检索结果-内蒙古大学图书馆

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Kambham, Suhas Preetham Varman, Raahul Ramya, Tadepalli Sri Valli Eniyan, M.K. Tangavel, Senthil Kaumar Somasundaram, K. Shanmugam, Selvanayaki Kolandapalayam Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Mathematics and Computer Science Ashland University United States

ISBN: (纸本)9798331510299

Various systems were developed to assist those with vision impairments and enhance their standard of life. Regrettably, the majority of these systems have restricted functionality. We decided to build a model that detects all possible surrounding things and guides them through voice description. Our main objective is to detect the obstacles in the person's pathway and warn them using voice description [1]. The model can assist blind people from the surrounding obstacles which exist in their pathway. The primary goal of the model is to identify the nearby obstacles - vehicles, animals, persons, objects, etc, in the person's pathway and guide or warn them using voice description. Our proposed system integrates advanced real-time obstacle detection and voice-guided navigation using a novel combination of DepthNet module with convolutional LSTM layers, enhancing spatial context awareness compared to traditional models. This approach, along with fine-tuning on diverse datasets such as MS COCO and BDD100K, ensures robust performance in varied environments and conditions. The real-time guidance capability is further improved by the integration of optical flow algorithms, which accurately estimate motion in dynamic scenes. This comprehensive solution significantly enhances the assistive technology for those with visual impairments. © 2024 IEEE.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Analysis: A Survey

Deep Learning in Medical Image Analysis: A Survey

引用

2024 IEEE International Conference on Innovation and Novelty in engineering and Technology, INNOVA 2024

作者： Agneya, D.A. Shekar, Mogaveera Sahil Bharadwaj, Anagha Vineeth, Nandhini Neelima, M. Lakshmi Department of Computer Science Engineering BMS College of Engineering Bengaluru India

ISBN: (纸本)9798331505134

Deep learning has emerged as one of the main study areas in recent years because of its wide range of applications. One of the major applications of deep learning is image processing, which, when integrated with the data received from medical imaging, has the ability to improve the diagnostic process by reducing analysis time and providing accurate results. The field of deep learning can provide scope for affordable diagnosis, proper medication assistance, and the tracking of disease progression. This survey article presents an overview of the numerous deep learning models that have been suggested for medical image analysis, highlighting the various designs of convolutional neural networks, datasets, and a brief description of the neural network layers that are utilized to produce extremely accurate findings. Since image processing is classified as supervised learning because of domain specificity, the application of a model proposed for the diagnosis of one disorder may not be applicable for the diagnosis of another. The high progress of research in this field can lead to an accurate, unsupervised image processing technology soon. This paper contrasts the accuracies of multiple algorithms and provides a brief overview of current research and development on this topic, including data pertaining to various CNN designs and layers. © 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

Hierarchical energy efficient secure routing protocol for optimal route selection in wireless body area networks

引用

International Journal of Intelligent Networks 2023年第1期4卷 19-28页

作者： Roshini, A. Kiran, K.V.D. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India

Growth in technology has witnessed the comfort of an individual in domestic and professional life. Although, such existence was not able to meet the medical emergencies during the pandemic COVID-19 and during other health monitoring scenarios. This demand is due to the untouched Quality of Service network parameters like throughput, reliability, security etc. Hence, remote health monitoring systems for the patients who have undergone a medical surgery, bed ridden patients, autism affected subjects etc is in need that considers postural change and then forward to the caretaker in hospitals through wireless body area networks (WBAN). Security in these data are very important as it deals with the life of a subject. In this work, a Hierarchical Energy Efficient Secure Routing protocol (HEESR) is proposed that categorizes the deployed body nodes in to direct node and relay node based on the threshold vale. Unlike other conventional protocols the cluster head selection is based on the energy levels and the traffic priority data like critical and non-critical data, followed by an optimal route to forward the acquired data is identified and the data is compressed using Huffman encoding technique and encrypted using asymmetric cryptographic algorithm for secure data transmission. This protocol mainly appends security and routing efficiency in a hierarchical pattern through data prioritization and out performs the other conventional routing protocols by yielding a better energy consumption of 6%, throughput 92% and security of 93%, which has balanced the packet drop rate considerably and deliver the data within the stipulated time period. © 2022 The Authors

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Ensuring privacy of data in Machine Learning 6

Ensuring privacy of data in Machine Learning

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Reshmi, T. Divakaran, Sumesh College of Engineering Trivandrum Department of Computer Science and Engineering Thiruvananthapuram India

ISBN: (纸本)9798350381689

Machine Learning is one of the most popular advancements in technology which is being widely used in various domains, including healthcare, avionics, automotive, business, education, etc. A Machine learning approach works by learning the required knowledge from the data to be supplied by a client system. In a typical scenario, a client entrusts a third-party agency to develop a machine learning application and shares the data to the developer to enable the development of a Machine learning application. This is badly affecting the privacy of data as a third-party is getting access to sensitive data from a client system. Therefore, an effective data encoding technique is required to ensure the privacy of sensitive data while enabling a third-party agency to develop a Machine learning application on the encoded data. Existing data masking/encoding techniques such as pseudonymization, anonymization and substitution are badly affecting the machine learning process as the modification they do for masking data is preventing a machine learning approach to learn the required knowledge. Another approach known in the literature is Fully Homomorphic Encryption. But, there is no tool available based on this technique which enables a client system to mask sensitive data before giving it to a third-party Machine Learning developer. We failed to obtain the expected outcome from an off-the-shelf Machine Learning classifier when we tried to classify a benchmark dataset masked using an available implementation of Fully Homomorphic Encryption. Since enough details about the implementation is not available, we could not find and fix the issues which is causing this problem. We propose a technique based on which we implemented a tool which provides an easy-to-use Graphical User Interface enabling the client to mask sensitive data before giving it to a third-party agency for developing a Machine Learning Application. Our tool enables a client to mask sensitive data through few mouse click

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of Crimes Against Women 3

Analysis and Prediction of Crimes Against Women

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Julian, Anitha Varshini, K. Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350381931

The proposed work addresses the escalating concern of crimes against women in contemporary society. This comprehensive endeavor employs a data-driven approach to tackle this critical issue. The primary objectives encompass crime rate analysis, crime rate prediction, and the implementation of an emergency alert system. The crime rate analysis module employs the K-Means clustering algorithm to identify crime-prone areas and high-probability crime occurrences. In the crime rate prediction component, machine learning algorithms, including DBSCAN, Agglomerative Clustering, and Mean Shift, are used to forecast emerging crime trends. The emergency alert system offers women real-time alerts and emergency assistance, fostering a safer environment. The Silhouette Score, an evaluation metric, helps assess the efficiency of these algorithms in capturing inherent data patterns. Proposed work has accessed the performance metrices of K-Means © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Soft-Touch or Hard-Touch: Quantifying Touches through A New System Focusing on A Pool Touchpad for Measuring Timing of Swimmers 23

Soft-Touch or Hard-Touch: Quantifying Touches through A New ...

引用

10th International Conference on Networking Systems and Security, NSysS 2023

作者： Quaium, Adnan Islam, Md. Ashraful Rahman, M. Sohel Islam, A. B. M. Alim Al Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Bangladesh and Department of Electrical and Electronic Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

ISBN: (纸本)9798400708787

The swimming turn or finishing presents an integral part of competitive swimming, and the time it takes by a swimmer to push off the wall is a significant factor in their ratings. Therefore, it is essential to have a reliable way to measure the timing of touch, i.e., wall-contact, over the finishing or turning points. To do so, swimming pool touchpads are widely used in swimming competitions to overcome human error in measurements by enabling touch-sensing systems at the finishing or turning points. The touch-sensing devices use their sensitive touch sensors to record time with millisecond accuracy, providing athletes with the most precise measurements possible. However, these devices might need a minimal force applied from the swimmers to sense the touch, and thus, to record the timing of the touch. As such, insufficient force applied on the touchpad during swimming could cause skipping the time log. As a result, it is critical to have a trustworthy method for measuring the extent of touch or wall-contact exerted over the touch-sensing systems. This study, for the first time in the literature to the best of our knowledge, proposes such a method for measuring the extent of touch or wall-contact for swimming pool touchpads. In the process of proposing the method, we design and develop a bi-modal sensing module to distinguish the soft-touch and hard-touch exerted over a real pool touchpad used in a swimming pool organizing national and international competitions. Our experiments show that the pool touchpad under experimentation is not always accurate in registering touches. It sometimes fails to register low-force touches while generally registering touches with high force. © 2023 ACM.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

A DRL-Based NOMA Power Allocation Scheme for LEO Satellite Networks 100

A DRL-Based NOMA Power Allocation Scheme for LEO Satellite N...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Lee, Jiun-Ian Hsu, Yi-Huai Sun, Shi-Sheng Yuan Ze University Department of Computer Science and Engineering Taoyuan Taiwan National Chengchi University Department of Computer Science Taipei Taiwan

ISBN: (纸本)9798331517786

Satellite networks provide higher coverage and provide ubiquitous mobile services. However, how to allocate precious satellite spectrum resources to improve better network performance has become an important issue in satellite networks. In this paper, we study the power allocation problem of the Low Earth Orbit (LEO) satellite to maximize the Supply-Demand Ratio (SDR) of the LEO satellite users while minimize the standard deviation (SD) of LEO satellite users' SDR. We propose an Event-Driven Deep Reinforcement Learning based Power Allocation Mechanism (EDRL-PAM), which utilizes the LEO satellite's power manager to intelligently allocate the power request for each cell of the LEO satellite. Furthermore, we propose a NOMA-based power allocation algorithm for allocating power to all LEO satellite users within the cells. The proposed EDRL-PAM fully utilizes a Deep Reinforcement Learning (DRL) technique, Deep Deterministic Policy Gradient (DDPG), to deal with stochastic arrivals of power requests in the power manager to achieve long-term optimization of the network performance. The simulation results show that our proposed EDRL-PAM can significantly improve the average data rate, and achieve the long-term optimization and fairness of network performance for satellite users. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Optimization of Logistic Regression Model by Feature engineering using Fuzzy Logic 18

Optimization of Logistic Regression Model by Feature Enginee...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Rohit Kumar, Vivek Abes Engineering College Department of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9789380544519

In modern era, the Machine learning especially Supervised Machine Learning is iridescent field where many researchers are shaping their research work. Innovations and new ideas in field are growing fast. Still in various fields like medical, financial and other, we need to enhance the predictions of the Logistic Regression classification models. In this research paper, we focused on the optimization of the supervised Logistic Regression model which can predict more accurately when implemented on clinical dataset. Our purpose is to introduce and implement the fuzzy logic for Features engineering technique to optimize the logistic regression model before training of the Logistic regression, which can predict more accurately in the medical data sets. In this paper, we use Coronary Heart Disease (CHD) for implementing the features engineering using fuzzy logic. Final result showed that Optimized Logistic Regression Model prediction of Ten Years Heart risk is improved with accuracy of. 863 when classical Logistic Regression classification model has been compared with it. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Coronary heart disease Feature engineering Fuzzy logic Logistic regression Machine learning

来源：评论

学校读者我要写书评

暂无评论

SemanticCuetSync at AraFinNLP2024: Classification of Cross-Dialect Intent in the Banking Domain using Transformers 2

SemanticCuetSync at AraFinNLP2024: Classification of Cross-D...

引用

2nd Arabic Natural Language Processing Conference, ArabicNLP 2024

作者： Paran, Ashraful Islam Shohan, Symom Hossain Hossain, Md. Sajjad Hossain, Jawad Ahsan, Shawly Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering and Technology Bangladesh

ISBN: (纸本)9798891761322

Intention detection is a crucial aspect of natural language understanding (NLU), focusing on identifying the primary objective underlying user input. In this work, we present a transformer-based method that excels in determining the intent of Arabic text within the banking domain. We explored several machine learning (ML), deep learning (DL), and transformer-based models on an Arabic banking dataset for intent detection. Our findings underscore the challenges that traditional ML and DL models face in understanding the nuances of various Arabic dialects, leading to subpar performance in intent detection. However, the transformer-based methods, designed to tackle such complexities, significantly outperformed the other models in classifying intent across different Arabic dialects. Notably, the AraBERTv2 model achieved the highest micro F1 score of 82.08% in ArBanking77 dataset, a testament to its effectiveness in this context. This achievement, which contributed to our work being ranked 5th in the shared task, AraFinNLP2024, highlights the importance of developing models that can effectively handle the intricacies of Arabic language processing and intent detection. ©2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Image to Text Conversion Using Deep Learning Algorithms: Survey 10

Image to Text Conversion Using Deep Learning Algorithms: Sur...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Saranya, M. Anusuya, V. Veera Santhiya, R. Vazhan Arul Srimathi, R. National Engineering College Department of Computer Science and Engineering Kovilpatti India

ISBN: (纸本)9798350384369

Image Captioning (ICs) seamlessly combines the realms of computer Vision (CV) and Natural Language Processing (NLP) task involved in producing textual sentences that summarise the image content in a way which is understandable to humans. The primary objective is to enable machines to convey the content of images in human-readable language. Image understanding and text formation are typically the two primary processes in the image captioning process. A family of Convolutional Neural Network (CNN) is used to retrieve visual information from an input image during the image understanding process. This visual information includes the image's scenes, relationships, and objects. To translate these visual features into coherent and contextually appropriate captions, recurrent neural network, long short-term memory, transformer-based models, etc. are used in the text generation step. In this article, we propose a survey about the previous research paper and the fundamental steps involved in image captioning tasks. © 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

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：