检索结果-内蒙古大学图书馆

Delhi Section Conference (DELCON), IEEE

作者： Ahmad Zia Sharifi Md. Abul Ala Walid Mohammad Dawood Momand Ihsan Ul Haq Safi Hamidullah Khanzai Safi Sadia Hossain Department of Networking and Communication Faculty of Computer Science Nangarhar University Afghanistan Department of Data Science and Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur Bangladesh Lautsprecher Teufel GMbH Berlin Germany Department of Internet of Things and Robotics Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur Bangladesh

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Modern organizations face rising levels of cyber risks, making cybersecurity a top priority for safeguarding sensitive data and maintaining operational continuity. Recent studies find human factors as the most critical contributors to cyber risks. These human-related risks include user misuse, user mistakes, and user malice. A large proportion of cyber risks arise when hackers use social engineering or phishing techniques to manipulate employees into disclosing confidential information. While some employees knowingly engage in these actions, some incidents occur accidentally due to a lack of awareness about cybersecurity protocols. As a result, governments around the world are enacting data protection legislation aimed at enhancing employees' cyber risk. This study explores the perception of US employees on the effectiveness of data protection legislation in countering cyber threats. It surveyed 30 randomly selected employees from various industries. The results showed that employees perceive data protection legislation as effective in mitigating employeerelated cyber risks.

关键词： Industries Protocols computer hacking Phishing Legislation Data protection Human factors computer crime Faces

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Semi-Steering and IoT Systems for Electric Mobility Systems

Design and Development of Semi-Steering and IoT Systems for ...

引用

Novel Intelligent and Leading Emerging sciences Conference (NILES)

作者： Shady R. Abdelmalek Ma Althea F. B. Retig Fakeha S. Ansari Mennatallah A. Gomaa Amr Alaaeldin Sahar S. Kaddah Basem M. Badr Robotics Department Faculty of Engineering University of Genoa Italy Computer Science Department Faculty of Engineering & IT The British University in Dubai United Arab Emirates Renewable and Sustainable Energy Department Mansoura University Mansoura Egypt Electrical Power Department Faculty of Engineering Mansoura University Mansoura Egypt Electrical Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Lotus Power Vancouver British Columbia Canada

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

Connecting electric mobility (E-Mobility) systems with Internet of Things (IoT) technology is a crucial strategy for modern transportation and driving assistance systems. IoT and Advanced Driver Assistance Systems (ADAS) applications in the field are examined in this research. Different techniques are designed and developed for ADAS functionality, such as lane and object detection via image and video segmentations. Multiple lane detection models are developed and tested, each of which is then deployed on AWS (Amazon Web Services) cloud and optimized using OpenVINO to speed up inference. Furthermore, telemetry data from various embedded devices are transmitted to AWS IoT core and presented on an easy-to-use web application. This paper shows how deploying systems on cloud platforms like AWS improves scalability and operational efficiency. It also highlights how IoT and cloud technologies may improve the performance of E-Mobility systems and offers a strong foundation for further advancements in the ADAS area.

关键词： Cloud computing Web services Scalability Transportation Machine learning Object detection Streaming media Real-time systems Internet of Things Telemetry

来源：评论

学校读者我要写书评

暂无评论

Machine Learning In Sustainable Development–An Overview

Machine Learning In Sustainable Development–An Overview

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Chadi Altrjman Richa Gupta Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Turkey Faculty of Engineering University of Kyrenia Kyrenia Turkey Waterloo University Canada Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

I have studied how artificial intelligence (AI) or machine learning (ML) is applied in a sustainable system called "Eugenie" for my work, project, and thesis. In this project, I get to discuss Eugenie’s role in ensuring the sustainability of large environmental business organizations. I also get to discuss how it aids operation managers in making predictions about when their machines will break down days, weeks, and months in advance, allowing them to schedule maintenance cycles more effectively. In other words, Eugenie provides plant operators with data so they can prioritize repairs. Eugenie executes this process by utilizing real-time data from numerous sensors attached to large machinery and equipment in the process industry, metals and mining, oil and gas, and smart cities industries. Two products make up this program; the first is named RAY-FINN and the second is called PAPILLON. Eugenie assists businesses in a variety of ways, including:•Aids in the attainment of operational excellence by process organizations•Always raise overall profitability.•Contributes to a greener and safer future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Portable Baby Incubator Monitoring using Smartphone

Portable Baby Incubator Monitoring using Smartphone

引用

International Conference on Electrical, Telecommunication and computer Engineering (ELTICOM)

作者： Nur Sultan Salahuddin Sri Poernomo Sari Nora Trisna Tumewa Aqilla Rahman Musyaffa Arif Wijaya Ema Herawati Satrio Dwi Yudhanto Ambariani Pujiati Faculty of Computer Science and Information Technology Gunadarma University Jakarta Indonesia Faculty of Industrial Technology Gunadarma University Jakarta Indonesia Multimedia And Robotics Laboratory Gunadarma University Depok Indonesia Industrial Automation Laboratory Gunadarma University Depok Indonesia Faculty of Health Sciences and Pharmacy Gunadarma University Depok Indonesia

Most neonatal deaths occur at the age of 0-6 days (78.5%) and prematurity is one of the main causes of infant death in Indonesia, ranking fifth in the number of premature births. A baby incubator is very necessary to help premature babies adapt to their new environment. An incubator is a health care tool for critical/premature neonates that provides warmth and humidity according to the needs of newborns under controlled conditions. A portable baby incubator monitoring system using wifi as a communication medium to monitor babies, equipped with a DS18B20 sensor to measure the baby’s body temperature, an AD8232 sensor to measure the baby’s heartbeat and an ESP32 Cam to capture the baby’s face has been created. The test results showed that this incubator was able to detect the baby’s body temperature, the baby’s heartbeat and take the baby’s face remotely using an Android-based smartphone, weighs around 5.8 kg, has a simple design, can be carried around making it easier for medical personnel to carry out supervision premature baby.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social engineering attack types and prevention techniques- A survey

Social engineering attack types and prevention techniques- A...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Shruti Bhatla Satya Prakash Yadav Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Turkey Research Center for AI and IoT Faculty of Engineering University of Kyrenia Kyrenia Turkey Department of Computer Science and Engineering Graphic Era Hill University Dehradun Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) Greater Noida India

The term "Cyber Security" is getting more and more popular and important over the last few years. Since computers and most of the devices are connected to the internet, they are likely to be hacked by the hackers. In the past, this issue was not a big problem, because not every device is required to be connected to the internet or the internet was not popular as today. But the case has changed over the years. All the changes in the technology area also changed the cyber-attack models as well. With the development of technology and the change of usage of the internet over the last years cyber-attacks have become more common and popular by the hackers. Hackers have discovered that they have an opportunity to steal or earn money in a short time without having to spend too much effort. These days, the type of cyber-attacks is not the same as the ones in the past. As time passes, the cyber-attack methods are also changing and evolving. Today, hackers are using more advanced and effective cyber-attack methods compared to past years. There are many methods that are impossible to cover all of them in this article. Our main focus will be on social engineering attacks in this article. Social engineering attacks use different approaches to cyber attacking. Unlike trying to explode a victim’s social media password etc. using advanced exporting programs, algorithms or techniques, social engineering attacks focus on fooling victims into providing their data to hackers by themselves without using or implementing any password cracking, exploiting techniques etc. We will go over what social media engineering is, type of social engineering methods, what countermeasures can be used to protect from social engineering and more in this article.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of LLM-based Chatbots for Task Scheduling in Robot Operations

Exploring the Potential of LLM-based Chatbots for Task Sched...

引用

IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

作者： Catarina Rema Armando Sousa Heber Sobreira Pedro Costa Manuel F. Silva CRIIS - Centre for Robotics in Industry and Intelligent Systems INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Faculty of Engineering University of Porto (FEUP) Porto Portugal ISEP Polytechnic of Porto rua Dr. António Bernardino de Almeida Porto Portugal

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

The rise of Industry 4.0 has revolutionized manufacturing by integrating real-time data analysis, artificial intelligence (AI), automation, and interconnected systems, enabling adaptive and resilient smart factories. Autonomous Mobile Robots (AMRs), with their advanced mobility and navigation capabilities, are a pillar of this transformation. However, their deployment in job shop environments adds complexity to the already challenging Job Shop Scheduling Problem (JSSP), expanding it to include task allocation, robot scheduling, and travel time optimization, creating a multi-faceted, non-deterministic polynomial-time hardness (NP-hard) problem. Traditional approaches such as heuristics, meta-heuristics, and mixed integer linear programming (MILP) are commonly used. Recent AI advancements, particularly large language models (LLM), have shown potential in addressing these scheduling challenges due to significant improvements in reasoning and decision-making from textual data. This paper examines the application of LLM to tackle scheduling complexities in smart job shops with mobile robots. Guided by tailored prompts inserted manually, LLM are employed to generate scheduling solutions, being these compared to an heuristic-based method. The results indicate that LLM currently have limitations in solving complex combinatorial problems, such as task scheduling with mobile robots. Due to issues with consistency and repeatability, they are not yet reliable enough for practical implementation in industrial environments. However, they offer a promising foundation for augmenting traditional approaches in the future.

关键词： Job shop scheduling Service robots Large language models Chatbots Real-time systems Mobile robots Resource management Reliability Autonomous robots Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

An Efficient USE-Net Deep Learning Model for Cancer Detection

引用

International Journal of Intelligent Systems 2023年第1期2023卷

作者： Almutairi, Saad M. Manimurugan, S. Aborokbah, Majed M. Narmatha, C. Ganesan, Subramaniam Karthikeyan, P. Industrial Innovation & Robotics Center Faculty of Computers and Information Technology University of Tabuk Tabuk71491 Saudi Arabia Department of Electrical and Computer Engineering Oakland University Rochester112345 United States Department of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan

Breast cancer (BrCa) is the most common disease in women worldwide. Classifying the BrCa image is extremely important for fnding BrCa at an earlier stage and monitoring BrCa during treatment. Te computer-aided detection methods have been used to interpret BrCa and improve the detection of BrCa during the screening and treatment stages. However, if a new BrCa image is generated for the treatment, it will not classify correctly. Te main objective of this research is to classify the BrCa images for newly generated images. Te model performs preprocessing, segmentation, feature extraction, and classifcation. In preprocessing, a hybrid median fltering (HMF) is used to eliminate the noise in the images. Te contrast of the images is enhanced using quadrant dynamic histogram equalization (QDHE). Ten, ROI segmentation is performed using the USE-Net deep learning model. Te CafeNet model is used for feature extraction on the segmented images, and fnally, classifcation is made using the improved random forest (IRF) with extreme gradient boosting (XGB). Te model obtained 97.87% accuracy, 98.45% sensitivity, 95.24% specifcity, 98.96% precision, and 98.70% f1-score for ultrasound images. Te model gives 98.31% accuracy, 99.29% sensitivity, 90.20% specifcity, 98.82% precision, and 99.05% f1-score for mammogram images. © 2023 John Wiley and Sons Ltd. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DEdgeNet: Extrinsic Calibration of Camera and LiDAR with Depth-discontinuous Edges

DEdgeNet: Extrinsic Calibration of Camera and LiDAR with Dep...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yiyang Hu Hui Ma Leiping Jie Hui Zhang Faculty of Science and Technology United International College BNU-HKBU Zhuhai China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Department of Computer Science Hong Kong Baptist University Hong Kong China

This paper addresses the problem of calibrating extrinsic parameter matrix between an RGB camera and a LiDAR. Multimodal sensing systems are essential for fully autonomous navigation platforms. A key pre-requisite for such a system is calibration between different sensors. As the two most widely equipped sensors, calibration between RGB cameras and LiDARs remains challenging. Existing methods address this problem without using explicit geometric priors. In this paper, we propose a novel real-time network that utilizes depth-discontinuous edges extracted from a single image to calibrate cameras and LiDARs. Our network consists of two key components: (1) a self-supervised edge extraction network named DEdgeNet, which detects depth-discontinuous edges from a single image and extracts corresponding features; (2) prediction of the extrinsic parameter matrix between the camera and the LiDAR by matching fixed features in RGB images and updating depth features in a coarse-to-fine frame. Specifically, considering that edges are rich and common in natural scenes, DEdgeNet simplifies RGB image encoding and extracts fixed edges for feature matching. We conducted extensive experiments on the KITTI-odometry dataset. The results show that our method achieves an average rotation error of 0.028° and an average translation error of 0.247 cm, which demonstrates the superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Bottom-Up Semi-Supervised Learning Framework for Salient Object Detection 11

A Novel Bottom-Up Semi-Supervised Learning Framework for Sal...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Pang, Yu Wu, Hao Wu, Yunhe Wu, Chengdong Zhou, Wei Yu, Xiaosheng Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China Australian Centre for Field Robotics University of Sydney Sydney Australia College of Information Science and Engineering Northeastern University Shenyang110819 China College of Computer Science Shenyang Aerospace University Shenyang110136 China

ISBN: (纸本)9781665425278

Salient object detection, which aims at locating the most important object in a scene (or image), has been extensively studied in various tasks, such as robot vision. In this paper, we present an effective salient object detection framework based on a novel bottom-up semi-supervised learning algorithm, which obviously outperforms the existing works in complex scenes. Given an input image, it is firstly segmented into a fixed number of non-overlapping image patches as basic units. A novel segmentation-based sampling method is developed to select a subset of all image patches as training samples. Then, all samples are divided into labeled and unlabeled groups based on multiple prior cues. The labels of all the unlabeled data are inferred by a novel label propagation mechanism. As a result, a complete training set can be obtained and used to train a classifier to classify all image patches into salient object and background. In addition, we also use neighbor-constraint smoothness function to further boost the saliency map. We compare the proposed method with the state-of-the-art approaches on two datasets. Experimental results demonstrate the effectiveness and superiority of the proposed method. © 2021 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Safety System for Industrial Robots Based on Human Detection Using an RGB-D Camera

Safety System for Industrial Robots Based on Human Detection...

引用

Proceedings of the International Convention MIPRO

作者： Valentin Šimundić Dario Mihelčić Damian Svirac Petra Đurović Robert Cupec Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia Chair of Automation and Robotics

A robotic system, in general, should be safe for the operators who are using it and, if possible, it should be safe for the system itself and the environment it interacts with. This paper investigates three methods for human detection by an RGB-D camera and their adjustments for monitored robot movement. The methods are implemented in ROS and integrated into a robotic system consisting of an industrial robot arm ABB IRB-2400L and an RGB-D camera. Validation and comparison of the implemented algorithms was performed on the recorded video dataset containing people in the robot working area with per-frame annotations of human presence, velocity and proximity to the robot. The algorithms detect humans with highest recall of 98%.

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：