检索结果-内蒙古大学图书馆

2nd International Conference on Sustainable computing and Data Communication Systems, ICSCDS 2023

作者： Eben, J. Lysa Kaur, Chamandeep Thelly, Mathews T Parimita Vels Institute of Science Technology and Advanced Studies School of Computing Sciences Department of Computer Applications Chennai India Jazan University Department of Computer Science and Information Technology Jazan Saudi Arabia Kuriakose Elias College Department of Botany Mannanam India Sam Higginbottom University of Agriculture Technology & Sciences Agricultural Engineering Prayagraj India

ISBN: (纸本)9781665491990

Most of India's population relies on farming for their livelihood. Every year brings new advances in agricultural technology. The use of wireless sensors in contemporary agriculture is crucial. The employment of wireless sensors across a wide range of agricultural applications has a profoundly favourable effect on crop productivity and economic efficiency. The mushroom business is still relatively young and modest compared to other sectors of India's agricultural market. The white button mushroom is India's most commercially significant fungus and is a global favourite. It may be grown anywhere with a suitable climate and soil, but most of the world's supply comes from North India in the winter. For mycelia to flourish, the ideal temperature range is between 22 and 25 degrees Celsius. In contrast, the sweet spot for developing fruit bodies is between 14 and 18 degrees Celsius with high relative humidity. Equipment for maintaining a steady temperature and pasteurising the mushrooms, should be present in the rooms used for growing. The primary objective of this study is to automate the mushroom production plant and keep track of the crop room's environmental state to reduce the amount of human care required for the mushroom plant. The Internet of Things has also modernized agriculture industries, creating an environmental monitoring and regulating system that is used in the mushroom farm in this work. Using the Speak internet platform, users may monitor ecological conditions in a mushroom farm on their Android mobile, including the ambient temperature, relative humidity, carbon dioxide level, and light intensity. The Arduino prototype platform is employed as the sensors station's controller, ensuring that the plant parameters are within the user-specified range. Using a pair of low-power ESP8266 as Wi-Fi modems, the current parameter status is relayed to a distant monitoring station. The integrated Arduino uses the programming environment to write the controller's cod

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Functional Analysis for Electricity Consumption Prediction Using Multi-Task Optimization Learning Model 1

Uncertainty-Aware Functional Analysis for Electricity Consum...

引用

1st International Conference on Computer Science and Emerging Technologies, CSET 2023

作者： Chandrasekaran, Saravanan Masthan, M. Mahesh, T.R. Athinarayanan, S. Ram, Ashwin Vivek, V. Chennai Ramapuram India Arffy Technogies Pvt Ltd. Karnataka Bengaluru India Faculty of Engineering and Technology Department of Computer Science & Engineering Bengaluru562112 India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Cse Chennai Tamil Nadu Avadi600062 India

ISBN: (纸本)9798350341737

Energy operators require the best forecasting tools for efficient power system planning and operation. Machine learning approaches are more popular for the modelling and optimization of real-world issues with a great degree of accuracy and certainty. Variation of neural network method for predicting electric energy usage is presented and the predictive modelling is applied to a time series dataset that includes electric consumption data captured over a certain time period. The work presents a methodology that employs a Multi-task Optimization Learning Model to forecast future electricity consumption while also taking into account prior electricity usage, without compromising the data's integrity. The research focuses on investigating the performance of different Neural Network models while improving the performance through optimization technique. The proposed forecasting model outperforms the other existing model with R2 of 0.96. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Frontal and temporo-parietal changes in delta and alpha power accompany stress-induced vasoconstriction and blood pressure response

引用

Journal of neurophysiology 2025年第6期133卷 2025 May 14页

作者： Joe Braun Mariya Patel Will Woods Charlotte Keatch Tatiana Kameneva Elisabeth Lambert School of Health Sciences Swinburne University of Technology Melbourne Australia. Centre for Mental Health and Brain Sciences Swinburne University of Technology Melbourne Australia. School of Science Computing and Engineering Technologies Swinburne University of technology Melbourne Australia. Iverson Health Innovation Research Institute Swinburne University of Technology Melbourne Australia.

Exaggerated blood pressure and vasoconstriction responses during acute mental stress are prospectively associated with an increased risk of hypertension, arrhythmia and vascular dysfunction. This study assessed electrophysiological brain power and cardiovascular response to acute psychological stress during concurrent recordings of magnetoencephalography, muscle sympathetic nerve activity and blood pressure in 29 healthy participants. Brain power was filtered through delta (1-4Hz), theta (4-8Hz), alpha (8-13Hz), beta (13-30Hz), low gamma (30-80Hz) and high gamma (80-120Hz) bands. Stress induced significant increases in systolic blood pressure (SBP), 5.2±5.6 mmHg, heart rate, 4.1±4.8 bpm and sympathetic nerve activity, 4.0±8.0 bursts per minute (mean ± standard deviation, P<05). Whole head and region of interest analyses showed stress induced significant increases in delta power in the right medial frontal cortex, anterior cingulate and amygdala. Alternatively, there were significant decreases in alpha power in the left and right precuneus, posterior cingulate, hippocampus and in the right thalamus and insula. Correlation analyses revealed that reduced alpha power in the right insula was correlated with SBP (=0.446). Moreover, reduced alpha power in the left amygdala was correlated with SBP (=0.392), anxiety and depression inventory scores, P<0.01. The reduced alpha power in the insula and amygdala was pronounced in participants displaying heightened sympathetic nerve reactivity to stress. Similarly, participants who displayed higher mean SBP reactivity (of 19 mmHg) to stress showed reduced alpha power in the precuneus, hippocampus and amygdala. Our results suggest that regionalized and frequency specific brain power is involved in neurogenic blood pressure regulation in normotensive individuals.

关键词： blood pressure cardiovascular magnetoencephalography neuroimaging stress

来源：评论

学校读者我要写书评

暂无评论

An Integrated CNN-RNN-SVM Framework for Classification of MRI Brain Tumor Images

An Integrated CNN-RNN-SVM Framework for Classification of MR...

引用

2024 IEEE International Conference on Imaging Systems and Techniques, IST 2024

作者： Jha, Abhinandan Singh, Onkar Singh, Koushlendra Kumar Akbari, Akbar Sheikh Takei, Masahiro Srm Institute of Science and Technology Dept.of Cse Chennai603203 India Manipal University Dept.of Cse Rajasthan Jaipur303007 India National Institute of Technology Jamshedpur Machine Vision and Intelligence Lab Dept.of Cse Jamshedpur831014 India School of Built Environment Engineering and Computing Leeds Beckett University United Kingdom Chiba University Department of Mechanical Engineering Chiba Japan

ISBN: (纸本)9798350378214

The early identification and categorization of brain tumor through MRI scans are pivotal for effective medical intervention. The present article encompasses a novel integrated framework that combines traditional machine learning and deep learning methods to categorize images of brain tumors. Utilizing the VGG-19 model pre-trained on ImageNet, we extract high-level features from MRI images, which are further processed by a Long Short-Term Memory (LSTM) framework to extract spatial and temporal dependencies within the data. To manage the high-dimensional feature space effectively, we employ Principal Component Analysis (PCA) for dimensionality reduction, followed by a Support Vector Machine (SVM) for the final classification task. We utilized a variety of data augmentation approach to enhance the capability of the architecture to generalize. Additionally, we fine-tuned the training parameters by employing the Adam optimizer along with early stopping and learning rate decay strategies. The model demonstrated exceptional precision, recall, and Fl-score metrics, with an accuracy of 97.86%. This study not only validates the effectiveness of integrating CNNs, RNNs, and SVMs but also opens avenues for future research in medical image analysis using hybrid deep learning frameworks. Experimental outcomes demonstrate that the proposed model significantly improves the accuracy of brain tumor classification compared to previous methods, offering a promising tool for aiding radiologists in the rapid and accurate diagnosis of brain tumors. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Sign to Speak: Real-time Recognition for Enhance Communication

Sign to Speak: Real-time Recognition for Enhance Communicati...

引用

Applied Artificial Intelligence and computing (ICAAIC), International Conference on

作者： S Baghavathi Priya P V R Subba Rao TamilSelvi Madeswaran Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Information Technology University of Technology and Applied Sciences Nizwa Oman

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Recent developments in the area of research on sign language recognition have led to making use of deep learning techniques with the goal to assist the self-learning transition of sign language from one language to another. In order to detect and classify characters from photographs in multiple sign languages, a number of deep-learning models, have been deployed. SLR is a prominent area of study and technology that aims to mitigate speaking barriers for individuals who unable to talk and listen. This involves the development of tools capable of understanding and deciphering sign language movements, hence facilitating a wider range of interactions for those who are difficult of listening and speaking. This paper demonstrates a novel model called CNN Inception Net, which is a neural network based on convolution. The use of an Indian sign dataset enables the achievement of a notable performance rate of 98.9%, enabling precise recognition of actions in the language of signs.

关键词： Deep learning Sign language Accuracy Convolution Neural networks Assistive technologies Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation

引用

ACM Transactions on Recommender Systems 2024年第4期2卷 1-27页

作者： Zhiyong Cheng Jianhua Dong Fan Liu Lei Zhu Xun Yang Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Shandong Artificial Intelligence Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computing National University of Singapore Singapore Singapore School of Electronic and Information Engineering Tongji University Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China and Hefei Comprehensive National Science Center Hefei China

Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items. To tackle these challenges, we propose the Disentangled Cascaded Graph Convolutional Network (Disen-CGCN), a novel multi-behavior recommendation model. Disen-CGCN employs disentangled representation techniques to effectively separate factors within user and item representations, ensuring their independence. In addition, it incorporates a multi-behavioral meta-network, enabling personalized feature transformation across user and item behaviors. Furthermore, an attention mechanism captures user preferences for different item factors within each behavior. By leveraging attention weights, we aggregate user and item embeddings separately for each behavior, computing preference scores that predict overall user preferences for items. Our evaluation of benchmark datasets demonstrates the superiority of Disen-CGCN over state-of-the-art models, showcasing an average performance improvement of 7.07% and 9.00% on respective datasets. These results highlight Disen-CGCN’s ability to effectively leverage multi-behavioral data, leading to more accurate recommendations.

关键词： Multi-Behavior Recommendation disentangled representation learning graph convolutional network multi-behavior recommendation multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Structured OFDM Design for Massive MIMO Systems with Dual-Wideband Effects

Structured OFDM Design for Massive MIMO Systems with Dual-Wi...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Wei Huang Lizheng Xu Haiyang Zhang Caihong Kai School of Computing Science and Information Hefei University of Technology Hefei China School of Communications and Information Engineering NJUPT Nanjing China

Massive multiple-input multiple-output (mMIMO) channels in wideband systems may exhibit the severe delay spread, due to its spatial- and frequency-wideband (dual-wideband) effects. The typical orthogonal frequency division multiplexing (OFDM) technology have to insert a larger number of cyclic prefix (CP) to overcome the inter-symbol interference (ISI) induced by delay spread. The additional CP overhead will counteract the improvement of spectral efficiency by the large antenna array. To address the issue, this paper proposes a structure OFDM modulation approach to reduce the CP overhead for wideband mMIMO systems with dual-wideband effects. Specifically, we propose a joint spatial precoding and frequency domain equalization scheme to maximize the system spectrum efficiency, where the closed-form solutions of precoding vectors and equalization matrices are derived by exploiting the unique characteristic of composite channel matrix. Numerical simulations indicate that the proposed scheme can effectively deal with the dual-wideband effects and significantly improve the spectral efficiency with low CP overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SHT-based public auditing protocol with error tolerance in FDL-empowered IoVs

引用

Digital Communications and Networks 2024年第1期10卷 142-149页

作者： Kui Zhu Yongjun Ren Jian Shen Pandi Vijayakumar Pradip Kumar Sharma School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Peng Cheng Laboratory Shenzhen518000China Department of Computer Science and Engineering University College of Engineering TindivanamTamil Nadu604001India Department of Computing Science University of AberdeenAberdeenAB243UEUK

With the intelligentization of the Internet of Vehicles(lovs),Artificial Intelligence(Al)technology is becoming more and more essential,especially deep *** Deep Learning(FDL)is a novel distributed machine learning technology and is able to address the challenges like data security,privacy risks,and huge communication overheads from big raw data ***,FDL can only guarantee data security and privacy among multiple clients during data *** the data sets stored locally in clients are corrupted,including being tampered with and lost,the training results of the FDL in intelligent IoVs must be negatively *** this paper,we are the first to design a secure data auditing protocol to guarantee the integrity and availability of data sets in FDL-empowered ***,the cuckoo filter and Reed-Solomon codes are utilized to guarantee error tolerance,including efficient corrupted data locating and *** addition,a novel data structure,Skip Hash Table(SHT)is designed to optimize data ***,we illustrate the security of the scheme with the Computational Diffie-Hellman(CDH)assumption on bilinear *** theoretical analyses and performance evaluations demonstrate the security and efficiency of our scheme for data sets in FDL-empowered IoVs.

关键词： Internet of vehicles Federated deep learning Data security Data auditing Data locating and recovery

来源：评论

学校读者我要写书评

暂无评论

Multi-Turn Jailbreaking Large Language Models via Attention Shifting 39

Multi-Turn Jailbreaking Large Language Models via Attention ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Xiaohu Mo, Fan Wen, Ming Gu, Tu Zheng, Huadi Jin, Hai Shi, Jie School of Cyber Science and Engineering Huazhong University of Science and Technology (HUST) China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab School of Computer Science and Technology HUST China JinYinHu Laboratory China Huawei International China

ISBN: (纸本)157735897X

Large Language Models (LLMs) have achieved significant performance in various natural language processing tasks but also pose safety and ethical threats, thus requiring red teaming and alignment processes to bolster their safety. To effectively exploit these aligned LLMs, recent studies have introduced jailbreak attacks based on multi-turn dialogues. These attacks aim to prompt LLMs to generate harmful or biased content by guiding them through contextual content. However, the underlying reasons for the effectiveness of multi-turn jailbreaks remain unclear. Existing attacks often focus on optimizing queries and escalating toxicity to construct dialogues, lacking a thorough analysis of the inherent vulnerabilities of LLMs. In this paper, we first conduct an in-depth analysis of the differences between single-turn and multi-turn jailbreaks and find that successful multi-turn jailbreaks can effectively disperse the attention of LLMs on keywords associated with harmful behaviors, especially in historical responses. Based on this, we propose ASJA, a new multi-turn jailbreak approach by shifting the attention of LLMs, specifically by iteratively fabricating the dialogue history through a genetic algorithm to induce LLMs to generate harmful content. Extensive experiments on three LLMs and two datasets show that our approach surpasses existing approaches in jailbreak effectiveness, the stealth of jailbreak prompts, and attack efficiency. Our work emphasizes the importance of enhancing the robustness of LLMs’ attention mechanism in multi-turn dialogue scenarios for a better defense strategy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Behind the Scenes: An Explainable Artificial Intelligence (XAI) on the Service Classification of the 5G/B5G Network

Behind the Scenes: An Explainable Artificial Intelligence (X...

引用

Digital Transformation and Applications (ICDXA), International Conference on

作者： Noormadinah Allias Diyana Ab Kadir Akibu Mahmoud Abdullahi Shahrinaz Ismail Faculty of Computing and Information Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia Computer Engineering Technology Universiti Kuala Lumpur- Malaysia Institute of Information Technology Kuala Lumpur Malaysia School of Computing and Informatics Albukhary International University Kedah Malaysia School of Technology Asia Pacific University of Technology & Innovation (APU) Kuala Lumpur Malaysia

Fifth generation and beyond (5G/B5G) is part of the next generation of mobile technology, which is expected to offer more capacity and faster speeds than the previous generation Long-Term Evolution (LTE) network. These features enable 5G/B5G to offer users a wide range of services, including smart cities, entertainment and multimedia, healthcare and mission-critical applications that benefit the entire economy and communities. However, due to growing demand, telecom service providers need to provide better Quality of service (QoS) on their networks to meet user expectations. Therefore, it is necessary to implement service classification that enables service providers to select the right network slices for each service to improve network QoS. Previous studies have predicted the classification of 5G/B5G services using traditional machine learning algorithms such as random forest and decision tree, achieving good accuracy. However, prediction based on black-box machine learning models was not transparent enough, so mobile service providers could not understand the reliability and interpretation of the results. Therefore, this article aims to model the system performance of 5G Key Performance Indicators (KPI) and extend the experiment to Explainable Artificial Intelligence (XAI) by using the Explainable AI to look behind the scenes of the chosen black-box models for service classification of 5G/B5G networks, as this is crucial for telecom service providers to make critical investment decisions around customer and employee experience. The results from the experiments show that the random forest has the highest confidence towards class Label 3 with the probability of 35 percent.

关键词：

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：