检索结果-南通市图书馆

Laser‑Induced and MOF‑Derived Metal Oxide/Carbon Composite for Synergistically Improved Ethanol Sensing at Room temperature

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2024年第6期16卷 210-220页

作者： Hyeongtae Lim Hyeokjin Kwon Hongki Kang Jae Eun Jang Hyuk‑Jun Kwon department of Electrical engineering and computer Science DGISTDaegu 42988South Korea convergence Research Advanced Centre for Olfaction DGISTDaegu 42988South Korea

Advancements in sensor technology have significantly enhanced atmospheric ***,metal oxide and carbon(MO_(x)/C)hybrids have gained attention for their exceptional sensitivity and room-temperature sensing ***,previous methods of synthesizing MO_(x)/C composites suffer from problems,including inhomogeneity,aggregation,and challenges in ***,we introduce a refined method that employs a metal–organic framework(MOF)as a precursor combined with direct laser *** inherent structure of MOFs ensures a uniform distribution of metal ions and organic linkers,yielding homogeneous MO_(x)/C *** laser processing facilitates precise micropatterning(<2μm,comparable to typical photolithography)of the MO_(x)/C *** optimized MOF-derived MO_(x)/C sensor rapidly detected ethanol gas even at room temperature(105 and 18 s for response and recovery,respectively),with a broad range of sensing performance from 170 to 3,400 ppm and a high response value of up to 3,500%.Additionally,this sensor exhibited enhanced stability and thermal resilience compared to previous MOF-based *** research opens up promising avenues for practical applications in MOF-derived sensing devices.

关键词： Metal-organic frameworks Metal oxide Carbon composite Laser Gas sensor

维普期刊数据库

Efficient Deep Learning Framework for Fire Detection in Complex Surveillance Environment

在线全文

学校读者我要写书评

暂无评论

computer Systems Science & engineering 2023年第7期46卷 749-764页

作者： Naqqash Dilshad Taimoor Khan JaeSeung Song department of convergence engineering for Intelligent Drone Seoul05006Korea department of computer Science Islamia College PeshawarPeshawar25120Pakistan

To prevent economic,social,and ecological damage,fire detection and management at an early stage are significant yet *** computationally complex networks have been developed,attention has been largely focused on improving accuracy,rather than focusing on real-time fire ***,in this study,the authors present an efficient fire detection framework termed E-FireNet for real-time detection in a complex surveillance *** proposed model architecture is inspired by the VGG16 network,with significant modifications including the entire removal of Block-5 and tweaking of the convolutional layers of *** results in higher performance with a reduced number of parameters and inference ***,smaller convolutional kernels are utilized,which are particularly designed to obtain the optimal details from input images,with numerous channels to assist in feature *** E-FireNet,three steps are involved:preprocessing of collected data,detection of fires using the proposed technique,and,if there is a fire,alarms are generated and transmitted to law enforcement,healthcare,and management ***,E-FireNet achieves 0.98 accuracy,1 precision,0.99 recall,and 0.99 F1-score.A comprehensive investigation of various Convolutional Neural Network(CNN)models is conducted using the newly created Fire Surveillance SV-Fire *** empirical results and comparison of numerous parameters establish that the proposed model shows convincing performance in terms of accuracy,model size,and execution time.

关键词： Deep learning drone embedded vision emergency monitoring fire classification fire detection IoT search and rescue

Adaptive Partial Task Offloading and Virtual Resource Placement in SDN/NFV-Based Network Softwarization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computer Systems Science & engineering 2023年第5期45卷 2141-2154页

作者： Prohim Tam Sa Math Seokhoon Kim department of Software convergence Soonchunhyang UniversityAsan31538Korea department of computer Software engineering Soonchunhyang UniversityAsan31538Korea

Edge intelligence brings the deployment of applied deep learning(DL)models in edge computing systems to alleviate the core backbone network *** setup of programmable software-defined networking(SDN)control and elastic virtual computing resources within network functions virtualization(NFV)are cooperative for enhancing the applicability of intelligent edge *** offer advancement for multi-dimensional model task offloading in edge networks with SDN/NFV-based control softwarization,this study proposes a DL mechanism to recommend the optimal edge node selection with primary features of congestion windows,link delays,and allocatable bandwidth *** partial task offloading policy considered the DL-based recommendation to modify efficient virtual resource placement for minimizing the completion time and termination drop *** optimization problem of resource placement is tackled by a deep reinforcement learning(DRL)-based policy following the Markov decision process(MDP).The agent observes the state spaces and applies value-maximized action of available computation resources and adjustable resource allocation *** reward formulation primarily considers taskrequired computing resources and action-applied allocation *** defined policies of resource determination,the orchestration procedure is configured within each virtual network function(VNF)descriptor using topology and orchestration specification for cloud applications(TOSCA)by specifying the allocated *** simulation for the control rule installation is conducted using Mininet and Ryu SDN *** delay and task delivery/drop ratios are used as the key performance metrics.

关键词： Deep learning partial task offloading software-defined networking virtual machine virtual network functions

Malicious Traffic Compression and Classification Technique for Secure Internet of Things

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2023年第9期76卷 3465-3482页

作者： Yu-Rim Lee Na-Eun Park Seo-Yi Kim Il-Gu Lee department of Future convergence Technology engineering SungshinWomen’s UniversitySeoul02844Korea department of convergence Security engineering SungshinWomen’s UniversitySeoul02844Korea

With the introduction of 5G technology,the application of Internet of Things(IoT)devices is expanding to various industrial ***,introducing a robust,lightweight,low-cost,and low-power security solution to the IoT environment is ***,this study proposes two methods using a data compression technique to detect malicious traffic efficiently and accurately for a secure IoT *** first method,compressed sensing and learning(CSL),compresses an event log in a bitmap format to quickly detect ***,the attack log is detected using a machine-learning classification *** second method,precise re-learning after CSL(Ra-CSL),comprises a two-step *** uses CSL as the 1st step analyzer,and the 2nd step analyzer is applied using the original dataset for a log that is detected as an attack in the 1st step *** the experiment,the bitmap rule was set based on the boundary value,which was 99.6%true positive on average for the attack and benign data found by analyzing the training *** results showed that the CSL was effective in reducing the training and detection time,and Ra-CSL was effective in increasing the detection *** to the experimental results,the data compression technique reduced the memory size by up to 20%and the training and detection times by 67%when compared with the conventional *** addition,the proposed technique improves the detection accuracy;the Naive Bayes model with the highest performance showed a detection rate of approximately 99%.

关键词： IoT security intrusion detection machine learning traffic classification

An improved brain MR image binarization method as a preprocessing for abnormality detection and features extraction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of computer Science 2017年第4期11卷 717-727页

作者： Sudipta ROY Debnath BHATTACHARYYA Samir Kumar BANDYOPADHYAY Tai-Hoon KIM department of computer Science and engineering Institute of Computer Technology (UVPCE) Ganpat University Ahmadabad 380060 India Information Technology department College of Engineering Bharati Vidyapeeth deemed University Pune 411043 India department of computer Science and engineering University of Calcutta Technology Campus Kolkata 700098 India department of convergence Security Sungshin Women's University Seoul 136-742 Korea

This paper propose a computerized method of magnetic resonance imaging （MR/） of brain binarization for the uses of preprocessing of features extraction and brain ab- normality identification. One of the main problems of MR/ binarization is that many pixels of brain part cannot be cor- rectly binarized due to extensive black background or large variation in contrast between background and foreground of MR/. We have proposed a binarization that uses mean, vari- ance, standard deviation and entropy to determine a thresh- old value followed by a non-gamut enhancement which can overcome the binarization problem of brain component. The proposed binarization technique is extensively tested with a variety of MR/and generates good binarization with im- proved accuracy and reduced error. A comparison is carried out among the obtained outcome with this innovative method with respect to other well-known methods.

关键词： image binarization thresholding image pre-processing segmentation performance analysis accuracy es-timation MRI of brain entropy

Suboptimal Feature Selection Techniques for Effective Malicious Traffic Detection on Lightweight Devices

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computer Modeling in engineering & Sciences 2024年第8期140卷 1669-1687页

作者： So-Eun Jeon Ye-Sol Oh Yeon-Ji Lee Il-Gu Lee department of Future convergence Technology engineering Sungshin Women’s UniversitySeoul02844Korea department of convergence Security engineering SungshinWomen’s UniversitySeoul02844Korea

With the advancement of wireless network technology,vast amounts of traffic have been generated,and malicious traffic attacks that threaten the network environment are becoming increasingly *** signature-based detection methods,static analysis,and dynamic analysis techniques have been previously explored for malicious traffic detection,they have limitations in identifying diversified malware traffic *** research has been focused on the application of machine learning to detect these ***,applying machine learning to lightweight devices like IoT devices is challenging because of the high computational demands and complexity involved in the learning *** this study,we examined methods for effectively utilizing machine learning-based malicious traffic detection approaches for lightweight *** introduced the suboptimal feature selection model(SFSM),a feature selection technique designed to reduce complexity while maintaining the effectiveness of malicious traffic *** performance was evaluated on various malicious traffic,benign,exploits,and generic,using the UNSW-NB15 dataset and SFSM sub-optimized hyperparameters for feature selection and narrowed the search scope to encompass all *** improved learning performance while minimizing complexity by considering feature selection and exhaustive search as two steps,a problem not considered in conventional *** experimental results showed that the detection accuracy was improved by approximately 20%compared to the random model,and the reduction in accuracy compared to the greedy model,which performs an exhaustive search on all features,was kept within 6%.Additionally,latency and complexity were reduced by approximately 96%and 99.78%,respectively,compared to the greedy *** study demonstrates that malicious traffic can be effectively detected even in lightweight device *** verified the possibility of detecting various attack

关键词： Feature selection lightweight device machine learning Internet of Things malicious traffic

Multi-Agent Deep Q-Networks for Efficient Edge Federated Learning Communications in Software-Defined IoT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第5期71卷 3319-3335页

作者： Prohim Tam Sa Math Ahyoung Lee Seokhoon Kim department of Software convergence Soonchunhyang UniversityAsan31538Korea department of computer Science Kennesaw State UniversityMariettaGA 30060USA department of computer Software engineering Soonchunhyang UniversityAsan31538Korea

Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging ***,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled *** paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and ***-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading *** gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state *** exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value ***-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation *** neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and *** scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term *** results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet

关键词： Deep Q-networks federated learning network functions virtualization quality of service software-defined networking

Duplexer Design for Full-Duplex Based Wireless Communications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2016年第11期13卷 1-13页

作者： Hui Zhuang Jintao Li Weibiao Geng Xiaoming Dai Beijing engineering and Technology Research Center for convergence Networks and Ubiquitous Services School of Computer and Communication EngineeringUniversity of Science and Technology

The full-duplex(FD) based wireless communication devices,which are capable of concurrently transmitting and receiving signals with a single frequency band,suffer from a severe self-interference(SI) due to the large power difference between the devices' own transmission and the useful signal comes from the remote transmitters. To enable the practical FD devices to be implementable,the SI power must be sufficiently suppressed to the level of background noise power,making the received signal-to-interference-plus-noise ratio(SINR) satisfy the decoding requirement. In this paper,the design and implementation of the duplexer for facilitating SI cancellation in FD based wireless communications are investigated,with a new type of duplexer(i.e. an improved directional coupler) designed for improving the spatial suppression of the SI power. Furthermore,the practical circuit boards are designed and verified for the proposed prototype,showing that the spatial suppression capability may be up to 36 d B(i.e. much higher than that attainable in the commonly designed ferrite circulator) by using the proposed design.

关键词： full-duplex wireless communications Self-interference cancellation Duplexer Directional coupler

维普期刊数据库

MMInstruct: a high-quality multi-modal instruction tuning dataset with extensive diversity

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第12期67卷 36-51页

作者： Yangzhou LIU Yue CAO Zhangwei GAO Weiyun WANG Zhe CHEN Wenhai WANG Hao TIAN Lewei LU Xizhou ZHU Tong LU Yu QIAO Jifeng Dai School of computer Science Nanjing University School of Electronic Information and Electrical engineering Shanghai Jiao Tong University Shanghai ai Laboratory School of computer Science Fudan University department of Information engineering The Chinese University of Hong Kong SenseTime Research department of Electronic engineering Tsinghua University

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of vision large language models(VLLMs), existing visual instruction tuning datasets include the following limitations.(1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance,instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations.(2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and closer to real-world scenarios outputs. To address these challenges, we construct a high-quality, diverse visual instruction tuning dataset MMInstruct,which consists of 973k instructions from 24 domains. There are four instruction types: judgment, multiplechoice, long visual question answering, and short visual question answering. To construct MMInstruct, we propose an instruction generation data engine that leverages GPT-4V, GPT-3.5, and manual correction. Our instruction generation engine enables semi-automatic, low-cost, and multi-domain instruction generation at 1/6 the cost of manual construction. Through extensive experiment validation and ablation experiments,we demonstrate that MMInstruct could significantly improve the performance of VLLMs, e.g., the model fine-tuning on MMInstruct achieves new state-of-the-art performance on 10 out of 12 benchmarks. The code and data shall be available at https://***/yuecao0119/MMInstruct.

关键词： instruction tuning multi-modal multi-domain dataset vision large language model

同方期刊数据库