检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Maruf, Md Al Azim, Akramul Auluck, Nitin Sahi, Mansi Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada Indian Institute of Technology Departmcnt of Computer Science and Engineering Ropar India

ISBN: (纸本)9798350345346

With the increasing demand for edge computing in cyber-physical system (CPS) applications, ensuring the safety and reliability of machine learning models running on edge devices during online model training and inference is essential. Although data and model parallelism offer significant advantages for large machine learning model training, adopting parallel computing architecture in edge networks is challenging. It introduces safety concerns while splitting and integrating machine learning models over different computing nodes, which can pose risks to the integrity and reliability of the system. Therefore, online model training and inference in edge networks require a safe parallel computing architecture to achieve improved performance with optimal resource utilization. To address this challenge, we propose an efficient machine learning model partitioning algorithm that considers the safety constraint and requirements of edge networks and includes the triple-modular redundancy (TMR) technique for trusted computation. Our proposed approach achieves a significant speedup of approximately 56.3% in net training time compared to the non-partitioning approach, making it more efficient and suitable for real-time applications in edge networks. © 2023 IEEE.

关键词： Edge Networks Machine Learning Model Partitioning Triple Modular Redundancy (TMR)

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Evolutionary Mating Algorithm for Covid19 Confirmed Cases Prediction based on Vaccination

A Novel Hybrid Evolutionary Mating Algorithm for Covid19 Con...

引用

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Ahmed, Marzia Mohamad, Ahmad Johari Rahman, Mostafijur Sulaiman, Mohd Herwan Kashem, Mohammod Abul Faculty of Electrical & Electronics Engineering Technology Pahang Malaysia Daffodil International University Department of Software Engineering Dhaka Bangladesh Green University of Bangladesh Department of Computer Science and Engineering Bangladesh DUET Department of Computer Science and Engineering Gazipur Bangladesh

ISBN: (纸本)9798350316001

Microorganisms may cause illness when they enter the body, multiply, and spread to other parts. The rapid spread of COVID-19 to neighboring countries is examined in this research. Anticipating a positive COVID-19 occurrence helps in determining risks and creating countermeasures. As a result, developing robust mathematical models with small error margins for predictions is crucial. Based on these findings, a combined method of evaluating confirmed cases of COVID-19 with universal immunization is recommended. First, the best hyperparameter values of the RBF kernel-based LSSVM (least square support vector machine) were determined using the most recent Evolutionary Mating Algorithm (EMA). After that, LSSVM will complete the task of prediction. This hybrid method has been utilized for time series forecasting in Malaysia since the country's immunization program against COVID-19 got underway. We evaluate our results next to those of well-known methodologies in nature-inspired metaheuristics. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

AI LipReader-Transcribing Speech from Lip Movements 6

AI LipReader-Transcribing Speech from Lip Movements

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Ajitha, D. Dutta, Disha Saha, Falguni Giri, Parus Kant, Rohan School of Computer Science and Engineering Vellore Institute of Technology Vellore Department of Software Systems Vellore India School of Computer Science and Engineering Vellore Institute of Technology Department of Database Systems Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore Department of Information Security Vellore India

ISBN: (纸本)9798350306613

Lip Reading AI is a discipline that is rapidly changing and has numerous applications in security, accessibility and human-computer interaction. This paper proposes a model which combines Convolutional Neural Networks (CNNs) to capture spatial capabilities, Long Short-Term Memory (LSTM) networks to examine temporal dependencies, and an adaptive interest mechanism. Meticulous preprocessing of the MIRACL VC-l dataset addressing challenges including one of a kind lip moves and occlusions accompanied with the aid of transitioning this study effortlessly to LRS2 dataset to complement lexemic versatility is one of its key function. The effects verify its robustness throughout unique datasets with superior overall performance towards cutting-edge techniques. Ablation checks suggest the crucial significance of every element in phrases of improving lip analyzing accuracy. Our proposed model version additionally suggests flexibility in restricted and naturalistic language situations. © 2024 IEEE.

关键词： Attention Mechanism Convolutional Neural Networks (CNNs) Deep Learning Lip Reading Long Short-Term Memory (LSTM) LRS2 Dataset MIRACLVC-J Dataset

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Audio Splicing Forgery Detection Using PVTv2 Transformer

Deep Learning-Based Audio Splicing Forgery Detection Using P...

引用

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Kanca, Elif Gulsoy, Tolgahan Ustubioglu, Arda Ustubioglu, Beste Ayas, Selen Baykal Kablan, Elif Ulutas, Guzin Department of Software Engineering Karadeniz Technical University Trabzon Turkey Department of Management Information Systems Trabzon University Trabzon Turkey Department of Computer Engineering Karadeniz Technical University Trabzon Turkey

ISBN: (纸本)9798350379433

Attacks on multimedia files by malicious users have become quite common, especially with the increase in the number of editing tools and their ease of use. Considering that such files can now be used both as evidence and for social visibility in all kinds of environments, it has become important to prove their authenticity. With the proposed method, the detection of merging forgeries in audio files has been carried out. For this purpose, the audio files received from the input are converted into cochleagram images. The PVTv2 based deep network architecture is trained with the generated cochleagram images. As a result of the training, the suspicious audio file given as input is labelled as original/fake. The proposed method gives 96.11% accuracy for 2s database, 94.63% accuracy for 3s database and 95.19% accuracy for 2s-3s database. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Viability Analysis Of Drug-Treated Tumor Spheroids Using Machine Learning

Viability Analysis Of Drug-Treated Tumor Spheroids Using Mac...

引用

2024 Medical Technologies Congress, TIPTEKNO 2024

作者： Oǧuz, Kaya Aslan, Arda Evcin, Emre Özoǧul, Emre Sönmez, Mehmet Eren Karabacak, Yaren Korkmaz, Ilker Karagonlar, Zeynep Fırtına Department of Computer Engineering Izmir University of Economics Izmir Turkey Department of Genetics and Bioengineering Izmir University of Economics Izmir Turkey Department of Software Engineering Izmir University of Economics Izmir Turkey

ISBN: (纸本)9798331529819

3D spheroids that are able to mimic the microenvironment of tumors effectively have emerged as significant structures in cancer biology and drug development. This study aims to help cancer researchers monitor the changes in human liver cancer spheroids in response to drug treatment by offering a software tool for evaluating cell viability within 3D spheroids. A dataset of spheroid images are collected, processed, and classified using alternative machine learning models constructed with Random Forest, Logistic Regression, Support Vector Machine and Extreme Gradient Boosting methods. The classification performances of the models are evaluated in terms of the prediction accuracy, precision, recall, and F1-score values. Based on the test experiments conducted, Extreme Gradient Boosting model achieved the highest ratios for all of the performance metrics. Furthermore, a standalone desktop application is implemented to perform analyses of the images with the help of its user-friendly interface. © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Mathematical Methods for Reducing the Search Space for Solutions in 'Big Data' Analysis and Management 14

Mathematical Methods for Reducing the Search Space for Solut...

引用

14th International Conference on Advanced computer Information Technologies, ACIT 2024

作者： Syrotkina, Olena Kobti, Ziad Aleksieiev, Mykhailo Moroz, Dmytro Udovyk, Iryna Martynenko, Andrii University of Windsor School of Computer Science Windsor Canada Dnipro University of Technology Department of Software Engineering Dnipro Ukraine

ISBN: (纸本)9798350350036

This paper addresses mathematical methods to reduce or segment the search space for big data solutions into distinct subspaces with partial solutions. It is achieved by using a data organization structure of 'm-tuples based on ordered sets of arbitrary cardinality.' We provide a mathematical description of this structure and review contemporary methodologies to address similar problems. The study highlights how these properties can significantly reduce the analyzed state space and includes graphs that demonstrate changes in data volume within these subspaces. Additionally, we analyze how variations in four specific arguments affect data volume changes and provide an overview of the efficiency gains in resource use from applying the mathematical methods discussed. © 2024 IEEE.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ANN

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ...

引用

2024 Multimedia University engineering Conference, MECON 2024

作者： Qamar, Muhammad Salman Haq, Ihsan Ul Munir, Muhammad Fahad Roslee, Mardeni Bin Awan, Adnan Anwar Waseem, Athar International Islamic University Department of Electrical and Computer Engineering Islamabad Pakistan Multimedia University Centre for Wireless Technology Faculty of Engineering Cyberjaya63100 Malaysia School of Engineering California Polytechnic State University Department of Computer Science and Software Engineering San Luis ObispoCA United States

ISBN: (纸本)9798331530747

This paper explores strategies to improve the energy efficiency and operational longevity of Wireless Sensor Networks (WSNs) through the optimization of clustering techniques and energy efficient routing protocols. The proposed methodology is precisely crafted to optimize energy consumption (EC) while preserving the overall effectiveness of WSNs. LEACH (Low Energy Adaptive Cluster Hierarchy) is a cluster-based protocol where non-cluster head nodes deactivate their RF until their allocated time slots. Nevertheless, a drawback of traditional LEACH is its random rotation of local Cluster Heads (CH), leading to unequal cluster distribution. To overcome this issue, we proposed a novel hybrid technique called LEACH-D protocol and Artificial Neural Network (ANN). The LEACH-D algorithm enhances the duration of transmission tasks while ensuring uniform battery energy consumption. On the other hand, the ANN plays a pivotal role in coordinating optimal routing decisions and CH placement, refining data aggregation and transmission mechanisms to restrain idle listening. The findings indicate that the suggested approach manifests as substantial reductions in energy consumption and prolonged network lifespan of WSN. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Static Analysis Techniques for Fixing software Defects in MPI-Based Parallel Programs

引用

computers, Materials & Continua 2024年第5期79卷 3139-3173页

作者： Norah Abdullah Al-Johany Sanaa Abdullah Sharaf Fathy Elbouraey Eassa Reem Abdulaziz Alnanih Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Software Engineering and Distributed System Research Group King Abdulaziz UniversityJeddah21589Saudi Arabia

The Message Passing Interface (MPI) is a widely accepted standard for parallel computing on distributed ***, MPI implementations can contain defects that impact the reliability and performance of parallelapplications. Detecting and correcting these defects is crucial, yet there is a lack of published models specificallydesigned for correctingMPI defects. To address this, we propose a model for detecting and correcting MPI defects(DC_MPI), which aims to detect and correct defects in various types of MPI communication, including blockingpoint-to-point (BPTP), nonblocking point-to-point (NBPTP), and collective communication (CC). The defectsaddressed by the DC_MPI model include illegal MPI calls, deadlocks (DL), race conditions (RC), and messagemismatches (MM). To assess the effectiveness of the DC_MPI model, we performed experiments on a datasetconsisting of 40 MPI codes. The results indicate that the model achieved a detection rate of 37 out of 40 codes,resulting in an overall detection accuracy of 92.5%. Additionally, the execution duration of the DC_MPI modelranged from 0.81 to 1.36 s. These findings show that the DC_MPI model is useful in detecting and correctingdefects in MPI implementations, thereby enhancing the reliability and performance of parallel applications. TheDC_MPImodel fills an important research gap and provides a valuable tool for improving the quality ofMPI-basedparallel computing systems.

关键词： High-performance computing parallel computing software engineering software defect message passing interface deadlock

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Variational Graph AutoEncoder against Attribute Inference Attacks for Cross-Domain Recommendation

引用

IEEE Transactions on Knowledge and Data engineering 2025年第07期37卷 3916-3932页

作者： Xiong, Yudi Guo, Yongxin Pan, Weike Yang, Qiang Ming, Zhong Zhang, Xiaojin Yu, Han Lin, Tao Tang, Xiaoying Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China School of Science and Engineering Shenzhen518172 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong WeBank Shenzhen China Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Westlake University School of Engineering Hangzhou China

Cross-domain recommendation (CDR) aims to alleviate the data sparsity problem by leveraging the benefits of modeling two domains. However, existing research often focuses on the recommendation performance while ignores the privacy leakage issue. We find that an attacker can infer user attribute information from the knowledge (e.g., user preferences) transferred between the source and target domains. For example, in our experiments, the average inference accuracies of attack models on gender and age attributes are 0.8323 and 0.3897. The best-performing attack model achieves accuracies of 0.8847 and 0.4634, exceeding a random inference by 25.10% and 64.04%. We can see that the leakage of user attribute information may significantly exceed what would be expected from random inference. In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability with the ability of GCNs in exploiting high-order relational information. Moreover, to ensure against attribute inference attacks without sacrificing the recommendation performance, we design a user attribute protection module that fuses user attribute-camouflaged information with knowledge transfer during cross-domain processes. We then conduct extensive experiments on three real-world datasets, and find our CVGAE is able to achieve strong privacy protection while making little sacrifices in recommendation accuracy. © 1989-2012 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Global Stock Market Prediction Using Transformer-Based Deep Learning Techniques 15

Global Stock Market Prediction Using Transformer-Based Deep ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Gothai, E. Thamilselvan, R. Natesan, P. Vignesh, K. Kongu Engineering College Department of Computer Technology Tamilnadu Perundurai India Kongu Engineering College Department of Cse Tamilnadu Perundurai India Kongu Engineering College Department of It Tamilnadu Perundurai India Kongu Engineering College Software Systems Department of Ct Tamilnadu Perundurai India

ISBN: (纸本)9798350370249

Deep learning approaches' use in financial market forecasting has recently drawn a lot of attention from both investors and scholars. The Transformer framework, initially created for natural language processing, is used in this study to propose a revolutionary approach for forecasting the stock market indices of seven different economies: China, Canada, India, Japan, Russia, the United Kingdom, and the United States. The well-known Transformer architecture, which excels at capturing complex non-linear patterns, is modified to study the unique dynamics of each nation's stock market. The model successfully determines the basic principles driving market behavior by using an encoder-decoder structure and a multi-head attention mechanism. The aforementioned indices are used in back-testing trials, which cover a variety of economic environments. The outcomes demonstrate that the Transformer performs better than conventional techniques, with Mean Squared Error (MSE) acting as a crucial evaluation criterion. Notably, the model shows promise for investors in these widely separated markets to receive excess profits. This study offers a thorough analysis of stock market forecasting, expanding its relevance to a wider global context. comprehension of how this strategy might adjust to various financial ecosystems is improved by the addition of seven unique economies. Future research may go more deeply into applications that are industry-specific and investigate potential extensions to additional international markets. © 2024 IEEE.

关键词： Deep Learning Encoder-Decoder Stock Prediction Transformer

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：