检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Yang, Nijing Peng, Hong Wang, Jun Lu, Xiang Wang, Xiangxiang Yu, Yongbin School of Computer and Software Engineering Xihua University Chengdu610039 China School of Electrical Engineering and Electronic Information Xihua University Chengdu610039 China Ascend Computing Product Department Huawei Technologies Co Ltd Chengdu610041 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

This paper investigates the exponential state estimation of discrete-time memristive spiking neural P system (MSNPS). The spiking neural P system (SNPS) offers algorithmic support for neural morphology computation and AI chips, boasting advantages such as high performance and efficiency. As a new type of information device, memristors have efficient computing characteristics that integrate memory and computation, and can serve as synapses in SNPS. Hence, to harness the advantages of SNPS and memristors synergistically, this paper presents a pioneering MSNPS circuit model, in which memristors are used to replace resistors in SNPS. Meanwhile, MSNPS mathematical model is constructed based on circuit model. To be more practical, the time delays are analyzed in the system. Then, because of the discreteness of SNPS, the continuous MSNPS is discretized. Moreover, some sufficient conditions for exponential state estimation are established by utilizing Lyapunov functional to MSNPS. Finally, a numerical simulation example is constructed to validate the main findings. © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Empowering Precision Machine: Deep Learning Technique for Lung Cancer Diagnosis

Empowering Precision Machine: Deep Learning Technique for Lu...

引用

computing and Data Analytics (ICCDA), International Conference on

作者： Danish Jamil Syed Mehr Ali Shah Muhammad Numan Ali Khan Fatma Mahfoodh Mohammed AlJarwani Galician Studies and Development Institute (IDEGA) University of Santiago de Compostela Spain Department of Software Engineering Sir Syed University of Engineering & Technology College of Computing & Information Sciences University of Technology and Applied Sciences Musandam Sultanat of Oman

ISBN: (数字)9798331542573

ISBN: (纸本)9798331542580

This research paper delves into the realm of lung cancer diagnosis, a critical area in modern healthcare owing to its substantial global impact. Leveraging cutting-edge technology and machine learning methodologies, specifically employing the VGG16 model, our study aims to enhance the early detection of lung cancer through the analysis of CT scan images. The dataset utilized comprises CT scan images sourced from the Lung Image Database Consortium (LIDC/IDRI) Image Dataset, categorized into three classes: malignant, benign, and normal. By harnessing the capabilities of the VGG16 model, we seek to accurately predict the classification of CT scan images into these distinct categories. Through rigorous experimentation and analysis, our findings shed light on the efficacy of this approach in aiding medical professionals in the timely identification and classification of lung cancer cases. Ultimately, our research contributes to advancing the field of medical imaging and underscores the potential of deep learning in revolutionizing healthcare diagnostics.

关键词： Deep learning Technological innovation Computed tomography Computational modeling Precision medicine Lungs Lung cancer Medical services Data models Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Multiple Classifier Aggregation

SSRN

引用

SSRN 2024年

作者： Zheng, Shaifeng Zhu, Qingling Lin, Qiuzhen Liu, Songbai Wong, Ka-Chun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science City University of Hong Kong Hong Kong

Personalized federated learning (PFL) has garnered attention due to its capability to address statistical heterogeneity among clients. Typically, prevailing PFL methods aggregate a single global model for personalization, which may be inadequate for clients with diverse data distributions. Furthermore, in the local update, each private dataset is used to optimize the model independently, which increases the risk of overfitting the current data distribution and losing previously acquired knowledge, resulting in knowledge forgetting. In this study, personalized federated learning with multiple classifier aggregation is proposed. The method involves splitting the client model into its head and base, then optimizing them respectively using an alternating optimization strategy that first optimizes the head and then the base. Initially, to address the suboptimal model problem, the proposed approach aggregates multiple classifiers using data distribution and employs knowledge distillation to impart positive and negative classifier knowledge for learning the most suitable personalized model head. Additionally, to mitigate knowledge forgetting, a learnable personalization layer is introduced, and hidden loss is utilized to learn the knowledge of the global base and prevent overfitting of the model base. Empirical results demonstrate that the proposed method achieves competitive performance across various benchmarks, outperforming the majority of state-of-the-art PFL algorithms. The source code is publicly available at \href{https://***/xiaye-maker/FedMCA}{https://***/xiaye-maker/FedMCA} © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

How Does Forecasting Affect the Convergence of DRL Techniques in O-RAN Slicing?

How Does Forecasting Affect the Convergence of DRL Technique...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Ahmad M. Nagib Hatem Abou-zeid Hossam S. Hassanein School of Computing Queen's University Canada Faculty of Computers and Artificial Intelligence Cairo University Egypt Department of Electrical and Software Engineering University of Calgary Canada

The success of immersive applications such as virtual reality (VR) gaming and metaverse services depends on low latency and reliable connectivity. To provide seamless user experiences, the open radio access network (O-RAN) architecture and 6G networks are expected to play a crucial role. RAN slicing, a critical component of the O-RAN paradigm, enables network resources to be allocated based on the needs of immersive services, creating multiple virtual networks on a single physical infrastructure. In the O-RAN literature, deep reinforcement learning (DRL) algorithms are commonly used to optimize resource allocation. However, the practical adoption of DRL in live deployments has been sluggish. This is primarily due to the slow convergence and performance instabilities suffered by the DRL agents both upon initial deployment and when there are significant changes in network conditions. In this paper, we investigate the impact of time series forecasting of traffic demands on the convergence of the DRL-based slicing agents. For that, we conduct an exhaustive experiment that supports multiple services including real VR gaming traffic. We then propose a novel forecasting-aided DRL approach and its respective O-RAN practical deployment workflow to enhance DRL convergence. Our approach shows up to 22.8%, 86.3%, and 300% improvements in the average initial reward value, convergence rate, and number of converged scenarios respectively, enhancing the generalizability of the DRL agents compared with the implemented baselines. The results also indicate that our approach is robust against forecasting errors and that forecasting models do not have to be ideal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSC- l0 : Sparse Subspace Clustering with the l0 Inequality Constraint 7th

SSC- l0 : Sparse Subspace Clustering with the l0 Inequality...

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Wang, Yangbo Zhou, Jie Lin, Qingshui Lu, Jianglin Gao, Can National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Basic Teaching Department Liaoning Technical University Huludao125105 China College of Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9783031476648

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using all points to represent a fixed sample in a class under the self-expression framework may not be ideal, as points from other classes participate in the representing process. To alleviate this issue, this study attempts to achieve representation learning between points only coming from the same class. In practice, it is easier for data points from the same class to represent each other than that from different classes. So, when reconstructing a point, if the number of non-zero elements in the coefficient vector is limited, a model is more likely to select data points from the class where the reconstructed point lies to complete the reconstruction work. Based on this idea, we propose Sparse Subspace Clustering with the l0 inequality constraint (SSC- l0 ). In SSC- l0, the l0 inequality constraint determines the maximum number of non-zero elements in the coefficient vector, which helps SSC- l0 to conduct representation learning among the points in the same class. After introducing the simplex constraint to ensure the translation invariance of the model, an optimization method concerning l0 inequality constraint is formed to solve the proposed SSC- l0, and its convergence is theoretically analyzed. Extensive experiments on well-known datasets demonstrate the superiority of SSC- l0 compared to several state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques

arXiv

引用

arXiv 2023年

作者： Su, Zihang Yu, Tianshi Lipovetzky, Nir Mohammadi, Alireza Oetomo, Denny Polyvyanyy, Artem Sardiña, Sebastian Tan, Ying van Beest, Nick School of Computing and Information Systems The University of Melbourne Australia Department of Mechanical Engineering The University of Melbourne Australia School of Computing Technologies RMIT University Australia Software Systems Group Data61 CSIRO Australia

A transhumeral prosthesis restores missing anatomical segments below the shoulder, including the hand. Active prostheses utilize real-valued, continuous sensor data to recognize patient target poses, or goals, and proactively move the artificial limb. Previous studies have examined how well the data collected in stationary poses, without considering the time steps, can help discriminate the goals. In this case study paper, we focus on using time series data from surface electromyography electrodes and kinematic sensors to sequentially recognize patients’ goals. Our approach involves transforming the data into discrete events and training an existing process mining-based goal recognition system. Results from data collected in a virtual reality setting with ten subjects demonstrate the effectiveness of our proposed goal recognition approach, which achieves significantly better precision and recall than the state-of-the-art machine learning techniques and is less confident when wrong, which is beneficial when approximating smoother movements of prostheses. © 2023, CC BY-NC-ND.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Instructors' Perspectives on Capstone Courses in computing Fields: A Mixed-Methods Study 2024

Instructors' Perspectives on Capstone Courses in Computing F...

引用

29th Working Group Reports on Innovation and Technology in Computer Science Education, ITiCSE WGR 2024

作者： Hooshangi, Sara Shakil, Asma Dasgupta, Subhasish Davis, Karen C.C. Farghally, Mohammed Fitzpatrick, KellyAnn Gutica, Mirela Hardt, Ryan Riddle, Steve Seyam, Mohammed Department of Computer Science Virginia Tech BlacksburgVA United States School of Computer Science University of Auckland Auckland New Zealand Info Systems and Tech Mgmt Dept George Washington University WashingtonDC United States Computer Science and Software Engineering Dept. Miami University OxfordOH United States School of Computing Instruction Georgia Institute of Technology AtlantaGA United States School of Computing & Academic Studies British Columbia Institute of Technology BurnabyBC Canada Computer & Information Science University of St. Thomas Saint PaulVA United States School of Computing Newcastle University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9798400712081

Team-based capstone courses are integral to many undergraduate and postgraduate degree programs in the computing field. They are designed to help students gain hands-on experience and practice professional skills such as communication, teamwork, and self-reflection as they transition into the real world. Prior research on capstone courses has focused primarily on the experiences of students. The perspectives of instructors who teach capstone courses have not been explored comprehensively. However, an instructor's experience, motivation, and expectancy can have a significant impact on the quality of a capstone course. In this working group, we used a mixed methods approach to understand the experiences of capstone instructors. Issues such as class size, industry partnerships, managing student conflicts, and factors influencing instructor motivation were examined using a quantitative survey and semi-structured interviews with capstone teaching staff from multiple institutions across different continents. Our findings show that there are more similarities than differences across various capstone course structures. Similarities include team size, team formation methodologies, duration of the capstone course, and project sourcing. Differences in capstone courses include class sizes and institutional support. Some instructors felt that capstone courses require more time and effort than regular lecture-based courses. These instructors cited that the additional time and effort is related to class size and liaising with external stakeholders, including industry partners. Some instructors felt that their contributions were not recognized enough by the leadership at their institutions. Others acknowledged institutional support and the value that the capstone brought to their department. Overall, we found that capstone instructors were highly intrinsically motivated and enjoyed teaching the capstone course. Most of them agree that the course contributes to their professional de

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Recursive Generation of Multi-Qubits Control Gate to Facilitate the Grover's Quantum Algorithm in Large Scale Database Search

Recursive Generation of Multi-Qubits Control Gate to Facilit...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Wen-Li Wang Shahid Hussain Nathaniel V. Rondinelli Mei-Huei Tang Saif Ur Rehman Khan Department of Computer Science and Software Engineering Penn State University Behrend Erie PA USA Department of Computer Information Science Gannon University Erie PA USA Department of Computing Shifa Tameer-e-Millat University Islamabad Pakistan

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Context: Grover's algorithm is a powerful tool in the realm of quantum computing because it offers exponential speedup over classical linear searching for unstructured / unsorted search problems. However, it is challenging to construct efficient and scalable circuits for a multi-input control gate in the algorithm, particularly with a huge number of qubit inputs. Problem: Traditional circuit construction methods often require manual composition for the multi-input gate from basic quantum gates, which can be time consuming and error prone, thus hindering practical implementation. Moreover, the number of simple gates in the composition grows exponentially with the addition of each qubit. Method: This research provides an approach to recursively generate the oracle using Toffoli gates as the fundamental units to enhance scalability and reusability while maintaining effectiveness. The methodology leverages IBM Qiskit and Quantum Lab to simulate quantum computation to prove the practicality and feasibility. Result: The findings from the experiments between recursively and non-recursively generated circuits suggest that our recursive approach can offer comparable accuracy and computational complexity compared to the non-recursive approach. However, it tends to require a larger number of basic quantum gates due to a lack of circuit optimization. Conclusion: The results showcase the applicability of utilizing recursion as a speedy and economical alternative to generate circuits when implementing the Grover's algorithm. It not only presents potential scalability benefits, but also creates an avenue for further research on test verification and performance improvement to the computing community when running in actual quantum hardware.

关键词： Quantum algorithm Scalability Circuits Qubit software algorithms software quality Logic gates Search problems software reliability Security

来源：评论

学校读者我要写书评

暂无评论

Business Process Remaining Time Prediction Based on Incremental Event Logs

引用

IEEE Transactions on Services computing 2025年第03期18卷 1308-1320页

作者： Guo, Na Liu, Cong Mo, Qi Cao, Jian Ouyang, Chun Lu, Xixi Zeng, Qingtian Shandong University of Technology School of Electrical and Electronic Engineering Zibo255000 China Nova University of Lisbon NOVA Information Management School Lisbon1070-312 Portugal Shandong University of Technology School of Computer Science and Technology Zibo255000 China Yunnan University School of Software Kunming650091 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200030 China Queensland University of Technology School of Information Systems BrisbaneQLD4000 Australia Utrecht University Department of Information and Computing Sciences CS Utrecht3584 Netherlands Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266590 China

Predictive Process Monitoring (PPM) aims to predict the future state of running process instances to enable timely interventions to mitigate potential risks. As one of the most fundamental tasks in PPM, process remaining time prediction focuses on preventing timeout occurrences. While various deep learning-based approaches have been developed for this purpose, they often rely on pre-established static prediction models and struggle to maintain accurate predictions when the process undergoes dynamic changes, such as an expanding sales channels. To tackle this challenge, this paper proposes an incremental process remaining time prediction framework by continuously updating the prediction model based on an incremental event log. Specifically, a feature selection strategy is first introduced to extract effective features from event logs. Leveraging effective features can significantly improve the prediction quality by capturing the changes in process information. Then, three incremental log-based updating mechanisms, including period-based updating, quantity-based updating, and concept-drift-based updating, along with a reconstruction strategy, are proposed to dynamically adjust the prediction model in response to business changes. Finally, LSTM, Transformer, and Auto-encoder models are adapted and integrated into the proposed framework. The approach has been implemented and publicly released. Experimental evaluation using nine real-life event logs demonstrate that the proposed framework and its three instantiations (i.e., LSTM-based, Transformer-based, and Auto-encoder-based ones) outperform state-of-the-art techniques in terms of prediction accuracy. © 2008-2012 IEEE.

关键词： Predictive Models Feature Extraction Business Adaptation Models Accuracy Long Short Term Memory Transformers Process Control Computational Modeling Process Monitoring Predictive Process Monitoring Remaining Time Prediction Process Mining Incremental Event Log Business Processes Event Log Prediction Model Prediction Accuracy Dynamic Changes Effects Of Characteristics Long Short Term Memory Static Model Prediction Framework Continuous Updating Incremental Process Reconstruction Scheme Neural Network Training Set Convolutional Neural Network Change Process Hidden Layer Combination Of Features Recurrent Neural Network Flow Control Neural Units Continuous Bag Of Words Mean Absolute Error Values Concept Drift Improve Prediction Accuracy Construction Of Prediction Model Dynamic Nature Of Processes Real Life Scenarios Prediction Task Incremental Learning

来源：评论

学校读者我要写书评

暂无评论

Tumor type classification and candidate cancer-specific biomarkers discovery via semi-supervised learning

引用

Biophysics Reports 2023年第2期9卷 57-66页

作者： Peng Chen Zhenlei Li Zhaolin Hong Haoran Zheng Rong Zeng School of Computer Science and Technology University of Science and Technology of China Anhui Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Department of Systems Biology University of Science and Technology of China CAS Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences School of Life Science and Technology ShanghaiTech University

Identifying cancer-related differentially expressed genes provides significant information for diagnosing tumors, predicting prognoses, and effective treatments. Recently, deep learning methods have been used to perform gene differential expression analysis using microarray-based high-throughput gene profiling and have achieved good results. In this study, we proposed a new robust multiple-datasetsbased semi-supervised learning model, MSSL, to perform tumor type classification and candidate cancer-specific biomarkers discovery across multiple tumor types and multiple datasets, which addressed the following long-lasting obstacles:(1) the data volume of the existing single dataset is not enough to fully exert the advantages of deep learning;(2) a large number of datasets from different research institutions cannot be effectively used due to inconsistent internal variances and low quality;(3) relatively uncommon cancers have limited effects on deep learning methods. In our article, we applied MSSL to The Cancer Genome Atlas(TCGA) and the Gene Expression Comprehensive Database(GEO) pan-cancer normalized-level3 RNA-seq data and got 97.6% final classification accuracy, which had a significant performance leap compared with previous approaches. Finally, we got the ranking of the importance of the corresponding genes for each cancer type based on classification results and validated that the top genes selected in this way were biologically meaningful for corresponding tumors and some of them had been used as biomarkers, which showed the efficacy of our method.

关键词： Deep learning Tumor type classification Cancer-specific biomarkers MSSL

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：