检索结果-内蒙古大学图书馆

10th International Conference on Web Research, ICWR 2024

作者： Talaeepoor, Maryam Soleimani Neysiani, Behzad Jezi, Mohammad Davarpanah Naghshe Jahan Institute of Higher Education Faculty of Computer Engineering Department of Computer Engineering Isfahan Iran Department of Software Engineering Isfahan Iran Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan Iran

ISBN: (纸本)9798350394986

As long as a computer system is connected to the Internet, it is susceptible to attack as a victim. In computer networks, it becomes important to manage the network based on parameters such as network size and network data. Firewalls are devices that help network administrators in this case to establish security in the network, and can be based on the rules that the firewall is based on. It is configured to control incoming and outgoing network traffic. Firewalls can be considered the most vital components of the network in establishing security. Firat University introduced a dataset containing firewall logs with multiple classes for firewall decisions. This study uses data mining techniques to improve the validation performance of classification using various machine learning algorithms like neural networks, deep learning, and kNN. The experimental results show more than 10% improvement according to precision and recall rates among various folding scenarios used in related works with minor improvement in accuracy, too. The decision tree algorithm is fast and explainable versus other algorithms. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Improving SVM Performance in Determining Cost and Kernel Parameter Values Through Grid Search 2

Improving SVM Performance in Determining Cost and Kernel Par...

引用

2nd International Conference on technology Innovation and Its Applications, ICTIIA 2024

作者： Sylvia, Visca Lydia, Maya Silvi Nasution, Benny Benyamin Universitas Sumatera Utara Faculty of Computer Science and Information Technology Medan Indonesia Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia

ISBN: (纸本)9798350351613

The purpose of this study is to improve the performance of Support Vector Machine (SVM) algorithm in sentiment analysis of trainee reviews through parameter optimization using Grid Search. Trainee reviews were taken from the Vocational and Productivity Training Center (BBPVP) Medan, which is the context of this study. The method used includes collection and preprocessing of review data, followed by the application of SVM for sentiment analysis. Grid Search is used to optimize the cost and kernel parameters of SVM. The results show that after optimization, the resulting SVM model shows significant performance improvement compared to the model before optimization. Accuracy increased from 68.75% to 71.96%, with improvements in other metrics such as precision, recall, and F1 score. These findings suggest that Grid Search is an effective method to optimize SVM parameters in sentiment analysis, providing a more accurate evaluation of the effectiveness of training programs at BBPVP Medan. This research makes an important contribution by applying hyperparameter optimization to SVM and suggests the application of this method for similar analysis in the future. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Tunable VO_(2) cavity enables multispectral manipulation from visible to microwave frequencies

引用

Light(Science & Applications) 2024年第3期13卷 510-518页

作者： Hang Wei Jinxin Gu Tao Zhao Zhiyuan Yan He-Xiu Xu Shuliang Dou Cheng-Wei Qiu Yao Li Center for Composite Materials and Structure Harbin Institute of TechnologyHarbin 150001China National University of Singapore Department of Electrical&Computer EngineeringSingapore 117583Singapore School of Chemical Engineering and Technology Harbin Institute of TechnologyHarbin 150001China Suzhou Laboratory Suzhou 215123China

Optical materials capable of dynamically manipulating electromagnetic waves are an emerging field in memories,optical modulators,and thermal ***,their multispectral design preliminarily attracts much attention,aiming to enhance their efficiency and integration of ***,the multispectral manipulation based on these materials is challenging due to their ubiquitous wavelength dependence restricting their capacity to narrow *** this article,we cascade multiple tunable optical cavities with selective-transparent layers,enabling a universal approach to overcoming wavelength dependence and establishing a multispectral platform with highly integrated *** on it,we demonstrate the multispectral(ranging from 400 nm to 3 cm),fast response speed(0.9 s),and reversible manipulation based on a typical phase change material,vanadium *** platform involves tandem VO_(2)-based Fabry–Pérot(F-P)cavities enabling the customization of optical responses at target bands *** can achieve broadband color-changing capacity in the visible region(a shift of~60 nm in resonant wavelength)and is capable of freely switching between three typical optical models(transmittance,reflectance,and absorptance)in the infrared to microwave regions with drastic amplitude tunability exceeding *** work represents a state-of-art advance in multispectral optics and material science,providing a critical approach for expanding the multispectral manipulation ability of optical systems.

关键词： spectral microwave visible

来源：评论

学校读者我要写书评

暂无评论

Highly Differentiated Target Detection under Extremely Low-Light Conditions Based on Improved YOLOX Model

引用

computer Modeling in engineering & Sciences 2024年第8期140卷 1507-1537页

作者： Haijian Shao Suqin Lei Chenxu Yan Xing Deng Yunsong Qi School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV89154USA Zhejiang Geely Automobile Research Institute Ningbo315336China

This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance *** methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging *** envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these *** enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image ***,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent *** utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic *** computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition *** validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced *** refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original *** Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX *** envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of lumi

关键词： Target detection extremely low-light wavelet transformation highly differentiated features YOLOX

来源：评论

学校读者我要写书评

暂无评论

Blockchain integrated DFL model for IIoT data security in smart cities

引用

International Journal of Information technology (Singapore) 2025年第2期17卷 911-923页

作者： Samanta, Saikat Sarkar, Achyuth Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Arunachal Pradesh Jote India

In the rapidly evolving landscape of the Industrial Internet of Things (IIoT) within smart cities, ensuring data security, confidentiality, and privacy remains a significant challenge. Decentralized Federated Learning (DFL) and Hyperledger Fabric (HF) based distributed databases ensure the confidentiality and privacy of data. We propose an innovative framework to fortify smart applications, aligned with the principles of IIoT. The proposed approach leverages the integration of the Elliptic Curve Digital Signature Algorithm (ECDSA) for data verification and the augmentation of DFL to bolster security measures. Our method uses ECDSA’s cryptographic power for safe data authentication and integrity checks in the context of smart city ecosystems. With the help of DFL, we do privacy and confidentiality-preserving collaborative model training. The integration of the HF blockchain framework further strengthens the resilience of the proposed framework. Our proposed approach outperforms existing models in terms of secure data transfer for IIoT devices, making it a robust solution for Industry 5.0 and the future of smart city development. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Data Security Decentralized Federated Learning Hyperledger Fabric Internet of things Smart City

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

Science China(Information Sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Aggregation Efficiency: Dynamic Energy-Aware Strategies in Wireless Sensor Networks

Enhancing Data Aggregation Efficiency: Dynamic Energy-Aware ...

引用

2024 International Conference on Smart Devices, ICSD 2024

作者： Agrawal, Navin Kumar Priya, Naincy Sinha, Priyanka Singh, Pranita Jain, Arpit Kumar, Munish GLA University Department of Computer Engineering & Applications U.P. Mathura India Muzaffarpur Institute of Technology Department of Computer Science & Engineering Bihar Muzaffarpur India Government Engineering College Khagaria Department of Computer Science & Engineering India Roorkee Institute of Technology Department of Computer Science and Engineering Roorkee India Koneru Lakshmaiah Education Foundation Department of Computer Science & Engineering Vaddeswaram AP India

ISBN: (纸本)9798350394412

In today's surplus world, wi-fi sensor networks are essential for many systems. This network encapsulates sensor nodes powered by irreplaceable batteries, preserving a fixed topology for displaying specific locations. Their efficiency makes it crucial for large data packages. Wireless sensor networks continuously analyze physical factors such as temperature, pressure, ambient soft, sunlight and humidity, dominating the process Energy consumption monitoring is a key task in this area. To address this framework, this paper proposes a different approach: a modified controlled, privacy-controlled approach to record collection. The method aims to reduce redundant sensitivity, thus increasing system lifetime by reducing the frequency of data transfer between nodes and large sinks A comparative study with existing methods shows how the proposed method is effective. Performance findings show that the proposed bundling method (MEBPP) provides high packet transmission values while consuming less power and extending network lifetime. © 2024 IEEE.

关键词： Data aggregation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Quasi-Hyperbolic Discounting (Extended Abstract) 10

Reinforcement Learning with Quasi-Hyperbolic Discounting (Ex...

引用

10th Indian Control Conference, ICC 2024

作者： Eshwar, S.R. Motwani, Mayank Roy, Nibedita Thoppe, Gugan Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

ISBN: (纸本)9798331517212

Human decision-making is better modeled via discounting schemes such as quasi-hyperbolic and hyperbolic than classical ones such as exponential or average reward. In [3], we initiated the study of reinforcement learning with Quasi-Hyperbolic (QH) discounting and proposed the first model-free algorithm for finding a type of policy called the Markov perfect equilibrium. This paper provides a summary of that algorithm and our other findings on its convergence. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A novel brain tumor segmentation and classification model using deep neural network over MRI-flair images

引用

Multimedia Tools and Applications 2025年第17期84卷 17645-17676页

作者： Rajendirane, Rajmohan Ananth Kumar, T. Sandhya, S.G. Hu, Yu-Chen Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Kattankulathur India Department of Computer Science and Engineering IFET College of Engineering Tamil Nadu Villupuram India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Brain tumors pose a significant health concern globally, with their detection and diagnosis being crucial for timely intervention and treatment planning. These abnormal growths can develop within the brain or originate from other parts of the body, spreading to the brain. They can be benign or malignant, and their impact on cognitive and physical function can vary widely depending on their location, size, and type. Detecting brain tumors involves a combination of imaging techniques and clinical assessment. Magnetic Resonance Imaging (MRI) is one of the primary imaging modalities used for this purpose due to its ability to provide detailed images of the brain's anatomy and pathology. Advanced image processing techniques and machine learning algorithms play an increasingly important role in enhancing the accuracy and efficiency of brain tumor detection. This study presents a comprehensive approach for enhancing brain tumor detection in MRI images using a combination of advanced techniques. Firstly, an improved K-means clustering algorithm is introduced to segment tumor regions effectively. Following this, Median Filtering is applied to refine image quality and reduce noise interference. Subsequently, a deep neural network architecture is employed for precise tumor classification utilizing the BRATS dataset. The proposed methodology aims to improve the accuracy and efficiency of brain tumor detection, offering potential advancements in medical image analysis and diagnosis. Experimental results demonstrate promising outcomes, indicating the effectiveness of the proposed approach in accurately identifying tumor regions in MRI scans. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Modeling and Evaluating Stock Market and Commodity Price Fluctuation Using Time Series Sequence Learning

引用

SN computer Science 2025年第5期6卷 1-18页

作者： Veningston, K. Ronalda, M. Shaikh, Tawseef Ayoub Gazi, Farhaan Bhagat, Sanket Department of Computer Science and Engineering National Institute of Technology Srinagar Jammu and Kashmir Srinagar 190006 India

Algorithmic trading using neural network models has gained significant attention in predicting stock and commodity price fluctuations and understanding their dynamics. Deep learning techniques have shown significant results in predicting stock market prices in recent years. Modelling stock market price dynamics using sequence learning techniques leverages the historical trends and dependencies in price data to predict future price movements. This paper presents a comprehensive analysis of Autoregressive Integrated Moving Average (ARIMA), standard neural network, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) for forecasting stock movements in various industry stocks. The main objective is to assess the performance of each model in predicting stock price fluctuations. Each model undergoes systematic validation and evaluation based on key performance indicators such as accuracy, normalised root mean squared error (NRMSE), and Weighted Mean Absolute Percentage Error (WMAPE). The forecast made by each model is compared to the actual stock prices to measure the effectiveness of the forecasting methods. This paper presents a time series sequence learning approach for modelling and evaluating stock market price fluctuation. The proposed approach uses an LSTM network to learn the sequential patterns in stock price data. The LSTM network is trained on a historical dataset of stock prices, and it is then used to predict future stock prices. The proposed approach is evaluated on a dataset of stock prices from seven different industry domains, including Investment, Infrastructure, Information technology, Pharma, Fast Moving Consumer Goods and agri-business (FMCG), Vehicles, and Banking, which enables a comprehensive evaluation of various models. The results show that the proposed LSTM approach can achieve notable accuracy in predicting future stock prices. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Lt

关键词： Algorithmic trading Sequence learning Share price dynamics Stock market price forecast Time-series analysis

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：