检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Electrical engineering, Big Data and Algorithms, EEBDA 2024

作者： Wang, Yuhang Fan, Yushan School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798350380989

The sailboat market is a dynamic industry characterized by fluctuations in demand and pricing due to factors such as economic conditions, area as well as the hull. Analyzing the factors influencing the listing price of sailboats has its pros and cons;the pros include a better understanding of market trends, informed decision-making for buyers and sellers, and insights into the most significant value drivers. The purpose of this study is to analyze the multiple influences on sailboat pricing. First, this paper finds that sailboat characteristics have little impact on pricing and other factors are more critical. The analysis shows that geographic region has an impact on pricing, but not significantly, while different sailboat types have different impacts in different regions. Finally, this paper finds that catamarans have a significantly greater impact on price than monohulls, emphasizing the importance of hull type in pricing. These findings deepen the understanding of sailboat pricing factors and have important implications for the market and consumer demand. © 2024 IEEE.

关键词： Multiple influences Pricing Sailboat Sailboat types

来源：评论

学校读者我要写书评

暂无评论

Block-Chain Enhanced Patient Triage System

Block-Chain Enhanced Patient Triage System

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Arjun, P. Geethan, Daniel Anandha Kanniga Devi, R. Sanjay K, S. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350378092

In today's fast-paced healthcare environment, efficient management of patient records and seamless patient-provider communication is crucial. This study proposes a comprehensive solution integrating blockchain technology (Ethereum), frontend web interfaces, natural language processing (NLP), and adverse drug event detecting functions. Through a user-friendly *** interface, patients input health data securely, while NLP automates medical information extraction from conversations. ADE detectors identify drug interactions and adverse events, enhancing care and safety. Ethereum integration via Metamask ensures secure record storage, with IPFS storage and CIDs enabling encrypted data sharing. A smart contract on Ethereum automates data management for transparency and accountability. © 2024 IEEE.

关键词： Records management

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between Online and In-Store Shopping: Fashion Recommendations and Virtual Try-On 5

Bridging the Gap Between Online and In-Store Shopping: Fashi...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Vaishnavi, V.V. Narendra, G.O. Boovaraghavan, Aravinda Anbarasi, L. Jani Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350389609

The development of extensive clothing databases has significantly advanced the field of clothing recognition and recommendation systems. However, existing datasets often suffer from a limited number of annotations and face challenges when applied to diverse, real-world scenarios. To address these limitations, the proposed research work leverages DeepFashion, a comprehensive large-scale garment dataset renowned for its detailed annotations. The primary objective is to develop an advanced fashion recommendation system combined with a virtual try-on feature using cutting-edge deep learning techniques. This system is designed to enhance the online shopping experience by providing personalized clothing recommendations and enabling users to visualize how the recommended garments would appear on them. By inputting an image, users can receive recommendations of similar clothing items by using powerful feature extraction capabilities of the ResNet50 model and the efficient retrieval mechanism of the Nearest Neighbor algorithm. Following the recommendation phase, the system employs the U2Net model for image segmentation to facilitate the virtual try-on feature. U2Net's two-level layered U-structure architecture performs well in detecting salient objects, producing high-resolution segmented images that isolate the clothing item from the background and the human body in the original input. This segmentation is crucial for accurately overlaying the recommended garment onto the user's image, creating a realistic virtual try-on experience. Following the recommendation phase, the system employs the U2Net model for image segmentation to facilitate the virtual try-on feature. The proposed research aims to address the problems of current fashion recommendation systems by utilizing the extensive and richly annotated DeepFashion dataset and integrating advanced deep learning models. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Measurement of Body Vitals using Photoplethysmography (PPG) and Smartphone Sensors 2

Measurement of Body Vitals using Photoplethysmography (PPG) ...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Furniturewala, Mahera Sivaraman, Arjun Anand, Anmol Kannuchamy, Tarun Sasikala, R. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

Every day, millions of people use portable health gadgets to monitor body vitals such as heart rate, blood oxygen level, blood pressure, etc. However, this can also be facilitated just by using normal smartphones which are commonly available. Thus, this paper aims to provide first aid in the measurement of body vitals for early diagnosis of symptoms. The outcome of this paper is a framework to measure the key body vitals such as blood oxygen, heart rate, blood pressure and respiratory rate using the built-in sensors in a smartphone namely a camera, flashlight, accelerometer, and microphone. These vitals are captured by analyzing the photoplethysmography (PPG) signals obtained from the red intensities of the images of the fingertip and performing further arithmetic calculations on the obtained values. On the other hand, respiratory rate is calculated using the deviation in the values obtained in the accelerometer readings during the movement of the chest upwards and downwards. All the algorithms are computationally feasible on mobile devices and make use of the built-in smartphone sensors only, without the need for external devices. Also, smartphones have become cheaper than before and more people in the society have access to it, thus giving them a wider reach. The paper also compares the values for the vitals measured on pulse oximeters, blood pressure monitors, health bands, and smartphones with low-and high-quality cameras. Comparisons are made on a sample size of 100 measurements, and the mean percentage error for each type of body vital measurement is calculated with respect to each measuring device. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

An Intelligent System for Preventing Accidents Due to Driver Distractions 2

An Intelligent System for Preventing Accidents Due to Driver...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Giridhar, S. Rhithik Raj, K. Sreeram, K.P. Menon, Nithish Ravikumar, Aswathy Sriraman, Harini Sriraman, Harini School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The paper presented introduces an innovative accident prevention system that employs deep learning models and sensors to identify and alert drivers who lose concentration while driving for a variety of reasons. The system targets drowsiness, cell phone use, and alcohol consumption, which are among the leading causes of automobile accidents. The proposed solution employs neural networks to identify specific patterns associated with driver inattention and generates an audible alert to refocus the driver's attention on the road. In addition, the system utilizes alcohol-detection sensors, as alcohol consumption is another significant cause of accidents. This system seeks to reduce the number of casualties by enhancing road safety considering the high number of daily collisions, which are primarily caused by speeding. The paper describes the design, architecture, and implementation of the system on a modest scale to provide a lifesaving, cost-effective solution. © 2024 Elsevier B.V.. All rights reserved.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Dynamic strategy to use optimum memory space in real-time video surveillance

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2771-2784页

作者： Biswas, Tamal Bhattacharya, Diptendu Mandal, Gouranga Department of Computer Science and Engineering National Institute of Technology Agartala Tripura Agartala India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India

In present days real-time video surveillance is a very essential aspect of establishing safety, observing traffic, and detecting violence and crimes. Intelligent video surveillance (IVS) is one of the most acknowledged frameworks in a security application. But, video surveillance systems consume huge memory space to store the recorded video, especially in the case of high-resolution recording. However, if we use low-resolution video recording then the video quality will be reduced and the objects/violence cannot be identified clearly. To overcome the stated limitation, this article introduced a smart video surveillance system with a dynamic strategy to use optimum memory space with the best surveillance objective. The proposed system can dynamically record video with high-resolution during suspicious movement of objects/violence as well as low-resolution video at other times. The system is based on the detection of suspicious movement of objects in consecutive frames, saving of suspicious frames with high resolution, and neglecting of less important frames. Finally, the Contrast Limited Adaptive Histogram Equalization (CLAHE) based on Color Channel is applied to all the suspicious frames as a post-processing step for better contract adjustment and to provide a clear view of suspicious objects in frames. The quality of enhanced frames are assessed by two no-reference methods, i.e. NIQMC and BIQME. Multiple visual quality parameters like sharpness, contrast, colorfulness, brightness, and naturalness of frames, etc. are used for assessment Several real-time experiments reveal that the proposed system can detect suspicious objects with 97.65% accuracy. Besides, it consumes 75% less memory space in real-time surveillance. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Extended Reality as an Assistive technology for Patients Suffering from Neurodegenerative Diseases 5

Extended Reality as an Assistive Technology for Patients Suf...

引用

5th International Conference on Electrical, Communication and computer engineering, ICECCE 2024

作者： Akilesh, S. Tulasi Raman, R. John, Sharon Pai, Tarun Vinod Sakthivel, V. Prakash, P. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331529437

Neurodegenerative diseases with memory impairment and difficulties in recognizing people pose significant challenges to patients' well-being and independence. This research proposes an approach leveraging extended reality (XR) headsets and computer Vision techniques to enhance person identification for such patients. The system utilizes Unity AR Foundation and OpenCV for real-time face detection and recognition, enabling accurate identification of familiar individuals within the wearer's environment with an immersive AR experience, overlaying digital information next to recognized faces in the wearer's field of view. This research aims to improve social interactions, reduce panic/confusion, and improve overall quality of life for patients with neurodegenerative diseases and represents an advancement in the intersection of healthcare and augmented reality technologies. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Automated Kidney Stone Detection using Deep Learning Technique 2

Automated Kidney Stone Detection using Deep Learning Techniq...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Guruarunachalam, G. Prabhath Sai, G.B. Hilda, J. Jabanjalin School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

Convolutional Neural Networks(CNN) are created to work mostly on the image datasets and have revolutionized image classification and object detection by introducing versatile architectures which can be modified according to the requirements needed with help of modifiable hyperparameters like architecture specifications, batch size, kernel, stride size, loss function, learning rate etc.,. The use of ResNet architecture introduces residual pathways which accelerates weight convergence compared to the traditional neural networks and other CNN architectures like AlexNet, LeNet, GoogLeNet by effectively preserves much patterns and informations contained in the images and giving a good accuracy in almost all cases considering the dataset size, quality and task complexity. In this proposed work, the CT images of Kidneys which are divided into train (1453 images) and test (346 images), encompassing both stones and non-stone cases. Employing ResNet50 architecture with meticulously configured hyperparameters and tailored preprocessing methods are made to learn the train data with a specific number of epochs and suggested learning rate. After training the model for 50 epochs, applied to detect stone's presence in the test set and achieved an accuracy of 93%. The limitations of conventional machine learning models in image classification tasks by considering Support Vector Machine, Logistic Regression and RandomForest demonstrates their challenges in capturing complex image patterns and features, often results in lower accuracy. And this deep learning model must need Graphics Processing Unit (GPU) for training to reduce the computation time and memory management. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Visible-Infrared Person Re-Identification Based on Dual Branch Structure and Attention 6

Visible-Infrared Person Re-Identification Based on Dual Bran...

引用

6th International Conference on Robotics and computer Vision, ICRCV 2024

作者： Zan, Guo Chen, Xiangyang Jiang, Zheng Lv, Weijie Yang, Mingyu School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331527426

Visible-infrared person re-identification (VI-ReID) is a difficult cross-modal pedestrian retrieval *** to the modality gaps between visible (VIS) and infrared (IR) images. In the process of visible-infrared person re-identification, it is difficult to extract effective information from modality-shared features due to the additional cross-modality discrepancy. To address this problem, we propose a visible-infrared person re-identification method based on dual-branch structure and attention. Firstly, a dual-branch convolution module is added to the ResNet-50 backbone network to extract more plentiful modality-shared features of different scales by using the dual-branch structure and dilated convolution with different expansion rates. Moreover, we design a Non- Local attention module to obtain the correlation between different pixels in spatial and channel dimensions by introducing and improving the Non-Local blocks, thereby enhancing the ability of the network to extract structural information. Finally, we design an efficient joint loss strategy to optimize the network to further reduce the modality discrepancy. Our method shows excellent performances on both SYSU-MM01 and RegDB datasets. © 2024 IEEE.

关键词： attention mechanism dual-branch structure Non-Local block ResNet VI-ReID

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Employee Attrition Prediction using Deep Learning and Fully Homomorphic Encryption

Privacy-Preserving Employee Attrition Prediction using Deep ...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Rajesh, R. Harshavardhan, S. Kirthana, B. Shreya, V. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

Employee attrition presents a significant challenge for organizations, impacting both finances and operations. Mean-while, the automation of human resource processes, including recruitment and performance monitoring, heavily relies on vast amounts of personal data. Traditional predictive models for employee attrition have increasingly turned to deep learning techniques due to their superior accuracy in deciphering complex data patterns. However, these methods raise serious privacy concerns due to their reliance on sensitive employee information. This paper introduces a novel solution by integrating Fully Homomorphic Encryption (FHE) with deep learning, ensuring data privacy without compromising predictive performance. This integration not only enhances attrition prediction accuracy but also maintains employee data confidentiality, potentially improving organizational efficiency and trust in HR processes. © 2024 IEEE.

关键词： Differential privacy

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：