检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yao, Shanle Pazho, Armin Danesh Ardabili, Babak Rahimi Noghre, Ghazal Alinezhad Neff, Christopher Tabkhi, Hamed Electrical and Computer Engineering Department The University of North Carolina at Charlotte Charlotte United States Public Policy The University of North Carolina at Charlotte Charlotte United States

Smart Video surveillance systems have become important recently for ensuring public safety and security, especially in smart cities. However, applying real-time artificial intelligence technologies combined with low-latency notification and alarming has made deploying these systems quite challenging. This paper presents a case study for designing and deploying smart video surveillance systems based on a real-world testbed at a community college. We primarily focus on a smart camera-based system that can identify suspicious/abnormal activities and alert the stakeholders and residents immediately. The paper highlights and addresses different algorithmic and system design challenges to guarantee real-time high-accuracy video analytics processing in the testbed. It also presents an example of cloud system infrastructure and a mobile application for real-time notification to keep students, faculty/staff, and responsible security personnel in the loop. At the same time, it covers the design decision to maintain communities’ privacy and ethical requirements as well as hardware configuration and setups. We evaluate the system’s performance using throughput and end-to-end latency. The experiment results show that, on average, our system’s end-to-end latency to notify the end users in case of detecting suspicious objects is 5.3, 5.78, and 11.11 seconds when running 1, 4, and 8 cameras, respectively. On the other hand, in case of detecting anomalous behaviors, the system could notify the end users with 7.3, 7.63, and 20.78 seconds average latency. These results demonstrate that the system effectively detects and notifies abnormal behaviors and suspicious objects to the end users within a reasonable period. The system can run eight cameras simultaneously at a 32.41 Frame Per Second (FPS) rate. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Flow Table Modification Using Behavioral-Based Fingerprinting Technique to Facilitate Zero Trust Identity Management and Access Control

Flow Table Modification Using Behavioral-Based Fingerprintin...

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Vinton Morris Kevin Kornegay Cybersecurity Assurance and Policy Center Morgan State University Baltimore MD Department of Electrical and Computer Engineering Morgan State University Baltimore MD

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

Traditional security mechanisms and architectures are falling short, impacting both organizations and end users alike. The rapid growth and variety of Internet of Things (IoT) devices have significantly expanded the attack surface and increased network vulnerabilities. In recent years, Zero Trust (ZT) has gained traction in its attempt to solve the inherent flaws of the traditional perimeter-centric security architecture. While there have been great strides in supporting users, applications, and general-purpose computing devices (GPD), current ZT architectures lack the necessary capabilities to support IoT devices. In this paper, we present a method of authentication that profiles the network traffic and builds unique fingerprints for IoT devices. The fingerprints are a representation of the behavior of the IoT devices. We then compare the on-demand generated fingerprints of a device attempting to communicate to those in the database and update the flow tables of a software-defined networking (SDN) switch, accordingly ensuring that only devices with matching profiles can communicate on the network. We argue that the predictive nature of IoT device traffic and their limited protocol set make them a candidate for this method of authentication and access control that can satisfies the Zero Trust Architecture's identity management component.

关键词： Access control Authentication computer architecture Telecommunication traffic Switches Fingerprint recognition Web servers Zero Trust Internet of Things Identity management systems

来源：评论

学校读者我要写书评

暂无评论

Assumed Identities: Quantifying Gender Bias in Machine Translation of Ambiguous Occupational Terms

arXiv

引用

arXiv 2025年

作者： Mastromichalakis, Orfeas Menis Filandrianos, Giorgos Symeonaki, Maria Stamou, Giorgos School of Electrical and Computer Engineering National Technical University of Athens Greece Department of Social Policy Panteion University of Social and Political Sciences Greece

Machine Translation (MT) systems frequently encounter ambiguous scenarios where they must assign gender to certain occupations when translating without explicit guidance or contextual cues. While individual translations in such cases may not be inherently biased, systematic patterns—such as the repeated association of certain professions with specific genders—can emerge, reflecting and perpetuating societal stereotypes. This ambiguity challenges traditional instance-level single-answer evaluation approaches, as no single gold standard translation exists. To address this, we propose an approach that evaluates gender bias through aggregated model responses. Specifically, we introduce a methodology to detect gender imbalances between source texts and translations, a benchmarking dataset with ambiguous English inputs, and probability-based metrics to quantify a model’s divergence from normative standards or reference distributions. © 2025, CC BY-NC-ND.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

CHARLIE: A Chatbot That Recommends Daily Fitness and Diet Plans

CHARLIE: A Chatbot That Recommends Daily Fitness and Diet Pl...

引用

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Chowdhury, Deepanjali Roy, Ahana Ramamurthy, Sreenivasan Ramasamy Roy, Nirmalya Texas A&m University Department of Electrical and Computer Engineering College Station United States Howard County Public School System MD United States Bowie State University Department of Computer Science Bowie United States University of Maryland Baltimore County Department of Information Systems Baltimore United States

ISBN: (纸本)9781665453813

Managing a work-life balance has always been challenging, especially after the recent trend of working from home, which has made maintaining one's fitness and diet regime strenuous. Failing to adhere to a fitness and diet plan has been shown to cause long-term effects on a person's health including obesity and shortened lifespans. Currently, people plan their fitness and diet plans around their schedule, but these tasks are challenging to maintain. Users tend to give up these plans due to a lack of time and planning. To help with better planning for a fitness and diet regime, we propose, CHARLIE, a chatbot that works around a user's schedule to intelligently recommend diets and fitness goals based on their calendar. CHARLIE is a recommendation system that suggests the users' a certain meal and fitness activities based on the amount of time they have left in their day and the number of calories they lose. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Keep it Local: Comparing Domain-Specific LLMs in Native and Machine Translated Text using Parallel Corpora on Political Conflict 2

Keep it Local: Comparing Domain-Specific LLMs in Native and ...

引用

2nd International Conference on Foundation and Large Language Models, FLLM 2024

作者： Osorio, Javier Alsarra, Sultan Converse, Amber Alshammari, Afraa Heintze, Dagmar Khan, Latifur Alatrush, Naif Brandt, Patrick T. D'orazio, Vito Zawad, Niamat Billah, Mahrusa University of Arizona School of Government and Public Policy Tucson United States King Saud University Department of Software Engineering Riyadh Saudi Arabia University of Arizona Department of Linguistics Tucson United States University of Texas - Dallas Department of Computer Science Dallas United States University of Texas - Dallas School of Economic Political and Policy Sciences Dallas United States West Virginia University Department of Political Science Morgantown United States

ISBN: (纸本)9798350354799

The dynamics of political conflict and cooperation require powerful computerized tools capable of effectively tracking security threats and cooperation around the world. This study compares the performance of domain-specific Large Language Models (LLMs) against generically-trained LLMs in binary and multi-class classification using native text in English, Spanish, and Arabic, and their corresponding machine translations. This endeavor yields four key contributions. 1) We present and make available a novel database of annotations using a multi-lingual parallel corpus from the United Nations. 2) Using various metrics, we assess the quality of different machine translation tools. 3) Our results indicate that the ConfliBERT family of LLMs, a set of domain-specific models tailored for political conflict, outperform generically-trained LLMs in English, Spanish, and Arabic in both binary and multi-class tasks. 4) We also disentangle the heterogeneous effects of machine translation on LLM performance in different languages. Overall, results reveal the comparative advantage of native-language domain-specific LLMs specialized on political conflict to understand the dynamics of violence and cooperation worldwide using native text. Our multi-lingual ConfliBERT LLMs provide critical cyber-infrastructure enabling scholars and government agencies use their local languages and information to foster safer, more stable political environments. © 2024 IEEE.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Convolutional Bi-GRU-based prediction model for Climate Indicators

Convolutional Bi-GRU-based prediction model for Climate Indi...

引用

7th International Conference on Electronics Technology, ICET 2024

作者： Lo, Tsung-Ming Zhang, Hong-Tao He, Yun-Bing Liu, Yi-Zhi Zhang, Wan-Ying Liang, Qiong-Dan Bei, Zhen Dongguan University of Technology Guangdong-Taiwan College of Industrial Science & Technology Dongguan China Guangxi Vocational and Technical College of Communications School of Traffic Information Engineering Nanning China Nanfang College Guangzhou Department of Public administration Guangzhou China Nanfang College-Guangzhou School of Electrical and Computer Engineering Guangzhou China Dongguan University of Technology Intelligent Manufacturing Engineering Dongguan China

ISBN: (纸本)9798350363951

Climate prediction is critical to a wide range of fields, from agriculture to public health, but traditional methods face challenges due to the complexity and time-space characteristics of climate data. Machine learning techniques provide a promising solution by effectively extracting features from climate indicator data. In this study, we propose a new method for predicting climate indicators by combining CNN-Bi-GRU models with FNN networks. Through evaluation, our method demonstrates excellent prediction performance in terms of RMSE and MAE on both test and training sets, and robust convergence behavior is observed in model training. In addition, our method achieves high accuracy in predicting key climate metrics such as temperature and rain frequency, providing valuable information for understanding climate dynamics. Comparison experiments with LSTM-FNN, Double-LSTM, BiLSTM, and Bi-GRU models highlight the superiority of the CNNBi-GRU approach, especially in reducing temperature prediction errors. In conclusion, this study presents a promising approach to climate prediction that can enhance our understanding of climate variability and support informed decision making in various industries. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Equitable Regional Load Curtailment Framework Considering Community Fairness and Line Congestion

Equitable Regional Load Curtailment Framework Considering Co...

引用

Grid Edge Technologies Conference & Exposition (Grid Edge), IEEE PES

作者： Nirasha Bataduvaarachchi Demy Alexander Adithya Melagoda Arun Manoharan Visvakumar Aravinthan Al Tamimi Department of Electrical and Computer Engineering Wichita State University Wichita Kansas USA Transmission Planning & Policy Sunflower Electric Corporation Wichita Kansas USA

ISBN: (数字)9798350352528

ISBN: (纸本)9798350352535

High impact low frequency events could lead to longlasting power outages and catastrophic grid failures. To limit the impact of such events, as the last resort, system operators might enforce emergency load curtailment. This emergency curtailment focusses mainly on system level load serving capacity i.e., necessary generation with reserve margin. As such the existing load curtailment policies employed by regional transmission operators have been identified to have key limitations as they do not take consumer fairness and system operational reliability impacts into consideration. This work proposes a two-stage framework that considers system operability and customer fairness in the computation of transmission node level load curtailment. In the first stage, the required system level load curtailment is allocated to each node through fairness-based load curtailment share ratio that considers the node level loading, impact to node voltage and equity. The second stage focuses on operational reliability of the curtailment share from stage 1 by reallocating to resolve any line loading violation. The effectiveness of the proposed framework is evaluated using the IEEE RTS 96 test system. The results highlight the importance of factoring both system operational impacts and consumer fairness in formulating emergency load curtailment policies.

关键词： Loading Load shedding Power system reliability Reliability Resource management Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Framework for Smart City Implementation using IoT-Cloud Based System Architecture 2

A Framework for Smart City Implementation using IoT-Cloud Ba...

引用

2nd IEEE International Conference on Distributed Computing and electrical Circuits and Electronics, ICDCECE 2023

作者： Dankan Gowda, V. Prasad, K.D.V. De, Tanmoy Srinivas, Ved Anil Kumar, N. Tejpal Moharekar, Tejashree Bms Institute of Technology and Management Department of Electronics and Communication Engineering Bangalore India Hyderabad India Symbiosis Institute of Business Management Hyderabad Pune India Public Policy Thiagarajar School of Management Madurai India School of Engineering and Technology Department of Electronics and Communication Engneering Tirupati India Yashwantrao Chavan School of Rural Development Shivaji University Computer Department Maharashtra Kolhapur India

ISBN: (纸本)9798350347456

The Internet, a key participant (world wide web) in worldwide information exchange and media sharing, has experienced cumulative upgrades, developments, and given up consequent product IOT, making technology affordable and practical for all uses. Research development includes smart sensors, a communication channel and protocols for exchanging data, and peripherals like an Arduino, a Texas Instruments MSP430G2553, a Weather-proof Tx. Rx. Kit (for exchanging data), a Data Receptor and Decoder Shield for Lab View Kit (for exchanging data), an addressing and de-addressing data module, a communication shield, etc. It is now possible to communicate from a desktop computer or an Android smartphone to a portable device that has an embedded device, such as a microcontroller, a microprocessor, or a sensor. In other words, IOT combines always-on networking, always-on computation, and always-on intelligence. The Internet of Things facilitates communication between the central hub (fitted with a Lab-View interface) and the distributed modules (found in places like parks, subways, and highways) that control the lights. The Internet of Things is also useful for keeping the overall cost of setup and maintenance within reasonable economic bounds. The planned development takes into account IoT on two main scales: city-wide automation (also known as smart city) and home-level automation (also known as covering up). © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Peer-to-Peer (P2P) Electricity Markets for Low Voltage Networks

Peer-to-Peer (P2P) Electricity Markets for Low Voltage Netwo...

引用

IEEE International Conference on Smart Grid Communications (SmartGridComm)

作者： Diana Vieira Fernandes Nicolas Christin Soummya Kar Dept. of Engineering & Public Policy Carnegie Mellon University USA IN+/LARSyS Instituto Superior Técnico Universidade de Lisboa Portugal Dept. of Electrical & Computer Engineering Carnegie Mellon University USA

ISBN: (数字)9798350318555

ISBN: (纸本)9798350318562

We develop a clearance and settlement model for Peer-to-Peer (P2P) energy trading in low-voltage networks. The model enables direct transactions between parties within an open and distributed system and integrates unused capacity while respecting network constraints. We evaluate the model through simulations of different scenarios (normal operating conditions and extreme conditions) for 24-hour time blocks. Our simulations highlight the benefits of our model in a decentralized energy system, notably its ability to deal with high-trade volumes.

关键词： Low voltage Adaptation models Schedules Renewable energy sources Electricity Peer-to-peer computing Smart grids Resource management Solar power generation Load modeling

来源：评论

学校读者我要写书评

暂无评论

PAIR: Prompt-Aware margIn Ranking for Counselor Reflection Scoring in Motivational Interviewing

PAIR: Prompt-Aware margIn Ranking for Counselor Reflection S...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Min, Do June Pérez-Rosas, Verónica Resnicow, Kenneth Mihalcea, Rada Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States School of Public Health University of Michigan Ann ArborMI United States

Reflections are a core verbal skill used by mental health counselors to express understanding and acknowledgement of the client's experience and concerns. In this paper, we propose a system for the automatic evaluation of counselor reflections. Specifically, our system takes as input one dialog turn containing a client prompt likely leading to a reflection and a counselor response to it, and outputs a numeric score indicating the quality of the reflection made by the counselor. We compile a dataset consisting of reflections portraying different levels of reflective listening skills, and propose Prompt-Aware margIn Ranking (PAIR), a novel framework for reflection scoring that contrasts positive and negative prompt and response pairs using adhoc multi-gap and prompt-aware margin ranking losses. Through empirical evaluations and deployment of our system in a real-life educational environment, we show that our scoring model outperforms several baselines on different metrics, and can be used to provide useful feedback to counseling trainees. © 2022 Association for Computational Linguistics.

关键词：

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：