检索结果-内蒙古大学图书馆

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Pokkuluri, Kiran Sree Sssn Usha Devi, N. Prasad, M. Raja Rao, Pbv Varma, Ch Phaneedra Ramesh Babu, G. Shri Vishnu Engineering College for Women Dept. of Computer Science and Engineering Bhimavaram India University College of Engineering College Dept. of Computer Science and Engineering JNTU Kakinada India

ISBN: (纸本)9798350371314

As the modern life is highly dependent on the modern transport system, road safety became a high priority. Most of the systems are aiming for very less reporting time to reduce the severity of the accidents. This paper presents an in-dept. analysis of crash detection on roads using deep learning(DL). We have use one of the mechanisms of deepening i.e. Convolutional Neural Networks (CNNs) to detect the same. These DL models are used to classify the traffic accidents and it automatically recognize accidents with minimum effort. We have integrated automatic SMS alert with the system, which send SMS automatically after detecting the crash. This feature enhances the acceleration of emergency response, which makes the system more robust. We have achieved an accuracy of 96.3% which relatively good compared with the existing baseline methods. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Image Partitioning and Compression Mechanisms 15

A Comparative Analysis of Image Partitioning and Compression...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Chaudhari, Sampada P. Thakur, Nileshsingh V. Dept. of Computer Science and Engineering Prof Ram Meghe College of Engineering & Management Badnera India Dept. of Computer Science and Engineering Yeshwantrao Chavan College of Engineering Nagpur India

ISBN: (纸本)9798331300579

This paper presents a comprehensive comparative analysis of image partitioning and compression mechanisms, two fundamental techniques in image processing and data compression. Image partitioning involves dividing an image into smaller components, while compression aims to reduce the size of digital images while preserving visual quality. The analysis encompasses various aspects of both techniques, including methodologies, algorithms, and performance metrics. For image partitioning, segmentation methods such as block-based, region-based, and hierarchical partitioning are examined, along with their respective advantages and limitations. Additionally, the paper explores compression mechanisms such as transform coding, quantization, entropy coding, and predictive coding, highlighting their roles in achieving efficient compression. Furthermore, the comparative analysis evaluates the tradeoffs between different partitioning and compression techniques in terms of compression ratio, image quality, computational complexity, and applicability across different types of images and applications. Various compression standards such as JPEG and PNG are also reviewed to provide insights into real-world implementations. Finally, the paper discusses future research directions and emerging trends in image partitioning and compression, including the integration of machine learning techniques for improved segmentation and compression performance. The findings presented in this comparative analysis can serve as a valuable resource for researchers, practitioners, and developers working in the fields of image processing, data compression, and multimedia systems. © Grenze Scientific Society, 2024.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

ENHANCING E-HEALTH CYBERSECURITY AND RESILIENCE: SHIFTING FROM MONOLITHIC TO MICROSERVICES ARCHITECTURE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2025年第1期87卷 21-34页

作者： Contașel, Cristian Rughiniș, Răzvan Trancă, Dumitru Cristian Țurcanu, Dinu Dept. of Computer Science and Engineering National University of Science and Technology POLITEHNICA Bucharest Romania Dep. of Software Engineering and Automatics Technical University of Moldova Chișinău Moldova

This study provides an innovative architectural model for e-Health systems that aims to improve cyber resilience while maintaining high availability under fluctuating traffic loads. We examined typical cybersecurity incidents in the field of e-Health, their correlations with architectural defects, and frequent design patterns in currently operational systems. A testing approach based on our research finds those weaknesses and proposes viable fixes. In this paper, a comprehensive support strategy for transitioning from conventional monolithic architectures to microservices is presented. This change makes use of cloud computing's vertical and horizontal scalability to maximize resource utilization while ensuring system reliability. We also discuss deployment ideas for the new microservices, focusing on operational resilience and cybersecurity in e-Health environments. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Mathematical Morphology Adopted Automatic Detection of Ground Glass Opacities in Lung CT Images of COVID-19 Patients

Mathematical Morphology Adopted Automatic Detection of Groun...

引用

2023 International Conference on Intelligent Systems, Advanced Computing and Communication, ISACC 2023

作者： Chatterjee, Soma Chatterjee, Rohit Kamal Goswami, R.T. Techno International New Town Dept. of Computer Applications Kolkata India Birla Institute of Technology Dept. of Computer Science & Engineering Mesra Ranchi India Techno International New Town Dept. of Computer Science Kolkata India

ISBN: (纸本)9798350399387

The severity of the nCOVID infection relies on the presence of Ground Glass Opacities (GGO) present in the patient's chest CT scan images. Although, detecting and delineating the precise boundaries of GGO in the chest CT images is challenging. Here, we proposed a fast and novel technique to automatically segment the regions containing GGO in lung CT images using mathematical morphology. We have tested our algorithm on the chest CT images of 145 Covid-positive cases. This unique segmentation approach correctly segments the lung field from chest CT images and identifies GGO with average sensitivity, specificity, and accuracy of 96.89%, 95.23%, and 97.22%, respectively. We used expert radiologists' hand-curated segmentation of GGO as ground truth for quantificational performance analysis. Our research results indicate that this algorithm performs well found in the literature. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Deep Learning Models in Driver Behavior Recognition

Performance Analysis of Deep Learning Models in Driver Behav...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Kapoor, Rameshwari Kuliyal, Rashmi Bhanot, Nilesh Bagla, Piyush Rawat, Ruchira Graphic Era Hill University Dept. of Computer Science and Engineering Uttarakhand Dehradun India University Dept. of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798331542344

The World Health Organization report states that nearly 1.25 million people lose their lives due to an increasing number of road accidents every year. The majority of accidents are reported due to driver errors, which include distractions like the use of mobile phones and fatigue, which causes drowsiness. This study aims to address these issues by performing a comparative analysis between different deep learning models representing two types of learning mechanisms: Traditional deep learning and transfer learning. This study portrays the use of two datasets to accomplish this task. These two datasets are the Driver Drowsiness Dataset DDD and the State Farm Distracted Drivers Dataset. The purpose of this investigative research is to explore the execution and efficiency differences between three deep learning algorithms, the traditional convolutional neural network, ResNet50, and VGG16, in classifying driver behavior by training these models individually on both datasets. This study also targets developing an alarm system that sounds an alarm based on a threshold by using an ensemble of all the models trained for comparative study and averaging their predictions to classify driver behavior. VGG16 achieved an accuracy of 99.74% on the driver drowsiness dataset, whereas Custom CNN Architecture achieved an accuracy of 98.70% on the driver distraction dataset. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach Using Cryptography and K-Least Significant Bit Steganography Algorithm in Cloud Computing 1

A Hybrid Approach Using Cryptography and K-Least Significant...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Goyal, Anshika Gupta, Bhumika VMSB Uttarakhand Technical University Dept. of Computer Science & Engineering Dehradun India G.B. Pant Institute of Engineering & Technology Dept. of Computer Science & Engineering Pauri India

ISBN: (纸本)9798331518578

The exponential growth of communication technologies has broadened the cloud computing ecosystem horizon to meet main communication needs. However, in-parallel upsurge in online attacks has alarmed industries to ensure optimal data security. The combination of steganography and cryptosystems has been recognized as an enhanced security model for data transfer among the main security systems now in use. In this paper, a hybrid approach using cryptography and K- Least Significant Bit Steganography algorithm in Cloud Computing (HYBC-KLSBS-CC) are proposed. Initially, input text data is retrieved from cloud storage and compressed using Huffman Compression Coding (HCC) to reduce data size. The compressed data is then encrypted with a Hybrid Cryptography Algorithm (Hyb-MRFC-ALC), combining Modified Random Fibonacci Cryptography and Asymmetric Lightweight Cryptography to ensure robust encryption. Finally, encrypted data is embedded within an image using the K-Least Significant Bit (KLSB) steganography technique, providing additional layer of security. The proposed method enhances data confidentiality, integrity, and storage efficiency in cloud environments. The proposed HYBC-KLSBS-CC approach attains 26.89%, 29.49% and 18.64% lower PSNR and 26.89%, 29.49% and 18.64% lower MSE when analyzed through existing techniques like data security dependent on cryptography steganography related with OTP procedure and Huffman coding in the cloud environment (CS-OTP-CE), a novel hybrid cryptographic framework for secure data storage in cloud computing: Integrating AES-OTP and RSA with adaptive key management and Time-Limited access control (AES-OTP-RSA-CC) and Crypto-Stegno dependent model for securing medical information on IOMT platform (CS-SMI-IOMT). © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Power Control of Preamble Transmission for Grant-free Random Access in Cell-Free IoT Networks 15

Power Control of Preamble Transmission for Grant-free Random...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Youn, Jiseung Cho, Sunghyun Hanyang University Dept. of Computer Science & Engineering Seoul Korea Republic of Hanyang University ERICA Dept. of Computer Science & Engineering Ansan Korea Republic of

ISBN: (纸本)9798350364637

As Internet of Things (IoT) technologies are inves-tigated to support key 5G services, significant research efforts are being made to enable machine-type communication (MTC). Cell-free IoT (CF-IoT) systems, characterized by favorable prop-agation and macro diversity, are being studied in conjunction with grant-free random access (GFRA) as a potential enabler to achieve massive connectivity for MTC. However, existing GFRA schemes in CF-IoT transmit preambles at a fixed power level resulting in severe preamble collisions at nearby access points (APs). In this paper, we analyzes the analysis of preamble collisions in massive connectivity scenario and proposes a sim-ple power control scheme to address preamble collision. The proposed scheme mitigates preamble collisions by transmitting preambles only to the nearest AP in high-density access scenes. Simulation results show that the proposed method improves the random access success rate compare to existing GFRA method by 10%. © 2024 IEEE.

关键词： cell-free massive MIMO grant-free random access Internet of Things power control

来源：评论

学校读者我要写书评

暂无评论

Gaze Detection and Text Extraction from Images using CNN with DBSCAN-based Filter Design 11

Gaze Detection and Text Extraction from Images using CNN wit...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Jose, Jithin Ramanujan, Ajeesh College Of Engineering Trivandrum Dept. Of Computer Science And Engineering Trivandrum India

ISBN: (纸本)9798350379136

Gaze detection and text extraction are pivotal technologies in the domain of human-computer interaction and computer vision, enabling applications such as assistive technologies, user interface optimization, and automated content analysis. This paper presents a novel method that identifies the user's gaze direction and extracts the necessary portion of text, which constitutes the user's region of interest, using a Convolutional Neural Network (CNN) integrated with a spatial attention mechanism. A Density-Based Spatial Clustering of applications with Noise (DBSCAN)-based filter is incorporated into the system to remove textual noise from the extracted image, thereby improving the model's accuracy and reducing computation time. The proposed method demonstrates reduced dependency on the CNN compared to previous approaches, resulting in enhanced real-time operation capability and lower latency. Computational optimization and real-time performance were thoroughly evaluated, showing that our system not only achieves high accuracy in gaze detection and text extraction but also maintains efficient processing speeds suitable for dynamic applications. This advancement offers significant improvements for applications in assistive technology, educational tools, and interactive media, where precise and efficient gaze detection and text extraction are critical. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ARNAV: computer vision and Machine Learning-Based Augmented Reality-Based Indoor Navigation System 5

ARNAV: Computer vision and Machine Learning-Based Augmented ...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Sai Suryaa, K. Saravana Kumar, C. Sudharsan, S. Anandkumar, K.M. Easwari Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

Introducing an advanced Augmented Reality (AR) indoor navigation system that uses computer vision for precise positioning and obstacle detection which eliminates the need for GPS. The system is implemented on Android devices using Unity. The system works based on a 3D model of the navigational space that provides the user with unique interior Point of Interests with AR guided overlays for navigation. It uses an advanced mapping and machine learning techniques for real time positioning and obstacle detection. The ARNAV system is independent of GPS making it reliable in complex indoor spaces where GPS fails. Additionally, in emergency situations where there is low visibility the system provides an advanced AR walls feature to guide users to reach the nearest exit by using AR generated walls and overlays. The retrace path feature which is designed especially for patients with cognitive impairments like Alzheimer's which allows the user to retrace the path that they have already traversed using the AR overlay. Additionally, it provides AR based reminders that helps them complete day to day tasks. In conclusion the ARNAV revolutionizes the AR technology to create a safe, dynamic and user centric system that handles emergency evacuation and needs of patients with special cognitive needs. © 2024 IEEE.

关键词： Augmented Reality computer Vision Indoor Navigation System Mobile Application

来源：评论

学校读者我要写书评

暂无评论

Assessment Technology for Physiotherapy Practices using Deep Learning 2

Assessment Technology for Physiotherapy Practices using Deep...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Vineeth, Nandhini Darshan, P.M. Deepu, K. Daragaj, Arihant Prabhu, Ananth G. Bms College of Engineering Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350370188

The innovative technology for physiotherapy assessment employing deep learning aims to offer a precise and streamlined approach to evaluating physiotherapy needs. Conventional manual assessment techniques utilized in physiotherapy often consume time and are susceptible to human inaccuracies, resulting in erroneous diagnoses and treatment strategies. This technology tackles these challenges by employing sophisticated deep learning algorithms that identify angles and offer auditory guidance to patients based on their posture. The process commences with capturing the patient's video through a webcam and extracting frames utilizing OpenCV. Following this, the frames undergo processing via a media pipe library, a sophisticated tool designed for body key point detection. These identified key points are subsequently utilized to connect essential body segments for a particular exercise and compute the angular measurements between them. Using these measurements, the system assesses the correctness of the posture, offering audio feedback with repetition counts for accurate postures and tailored guidance for incorrect ones. The audio cues are exercise-specific, delivering precise instructions to aid the patient in refining their posture. The system also keeps track of patient's progress over time and provides a visual display of their improvement. This helps the patient monitor their progress and provides motivation for them to continue with their therapy. The use of learning algorithms and the media pipe library makes this solution an accurate, efficient, and cost-effective method for physiotherapy assessments. © 2024 IEEE.

关键词： Deep learning

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：