检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 317-332页

作者： Liu, Guangrui Zhang, Weizhe Wang, Xurun King, Stephen Yu, Shui Harbin Institute of Technology School of Cyberspace Science Heilongjiang Harbin150001 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Leland High school San JoseCA95120 United States University of Technology Sydney School of Computer Science UltimoNSW2007 Australia

Malicious traffic identification methods in intrusion detection systems have evolved from rule-based matching to machine learning. However, security risks such as membership inference and adversarial attacks hinder the practical deployment of machine learning-based network intrusion detection systems (ML-NIDSs). In this work, we design a defense framework called hierarchical differential privacy (HierarchicalDP) to safeguard ML-NIDS against membership inference and adversarial attacks. First, we analyze the principles of membership inference and adversarial attacks to find their correlation. Based on this, we propose the feature distribution security metric (FDSM) to measure the risk of membership inference and adversarial attacks on ML-NIDS. Then, we design the HierarchicalDP framework, which partitions network traffic sample features according to security levels and introduces distinct noise on each security level feature to satisfy FDSM, thus defensing against membership inference and adversarial attacks. Finally, we evaluate the defensive performance of the HierarchicalDP framework on two network traffic datasets and four machine-learning models. The HierarchicalDP defense framework, based on Laplace noise, reduces the success rate of membership inference from 64.9% to 54.4% (ineffective binary classification), the evasion rate of adversarial samples from 86.1% to 23.2%, and maintains model accuracy (ACC) fluctuations within 4.2%. Furthermore, the HierarchicalDP framework adjusts sample features without modifying the model, thereby not affecting the inference speed. HierarchicalDP offers efficient and convenient defenses for ML-NIDS deployed in a network. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Experimental research on the cold storage and release performance of air conditioning systems using phase change tubes 3

Experimental research on the cold storage and release perfor...

引用

2024 3rd International Conference on Energy and Power Engineering, EPE-AEIC 2024

作者： Jia, Rongrong Qi, Hong School of Energy Science and Engineering Harbin Institute of Technology Harbin150006 China

A phase-change cold storage air conditioning system incorporates phase-change rods to facilitate thermal energy storage and subsequent release for temperature regulation. Water and PCM systems can be utilized as thermal storage media to accumulate cold energy during the nocturnal period, thereby facilitating the release of this stored cold energy throughout daylight hours to accomplish the intended cooling objective. This work presents an innovative approach involving phase change materials, which investigates the methodologies for load balancing through peak shaving and valley filling to achieve equilibrium in power distribution. The phase-change material with a phase-change temperature of 6 ., is filled into an aluminium rod with a diameter of 50mm. 950 PCM aluminium rods are put vertically in the space of about 4.3 m3 tank. The duration for the system to achieve the cooling of the storage compartment, along with its resultant impact on investigations into the differential effects of various cooling storage and thermal release conditions on the water-based and Phase-Change Composite (PCCS) systems, were conducted. © Published under licence by IOP Publishing Ltd.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Analyzing User Needs of Autonomous Transportation Systems with Activity Theory and Knowledge Graph

Analyzing User Needs of Autonomous Transportation Systems wi...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Zheng, Lai Bao, Chunrong Wei, Wei School of Transportation Science and Engineering Harbin Institute of Technology Harbin150000 China

ISBN: (纸本)9789819639724

Thanks to the progress of emerging technologies such as autonomous driving and vehicle networking, China’s transportation system has been continuously and rapidly developing towards autonomy. Autonomous Transportation System (ATS) will integrate the new concepts of modern transportation on a basis of traditional Intelligent Transportation System (ITS), and is committed to achieving the great transportation concepts of collaborative services, intelligent travel and comprehensive transportation. This paper uses the decomposition model of activity theory to elicit the user needs of ATS from multiple dimensions and constructs a knowledge graph network of ATS user needs to understand and analyze. Combining the content of activity theory and the structure results of the knowledge graph for user needs, the core components of the transportation system and complex interaction among them are studied, which helps to expand the user needs of ATS from two dimensions of technology promotion and policy guidance, thereby promoting the development of ATS. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Versatile BiFeO_(3) shining in piezocatalysis:From materials engineering to diverse applications

引用

Journal of Advanced Ceramics 2025年第3期14卷 1-27页

作者： Jian Dai Zhenhao Fan Hang Xie Yitao Jiao Fu Huang Ahmad Azmin Mohamad Yunfei Chang Yangke Long Dawei Wang School of Instrumentation Science and Engineering Harbin Institute of TechnologyHarbin 150080China Institute of Applied Physics and Materials Engineering University of MacaoAvenida da UniversidadeMacao 999078China Energy Materials Research Group(EMRG) School of Materials and Mineral Resources EngineeringUniversiti Sains MalaysiaNibong Tebal 14300Malaysia Zhengzhou Research Institute Harbin Institute of TechnologyZhengzhou 450046China Department of Transportation and Environment Shenzhen Institute of Information TechnologyShenzhen 518172China

The growing global demand for sustainable solutions to address energy and environmental challenges has spurred significant interest in catalytic *** has emerged as a sustainable technology for environmental remediation and energy conversion because of its unique characteristics of harvesting mechanical energy into electrochemical *** BiFeO_(3)(BFO)stands out among a range of piezocatalysts for its distinctive integration of piezoelectric,multiferroic,and optical *** review critically examines piezocatalytic mechanisms,including energy band theory,screening charge effects,and displacement current theory,revealing the intricate roles of internal charges,screening charges,and piezoelectric electrons in driving catalytic ***,the evolution of BFO-based piezocatalysis is systematically reviewed,emphasizing its structural characteristics,representative synthesis methods,performance optimization strategies,and diverse applications,such as organic pollutant degradation,H_(2) production,H_(2)O_(2)generation,CO_(2)reduction,and *** particular,the underestimated ferroelectric polarization effect of BFO on CO_(2)reduction is critically analyzed and *** review identifies critical challenges and outlines future research directions to advance high-efficiency BFO-based piezocatalytic ***,this comprehensive analysis underscores the potential of BFO in piezocatalysis,bridging materials engineering with practical applications and offering insights into future advancements.

关键词： BiFeO_(3)(BFO) piezocatalysis piezoelectric effect environmental remediation energy conversion

来源：评论

学校读者我要写书评

暂无评论

Computational approaches for circRNA-disease association prediction:a review

引用

Frontiers of computer science 2025年第4期19卷 99-113页

作者： Mengting NIU Yaojia CHEN Chunyu WANG Quan ZOU Lei XU Center for Informational Biology University of Electronic Science and Technology of ChinaChengdu 610054China School of Applied Chemistry and Biological Technology Shenzhen Polytechnic UniversityShenzhen 518055China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 610054China Yangtze Delta Region Institute(Quzhou) University of Electronic Science and Technology of ChinaQuzhou 324000China Faculty of Computing Harbin Institute of TechnologyHarbin 150006China

Circular RNA(circRNA)is a covalently closed RNA molecule formed by back *** role of circRNAs in posttranscriptional gene regulation provides new insights into several types of cancer and neurological *** are associated with multiple diseases and are emerging biomarkers in cancer diagnosis and *** associations prediction is one of the current research hotspots in the field of *** research on circRNAs has made great progress,the traditional biological method of verifying circRNA-disease associations is still a great challenge because it is a difficult task and requires much ***,advances in computational methods have made considerable progress in circRNA *** review comprehensively discussed the functions and databases related to circRNA,and then focused on summarizing the calculation model of related predictions,detailed the mainstream algorithm into 4 categories,and analyzed the advantages and limitations of the 4 *** not only helps researchers to have overall understanding of circRNA,but also helps researchers have a detailed understanding of the past algorithms,guide new research directions and research purposes to solve the shortcomings of previous research.

关键词： circular RNA disease association prediction machine learning data mining deep learning

来源：评论

学校读者我要写书评

暂无评论

Progress of crystalline carbon nitride in synthesis,atomic structure characterization and photocatalysis

引用

Nano Research 2025年第1期18卷 455-476页

作者： Yueyang Tan Zhongyan Zhang Yayun Pu Zongzhao Sun Limin Huang School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemistry Southern University of Science and TechnologyShenzhen 518055China School of Traffic and Environment Shenzhen Institute of Information TechnologyShenzhen 518172China College of Chemistry and Chemical Engineering Linyi UniversityLinyi 276000China School of Optoelectronic Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China

Crystalline carbon nitride(CCN)has emerged as a highly promising semiconductor photocatalyst with unique properties,such as enhanced charge migration rate,reduced carrier recombination probability,narrow band gap and improved light-harvesting efficiency,which are suitable for a wide range of applications in solar-to-chemical conversion,energy storage,therapeutic and environmental pollution *** the past few years,there has been an increasing number of reviews on CCN ***,most of these reviews mainly focus on synthesis methods,modification and applications,with less emphasis on the relationship between structures and properties,as well as on indepth exploration of the crystalline *** electronic instability of CCN presents challenges for conventional characterization techniques to directly and thoroughly investigate the relationship between its intrinsic atom structure and photocatalytic *** mini-review not only highlights the progress in CCN-based photocatalysts,with a focus on molten-salt synthesis(including solid-salt-induced crystallization),but also emphasizes the atomic structure characterization by specifically introducing the differential phase contrast(DPC)scanning transmission electron microscopy(STEM)technique,which is essential for enhancing our understanding of the crystal structure and photocatalytic mechanisms of ***,the review outlines the photocatalytic performance and puts forward potential challenges on CCN *** review will provide a clearer understanding of the relationship in developing precise customization strategies for CCN materials and ultimately explain the regularity and specificity of the enhanced performance in targeted photocatalytic systems.

关键词： crystalline carbon nitride synthesis characterization photocatalysis

来源：评论

学校读者我要写书评

暂无评论

Effect of thermal annealing on the structure and optical properties of Sn doped Ge28Sb12Se60 chalcogenide glass films

引用

Ceramics International 2025年第12期51卷 15160-15170页

作者： Gong, Nannan Zhao, Jianxing Cao, Yinghao Zhang, Yue Ren, Jiaxuan Zhou, Yao Wang, Chonge Song, Yinglin Zhou, Jianhong School of Photoelectric Engineering Changchun University of Science and Technology Changchun130022 China Key Laboratory of Optoelectric Measurement and Optical Information Transmission Technology of Ministry of Education Changchun University of Science and Technology Changchun130022 China School of Physics Harbin Institute of Technology Harbin150001 China

Chalcogenide glass is widely used as a novel matrix material for photonic devices. The modification of the optical properties of chalcogenide glasses through thermal annealing has become a significant area of research. In this study, the effects of thermal annealing on the structure, morphology, linear and nonlinear optical properties of Sn-doped Ge28Sb12Se60 (GSS) chalcogenide glass films were investigated. The Sn-doped GSS chalcogenide glass films were prepared by the co-evaporation method, and the as-prepared films were placed in a muffle furnace for annealing at 265 and 275 °C for 1 h. The structure and morphology of all the thin films were characterised by X-ray diffraction (XRD) and field-emission scanning electron microscopy (FESEM). The results revealed that the as-prepared films exhibit amorphous characteristics, whereas the annealed films exhibit crystalline properties. The grains in the films became larger with annealing and the crystallinity improved. Additionally, the elemental composition and atomic percentages in the thin-film samples were confirmed by energy dispersive X-ray analysis (EDX) and were not significantly influenced by annealing. The optical parameters of the thin films were estimated using several empirical formulas based on the measured refractive indices and transmittances. As the annealing temperature increased, the optical bandgap decreased and the absorbance increased. Meanwhile, the values of nonlinear refractive index and third-order nonlinear polarisability of the thin films both doubled after annealing, increasing from 1.739 × 10−10 to 3.620 × 10−10 esu and from 1.269 × 10−11 to 2.892 × 10−11 esu, respectively. The results of this study have significant implications for the further study of the optical properties of chalcogenide glass films and the development of semiconductor materials for optoelectronic applications. © 2025

关键词： Amorphous films

来源：评论

学校读者我要写书评

暂无评论

Multiscale damage and failure behavior of SiCf/SiC composites with initial defects

引用

Ceramics International 2025年第14期51卷 19366-19381页

作者： Wang, Ben Wang, Jialin Lyu, Qihui Guo, Zaoyang Research Institute of Interdisciplinary Science & School of Materials Science and Engineering Dongguan University of Technology Guangdong Dongguan523808 China School of Science Harbin Institute of Technology Guangdong Shenzhen518055 China

A multiple damage mechanisms-based multiscale model is developed and implemented within a multiscale simulation framework, which incorporates the statistical distributions of SiC fiber strength and SiC matrix microcrack size to capture the mechanical response and defect-induced nonlinear behavior of SiCf/SiC composites. The micro- and mesoscale representative volume element (RVE) models accounting for the initial defects, are established to simulate the key deformation and damage evolution at the fiber bundle and material levels, and whose predictions are in good agreement with the experimental results for SiCf/SiC minicomposites and 2D SiCf/SiC composites. Based on the validated multiscale models, the effects of the multiscale components and defects on the failure envelopes of 2D SiCf/SiC composites under combined loadings are studied. Subsequently, a unified failure criterion with minimal non-physical parameters is formulated. This multiscale modeling strategy provides an effective way to predict the strength of SiCf/SiC composite structures related to the micro-mesoscopic characteristics. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Ceramic matrix composites

来源：评论

学校读者我要写书评

暂无评论

On the Stability of Random Access with Congestion Control 14th

On the Stability of Random Access with Congestion Control

引用

14th EAI International Conference on Wireless and Satellite Systems, WiSATS 2024

作者： Xu, Yu Cui, Chen Wang, Zhenyong Guo, Qing School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Songjiang Laboratory Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9783031861956

The random access protocol is a critical technique widely used in various wireless networks. A significant challenge is analyzing the stability of the random access system when a large number of users transmit packets independently. Although the congestion control policy can enhance the stability of the system, there is currently a lack of quantitative analysis on the stability of random access with congestion control. In this paper, we analyze the random access system with congestion control and quantify its stability. Specifically, we consider a congestion control scheme to enhance the stability of the random access system and present the graphical analytical model. Based on this graphical model, we qualitatively discuss the behavioral variations of the system as it works and quantify its stability. © ICST institute for computer sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

HDNeXt: Hybrid Dynamic MedNeXt with Level Set Regularization for Medical Image Segmentation 17th

HDNeXt: Hybrid Dynamic MedNeXt with Level Set Regularizatio...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Cao, Haoyu Han, Tianyi Yang, Yunyun School of Science Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9789819609628

Deep learning has been extensively employed in the field of medical image segmentation, demonstrating its robustness and efficacy. However, the pursuit of consistent segmentation performance across diverse instrumental conditions and the challenge of achieving precise boundary delineation in segmented images remain significant hurdles. In this paper, we aim to develop a model capable of achieving consistent, high-quality segmentation of identical regions of interest across varying instrumental conditions, with precise boundary delineation. Toward this end, we introduce our Hybrid Dynamic MedNeXt (HDNeXt) model, an advanced framework capable of dynamically generating weights across diverse medical images to maintain consistently high segmentation performance. HDNeXt builds on the robust segmentation framework of MedNeXt by incorporating dynamic convolution techniques, which endow the model with the capability for dynamic weight adjustment, significantly enhancing its segmentation performance. To tackle the second challenge, we devised a novel loss function, LCR, formulated on the Curvature of the segmentation boundary and Region-Fitting energy derived from level set methods, which significantly enhances boundary precision during training and optimizes overall segmentation performance. Experiments were conducted on the abdominal CT datasets Synapse and the cardiac MRI datasets ACDC to demonstrate the efficiency and effectiveness of our method. Our method achieved an average Dice coefficient of 84.38 on the Synapse datasets and 93.59 on the ACDC datasets, surpassing other 2D state-of-the-art segmentation models and achieving optimal performance for 2D medical image segmentation. Codes are available at https://***/HaoyuCao/HDNeXt. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

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：