposing the data to a gloss layer. Whenever gloss annotations are used which frequently are incomplete and act as an intermediate representation, it is usually found to be a bottleneck in translating sign language videos. In order to avoid this, the authors use a combination of modern machine learning algorithms to arrive at the conclusion. They use Dino-V2 Vision Transformer to implement the function of extracting the spatial features of the input sign language video frames. This model is particularly suitable for learning and visual patterns in general and particularly for capturing fine details of these patterns. Further, a spatio-temporal transformer layer is added to automate the temporal processing of the Sign-Language which helps in the arrangement of the body gestures and limb movements needed at a specific temporal frame. It is then translated into the desired spoken language using a multilingual Generative Pre-trained Transformer (GPT) model. The approach can be said to be a big leap forward in sign language transliteration especially for such situations where few Gloss annotations are available, and making way for better and improved tools for the Deaf and the hard-of-hearing. © 2024 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of K-means Clustering-Based Outlier Handling Techniques in Colonic Condition Endoscopy Image Classification Using CNN 13

Effectiveness of K-means Clustering-Based Outlier Handling T...

引用

13th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2024

作者： Athiyah, Ummi Rustad, Supriadi Soeleman, Moch Arief Muljono Akrom, Muhamad Dian Nuswantoro University Faculty of Computer Science Semarang Indonesia Telkom University Department of Data Science Purwokerto Indonesia

ISBN: (纸本)9798350368086

Colorectal cancer is one of the leading causes of cancer death worldwide, so accurate early detection is needed. Endoscopic imaging technology plays a vital role in diagnosis, but the presence of outliers in endoscopic images can significantly affect the accuracy of the classification model. This study addresses this challenge by applying Histogram of Oriented Gradients (HOG) for feature extraction and K-means Clustering for outlier detection and removal. A dataset of colon endoscopic images was obtained from the public database Gastrovision, which was divided into two classes: normal and abnormal conditions. This study applied a two-step modeling process, first with the original dataset and then with the cleaned dataset after outlier removal. The results showcased a significant improvement in model performance after outlier handling, with accuracy increasing from 61% to 85%. The Area Under Curve (AUC) of the ROC curve also increased from 0.84 to 0.92, indicating a better model ability to distinguish between normal and abnormal conditions. These findings emphasize the importance of data quality and effective outlier management in training a machine-learning model for colon cancer endoscopic image conditions. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

data Aggregation Point Placement and Subnetwork Optimization for Smart Grids

引用

computers, Materials & Continua 2025年第4期83卷 407-434页

作者： Tien-Wen Sung Wei Li Chao-Yang Lee Yuzhen Chen Qingjun Fang Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and MathematicsFujian University of TechnologyFuzhou350118China Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin640301TaiwanChina

To transmit customer power data collected by smart meters(SMs)to utility companies,data must first be transmitted to the corresponding data aggregation point(DAP)of the *** number of DAPs installed and the installation location greatly impact the whole *** the traditional DAP placement algorithm,the number of DAPs must be set in advance,but determining the best number of DAPs is difficult,which undoubtedly reduces the overall performance of the ***,the excessive gap between the loads of different DAPs is also an important factor affecting the quality of the *** address the above problems,this paper proposes a DAP placement algorithm,APSSA,based on the improved affinity propagation(AP)algorithm and sparrow search(SSA)algorithm,which can select the appropriate number of DAPs to be installed and the corresponding installation locations according to the number of SMs and their distribution locations in different *** algorithm adds an allocation mechanism to optimize the subnetwork in the *** is evaluated under three different areas and compared with other DAP placement *** experimental results validated that the method in this paper can reduce the network cost,shorten the average transmission distance,and reduce the load gap.

关键词： Smart grid data aggregation point placement network cost average transmission distance load gap

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：