检索结果-内蒙古大学图书馆

58th Annual Allerton conference on Communication, control, and Computing (Allerton)

作者： Dahlin, Nathan Chang, Kevin Kalagarla, Krishna Chaitanya Jain, Rahul Nuzzo, Pierluigi UIUC ECE Dept Champaign IL USA USC Ctr Auton & AI Los Angeles CA USA USC ECE Dept Los Angeles CA USA

ISBN: (数字)9798350399981

ISBN: (纸本)9798350399981

Deep Reinforcement Learning (RL) methods produce often performance-leading controllers. Yet, in many applications (e.g., when safety and assurance are critical), they cannot be deployed. Deep Neural Nets (DNN) controllers are nearly impossible to verify and their behavior hard to interpret. In this paper, we first show, through a simple example, that there exist soft decision tree (SDT) controllers that are equivalent to neural network (NN) controllers in terms of input-output behavior. Based on imitation learning, we then show via three OpenAl gym environment case studies that it is possible to distill high-performance DNN controllers into non-DNN controllers (e.g., leveraging decision tree and support vector machine architectures) that, while sacrificing performance just a bit, can be simpler, more interpretable, hence amenable to verification and validation. We thus propose the natural control design paradigm that leverages the power of deep RL methods to design reference DNN controllers, and then distill them into non-DNN controllers which can be validated and deployed in real systems. Finally, we identify some distillation metrics that can be useful in assessing the quality of the distilled controllers.

关键词： Support vector machines Measurement Deep learning control design Design methodology Reinforcement learning Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Behaviour Trace-Based Unsupervised Deep Embedding for Online Multiple Product Recommendation in Commercial Banks 9

Behaviour Trace-Based Unsupervised Deep Embedding for Online...

引用

9th International conference on control Science and systems Engineering, ICCSSE 2023

作者： Gao, Bo Hu, Liang Wang, Haotian Wen, Han Wang, Fei Yan, Lu Huang, Muqing Zhu, Haiwei Beijing Branch of ICBC Dept. Financial Technology Beijing China Beijing Branch of ICBC Dept. Internet Finance Beijing China

ISBN: (纸本)9798350339055

Recommender systems (RSs) for products and services stay central to the operations of commercial banks in China. Efficiency, effectiveness and resilence of relevant methods are therefore the main focus. In this paper, a novel Behaviour Trace-based Unsupervised Deep Embedding (BTUDE) architecture has been developed for online recommendation of multiple products in the mobile bank application of a large commercial bank in China (LCB). BTUDE is implemented with a Variational AutoEncoder (VAE) model in which a ResNet1D network and its reverse implementation, modified for 1D time series processing, play the role of encoder and decoder, respectively. In this architecture, Customer behaviour data grouped in many time series are first processed with a novel normalization method, and then fed into the VAE model. As a quantitative form of the customer profile system, BTUDE represented as the latent space embedding generated by VAE is built up independent of scenarios for any specific product recommendation. In recommendation events for each specific product, BTUDE similarity between potential customers and those already possessed the product can be used as the feature to further detect target customers via a two-component Gaussian Mixture Model (GMM). Different types of tests have been carried out. Online A/B tests have been conducted for a money market fund product. performance for wealth management and life insurance products are also evaluated. The promising results show that BTUDE is effectively adapted to online environment for recommendation shifting among multiple products in a fast pace. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Cross-Layer DoS Attack Detection Technique for internet of Things 7

Cross-Layer DoS Attack Detection Technique for Internet of T...

引用

7th International conference on Communication and Electronics systems, ICCES 2022

作者： Kharkwal, Ayushi Mishra, Saumya Paul, Aditi Banasthali Vidyapith School of Mathematics and Computing Rajasthan India

ISBN: (数字)9781665496346

ISBN: (纸本)9781665496346

Security of internet of Things (IoT) is one of the most prevalent crucial challenges ever since. The diversified devices and their specification along with resource constrained protocols made it more complex to address over all security need of IoT. Denial of Service attacks, being the most powerful and frequent attacks on IoT have been considered so forth. However, the attack happens on multiple layers and thus a single detection technique for each layer is not sufficient and effective to combat these attacks. Current study focuses on cross layer intrusion detection system (IDS) for detection of multiple Denial of Service (DoS) attacks. Presently, two attacks at Transmission control Protocol (TCP) and Routing Protocol are considered for Low power and Lossy networks (RPL) and a neural network-based IDS approach has been proposed for the detection of such attacks. The attacks are simulated on NetSim and detection and the performance shows up to 80% detection probabilities. © 2022 IEEE.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

Run-Time Probabilistic Model Checking for Failure Prediction: A Smart Lift Case Study 8

Run-Time Probabilistic Model Checking for Failure Prediction...

引用

8th IEEE World Forum on the internet of Things (WF-IoT) - Sustainability and the internet of Things

作者： Xin, Xin Keoh, Sye Loong Sevegnani, Michele Saerbeck, Martin TUD SUD Asia Pacific Digital Serv Singapore Singapore Univ Glasgow Sch Comp Sci Glasgow Scotland

ISBN: (纸本)9781665491532

Modern smart systems are powered by cyberphysical systems integrating sensor networks with service-oriented architecture to automate their operations. control algorithms deployed on smart systems are now driven by connected sensors with control decisions being made based on the sensor generated data. As sensors tend to be unreliable and prone to failures, this has resulted in the increase of system errors due to the wrong control decisions derived from the faulty sensor readings, thus affecting the performance, safety and quality of the operational tasks. Existing methodologies to evaluate and test such systems do not take into account the complexity and uncertainty exhibited by the underlying sensor networks, and hence not being able to dynamically verify the behaviour of the smart systems at run-time. This paper proposes a novel run-time verification framework combining sensor-level fault detection and system-level probabilistic model checking. This framework rigorously quantifies the trustworthiness of sensor readings, hence enabling formal reasoning for system failure prediction. We evaluated our approach on a passenger lift equipped with sensor networks to monitor its main components continuously. The results indicate that the proposed verification framework involving the quantified sensor's trustworthiness enhances the accuracy of the system failure prediction.

关键词： Probabilistic Model Checking Sensor Confidence Sensor Trustworthiness Sensor network

来源：评论

学校读者我要写书评

暂无评论

Scalable internet of things network design using multi-hop IEEE 802.11ah

引用

TELECOMMUNICATION systems 2021年第4期78卷 577-588页

作者： Ahmed, Nurzaman Hussain, Md Iftekhar North Eastern Hill Univ Dept Informat Technol Shillong 793022 Meghalaya India

The emerging IEEE 802.11ah is a promising communication standard for large-scale networks particularly the internet of Things (IoT). The single-channel-based centralized channel access mechanism employed in 802.11ah does not scale well in such networks and leads to poor data reception quality. In this paper, we propose an Enhanced and Scalable Medium Access control (ES-MAC) protocol, which employs multi-band sectorization and dynamic load balancing. These features facilitate multi-hop communication more efficiently and enhance network capacity. Traffic congestion issues prevailing around the access point node due to the large volume of uplink traffic is mitigated by allowing simultaneous transmission using multiple orthogonal channels and sectors. Simulation and analytical results establish the essence of the novel protocol by showing significant improvements in terms of throughput and average packet delay over the existing schemes. The proposed network architecture improves throughput and delay performance up to 150% and 100% respectively compared to the relevant schemes.

关键词： IEEE 802 11ah Sub-1 GHz Restricted access window (RAW) internet of things (IoT) M2M communication Relay AP

来源：评论

学校读者我要写书评

暂无评论

Secure and Energy-Efficient Framework for internet of Medical Things (IoMT)-Based Healthcare System

Secure and Energy-Efficient Framework for Internet of Medica...

引用

International conference on Data Science and network Engineering, ICDSNE 2023

作者： Dewan, Ritu Nagpal, Tapsi Ahmad, Sharik Rana, Arun Kumar Islam, Sardar M. N. Department of Computer Science and Engineering Lingaya’s Vidyapeeth Faridabad India Department of Computer Science and Engineering Galgotias College of Engg. and Technology Greater Noida India SILC and Decision Sciences and Modelling Program Victoria University Footscray Australia

ISBN: (纸本)9789819967544

Manufacturing, energy, finance, education, transportation, smart home, and medicine employ IoT technology. IoT solutions can efficiently manage hospital patients and mobile assets to provide high-quality medical services. The internet of Medical Things (IoMT) integrates IoT with medical equipment to increase patient comfort, cost-effective medical solutions, hospital treatment speed, and personalized healthcare. This work uses Constrained Application Protocol to secure remote patient health data (CoAP). Nevertheless, the CoAP DTLS layer lacks key control, session establishment, and multicast message exchange. Hence, IoMT communication requires an efficient protocol for safe CoAP session formation. Consequently, to address key management and multicast security issues in CoAP, we presented an efficient and secure communication method to establish a secure session key between IoMT devices and distant servers utilizing lightweight, energy efficient, and Secure CoAP Elliptic Curve Cryptography (E2SCEC2). E2SCEC2 can use a smaller key size than Rivest-Shamir-Adleman (RSA) due to its tiny key size. To determine if these algorithms are compatible in limited contexts, the paper examines key creation, signature generation, and verification of E2SCEC2 and RSA algorithms, energy consumption, and radio duty cycle. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

A multi-objective distribution network partitioned voltage active-reactive coordination control strategy based on Synchronous ADMM

A multi-objective distribution network partitioned voltage a...

引用

Smart Grid and Energy internet (SGEI), International conference on

作者： Huifeng Wang Bowen Zou Zhigang Song Lei Song Yue Gao Miaomiao Wang Xin Wang State Grid LongNan Power Supply Company LongNan China School of Electrical and Electronic Information Xihua University Chengdu China

ISBN: (数字)9798350368314

ISBN: (纸本)9798350368321

In the face of the increasingly intricate and fluid landscape of contemporary power systems, the effective administration of distribution networks has emerged as a pivotal issue for electricity companies. In light of this, this paper proposes a multi-objective distribution network partitioned voltage active-reactive coordination control strategy based on Synchronous ADMM. Firstly, a holistic electrical distance metric, regional coupling intensity, and regional reactive power equilibrium indicator have been formulated for the distribution network. The PSO technique is employed for the network partitioning process. Secondly, based on the regional partitioning, a regional voltage autonomous model is constructed with the objective function of minimizing the sum of photovoltaic active power reduction, node voltage deviation, and network loss. Finally, network is partitioned and decoupled, and the synchronous ADMM algorithm is utilized to achieve coordinated optimization control of voltage levels based on inter-regional information exchange. The simulations performed on the improved IEEE 33-node distribution network validate the effectiveness of the proposed regional voltage control strategy. This method is demonstrated to markedly enhance the general voltage quality and boost the safety and stability of the distribution network.

关键词： Photovoltaic systems Reactive power Voltage fluctuations Distribution networks Power system stability Linear programming Partitioning algorithms Voltage control Optimization Information exchange

来源：评论

学校读者我要写书评

暂无评论

Lung Disease Classification from Chest X-ray Images Using Convolutional Neural network and Long Short-Term Memory Model 3

Lung Disease Classification from Chest X-ray Images Using Co...

引用

3rd International conference on Artificial Intelligence For internet of Things, AIIoT 2024

作者： Khaing, Ei Ei Aung, Thu Zar Faculty of Computer Systems and Technologies Taungoo Myanmar Pyin Oo Lwin Myanmar

ISBN: (纸本)9798350372120

The global expansion of lung illness necessitates the development of a reliable diagnostic technique. A lung illness diagnosis might be difficult for doctors to make. The goal of this approach is to develop a means of promptly identifying lung issues and halting the virus's transmission. Five diseases are distinguished in the proposed framework: COVID-19, lung opacity, normal, tuberculosis, and viral pneumonia. The proposed system consists of three main steps: the preprocessing step, the feature extraction step, and the classification step. In the preprocessing step, to improve the quality of raw chest-Xray images using the image preprocessing method without data loss, this system proposes modelling the feature map and vector by using pre-trained Alexnet and LSTM. Machine learning techniques (such as SVM) are used for the categorization of lung diseases. Two publicly available datasets from Kaggle websites were used to create a dataset of COVID-19 3616, lung opacity 350, tuberculosis 500, normal 10192, and viral pneumonia 1345 chest X-ray images for this study. The dataset is divided into 70% training images and 30% testing images. The performance of the classifier is measured in experiments using accuracy, true positive, false negative, positive predictive, and false discovery rates. The purposed lung illness categorization method is built using MATLAB 2021b, which is used with an Intel Core i5 CPU running Windows 10 64-bit and 8GB of Random Access Memory (RAM). Finally, this system compares the proposed feature vector by adding the convolution and pooling layers of the pre-trained Alexnet and LSTM with the state-of-the-art pretrained Alexnet and LSTM. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Novel Tuning Strategies to Enhance State Estimator performance and quality in the All India Power System network 23

Novel Tuning Strategies to Enhance State Estimator Performan...

引用

23rd National Power systems conference, NPSC 2024

作者： Singh, Bhavneet Madhukar, Neha Shukla, Rohit Singh, Pramod Roy, B.S. Grid Controller of India Limited New Delhi India

ISBN: (纸本)9798331519568

The accuracy and reliability of state estimation are crucial for the effective operation and control of power systems, particularly in large-scale networks. Operators often face challenges such as measurement noise, data redundancy, and computational inefficiencies while striving for optimal solutions. This paper introduces novel tuning strategies to enhance state estimator performance and quality. The paper begins by underscoring the importance of state estimation in power systems. It then examines the integration of SCADA (Supervisory control and Data Acquisition) and EMS (Energy Management System) applications, highlighting their interlinking and significance in data collection and system monitoring. Key features of state estimator(SE) are detailed, including real-time sequencing, data filtration, handling various types of measurements, and consistency checks. A comprehensive discussion of the processes involved in achieving an optimal state estimator solution follows, covering SCADA data import, network topology processing, and observability analysis. The paper then delves into specific tuning strategies designed to improve state estimator performance. These strategies include network truncation, verification of network parameters, incorporation of pseudo measurements, correction of ICCP (Inter control Centre Communication Protocol) mismatches, and network topology corrections, etc. Finally, the paper evaluates the quality of the state estimator solution and the associated objective function values, demonstrating significant improvements through the proposed strategies. This study provides practical and innovative solutions to enhance state estimation in large and complex power networks, contributing to more reliable and efficient power system operations. © 2024 IEEE.

关键词： SCADA systems

来源：评论

学校读者我要写书评

暂无评论

Encrypted Malicious Traffic Detection Based on Sample Selection Optimization and Data Augmentation 9

Encrypted Malicious Traffic Detection Based on Sample Select...

引用

9th IEEE International conference on Data Science in Cyberspace, DSC 2024

作者： Liang, Rui Zhang, Hanchong Liu, Fuqiang Zhang, Jinyun Sun, Zhe Song, Yanfei Li, Chao Zhang, Liang Guangzhou University Cyberspace Institute of Advanced Technology Guangzhou China Cyber Emergency Response Team China Industrial Control Systems Beijing China PipeChina North Pipeline Company Information Center Langfang China

ISBN: (纸本)9798350391367

A large number of network services and applications now use encryption technology to ensure network information security. However, while encryption technology protects user privacy, it also presents new challenges. Traditional traffic detection methods rely on payloads and cannot effectively detect encrypted traffic, thereby providing opportunities for malicious behavior. Detecting encrypted malicious traffic through machine learning or deep learning has become a research hotspot, but there are still some shortcomings: Using the aforementioned artificial intelligence technologies for detection requires a large amount of data for training. In real network environments, the collected datasets have an imbalance between malicious traffic and benign traffic, which severely affects the detection performance of classification models. This paper proposes a method of sample selection optimization and data augmentation to improve the imbalance problem. The roulette wheel selection algorithm is applied to the field of encrypted malicious traffic detection. This algorithm is used only for real malicious samples, assigning different selection probabilities to malicious samples based on sample characteristics. The optimized selected samples are then placed into an improved GAN model named Filtered Auxiliary Classifier GAN (FAC-GAN) for data augmentation. Finally, the balanced dataset is put into a Random Forest (RF) classifier for detection. Experimental results show that the proposed method can generate high-quality samples and its detection performance on the CIC-IDS2017 dataset is superior to existing data augmentation methods. © 2024 IEEE.

关键词： Generative adversarial networks

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：