检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Rampriya, R.S. Sabarinathan Suganya, R. Prathiba, Sahaya Beni Perumal, P. Shunmuga Wang, Wei School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamilnadu Vellore632014 India Couger Inc Tokyo Japan School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Chennai600127 India Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518172 China School of Medical Technology Beijing Institute of Technology Beijing100081 China

Derailments significantly harm railroads in terms of severity and fatality rates. Manual monitoring railway tracks is a tedious and often insufficient task to prevent derailment accidents. This necessitates the development of an automated monitoring system to oversee the condition of railway tracks. In the foreseeable future, Unmanned Aerial Vehicle (UAV), artificial intelligence, and computer vision will play a crucial role in periodically assessing the railway environment to ensure passenger safety. This paper proposes a lightweight and efficient railroad semantic segmentation network (Lite-RSNet), which segments real-time aerial railroad images into rails, gauges, and backgrounds. The segmented regions then compute the distance between rails and obstacles, identifying potential derailment hazards in railroad application. Lite-RSNet incorporates a multi-level feature fusion framework that includes a residual layer, a multi-head attention layer, a Concurrent Spatial and Channel Squeeze Excitation (CSSE) block, and a Convolution Block Attention Module (CBAM). Furthermore, this work supports onboard processing by reducing the number of parameters and minimizing storage footprint. The effectiveness of the proposed model is evaluated using the self-built dataset called Rail Segmentation Dataset (RSD), comprising low-altitude, high-resolution aerial railroad images from India. Lite-RSNet demonstrates superior performance compared to existing state-of-the-art methods, with 6M parameters, achieving a Dice Coefficient (DC) of 0.971 and a Jaccard Index (JI) of 0.947 on test data. © 2024, The Authors. All rights reserved.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

IoT based Smart Cradle for Neonatal Monitoring 6

IoT based Smart Cradle for Neonatal Monitoring

引用

6th International Conference on Electronics, Communication and Aerospace technology, ICECA 2022

作者： Sonia, R. Jayadeva, Sujay Mugaloremutt Ragavendiran, S.D. Prabu Revathi, N. Arumugam, Jeevanantham Kumar, S Sandeep B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Tamil Nadu Vandalur600048 India Jss Academy of Higher Education and Research Department of Health System Management Studies Karnataka Mysuru570004 India Rvs Technical Campus Department of Computer Science and Engineering Tamil Nadu Coimbatore641402 India Panimalar Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai600123 India Kongu Engineering College Department of Information Technology Tamil Nadu Perundurai638060 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522502 India

ISBN: (纸本)9781665482714

India has the highest percentage of working women and mothers. It also has a record for the highest number of babies being born every single day. These two statements highly contradict each other. When a woman gives birth to a baby, she needs to spend almost a year or two taking care of the necessities of the baby. But when a need to leave the baby for a certain time arises regularly, it becomes tougher for them to do so. This study provides a solution to this problem. This research aims at the construction of a smart cradle. This cradle is des igned using various input elements, output elements, a controller module, and a mobile application. The input elements consist of a temperature sensor, a sound sensor or a microphone,a moisture sensor, and a music player. The output elements include the motor and The controller used in this study is the NodeMCU module. Cloud storage is also used and it is provided by the Arduino loT software. The sensors in the smart cradle begin recording relevant parameters such as temperature, humidity, and sound as soon as it is turned on. The information is then uploaded to the cloud The data is then processed in the cloud for analysis. If indeed the child's temperatures is over the safe range, the user receives a warning. Moisture levels above normal suggest that the infant has urinated The sound of the baby crying will be recorded in the microphone. The output elements are energized as a result of the sensor's data. If the baby has a high fever or has to go to the bathroom, the app will notify the parent. © 2022 IEEE.

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

A Privacy-preserving Large-scale Image Retrieval Framework with Vision GNN Hashing

引用

IEEE Transactions on Big Data 2024年

作者： Cao, Yuan Meng, Fanlei Shang, Xinzheng Gui, Jie Tang, Yuan Yan The School of Computer Science and Technology Ocean University of China Qingdao266100 China The School of Cyber Science and Engineering Southeast University Nanjing211189 China Ministry of Education Purple Mountain Laboratories Nanjing210000 China Zhuhai UM Science and Technology Research Institute FST University of Macau Macau China

With the growing popularity of cloud services, companies and individuals outsource images to cloud servers to reduce storage and computing burdens. The images are encrypted before outsourcing for privacy protection. It has become urgent to solve the privacy-preserving image retrieval problem on the cloud. There are three main challenges in this area. First, how can we achieve high retrieval accuracy on the encryption domain? Second, how can we improve efficiency in large-scale encrypted image retrieval? Third, how can we ensure the reliability of the retrieval results? The existing schemes only consider some of these characteristics and the retrieval accuracy is insufficient. In this paper, we propose a privacy-preserving large-scale image retrieval framework with vision graph convolutional neural network hashing (ViGH). To the best of our knowledge, this is the first framework that is able to address all the above challenges with more advanced accuracy performance. To be specific, cycle-consistent adversarial networks and vision graph convolutional networks (ViG) are utilized to increase retrieval accuracy. By embedding encrypted images into hash codes, we can obtain high retrieval efficiency by Hamming distances. Cloud servers store the hash codes on the blockchain (Ethereum). The retrieval algorithm on the smart contracts and the consensus mechanism of blockchain ensure reliability of the retrieval results. The experimental results on three common datasets verify the effectiveness and efficiency of the proposed privacy-preserving image retrieval framework. The reliability of the retrieval results is ensured by the consensus mechanism of blockchain with no need for verification. Our code is available at https://***/caoyuan57/ViGH. © 2015 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Data Security and Protection: A Mechanism for Managing Data Theft and Cybercrime in Online Platforms of Educational Institutions

Data Security and Protection: A Mechanism for Managing Data ...

引用

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing, COM-IT-CON 2022

作者： Mohammed, Abubakar Kumar, Sanjeev Mu'Azu, Hammandikko Gaya Kumar, Rajiv Shah, Praveen Memoria, Minakshi Rawat, Amarjeet Gupta, Ashulekha Federal University Department of Information Technology Dutse Nigeria Himgiri Zee University Department of Computer Science & Information Technology Dehradun India Modibbo Adama University Department of Statistics and Operations Research Yola Nigeria Uttaranchal Institute of Management Uttaranchal University Department of Computer Applications Dehradun India Uttaranchal Institute of Technology Uttaranchal University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Management Studies Dehradun India

ISBN: (数字)9781665496025

ISBN: (纸本)9781665496025

Advancement in technology has brought changes in educational institutions that leads to the adoption of several information system and online platforms. Students and staff were sharing important data through these platforms. This has exposed the institution to cybercrime activities by both internal and external agents of malicious users. Their motive is to gain access to the platforms in order to data related to fees and other academic records, or to distort the entire system to steal the data with the aim of committing an illicit transactions or activities. This paper aimed at providing security mechanism or model for data security and protection in educational institutions. It provides empirical studies related to data security and protection as well as cyberspace and online data theft in educational institutions. The paper recommends that educational institutions should adopt and implement the security mechanism and models to prevent cybercrime activities. It also recommends that sensitization should be organized for both students and staff on the use online platforms to prevent them from being exposed to malicious users. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improving Search Engine Results Using AI Methods

Improving Search Engine Results Using AI Methods

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Jitendra Kumar Katariya Geetha. B Rupali A. Mahajan Manpreet Singh Rakesh Kumar Yadav Vivek V Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India

This paper examines how artificial Intelligence (AI) algorithms can be used to improve seek engine consequences. It outlines key terms, demanding situations, and opportunities related to AI -based totally search engine optimization. initial studies shows that AI-based totally tactics display promising ability to increase accuracy and relevancy in search engine consequences. AI strategies such as natural language processing (NLP), system getting to know (ML), and sentiment analysis are explored in element. additionally, the paper compares current answers that rent AI algorithms to conventional search engines and evaluates their performance, scalability, and applicability. ultimately, the paper discusses the destiny outlook of AI in seo and its potential implications for web users, corporations, and seeks engine developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantitative Applications of Weather Satellite Data for Nowcasting:Progress and Challenges

引用

Journal of Meteorological research 2024年第3期38卷 399-413页

作者： Jun LI Jing ZHENG Bo LI Min MIN Yanan LIU Chian-Yi LIU Zhenglong LI WPaul MENZEL Timothy J.SCHMIT John L.CINTINEO Scott LINDSTROM Scott BACHMEIER Yunheng XUE Yayu MA Di DI Han LIN Innovation Centre for Fengyun Meteorological Satellite(FYSIC) National Satellite Meteorological CentreChina Meteorological AdministrationBeijing100081China School of Atmospheric Sciences and Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies Sun Yat-sen University and Southern Laboratory of Ocean Science and EngineeringZhuhai519082China Key Laboratory of Geographic Information Science(Ministry of Education) East China Normal UniversityShanghai200241China Research Center for Environmental Changes Academia SinicaTaipei11529China Cooperative Institute for Meteorological Satellite Studies University of Wisconsin-MadisonMadisonWI53706USA Sensors and Calibration Branch STAR/NESDISMadisonWI53706USA Wuxi University Wuxi214105China School of Computer Science Chengdu University of Information TechnologyChengdu610225China Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science&TechnologyNanjing210044China Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education National and Local Joint Engineering Research Center of Satellite Geospatial Information TechnologyFuzhou UniversityFuzhou350108China

Monitoring and predicting highly localized weather events over a very short-term period,typically ranging from minutes to a few hours,are very important for decision makers and public *** these events usually relies on radar observations through monitoring and *** advanced high-resolution imaging and sounding observations from weather satellites,nowcasting can be enhanced by combining radar,satellite,and other data,while quantitative applications of those data for nowcasting are advanced through using machine learning *** applications include monitoring the location,impact area,intensity,water vapor,atmospheric instability,precipitation,physical properties,and optical properties of the severe storm at different stages(pre-convection,initiation,development,and decaying),identification of storm types(wind,snow,hail,etc.),and predicting the occurrence and evolution of the *** observations can provide information on the environmental characteristics in the preconvection stage and are very useful for situational awareness and storm *** paper provides an overview of recent progress on quantitative applications of satellite data in nowcasting and its challenges,and future perspectives are also addressed and discussed.

关键词： weather satellite quantitative applications nowcasting pre-convection

来源：评论

学校读者我要写书评

暂无评论

computer Vision & Deep Learning based Realtime and Pre-Recorded Human Pose Estimation

Computer Vision & Deep Learning based Realtime and Pre-Recor...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Milind Shah Kinjal Gandhi Bhagyesha M Pandhi Priyanka Padhiyar Sheshang Degadwala Department of Computer Science & Engineering Krishna School of Emerging Technology & Applied Research Drs. Kiran & Pallavi Patel Global University (KPGU) Vadodara Gujarat India Department of Computer Science & Engineering Parul Institute of Engineering & Technology (PIET) Parul University (PU) Vadodara Gujarat India Department of Computer Science & Engineering Depstar Charusat University Anand Gujarat India Head of Computer Engineering Department Sigma Institute of Engineering Vadodara Gujarat India

This research study utilizes computer vision to estimate multi-person human pose from real-time and pre-recorded video. computer vision examines human posture detection from RGB images. The proposed method works well for gesture control, gaming, human tracking, action detection, and action tracking. Tracking semantic important points is pose estimation. Two-dimensional human pose estimation predicts the spatial placement of key human body points from images and videos. Several anatomical areas use hand-crafted feature extraction methods to estimate two-dimensional human position. Visual input data and human body component locations are used to estimate human pose. OpenCV and Mediapipe detected 33 posture landmarks in our research. Estimating human body state requires modeling. Model-based methods are used to describe and infer human posture in 2D or 3D. This research uses the BlazePose GHUM 3D Pose Landmark Model for 2D human pose estimation. Output poses include x, y, z, and visibility. Image width and height are X and Y landmark coordinates. landmark depth Z Image shows landmark. Image or video resolution, the number of persons in the scene, and anomalies might impact visibility point accuracy, which was 0.969%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FELSDiff: Image Super-Resolution Based on Diffusion Model Fusing Feature Extraction with Latent Space

FELSDiff: Image Super-Resolution Based on Diffusion Model Fu...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Cancan Wu Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

In addressing issues like an excessive number of network parameters and the loss of fine texture details in image super-resolution reconstruction approaches based on diffusion models, this passage introduces a novel image super-resolution model (FELSDiff). This model relies on the fusion of diffusion models, feature extraction, and latent space. FELSDiff utilizes a Pre-trained CNN for initial super-resolution to extract the primary low-band features and part high-band features of the image. The preliminary super-resolved image is then concatenated as a condition to this model. We introduce a cross-attention mechanism guided by the high-band features of the preliminary super-resolved image to enhance the network's feature extraction capability and obtain more effective features. In the U-Net structure, we incorporate a latent space strategy, enabling the model's training and inference processes to be conducted in the latent space, thereby reducing the number of network parameters. Experimental results on multiple standard datasets indicate that this method outperforms other advanced methods overall.

关键词： Training Runtime Computational modeling Superresolution Memory management Feature extraction Diffusion models Convolutional neural networks Image reconstruction Standards

来源：评论

学校读者我要写书评

暂无评论

Design of a Secure Machine Learning-Based Malware Detection and Analysis Scheme

Design of a Secure Machine Learning-Based Malware Detection ...

引用

2023 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2023

作者： Kumar, Pankaj Obaidat, Mohammad S. Pandey, Piyush Wazid, Mohammad Das, Ashok Kumar Singh, Devesh Pratap Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computing Srm University Jordan University of Science and Technology Beijing Beijing100083 China School of Computing Srm University TN Kattankulathur603203 India Algorithmic Research International Institute of Information Technology Center for Security Theory Hyderabad India

ISBN: (纸本)9798350302561

Today's world is rapidly growing towards the advanced concept of technology. technology nowadays is at its peak of development and has great advantages in all fields of work, whether it is in industrial automation, farming, weather forecasting, or disease detection and control. Despite its great advantages, it does have its negative side because a major population is using technology and general-purpose computing devices (i.e., desktops, laptops, smartphones, tablets, etc.). Therefore, most of their personal data is available online. The data is constantly in danger of getting stolen by malicious actors (i.e., hackers), who can find a way to get their hands on this data and then use it for their personal gain (i.e., money-making). The best-known technique to get this information is by using malware exploitation on the machine of the target. Malware is an executable or a binary that is malicious in nature. It may have various devastating effects, and in order to detect and make the system defensive, we need to propose a scheme to detect the malware in the system, analyze the particular file, and then mitigate it. In this paper, we propose a secure machine learning-based malware detection and analysis scheme (in short, SML-MDA). The conducted security analysis and formal security verification of the proposed SMLMDA prove its security against various types of potential attacks. The proposed SML-MDA is then compared with the other similar competing schemes, and its performance has been found to be better in terms of various performance metrics like accuracy and F1-score. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cultural-Aware AI Model for Emotion Recognition

Cultural-Aware AI Model for Emotion Recognition

引用

Iranian Machine Vision and Image Processing (MVIP)

作者： Mehrdad Baradaran Payam Zohari Abtin Mahyar Hossein Motamednia Dara Rahmati Saeid Gorgin Department of Computer and Data Sciences Shahid Beheshti University Tehran Iran Department of Computer Engineering Khaje Nasir University Of Technology Tehran Iran High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Department of Computer Engineering Chosun University Gwangju South Korea

Emotion AI is a research domain that aims to understand human emotions from visual or textual data. However, existing methods often ignore the influence of cultural diversity on emotional interpretation. In this paper, we propose a multimodal deep learning model that integrates cultural awareness into emotion recognition. Our model uses images as the primary data source and comments from individuals across different regions as the secondary data source. Our results show that our model achieves robust performance across various scenarios. Our contribution is to introduce a novel fusion approach that bridges cultural gaps and fosters a more nuanced understanding of emotions. Due to the best of our knowledge, few works are using this approach, for Emotion AI, combining different types of data sources and models. We evaluate our model on the ArtELingo dataset, which contains image-comment pairs with Chinese, Arabic, and English annotations. The experimental results in the evaluation phase demonstrate an impressive 80% recognition accuracy for the model that merges image-text features.

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：