检索结果-内蒙古大学图书馆

ToSiM-IoT: Towards a Sustainable Optimisation of Machine Learning Tasks in Internet of Things

IEEE Internet of Things Journal 2025年

作者： Kaushal, Ashish Almurshed, Osama Muftah, Asmail Auluck, Nitin Rana, Omer Indian Institute of Technology Department of Computer Science and Engineering Ropar India Cardiff University School of Computer Science and Informatics United Kingdom Azzaytuna University Libya

With the rise of digital infrastructure and Internet of Things (IoT), a substantial amount of data is continuously generated that needs to be processed efficiently. While modern artificial intelligence (AI) approaches have shown good capabilities in handling large volumes of data, their excessive demands for memory and processing power result in very high utilisation of resources. In this work, we propose ToSiM-IoT, an optimisation framework that introduces a layer selection approach to identify an ideal mix of active, and inactive layers, using a genetic algorithm for model training. Next, we design a pruning mechanism that identifies performance-critical features using heatmap visualisation, during model inference, and eliminates the remaining features. Two machine learning (ML) models - InceptionV3 and VGG16, have been evaluated on an agricultural weed detection scenario, using the DeepWeeds image classification dataset. Experimental results demonstrate that our framework can achieve a significant reduction in model size and training time, while maintaining high accuracy, for both models. Therefore, this approach provides the potential to be efficiently deployed on intelligent IoT systems where computational capabilities are limited. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SACR: Self-training with Saliency-Augmented Consistency Regularization for Few-Shot Learners

SACR: Self-training with Saliency-Augmented Consistency Regu...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Feng, Yanyan Zhou, Yue Xue, Yun Li, Fenghuan Lin, Zehong School of Electronics and Information Engineering South China Normal University Foshan China Department of Artiffcial Intelligence School of Informatics Xiamen University Xiamen China School of Computer Science and Technology Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Pre-trained language models have made significant strides in natural language processing tasks, enabling flexible fine-tuning for downstream applications. However, in few-shot learning scenarios, pre-trained models face challenges related to overfitting due to limited training samples, which hinders their ability to capture data diversity and robustly handle input variations. To overcome these limitations, we propose the Saliency-Augmented Consistency Regularization (SACR) framework, a novel self-training strategy designed to improve few-shot learning performance and robustness. SACR consists of three key components: (1) Saliency-guided Data Perturbation, which uses saliency analysis to identify and perturb words that significantly influence model predictions, generating semantically consistent pseudo-samples;(2) Semantic-equivalent Sample Mining, which employs K-means clustering to select semantically similar samples and prevent semantic shift;and (3) Consistency Training, where regularization ensures consistency between the semantics and prediction distributions of the original and perturbed samples. We conducted extensive experiments on 15 public datasets to evaluate our approach. SACR significantly outperforms strong baseline models and demonstrates superior generalization capabilities compared to state-of-the-art methods, achieving an average 1.0% improvement in classification accuracy. © 2025 IEEE.

关键词： consistency regularization few-shot learning saliency self-training

来源：评论

学校读者我要写书评

暂无评论

BEDiff: denoising diffusion probabilistic models for building extraction

引用

Optoelectronics Letters 2025年第5期21卷 298-305页

作者： LEI Yanjing WANG Yuan CHAN Sixian HU Jie ZHOU Xiaolong ZHANG Hongkai College of Computer Science and Technology Zhejiang University of Technology Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information China Three Gorges University Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University College of Electrical and Information Engineering Quzhou University School of Electronic and Information Engineering Anhui Jianzhu University

Accurately identifying building distribution from remote sensing images with complex background information is challenging. The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds. Building on this concept, we propose a novel framework, building extraction diffusion model(BEDiff), which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion. Our approach begins with the design of booster guidance, a mechanism that extracts structural and semantic features from remote sensing images to serve as priors, thereby providing targeted guidance for the diffusion process. Additionally, we introduce a cross-feature fusion module(CFM) that bridges the semantic gap between different types of features, facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively. Our proposed BEDiff marks the first application of diffusion models to the task of building extraction. Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff, affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.

关键词： A

来源：评论

学校读者我要写书评

暂无评论

Diffusion Models as Network Optimizers: Explorations and Analysis

引用

IEEE Internet of Things Journal 2025年第10期12卷 13183-13193页

作者： Liang, Ruihuai Yang, Bo Chen, Pengyu Li, Xianjin Xue, Yifan Yu, Zhiwen Cao, Xuelin Zhang, Yan Debbah, Merouane Poor, H. Vincent Yuen, Chau Northwestern Polytechnical University School of Computer Science Shaanxi Xi'an710129 China Xidian University School of Cyber Engineering Shaanxi Xi'an710071 China University of Oslo Department of Informatics Oslo0316 Norway Khalifa University KU6G. Research Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates University Paris-Saclay CentraleSupelec Gif-sur-Yvette91192 France Princeton University Department of Electrical and Computer Engineering NJ08544 United States Nanyang Technological University School of Electrical and Electronics Engineering Singapore

Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Recently, generative diffusion models (GDMs) have emerged as a promising new approach to network optimization, with the potential to directly address these optimization problems. However, the application of GDMs in this field is still in its early stages, and there is a noticeable lack of theoretical research and empirical findings. In this study, we first explore the intrinsic characteristics of generative models. Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization. Based on this exploration, we implement GDMs as optimizers aimed at learning high-quality solution distributions for given inputs, sampling from these distributions during inference to approximate or achieve optimal solutions. Specifically, we utilize denoising diffusion probabilistic models (DDPMs) and employ a classifier-free guidance mechanism to manage conditional guidance based on input parameters. We conduct extensive experiments across three challenging network optimization problems. By investigating various model configurations and the principles of GDMs as optimizers, we demonstrate the ability to overcome prediction errors and validate the convergence of generated solutions to optimal solutions. We provide code and data at https://***/qiyu3816/DiffSG. © 2014 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Zirkus Empathico 2.0: a multiplayer serious mobile game for children with autism spectrum disorder (ASD), with a focus on enhancing social and emotional development

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Hassan, Ahmed Pinkwart, Niels Shafi, Muhammad Department of Computer Science and Informatics Berlin School of Business and Innovation Karl Marx Strasse 97 - 99 Berlin12043 Germany Institute for Informatic Humboldt University Berlin Rudower Chaussee 25 Berlin Berlin12489 Germany School of Computing Ulster University Belfast Campus United Kingdom Faculty of Computing & Information Technology Sohar University Sohar Oman

This study explores the effectiveness of the multiplayer serious mobile game "Zirkus Empathico (ZE) 2.0" in enhancing social-emotional behaviors in children diagnosed with autism spectrum disorder (ASD). It aims to assess how such games can foster emotional recognition, empathy, and prosocial behavior, thereby supporting the holistic development of children with ASD. An eight-week randomized controlled trial (RCT) was conducted between January and April 2021 at autism centers in Islamabad, Pakistan, and Berlin, Germany. The study involved 107 children aged 5–11 years, with 60 diagnosed with ASD and 47 typically developing children serving as an Active Control Group (ACG). Participants were engaged in sessions using the bilingual"ZE 2.0"game, incorporating multiplayer and emotional learning modules. The intervention required 120 min of weekly training supplemented by daily sessions. Post-intervention assessments demonstrated significant improvements in the ASD group compared to the control group in areas of empathy and emotional awareness, as evidenced by higher scores on the Griffith Empathy Measure (GEM) and multiplayer module evaluations. Notable was the ability of participants to apply learned social skills in dynamic, real-world contexts, which suggests the game’s effectiveness transcends the controlled settings typically associated with ASD interventions. ZE 2.0 adds to the social and teamwork competencies of children with ASD. Besides encouraging peers to be proactive in communications and cooperation, the multiplayer mode provides an immersion learning atmosphere for facilitating social and emotional development. Such an outcome underlines the perspectives of serious games for use as a framework for the treatment and education of children who have ASD. In this manner, serious games can be utilized as a supplementary or alternative means of treating ASD. Future research may focus on distinguishing the effects of intervention from those of other therapy modalit

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Shifting Perspectives: Steering Vector Ensembles for Robust Bias Mitigation in LLMs

arXiv

引用

arXiv 2025年

作者： Siddique, Zara Khalid, Irtaza Turner, Liam D. Espinosa-Anke, Luis School of Computer Science and Informatics Cardiff University United Kingdom AMPLYFI United Kingdom

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We employ Bayesian optimization to systematically identify effective contrastive pair datasets across nine bias axes. When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.2%, 4.7%, and 3.2% over the baseline for Mistral, Llama, and Qwen, respectively. Building on these promising results, we introduce Steering Vector Ensembles (SVE), a method that averages multiple individually optimized steering vectors, each targeting a specific bias axis such as age, race, or gender. By leveraging their collective strength, SVE outperforms individual steering vectors in both bias reduction and maintaining model performance. The work presents the first systematic investigation of steering vectors for bias mitigation, and we demonstrate that SVE is a powerful and computationally efficient strategy for reducing bias in LLMs, with broader implications for enhancing AI safety.1 © 2025, CC BY-SA.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Cyber Risk Identification and Classification-Based Load Forecasting Tool for Pandemic Situations

引用

IET Cyber-Physical Systems: Theory and Applications 2025年第1期10卷

作者： Shivran, Kuldeep Singh Swire-Thompson, Kyle Saxena, Neetesh Das, Sarasij Department of Electrical Engineering Indian Institute of Science Bangalore India School of Computer Science and Informatics Cardiff University Cardiff United Kingdom

Smart grid operators use load forecasting algorithms to predict energy load for the reliable and economical operation of the electricity grid. COVID-19 pandemic-like situations (PLS) can significantly impact energy load demand due to uncertainties in factors such as regulatory orders, pandemic severity and human behavioural patterns. Additionally, in a smart grid, cyberattacks can manipulate forecasted load data, leading to suboptimal decisions, economic losses and potential blackouts. Forecasting load during these situations is challenging for traditional load forecasting tools, as they struggle to identify cyberattacks amidst uncertain load demand, where cyberattacks may mimic pandemic-like load patterns. Traditional forecasting methods do not incorporate factors related to pandemics and cyberattacks. Recent studies have focused on forecasting by considering factors such as COVID-19 cases, social distancing, weather, and temperature but fail to account for the impact of regulatory orders and pandemic severity. They also lack the ability to differentiate between normal and anomalous forecasts and classify the type of attack in anomalous data. This paper presents a tool for short-term load forecasting, anomaly detection and cyberattack classification for pandemic-like situations (PLS). The proposed short-term load forecasting algorithm uses a weighted moving average and an adjustment factor incorporating regulatory orders and pandemic severity, making it computationally efficient and deterministic. Additionally, the proposed anomaly detection and cyberattack classification algorithm provides robust options for detecting anomalies and classifying various types of cyberattacks. The proposed tool has been evaluated using K-Fold cross-validation to improve generalisability and reduce overfitting. The mean squared error (MSE) was used to measure prediction accuracy and detect discrepancies. It has been analysed and tested on real-load data from the State Load Dispatch Ce

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM-Based Energy Consumption Forecasting:Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

引用

computers, Materials & Continua 2025年第5期83卷 2907-2926页

作者： Sheik Mohideen Shah Meganathan Selvamani Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Wajdan Al Malwi Mohammad Tabrez Quasim Department of Computer Science and Engineering Srinivasa Ramanujan CentreSASTRA Deemed UniversityKumbakonam612001India Department of Computer Science and Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bangalore562112India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia Centre for Research Impact and Outcome Chitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura140401PunjabIndia Department of Information Systems College ofComputer and Information SciencePrincessNourah bintAbdulrahmanUniversityP.O.Box 84428Riyadh11671Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid UniversityAbha61421Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these *** results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.

关键词： Deep learning bidirectional LSTM energy consumption forecasting time-series analysis predictive modeling machine learning in energy management

来源：评论

学校读者我要写书评

暂无评论

Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction

arXiv

引用

arXiv 2025年

作者： Yang, Leyuan Deng, Bailin Zhang, Juyong The School of Mathematical Sciences University of Science and Technology of China China The School of Computer Science and Informatics Cardiff University United Kingdom

Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network, existing methods still suffer from many drawbacks, such as limited accuracy and scale of the reconstruction. In this paper, we propose a versatile, scalable and high-quality neural implicit representation to address these issues. We integrate a divide-and-conquer approach into the neural SDF-based reconstruction. Specifically, we model the object or scene as a fusion of multiple independent local neural SDFs with overlapping regions. The construction of our representation involves three key steps: (1) constructing the distribution and overlap relationship of the local radiance fields based on object structure or data distribution, (2) relative pose registration for adjacent local SDFs, and (3) SDF blending. Thanks to the independent representation of each local region, our approach can not only achieve high-fidelity surface reconstruction, but also enable scalable scene reconstruction. Extensive experimental results demonstrate the effectiveness and practicality of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLM in Genetic Programming Hyper-heuristics for Dynamic Microservice Deployment 37th

Leveraging LLM in Genetic Programming Hyper-heuristics for...

引用

37th Australasian Joint Conference on Artificial Intelligence, AJCAI 2024

作者： Fang, Zhengxin Ma, Hui Chen, Gang Hartmann, Sven Wang, Chen Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany National Institute of Water and Atmospheric Research Wellington New Zealand

ISBN: (纸本)9789819603473

Microservice deployment in cloud computing is a challenging combinatorial optimization problem due to the complex dependencies among microservices and the intricate trade-offs among different QoS requirements, e.g., minimizing Energy Consumption (EC) vs. minimizing Communication Overhead (CO). Recently, some hyper-heuristics methods, particularly Genetic Programming Hyper-Heuristics (GPHH), have been proposed to automatically generate heuristics for solving dynamic microservice deployment problems. Meanwhile, Large Language Models (LLMs) are becoming popular for solving various domain-specific problems thanks to their strong ability to learn problem-related knowledge. However, hybridizing GPHH with LLM by combining their abilities in solving complex optimization problems remains unexplored. In this paper, we propose an LLM-enhanced Genetic Programming Hyper-Heuristic (LLM-GPHH) algorithm to evolve heuristics for the dynamic deployment of applications composed of microservices, to jointly optimize EC and CO. Our experiments on real-world datasets demonstrate the effectiveness of the newly proposed LLM-GPHH. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic programming

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：