检索结果-内蒙古大学图书馆

An Unsupervised Writer Identification Based on Generating Clusterable Embeddings

computer Systems Science & engineering 2023年第8期46卷 2059-2073页

作者： M.F.Mridha Zabir Mohammad Muhammad Mohsin Kabir Aklima Akter Lima Sujoy Chandra Das Md Rashedul Islam Yutaka Watanobe Department of Computer Science and Engineering American International University BangladeshDhaka1229Bangladesh Department of Computer Science&Engineering Bangladesh University of Business&TechnologyDhaka1216Bangladesh Department of Computer Science and Engineering University of Asia PacificDhaka1216Bangladesh Department of Computer Science and Engineering University of AizuAizu-Wakamatsu965-8580Japan

The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification *** to its importance,numerous studies have been conducted in various *** have established several learning methods for writer identification including supervised and unsupervised ***,supervised methods require a large amount of annotation data,which is impossible in most *** the other hand,unsupervised writer identification methods may be limited and dependent on feature extraction that cannot provide the proper objectives to the architecture and be *** paper introduces an unsupervised writer identification system that analyzes the data and recognizes the writer based on the inter-feature relations of the data to resolve the uncertainty of the features.A pairwise architecturebased Autoembedder was applied to generate clusterable embeddings for handwritten text ***,the trained baseline architecture generates the embedding of the data image,and the K-means algorithm is used to distinguish the embedding of individual *** proposed model utilized the IAM dataset for the experiment as it is inconsistent with contributions from the authors but is easily accessible for writer identification *** addition,traditional evaluation metrics are used in the proposed ***,the proposed model is compared with a few unsupervised models,and it outperformed the state-of-the-art deep convolutional architectures in recognizing writers based on unlabeled data.

关键词： Writer identification pairwise architecture clusterable embeddings convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Complex preference analysis: a score-based evaluation strategy for ranking and comparison of the evolutionary algorithms

引用

Soft Computing 2025年第4期29卷 1967-1980页

作者： Sarkar, Debojyoti Biswas, Anupam Department of Computer Science and Engineering National Institute of Technology Silchar Assam Silchar788010 India

In this paper, an evaluation strategy is proposed for evaluation of optimization algorithms, called the Complex Preference Analysis, that assesses the efficiency of different evolutionary algorithms by considering multiple performance metrics concurrently across diverse dimensions and generating a single score for ranking. The proposed strategy allows for a thorough evaluation by assigning distinct priorities in the form of weights, to various performance parameters. The algorithm’s performances on each performance parameter are captured and the best and worst performances in each performance category are identified. The deviation of each algorithm from the best and worst performances in the respective performance category is formulated to generate a single score for each of the algorithms for comparison. The flexibility to adjust weights provides a valuable tool for customizing evaluations according to individual needs and preferences. The proposed evaluation strategy is studied by running evaluations on nine evolutionary algorithms based on their performance over five performance indicators on six datasets of the Travelling Salesman Problem. Conducting Complex Preference Analysis on the different evolutionary algorithms reveals distinctive patterns in their performance, with some algorithms such as Simulated Annealing, Tabu Search, Bat Algorithm, Genetic Algorithm, etc. consistently demonstrating superior results across multiple Travelling Salesman Problem instances, while other algorithms such as Ant Colony Optimization, Teaching Learning Based Optimization, etc. rank lower. The algorithms’ performances on individual performance parameters, when reflected on the final rank of the algorithms, generated based on the collective impact of all the parameters, elucidate the efficiency of the proposed evaluation strategy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing XGBoost for Enhanced Electrical Theft Detection: A Fusion of Particle Swarm and Jaya Optimization Techniques 4

Optimizing XGBoost for Enhanced Electrical Theft Detection: ...

引用

4th IEEE International Conference on Sustainable Energy and Future Electric Transportation, SEFET 2024

作者： Prusty, Sashikanta Nayak, Debasish Swapnesh Kumar Moharana, Meena Prusty, Sushree Gayatri Priyadarsini Sahoo, Manmohan Rautaray, Jyotirmayee Department of Computer Science & Engineering Bhubaneswar India Centurion University of Technology & Management Department of Computer Science & Engineering Bhubaneswar India Department of Computer Science & Engineering Bhubaneswar India Odisha University of Technology & Research Department of Computer Science & Engineering Bhubaneswar India

ISBN: (纸本)9798350383997

The most serious and hazardous for an electrical provider these days are non-technical losses caused due to electricity theft. The economy as a whole is impacted by fraudulent electricity usage, which lowers supply quality, raises generator load, and drives up costs for legal customers. To avoid these issues, this work proposes a smart electrical theft detection system using the XGBoost model combined with two optimization techniques Particle Swarm Optimization (PSO) and Jaya Optimization (JO). Furthermore, to handle the missing instances in the State Grid Corporation of China (SGCC) imbalanced dataset, we implemented a novel LORAS (Local Outlier-Robust Adaptive Synthetic) technique that balances the target class by making fake data points near the edges of different classes. Finally, the results show that the optimized XGBoost-PSO technique significantly classifies into two distinct categories (i.e. theft as '1' or no theft as '0') with having higher F1 Score (PSO Optimized): 0.9552 and AUC (PSO Optimized): 0.9667. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

VirtualHAR: Virtual Sensing Device and Correlation-Based Learning Approach for Multi-Wearable Sensing Device-Based Human Activity Recognition

引用

IEEE Internet of Things Journal 2025年第13期12卷 23577-23597页

作者： Ahmad, Nafees Leung, Ho-Fung Farnia, Farzan The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Hong Kong

Human activity recognition (HAR) is a prominent research direction in ubiquitous computing. Current state-of-the-art HAR models achieve great success by learning the correlations between the regions of the body parts by using the attached sensing devices for feature extraction. However, explicitly computing the correlations between whole body parts and whole sub-body parts, which is crucial for extracting discriminatory features for some activities, has not been investigated due to lack of sensing devices that capture the movements of the whole (sub-)body parts. This study proposes an effective yet lightweight VirtualHAR framework, which automatically models correlations between the whole body parts, whole sub-body parts, and regions based on the concept of virtual sensing devices. The VirtualHAR framework mainly encompasses three modules. The Backbone Feature Extraction module extracts the features from a physical sensing device, based on which the Multi-purpose Correlations Learning module constructs virtual sensing devices for body parts and sub-body parts and then exploits the explicit correlations between body parts, sub-body parts as well as in regions by using their attached physical sensing devices. Finally, the Global Aggregation module learns the global aggregation representation for each physical sensing device by collecting the learned correlated representation from each virtual sensing device and physical sensing device. Comprehensive experiments on benchmark HAR datasets and a resource-constrained device confirm that VirtualHAR outperforms SOTA models in recognition performance and computational complexity. Through thorough quantitative and qualitative analysis, we validate the proposed VirtualHAR framework’s effectiveness and efficiency. © 2014 IEEE.

关键词： Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

Energy efficient waste collection vehicle routing system using time series prediction

引用

Multimedia Tools and Applications 2025年第9期84卷 6157-6186页

作者： Kapadia, Neha Mehta, Rupa Computer Engineering Department Sardar Vallabhbhai National Institute of Technology University in Surat Gujarat India IT Department Thakur College of Engineering and Technology Mumbai India

The focus of this research is on addressing the inefficient management of Municipal Solid Waste (MSW), which often results in large quantities of waste being dumped into garbage bins. Previous approaches have struggled to effectively manage MSW promptly. To improve this process, we propose a time-series-based, energy-efficient waste prediction model. Initially, we convert the Bins Historical Time Series Dataset into a Comma-Separated Values (CSV) file format. The model, named Exponential Auto-Regressive Integrated Moving Average-Nesterov-accelerated Adaptive Moment estimation-Long-Short Term Memory (EARIMA-LSTM) using NADAM optimizer, is trained and tested using numeralized features extracted from the dataset. Smart bins equipped with Internet of Things (IoT) technology are then deployed to predict waste levels using the EARIMA-NADAM-LSTM model. After waste level detection, we employ the Scramble Mutation Coral Reefs Optimization-Haversine distance-based K-Means (SMCRO-HK-Means) clustering technique to group the bins. Next, we establish multiple paths between bins nearing capacity using the Ad-hoc On-Demand Distance Vector (AODV) protocol. Finally, the Optimal Path (OP) is determined using the modified A* algorithm based on multi-weight heuristics (Op A*). This approach effectively manages waste collection by preventing bin overflow. Our model achieves good accuracy for waste prediction model with a Mean Absolute Error (MAE) of 0.138%, and 42,518 ms for clustering 500 waste bins, outperforming existing methods. Also, it finds the dynamic optimal route for waste collection with optimal cost. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

LARSI-TPE-XGB: Short-Term Load Forecasting by Load-Adaptive Relative Strength Index and Fusion of Tree-Structured Parzen Estimator and XGBoost

引用

IEEE Transactions on Power Delivery 2025年第3期40卷 1318-1330页

作者： Liu, Jin-Xian Leu, Jenq-Shiou National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106216 Taiwan

Power load forecasting is essential for optimizing power generation and distribution efficiency. This paper proposes a novel method for daily average load forecasting, referred to as LARSI-TPE-XGB, which integrates the Load-Adaptive Relative Strength Index (LARSI) with the Tree-structured Parzen Estimator (TPE) and eXtreme Gradient Boosting (XGBoost). Our method significantly improves the accuracy and generalization ability of short-term load forecasting (STLF) by addressing limitations in feature extraction and hyperparameter optimization. The proposed LARSI enhances the forecasting model by adapting an improved Relative Strength Index (RSI) for power load prediction, while TPE optimizes the model's hyperparameters to dynamically adjust to time-series updates, thus mitigating the issue of XGBoost's sensitivity to hyperparameters in high-dimensional scenarios. Experimental results on real-world power load datasets demonstrate that LARSI-TPE-XGB reduces errors by 18.58% and 30.73% in root mean squared error (RMSE) across two different datasets compared to models without LARSI-TPE-XGB and outperforms state-of-the-art models, as confirmed by the Diebold-Mariano (DM) test. Our method consistently improves performance across various datasets, while we further investigate the influence of LARSI and other factors, such as weather conditions, on forecasting accuracy. © 1986-2012 IEEE.

关键词： Electric load forecasting

来源：评论

学校读者我要写书评

暂无评论

Cost minimization approach with hybrid optimization based task scheduling in Geo-distributed cloud

引用

Australian Journal of Electrical and Electronics engineering 2025年第2期22卷 169-181页

作者： Vasantham, Vijay Kumar Donavalli, Haritha Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur India

To manage the huge data, cloud computing necessitates a significant number of disc I/O, network bandwidth and CPU cycles. To handle the massive volumes of data, the programming paradigm known as data flow integrates the tasks to a graph structure. Task scheduling is one of the main areas of current study that primarily aims to allocate the tasks to resources. It is essential to organise the tasks in a way which saves time and makes the most use of available resources. In recent years, scholars have offered different job scheduling techniques. This work intends to introduce a novel cost minimisation for big data processing with respect to task allocation or scheduling. Initially, the big data is processed under Map Reduce framework. This allocation processes is taken as the optimisation issue, which is solved under the consideration of minimisation factors like execution cost, makespan, communication cost, and energy consumption and risk. For solving this issue, a new hybrid optimisation algorithm known as Hybrid bald eagle and Archimedes Optimisation algorithm (HBE-ArCA) is developed. The betterment of HBE-ArCA is proven regarding cost, makespan and so on. ©, Engineers Australia.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Fundamental Limits to Exploiting Side Information for CSI Feedback in Wireless Systems

引用

IEEE Journal on Selected Areas in Communications 2025年第7期43卷 2417-2430页

作者： Kim, Heasung De Veciana, Gustavo Kim, Hyeji University of Texas at Austin Department of Electrical and Computer Engineering AustinTX78712 United States

In modern wireless systems, the feedback of DownLink (DL) Channel State Information (CSI) from User Equipment (UE) to Base Stations (BS) may require substantial computational and feedback bandwidth overheads. A promising approach to improve feedback efficiency is to leverage side information which is correlated to DL CSI. Despite potential of doing so, critical aspects remain underexplored in current research, particularly the quantification of the benefits and the inherent limitations of utilizing side information. This paper addresses these gaps by introducing a novel algorithm to compute the rate-distortion function for general compression scenarios incorporating side information. We apply this algorithm to the DL CSI feedback problem having UL CSI as the side information and generate rate-distortion functions. Using the estimated rate-distortion functions, we measure the gain of side information over diverse feedback rates and UE mobility profiles. The results reveal that the benefits of leveraging side information are particularly significant for UEs characterized by high mobility and constrained to operate at low feedback overheads. © 1983-2012 IEEE.

关键词： Signal distortion

来源：评论

学校读者我要写书评

暂无评论

A Modified Marine Predators Algorithm for Numerical Function Optimization 9

A Modified Marine Predators Algorithm for Numerical Function...

引用

9th International Conference on computer Science and engineering, UBMK 2024

作者： Özdemir, Resul Taşyürek, Murat Aslantaş, Veysel Erciyes University Department of Computer Engineering Kayseri Turkey Kayseri University Department of Computer Engineering Kayseri Turkey

ISBN: (纸本)9798350365887

The Marine Predators Algorithm (MPA) is an effective optimization technique that simulates the foraging behavior of ocean creatures. Despite its strong performance on numerical optimization problems, the MPA algorithm requires enhancement in its exploitation and exploration mechanisms. This paper introduces a modified MP A algorithm designed to improve the exploration capability. A novel search mechanism, which fulfils the exploration process depending on the Fish Aggregating Devices (FADs) mechanism of the algorithm, is proposed. The modified MP A a lgorithm is evaluated on the CEC 2017 numerical optimization test suite. The results indicate that the proposed MPA algorithm surpasses the original MPA algorithm in terms of solution quality and convergence speed. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploration of alzheimer disease using design of experiments

引用

Multimedia Tools and Applications 2025年第3期84卷 1079-1101页

作者： Gupta, Pranav Pandey, Kavita Gupta, Sanskar Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

This study examines the use of experimental designs, specifically full and fractional factorial designs, for predicting Alzheimer’s disease with fewer variables. The full factorial design systematically investigates the effects of selected factors, providing a comprehensive analysis of their individual and interactive impacts on Alzheimer’s prediction. On the other hand, the fractional factorial design simplifies the model by selecting key factors and removing non-significant ones. For Alzheimer’s, among all the factors examined, the MMSE (Mini-mental state Examination) score emerged as the most significant, which was further cross-validated using Minitab Software Analysis. Importantly, the findings suggest that the fractional factorial design is a better alternative, particularly when time and cost constraints are present. The results highlight the effectiveness and efficiency of these experimental designs, demonstrating their potential for early detection, prevention, and treatment of Alzheimer’s disease. By contributing to the expanding knowledge base on experimental designs in medical research, this study emphasizes their crucial role in understanding and combating complex diseases like Alzheimer’s. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Design of experiments

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：