检索结果-内蒙古大学图书馆

Accelerating Mobile Edge Generation (MEG) by Constrained Learning

IEEE Transactions on Cognitive Communications and Networking 2025年第3期11卷 1854-1869页

作者： Xu, Xiaoxia Liu, Yuanwei Mu, Xidong Xing, Hong Nallanathan, Arumugam Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong School of Electronics Electrical Engineering and Computer Science BelfastBT3 9DT United Kingdom The Hong Kong University of Science and Technology IoT Thrust Guangzhou Guangzhou511453 China Hong Kong University of Science and Technology Department of ECE Hong Kong Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of

A novel mobile edge generation (MEG) framework is proposed for low-latency image generation on mobile devices. Exploiting a latent diffusion model (LDM) distributed across the edge server (ES) and the user equipment (UE), only low-dimension features need to be transmitted for creating artificial intelligence generative content (AIGC). Two novel modules, namely dynamic diffusion and feature merging, are conceived to compress the diffusion model and transmitted features, respectively. By jointly optimizing compression rates of denoising steps and feature merging, the image quality maximization problem is formulated subject to latency and energy consumption constraints. To address this problem in dynamic channel conditions, a low-complexity compression protocol is developed. First, a backbone LDM architecture is learned by offline distillation to support various compression options. Then, compression rates are predicted in online environment specific to channel and task features. To solve the resultant constrained Markov Decision Process (MDP), a constrained variational policy optimization (CVPO) based MEG algorithm, MEG-CVPO, is further developed to learn constraint-guaranteed optimization. Numerical results demonstrate that: 1) The proposed framework improves image distortions while reducing over 40% latency compared to conventional generation schemes. 2) MEG-CVPO stringently guarantee constraints and realizes a flexible trade-off between generation qualities and overheads. © 2015 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo modelling of Raman signal enhancement using power-efficient Apple processors 15

Monte Carlo modelling of Raman signal enhancement using powe...

引用

Biomedical Light Scattering XV 2025

作者： Vladyko, Ilya Yakovlev, Vladislav Doronin, Alexander School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand Department of Biomedical Engineering Department of Electrical and Computer Engineering Department of Physics and Astronomy Institute for Quantum Science and Engineering Texas A&M University College StationTX77843 United States

ISBN: (纸本)9781510683884

Modern optical technologies encompass classical light phenomena and non-linear effects, crucial for biomedical imaging and therapies. Despite substantial interest and many experimental studies, non-linear optical effects in inhomogeneous scattering media require extensive computer modeling to understand light-material interactions. This report focuses on Monte Carlo simulations of Raman scattering in turbid media, such as biological tissues, essential for clinical applications. We developed a novel, open-source, power-efficient Monte Carlo algorithm optimized for Apple s M-series chips. By incorporating single-photon tracking, the algorithm accurately models time-resolved light-Tissue interactions. Validated against experiments, it matches traditional methods accuracy while offering superior efficiency, advancing Raman functional imaging. © 2025 SPIE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

IRS-Assisted Hybrid Spatial Modulation for Full-Duplex MIMO Communications 18

IRS-Assisted Hybrid Spatial Modulation for Full-Duplex MIMO ...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Sanila, Kunnathully Sadanandan Rajamohan, Neelakandan Luleå University of Technology Department of Computer Science Electrical and Space Engineering Sweden Indian Institute of Technology School of Electrical Sciences Goa India

ISBN: (纸本)9798350391725

In this paper, we propose an intelligent reflecting surface (IRS)-assisted hybrid transmit-receive spatial modulation (HSM) for full-duplex (FD) multi-input multi-output communication, referred to as FD-IRS-HSM. In the proposed FD-IRS-HSM, the FD communication between two users is accomplished with a dedicated IRS for each user. In addition to the conventional data transfer, transmit and receive spatial modulations are simultaneously employed in the transmission by tuning the reflecting elements in the IRS. Further, we characterize the self-interference power, present the theoretical analysis for ergodic capacity and outage probability for the proposed system, and substantiate it with simulation results. We also compare the proposed FD-IRSHSM with closely related works in the literature and demonstrate the outperformance of our proposed system in terms of higher transmission rate and greater flexibility. © 2024 IEEE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Framework for Churn Prediction using Stratifed Bagging and Stacked Multi-Output Random Forests 3

An Enhanced Framework for Churn Prediction using Stratifed B...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Bhardwaj, Anay Radha, D. Kirthika Devi, V.S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Customer churn prediction is an important task in customer relationship management because it helps businesses know who is at risk of leaving and retain such at-risk *** and time-efficient churn prediction is essential to identify the factors driving churn, enabling businesses to implement timely and effective retention strategies.A framework is proposed which combines stratified bagging with multi-output Random Forest and stacked feature transformation, to enhance prediction accuracy. This approach balances the dataset, trains a custom Random Forest using stratified bagging, and applies stacked learning using Logistic Regression on transformed features. Tested on real-world data, the model demonstrated 99% accuracy, showing improvements over the classic Random Forest in precision, recall, and prediction time. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Ultimately Bounded Output Feedback Control for Networked Nonlinear Systems With Unreliable Communication Channel: A Buffer-Aided Strategy

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1566-1578页

作者： Yuhan Zhang Zidong Wang Lei Zou Yun Chen Guoping Lu the College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China IEEE the Department of Computer Science Brunel UniversityUB83PHUnited Kingdom the College of Information Science and Technology Donghua UniversityShanghai 201620 the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of EducationShanghai 201620China the School of Automation Hangzhou Dianzi UniversityHangzhou 310018China the School of Electrical Engineering Nantong UniversityNantong 226019China

This paper concerns ultimately bounded output-feedback control problems for networked systems with unknown nonlinear dynamics. Sensor-to-observer signal transmission is facilitated over networks that has communication *** transmissions are carried out over an unreliable communication channel. In order to enhance the utilization rate of measurement data, a buffer-aided strategy is novelly employed to store historical measurements when communication networks are inaccessible. Using the neural network technique, a novel observer-based controller is introduced to address effects of signal transmission behaviors and unknown nonlinear *** the application of stochastic analysis and Lyapunov stability, a joint framework is constructed for analyzing resultant system performance under the introduced controller. Subsequently, existence conditions for the desired output-feedback controller are delineated. The required parameters for the observerbased controller are then determined by resolving some specific matrix inequalities. Finally, a simulation example is showcased to confirm method efficacy.

关键词： Buffer-aided strategy neural networks nonlinear control output-feedback control unreliable communication channel

来源：评论

学校读者我要写书评

暂无评论

Design Method for Q-Enhanced Reconfigurable Bandpass Filters With High Selectivity, Large Bandwidth Variable Range, and Large Dynamic Range

引用

IEEE Transactions on Microwave Theory and Techniques 2024年第11期72卷 6387-6400页

作者： Chen, Ziyuan Li, Kun Liu, Yuanan Chi, Pei-Ling Yang, Tao University of Electronic Science and Technology of China School of Electronic Science and Engineering Sichuan Chengdu610054 China Beijing University of Posts and Telecommunications School of Electronic Engineering Beijing100876 China National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu300 Taiwan

A design method of generating multiple transmission zeros (TZs) is proposed by introducing feeding-forward transconductance amplifiers for the cascaded Q-enhanced reconfigurable bandpass filters (BPFs) in this article. With the proposed method, it can generate two TZs at the upper and lower stopbands for every two Q-enhancement resonant units, significantly improving the stopband suppression. Furthermore, by controlling the feeding-forward amplifiers, the position of the zero and the depth of the TZs can be flexibly controlled. Meanwhile, to improve the power consumption, linearity, and noise figure (NF), the guideline of distribution of the transmission poles (TPs) generated by the Q-enhancement units is discussed in detail. To demonstrate the proposed method, a reconfigurable on-chip Q-enhanced BPF was designed and measured based on a 55-nm CMOS process with a core area of 1.36× 0.62mm. Multiple TZs were clearly observed in the filter and achieved a stopband suppression of more than 50 dBc up to 15 GHz. The bandwidth of the proposed filter can be tuned with a range covering from 0.2 to 1 GHz at a center frequency of 1.8 GHz, while the center frequency can be tuned from 1.68 to 1.94 GHz with a constant bandwidth of 600 MHz. The input 1-dB compression point (IP1dB) is better than -1 dBm for all tuning states, and the NF varies from 12.7 to 20.3 dB. The dynamic range (DR) can reach more than 165 dB and the total power consumption is less than 180 mW. © 2024 IEEE.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Predicting Customer Lifetime Value in E-commerce: A Data-Driven Approach to Enhance Customer Retention Strategies 3

Predicting Customer Lifetime Value in E-commerce: A Data-Dri...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dey, Sonali Radha, D. Kirthika Devi, V.S. Department of Computer Science Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Predicting Customer Lifetime Value (CLV) is one of the most critical tasks that businesses undertake in order to improve customer retention and optimize marketing strategies. The present paper proposes a predictive model for CLV using several machine learning techniques. The features considered include customer demographics, purchasing behavior, and transaction history. All these features were preprocessed using feature engineering and missing value handling. Several regression models, including Linear Regression, Decision Tree, and Random Forest Regressor, were compared in terms of predictive performance. The study includes the decision trees,hash tables as advance data structures such that they can handle large datasets effectively. Of the ones tested, Random Forest Regressor proved to be superior to the others, having the lowest Mean Squared Error (MSE) and highest R2 score, thereby validating its robustness in identifying the complex patterns within the data. The work highlights the time and space complexities of different models. This study contributes to the application of machine learning in customer analytics and provides a foundation for future research to integrate more diverse data sources and enhance model performance through hyperparameter optimization. Future work will also explore real-time prediction capabilities and the integration of multimodal data to further refine CLV forecasting. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Exploring the Predictive Capabilities of AlphaFold Using Adversarial Protein Sequences

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3384-3392页

作者： Alkhouri, Ismail R. Jha, Sumit Beckus, Andre Atia, George Jha, Susmit Ewetz, Rickard Velasquez, Alvaro OrlandoFL32816 United States Michigan State University Computational Mathematics Science and Engineering Department East LansingMI48824 United States University of Michigan Electrical Engineering and Computer Science Department Ann ArborMI48109 United States Florida International University Knights Foundation School of Computing and Information Sciences MiamiFL33199 United States Air Force Research Laboratory Rome Information Directorate NY13441 United States Department Computer Science Department OrlandoFL32816 United States SRI International Computer Science Laboratory Menlo ParkCA94025 United States Electrical and Computer Engineering Department OrlandoFL32816 United States University of Colorado Computer Science Department BoulderCO80309 United States

Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been fully explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations to noncritical residues of a protein sequence do not typically lead to drastic changes in the protein structure. Our study demonstrates that, similar to adversarial methods in machine learning, small changes to protein sequences can result in significant differences in the predicted protein structures using AlphaFold as determined by large distance measures. Despite this, our findings using multiple protein sequences suggest that AlphaFold is able to accurately predict the domain structure and folding regions of a protein. To gauge structural differences, we employ two alignment-based measures [root-mean-square deviation (RMSD) and the global distance test (GDT) similarity], and one alignment-free measure, which is an effective graph-based structure representation (GraSR) method. We prove that the problem of minimally perturbing protein sequences is NP-complete. Based on the well-established block substitution matrices (BLOSUM62) sequence alignment scoring matrix, we generate adversarial sequences. In our experimental evaluation, we consider 111 proteins (including 29 COVID-19 sequences) in the Universal Protein resource (UniProt), a central resource for protein data. Our findings suggest that, despite the high RMSD values returned by AlphaFold, it is capable of handling the BLOSUM adversarial sequences considered in our analysis, as evidenced by the preservation of the folded regions and the GraSR results. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Edge-Aided Eigenvalue Decomposition in Internet of Things

引用

IEEE Internet of Things Journal 2025年第12期12卷 19901-19914页

作者： Zhao, Xiaotong Zhang, Hanlin Lin, Jie Liang, Fan Kong, Fanyu Xu, Hansong Hua, Kun Qingdao University College of Computer Science and Technology Qingdao266071 China Xian Jiaotong University School of Electronic and Information Engineering Xian710049 China Sam Houston State University Department of Computer Science HuntsvilleTX77340 United States Shandong University School of Software Jinan250101 China Shanghai Jiao Tong University School of Cyber Science and Engineering Shanghai200240 China California Polytechnic State University Department of Electrical Engineering San Luis ObispoCA93407 United States

Eigenvalue decomposition (EVD) is a fundamental yet time-consuming operation with extensive applications in IoT. When the matrix dimension reaches millions, resource-limited IoT devices struggle to perform such computationally expensive operations. Edge computing, with its plentiful computing resources, offers an effective solution to this problem. However, privacy concerns arise because outsourced tasks may contain sensitive user data. In this paper, we propose the first privacy-preserving, edge-assisted EVD outsourcing scheme that securely enables users to outsource EVD tasks to edge servers. We design a privacy-preserving matrix transformation method to encode the original data, ensuring that edge servers cannot access users' private information. Additionally, we design a verification scheme that enables the user to verify the correctness of the results returned by the edge servers. Our protocol supports parallel computation by multiple edge servers, thus enhancing the efficiency of EVD. The feasibility of our proposed scheme is demonstrated through both theoretical and experimental perspectives. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Models for electrical Fault Detection and Classification in Transmission Lines 3

Advanced Machine Learning Models for Electrical Fault Detect...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Deepika, Dugganapalli Charan, Maridinapalli Madhu Nossam, Sri Chakradhar Manitha, P.V. Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

With the fast development of power systems, efficient methods for fault detection and classification are needed to maintain the stability, safety and efficiency of the systems. In particular, this paper investigates advanced machine learning techniques for fault detection and classification in transmission lines using supervised learning algorithms, including Support Vector Machines (SVM), Decision Trees, Random Forests, Naïve Bayes and Linear Discriminant Analysis (LDA). A dataset consisting of three phase currents and voltages from MATLAB simulations of normal and faulty system operations are used to study the problem. These models classify faults to be single line to ground, line to line and the three phase faults. Performance evaluation is done by metrics such as accuracy, precision, recall, F1 score, and AUC with respect to ROC analysis. Decision Trees are of high reliability and have good computational efficiency for fault detection among the models. The results presented in this research point to the importance of machine learning in reducing fault diagnosis circuit in order to achieve a more intelligent and resilient power transmission systems. © 2025 IEEE.

关键词： Power transmission lines

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：