检索结果-内蒙古大学图书馆

7th international conference on Digital Arts, Media and Technology, DAMT 2022 and 5th ECTI Northern Section conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2022

作者： Smunyahirun, Nathnaree Karnjana, Jessada Laitrakun, Seksan Nishio, Takayuki Deepaisarn, Somrudee Sirindhorn International Institute of Technology School of ICT Thailand NSTDA National Electronics and Computer Technology Center Thailand Tokyo Institute of Technology Department of Information and Communications Engineering Japan

ISBN: (纸本)9781665495103

this paper aims to extend the lifetime of polymer dielectric-based humidity sensors used in landslide monitoring systems by mathematically adjusting the sensor's drifting value as time passes. therefore, a strategy based on nested Kalman filters, cosine similarity, and Euclidean distance was proposed in this paper. An outer Kalman filter is used top redict humidity values, with the prediction based on an inner Kalman filter that fuses data from surrounding sensors. To adjust the process noise covariance of the nested Kalman filter, cosine similarity and Euclidean distance are used. When the sensor is in normal conditions, the process noise covariance remains constant;however, when the sensor is drifting, the process noise covariance changes depending on the angle and distance between the value from surrounding sensors and the drift. the proposed method could reduce the drifting value error by 14.85 percent, according to the experimental results. © 2022 ieee.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

UWSN: A Novel Artificial Intelligence (AI) enabled Scheme to Improve Security and Energy Efficiency over Underwater Wireless sensor Networks 5

UWSN: A Novel Artificial Intelligence (AI) enabled Scheme to...

引用

5th ieee international conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Bharathi, P. Shyamala Reddy, M. Jaya Bharatha Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350356236

Underwater Wireless sensor Networks (UWSNs) are critical for monitoring and managing marine environments, supporting applications in environmental science, defense, and resource exploration. this study presents an innovative AIenabled scheme for improving security and energy efficiency in Underwater Wireless sensor Networks (UWSNs). By incorporating artificial intelligence, the proposed AI-UWSN protocol dynamically adapts to environmental and network conditions, enhancing key performance metrics like energy consumption, packet delivery ratio (PDR), latency, and network lifetime. the AI-UWSN achieved an average energy consumption of 146J, which is 24% lower than conventional protocols, extending the network lifetime to 1067 hours, compared to 722 hours in existing methods. Additionally, the protocol's intelligent routing increased PDR to 89%, significantly reducing data loss, and maintained an average latency of 108ms, 15% lower than alternative protocols. these improvements result from AI-based routing and clustering strategies, which optimize data aggregation and power usage, extending the network's functionality even in high-density, high-traffic environments. © 2025 ieee.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Prevention and Retrieval of Children from Borewell using Arduino 5

Prevention and Retrieval of Children from Borewell using Ard...

引用

5th international conference on Inventive Computation Technologies (ICICT)

作者： Nair, Akhil U. Babu, R. Balakrishnan, M. Sekar, Dhanaraja S. Lakshmi, K. Sri Krishna Coll Technol Elect & Elect Engn Coimbatore Tamil Nadu India

ISBN: (数字)9781665408370

ISBN: (纸本)9781665408387;9781665408370

Recently, India has experienced a spate of accidents in which children have fallen into abandoned borewells that are left uncovered and get trapped. Abandoned boreholes are death traps for children and are responsible for the deaths of many children. therefore, this venture entails the usage of a sensor and a digital digicam to save the kid if they fall into the borewell. the sensor is positioned on the pinnacle of the borewell hollow. the kids are stopped from falling beneath the horizontal closure, which mechanically closes at an intensity of approximately 5 ft when the device acknowledges the kid. Additionally, this venture also entails the usage of a robot that has arm-like systems to deliver the kid from the hollow. According to the National Disaster Response Force, over 40 children have died by falling into borewells since 2009, and rescue operations failed at least 70 percent of the time. this project makes sure that the child is prevented from falling deep into the borewell holes.

关键词： Borewell Child rescue servo motors ultrasonic sensor

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Uneven Data in Industrial IoT Using a distributed Bias-Aware Adversarial Network 5

Deep Learning for Uneven Data in Industrial IoT Using a Dist...

引用

5th international conference on Inventive Research in computing Applications, ICIRCA 2023

作者： Gupta, Raj Kumar Naveena, N. Rao, B. Srinivasa Rs, Rajasree Sarkar, Swagata Kumar, Kallakunta Ravi Sardar Vallabhbhai Patel College Veer Kunwar Singh University Physics Department Bihar Ara Bhabua India Kongu Engineering College Computer Technology-UG Perundurai India Gokaraju Rangaraju Institute of Engineering & Technology Department of Computer Science and Engineering Hyderabad500090 India New Horizon College of Engineering Artificial Intelligence and Machine Learning Bangalore India Sri Sairam Engineering College Department of Artificial Intelligence and Data Science Sai Leo Nagar Chennai44 India Koneru Lakshmaiah Education Foundation Department of Ece AP Vaddeswaram India

ISBN: (纸本)9798350321425

In minority class and noisy data situations, supervised learning performs more favorably for the majority class but cannot generalize testing data. Performance in the aforementioned use cases might be improved with the help of neural-based data augmentation approaches for generating new data and deep convolutional models for classification. GANs (generative adversarial networks) have recently demonstrated impressive advancements in picture generation. To address the restrictions imposed by the distribution bias problem between the produced data and the unique data, and to provide a more vigorous data augmentation, the presented distribution bias aware collaborative GAN (DGAN) model for unbalanced deep learning in industrial IoT. By including an auxiliary classifier in the foundational GAN model, a comprehensive data augmentation system may be built. In particular, a provisional source of energy with random labels is envisioned and trained combatively with the classification model to appropriately augment the amount of data specimens in minority classes, and a mass fraction system is newly envisioned between two distinct feature extraction, allowing the cooperative adversarial training among some of the power source, voltage divider, and classification algorithm. the next step is to develop an augmentation approach for smart anomaly detection in class imbalance, which, by adjusting for dispersion bias using the properly balanced data, might significantly improve classification precision. Experiment assessments using real-world unbalanced datasets show the superior recital of the suggested model in addressing the distribution biased issue for multi-class classification in class imbalance for commercial IoT applications, as compared to five baseline techniques. © 2023 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

2022 ieee 5th international conference on Automation, Electronics and Electrical Engineering, AUTEEE 2022

2022 IEEE 5th International Conference on Automation, Electr...

引用

5th ieee international conference on Automation, Electronics and Electrical Engineering, AUTEEE 2022

ISBN: (纸本)9781665471978

the proceedings contain 209 papers. the topics discussed include: research on the fault diagnosis of pre-insertion resistor of AC filter circuit breakers;a new state estimation method for power cooling integrated energy system;longitudinal tracking control of autonomous vehicle based on improved model predictive control;energy dispatching strategy of remote islanded microgrid with energy storage vessel under emergency scenario;conventional detection methods for the combination of power lines and power towers;double-layer planning configuration with distributed PV power and energy storage system;evaluation method for insulation state of cable intermediate joint based on variable weight and set pair analysis;investigation on bandwidth enhancement in copper—carbon nanotube composite interconnects;research on human posture recognition system based on inertial sensor;research on driving technology of high-power motor for lunar soil drilling;coordinated planning model of charging station and rural multi-energy system considering traffic characteristics;optimal operation strategy of multi-energy microgrid considering orderly energy consumption;research on voltage and reactive power control strategy based on intelligent detection of abnormal data and coordinated control of dynamic reactive power;based on the wavelet transform and the half-wave Fourier transform study of intelligent decoupler algorithms;study of defense methods for additional generative adversarial networks;and an analytical model for frequency nadir prediction based on probabilistic production simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Control Method for a Novel One-Control-three Type of TSC for Power Distribution Network with distributed PV system 5

Design and Control Method for a Novel One-Control-Three Type...

引用

5th ieee international Electrical and Energy conference, CIEEC 2022

作者： Xiao, Feng Liu, Xinchao Zhu, Weixin Li, Guangyi Yang, Huanhong Jiao, Wei Shanghai Fengxian Gas Turbine Power Generation Co. Ltd Shanghai China Shanghai University of Electric Power Shanghai China

ISBN: (数字)9781665411042

ISBN: (纸本)9781665411042

Large fluctuations of power output of Photovoltaic(PV) system will cause the corresponding voltage fluctuations at Point of Common Coupling(PCC), which leads to frequent switching of reactive power compensation devices. Normally reactor with circuit breaker, thyrister Controlled Reactor(TCR) or Static Var Generator(SVG) are used for regulating over voltage caused by high PV power output, but with problems of high cost, high loss, complex control and poor reliability. the paper proposes a novel one-control-three type of thyrister Switched Capacitor (TSC) for compensating the grid connected distributed PV system, which coordinated with distribution transformer to improve voltage quality on PCC. the proposed type only use single thyrister to control three phase capacitors, the switching process is both simple and reliable. A simulation is conducted to show the effectiveness of proposed TSC by comparing it with conventional TSC and circuit breaker switched capacitor. Simulation results show that proposed TSC can effectively handle surge current, and the control method is simple and reliable. the total device cost is further lowered down comparing with existing devices without sacrificing switching performance, which shows high practicability in the circumstances of Var compensation of distributed PV systems. © 2022 ieee.

关键词： Electric circuit breakers

来源：评论

学校读者我要写书评

暂无评论

A surrogate-assisted point estimate method for hybrid probabilistic and interval power flow in distribution networks

引用

ENERGY REPORTS 2022年 8卷 713-721页

作者： Wang, Chenxu Peng, Yan Zhou, Yixi Ma, Junchao Lu, Chengyu Yang, Xiyun State Grid Zhejiang Elect Power Corp Elect Power Res Inst Hangzhou 310014 Peoples R China State Grid Hangzhou Elect Power Supply Co Hangzhou 310020 Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing 102206 Peoples R China

the uncertain power flow analysis is essential to assessing the operating states of distribution networks under various uncertainties. the power flow calculations considering the single uncertainty have been well developed. However, different types of uncertainties may coexist in power systems. In order to comprehensively assess the impacts of mixed uncertainties, this paper proposes a surrogate-assisted point estimate method to solve the hybrid probabilistic and interval power flow. By taking advantage of the point estimate method and high-fidelity surrogate model, the proposed method can accurately obtain the relevant results of power flow calculation with high efficiency. the numerical studies in ieee 33-bus and 141-bus systems verify the accuracy and efficiency of the proposed method by comparing it with other well-known methods. (C) 2022 the Author(s). Published by Elsevier Ltd.

关键词： Uncertain power flow Hybrid uncertainties distributed generators Point estimate method Surrogate model

来源：评论

学校读者我要写书评

暂无评论

Wireless sensor network for industrial monitoring and controlling 5

Wireless sensor network for industrial monitoring and contro...

引用

5th international conference on Intelligent computing and Control systems, ICICCS 2021

作者： Dharani, N. Krishnan, Kirupa Mohan, Komati Vishwa Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Electronics and Communication Chennai India

ISBN: (纸本)9781665412728

Wireless sensor network is used in various fields like automation in industries for monitoring and control of the industrial plants. Wireless sensor network is used wirelessly transmit the information from various analog sensors. Adopting wireless sensor network for monitoring the industrial activities controlling provides greater advantages over the traditional wired systems regarding cost reduction bought by elimination of wiring and increased productivity. the data collected from the sensor nodes can be secured using Advanced Encryption Scheme algorithm. this algorithm is highly efficient because it provides high performance, low cost, low power consumption, maximum throughput. this is highly secure because it uses 256 bit key for encryption and decryption. © 2021 ieee.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

SpecTextor: End-to-End Attention-based Mechanism for Dense Text Generation in Sports Journalism 8

SpecTextor: End-to-End Attention-based Mechanism for Dense T...

引用

8th ieee international conference on Smart computing (SMARTCOMP)

作者： Ghosh, Indrajeet Ivler, Matthew Ramamurthy, Sreenivasan Ramasamy Roy, Nirmalya Univ Maryland Baltimore Cty Mobile Pervas & Sensor Comp Lab Baltimore MD 21228 USA Univ Maryland Baltimore Cty Ctr Real Time Distributed Sensing & Auton Cards Baltimore MD 21228 USA Univ Maryland Baltimore Cty Dept Informat Syst Baltimore MD 21228 USA Pomona Coll Dept Comp Sci Claremont CA 91711 USA

ISBN: (纸本)9781665481526

Language-guided smart systems can help to design next-generation human-machine interactive applications. the dense text description is one of the research areas where systems learn the semantic knowledge and visual features of each video frame and map them to describe the video's most relevant subjects and events. In this paper, we consider untrimmed sports videos as our case study. Generating dense descriptions in the sports domain to supplement journalistic works without relying on commentators and experts requires more investigation. Motivated by this, we propose an end-to-end automated text-generator, SpecTextor, that learns the semantic features from untrimmed videos of sports games and generates associated descriptive texts. the proposed approach considers the video as a sequence of frames and sequentially generates words. After splitting videos into frames, we use a pre-trained VGG-16 model for feature extraction and encoding the video frames. With these encoded frames, we posit a Long Short-Term Memory (LSTM) based attention-decoder pipeline that leverages soft-attention mechanism to map the semantic features with relevant textual descriptions to generate the explanation of the game. Because developing a comprehensive description of the game warrants training on a set of dense time-stamped captions, we leverage two available public datasets: ActivityNet Captions and Microsoft Video Description. In addition, we utilized two different decoding algorithms: beam search and greedy search and computed two evaluation metrics: BLEU and METEOR scores.

关键词： Sports Journalism Semantic Knowledge LSTM Soft-Attention Mechanism Beam Search Greedy Search Human-Machine Interactive Applications

来源：评论

学校读者我要写书评

暂无评论

New Attacks on Cloud Container-Based IoT systems in 5G-Advanced and Beyond 9

New Attacks on Cloud Container-Based IoT Systems in 5G-Advan...

引用

9th ieee international conference on Electronics, computing and Communication Technologies, CONECCT 2023

作者： Pimpalkar, Yogita Ravindran, Sharvari Bapat, Jyotsna Das, Debabrata Networking and Communication Research Lab International Institute of Information Technology Electronics City Bangalore560 100 India

ISBN: (纸本)9798350334395

the Internet of things (IoT) devices generate a large amount of data that get processed in the cloud. Typically, different IoT devices will be allocated to the same Fifth Generation (5G) mobile network slice, on which the IoT services will be using different containers. While cloud containers can offer many benefits, they also introduce new security risks from co-resident containers that can be particularly problematic for IoT devices. the need for long-lasting batteries is essential for the success of wireless-connected IoT devices, particularly in applications where regular battery replacement is impractical or impossible. Energy Depletion Attacks (EDA) can drastically reduce the lifespan of IoT sensor device batteries, whereas Synergistic Power Attacks (SPA) can cause power outages in data centers and disrupt critical services. Although EDA and SPA have been studied in the literature, the IoT cloud information leakages with the advent of network slicing concepts in 5G and 6G leading to these attacks have not been addressed yet. this paper presents comprehensive studies of 5G-Advanced IoT cloud framework and related attacks. It reveals novel systematic methods through which powerful stealth Cloud Container-Based EDA (CC-EDA) and Cloud Container-Based SPA (CC-SPA) can be launched. these attacks are difficult to detect as the attacker impersonates a valid IoT management system and manipulates the system's behavior. With a quantitative assessment of the performance of a battery under attack, this paper additionally shows that an aggressive CC-EDA will be deeply damaging and can bring down the entire IoT network within a day. Possible mitigation strategies to address the security concerns associated with IoT cloud-based attacks are proposed. © 2023 ieee.

关键词： Internet of things

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：