检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Arora, Utkarsh Mishra, Upendra Singh, Samaira Singh, Vaibhav Kiet Group of Institutions Department of Computer Science & Engineering Ghaziabad India Kiet Group of Institutions Department of Computer Science & Engineering Delhi-NCR Ghaziabad India

ISBN: (纸本)9798350370249

The increasing incidence of leaf diseases in agricultural crops has necessitated the development of efficient and automated detection methods to safeguard crop health and maximize yield. In the field of artificial intelligence, deep learning has emerged as a major computing paradigm with immense potential for solving computer vision problems. CNN is a type of deep learning architecture that is designed to provide accurate results for tasks such as image recognition and object detection. This study utilizes state-of-the-art ResNet-50 model to identify and classify plant leaf diseases combined with transfer learning to enhance its accuracy and efficiency. The proposed methodology involves dataset curation, preprocessing, and finetuning of the ResNet-50 architecture. We have tested and assessed the performance of VGG16, Inception V4, AlexNet, and ResNet-50. Upon examining the results, ResNet50 has demonstrated good outcomes in the identification and categorization of leaf diseases and outperformed alternative architectures with an accuracy of 99.7%. © 2024 IEEE.

关键词： CNN Deep Learning Plant leaf disease ResNet-50

来源：评论

学校读者我要写书评

暂无评论

Blink: Blank Node Matching Using Embeddings 23rd

Blink: Blank Node Matching Using Embeddings

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Becker, Alexander Sherif, Mohamed Ahmed Ngonga Ngomo, Axel-Cyrille DICE Group Department of Computer Science Paderborn University Paderborn Germany

ISBN: (纸本)9783031778438

Knowledge graphs (KGs) differ significantly over multiple different versions of the same data source. They also often contain blank nodes that do not have a constant identifier over all versions. Linking such blank nodes from different versions is a challenging task. Previous works propose different approaches to create signatures for all blank nodes based on named nodes in their neighborhood to match blank nodes with similar signatures. However, these works struggle to find a good mapping when the difference between the KGs’ versions grows too large. In this work, we propose Blink, an embedding-based approach for blank node linking. Blink merges two KGs’ versions and embeds the merged graph into a latent vector space based on translational embeddings and subsequently matches the closest pairs of blank nodes from different graphs. We evaluate our approach using real-world datasets against state-of-the-art approaches by computing the blank node matching for isomorphic graphs and graphs that contain triple changes (i.e., added or removed triples). The results indicate that Blink achieves perfect accuracy for isomorphic graphs. For graph versions that contain changes, such as having up to 20% of triples removed in one version, Blink still produces a mapping with an Optimal Mapping Deviation Ratio of under 1%. These results show that Blink leads to a better linking of KGs over different versions and similar graphs adhering to the linked data guidelines. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Language Identification in Code-Mixed Text 6th

Deep Learning-Based Language Identification in Code-Mixed Te...

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Deka, Brajen Kumar Department of Computer Science NERIM Group of Institutions Guwahati India

ISBN: (纸本)9789819940707

Language identification (LID) research is a significant area of study in speech processing. The construction of a language identification system is highly relevant in the Indian context, where almost every state has its language, and each language has many dialects. Social networking is becoming increasingly important in today’s social media platforms for people to convey their opinions and perspectives. As a result, it might be challenging to distinguish between specific languages in a multilingual nation like India. Data was gathered from publicly accessible Facebook postings and tagged with a code-mixed data tag created for this study. This study uses deep learning techniques to identify languages at the word level, where the encoded content may be in Hindi, Assamese, or English. Convolutional neural networks (CNNs) and long short-term memory (LSTM), two deep neural techniques, are compared to feature-based learning for this task. According to the finding, CNN has the best language identification performance with an accuracy of 89.46%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation with Attention Dense U-Net for Lung Extraction from X-ray Images 6

Semantic Segmentation with Attention Dense U-Net for Lung Ex...

引用

6th International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2024

作者： Mahmud Auvy, Akib Al Zannah, Rafiatul Mahbub-E-Elahi Sharif, Shezhan Mahmud, Washik Al Noor, Jannatun Research Group Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

Deep learning and digital image processing are crucial in medical imaging research. Lung segmentation is particularly challenging, demanding accurate differentiation of complex structures, sophisticated algorithms, and deep learning models for reliable results. In our research, We used the Shen-zhen chest X-ray dataset, comprising 566 frontal chest X-rays focused on pulmonary tuberculosis. This dataset, compiled by the Guangdong Medical College and Shenzhen No. 3 People's Hospital, was released by the United States National Library of Medicine. Images, captured using a Philips DR Digital Diagnostic system, were resized from $3000 \times 3000$ pixels to $512 \times 512$ pixels for computer-aided diagnosis research. We initially used the Attention Dense U-Net to extract lungs from chest X-rays, leveraging attention mechanisms to focus on relevant features and dense blocks to improve feature reuse. Our goal is to assess its performance for chest X-ray segmentation, comparing it with other deep learning models due to limited research in this area. So, the model is compared with four other variants of U-Net architectures to segment lung pixels from an X-ray image. After implementing the approach using a benchmark dataset and comparing it to other existing architectures, we present that Attention Dense U-Net gives the best accuracy for all given parameters, with a result of accuracy: 97.48%, Dice coefficient: 94.87%, and IoU: 93.87%. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Xcelerate5G: Optimizing Resource Allocation Strategies for 5G Network Using ML 5

Xcelerate5G: Optimizing Resource Allocation Strategies for 5...

引用

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

作者： Shukla, Neha Siloiya, Ayush Singh, Apoorva Saini, Aayushi Kiet Group of Institutions Department of Computer Science Ghaziabad India

ISBN: (纸本)9798350383522

As we embrace the transformative era of 5G technology, promising unprecedented data rates, minimal latency, and extensive device connectivity, the need for effective resource allocation becomes paramount. This research delves into the realm of machine learning, specifically exploring linear regression, support vector machines (SVM), and k-nearest neighbor (KNN) models to optimize resource allocation in 5G networks. Examining previous research, we uncover a focus on training models to assess incoming traffic and predict network slices for unknown device types using key performance indicators (KPIs) [1]. To enhance resource utilization, our study introduces and compares three machine learning models: linear regression, SVM, and KNN. These models forecast optimal resource allocation based on past network data and user trends. While linear regression offers simplicity, SVM and KNN present more sophisticated and adaptive models. In the dynamic conditions of 5G networks, machine learning-based resource allocation outperforms traditional methods, excelling in bandwidth efficiency, user satisfaction, noise reduction, and signal strength. Key considerations include accuracy, scalability, and resource distribution for various application types. This study underscores the significance of machine learning techniques, contributing to a deeper understanding of resource allocation in 5G networks. It provides comprehensive insights into the advantages and limitations of linear regression, SVM, and KNN models, empowering network operators and researchers to make informed decisions that enhance the overall performance and efficiency of evolving 5G networks across diverse use cases. © 2024 IEEE.

关键词： K-Nearest Neighbor Multiple Linear Regression Resource Allocation Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Bi-GAE:A Bidirectional Generative Auto-Encoder

引用

Journal of computer science & Technology 2023年第3期38卷 626-643页

作者：华勤胡瀚文钱诗友杨定裕曹健 Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Alibaba Group Shanghai 201210China

Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by in the reconstruction of 512*512 images.

关键词： auto-encoder adversarial network image reconstruction and generation feature representation

来源：评论

学校读者我要写书评

暂无评论

IoT Cryptography: A Secure Communication Framework for the Internet of Things

IoT Cryptography: A Secure Communication Framework for the I...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Rishi, Midhvana Dubey, Vaibhav Bhardwaj, Mukesh Kumar Singh, Mahesh Kumar Dronacharya Group of Institutions Department of Computer Science Engineering India

ISBN: (纸本)9798350375237

IoT is a lightning-fast technology that uses clever objects or stuff that speak uncomplicatedly to the work of our daily lives. Smart homes, wearables, connected automobiles, vibrant urban communities;savvy retail, agribusiness, healthcare, and other areas are some of the most well-known applications of IoT. This document provides an overview of IoT Crypto a safe platform Internet of Things communication. Typically, they have elements from Internet of Things (IoT), such as the device functionality they need, the requirement to restrict the amount of information sent, and the ability to connect to the Internet. With real business relationships in mind, Innovative lightweight authentication setup and trust concepts are provided by IoT-Crypto. Include a secure communication protocol that only makes use of one DTLS connection that is encrypted. This article discusses and presents the unique components and nuanced execution details of IoT crypto in terms of essentially equivalent arrangements. Post-implementation testing and analysis of the IoT encrypted network have proven its accuracy and safety. Additionally, a test network was conducted to determine if the BLE IPSP profile and coding standards are suitable for IoT. Based on these results, the significance of future research was discussed. The IoT paradigm and communication protocols are introduced at the outset of this work and then compare countermeasures for a few security vulnerabilities at each tier of the IoT model to protect such a large and diverse company. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimizing Storage for Energy Conservation in Tracking Wireless Sensor Network Objects

引用

computer Systems science & Engineering 2023年第5期45卷 1211-1231页

作者： Vineet Sharma Mohammad Zubair Khan Shivani Batra Abdullah Alsaeedi Prakash Srivastava Department of Computer Science and Engineering KIET Group of InstitutionsDelhi-NCRGhaziabad201206India Department of Computer Science and Information Taibah UniversityMedina42353Saudi Arabia Department of Computer Science Taibah UniversityMedina42353Saudi Arabia Department of Computer Science and Engineering Graphic Era(Deemed to be University)Dehradun248002India

The amount of needed control messages in wireless sensor networks(WSN)is affected by the storage strategy of detected *** broadcasting superfluous control messages consumes excess energy,the network lifespan can be extended if the quantity of control messages is *** this study,an optimized storage technique having low control overhead for tracking the objects in WSN is *** basic concept is to retain observed events in internal memory and preserve the relationship between sensed information and sensor nodes using a novel inexpensive data structure entitled Ordered Binary Linked List(OBLL).Whenever an object passes over the sensor area,the recognizing sensor can immediately produce an OBLL along the object’s *** retrieve the entire information,the OBLL can be traversed with logarithmic complexity which is much less than the traversing complexity of existing linked list *** evaluation and simulations were carried out to ensure that the suggested technique minimizes the number of messages and thus saving energy and extending the network life.

关键词： Energy conservation linked list object tracking wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based Approach to Monitor the Health of Water Bodies Nearby Indian Villages 1

An IoT-Based Approach to Monitor the Health of Water Bodies ...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Singh, Shweta Agarwal, Prashant Gupta, Amit Kumar Bhardwaj, Manish Rishika Nigam, Kratika KIET Group of Institutions Department of Computer Applications Ghaziabad India KIET Group of Institutions Department of Computer Science and Information Technology Ghaziabad India

ISBN: (纸本)9798350353648

In 2018, 351 contaminated river segments in India were identified by the Central Pollution Control Board (CPCB). Thirty-one provinces and the union territories (UT) have rivers and streams that failed to meet the criteria for the evaluation of water quality to identify polluted river lengths. to protect everyone's life on the planet. In recent years, a number of writers have put forth architectural-based solutions that emphasise increased efficiency and adaptability. New sensor capabilities are being created by improvements in sensor detection and communication. Water Quality Monitoring (WQM) is an economical and effective method that uses Internet of Things (IOT) technology to monitor the quality of water. These sensors were interfaced with a Microcontroller Unit (MCU), and additional processing was carried out on a Personal computer (PC). An IOT-based ThingSpeak application is used to transmit the acquired data to the cloud in order to track the water quality. The accuracy of the prediction is increased with the proposed system, and the power of drawing conclusions is enhanced with IOT technology. © 2024 IEEE.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

ElderEase AR: Enhancing Elderly Daily Living with the Multimodal Large Language Model and Augmented Reality 24

ElderEase AR: Enhancing Elderly Daily Living with the Multim...

引用

2024 International Conference on Virtual Reality Technology, ICVRT 2024

作者： Song, Tianyu Liu, Zhengyi Zhao, Ruibin Fu, Jie Department of Computer Science and Technology School of Computer Science and Technology Intelligent Perception Group Anhui University Anhui Hefei China Chuzhou University Anhui Chuzhou China Department of Computer Science and Technology School of Computer Science and Technology Artificial Intelligence Group Anhui University Anhui Hefei China Department of Computer Science and Technology School of Information Engineering Intelligent Perception Group Chuzhou University Anhui Chuzhou China

ISBN: (纸本)9798400710186

Elderly individuals often face challenges in independent living due to age-related cognitive and physical decline. To address these issues, we propose an innovative Augmented Reality (AR) system, "ElderEase AR", designed to assist elderly users in their daily lives by leveraging a Multimodal Large Language Model (MLLM). This system enables elderly users to capture images of their surroundings and ask related questions, providing context-aware feedback. We evaluated the system’s perceived ease-of-use and feasibility through a pilot study involving 30 elderly users, aiming to enhance their independence and quality of life. Our system integrates advanced AR technology with an intelligent agent trained on multimodal datasets. Through prompt engineering, the agent is tailored to respond in a manner that aligns with the speaking style of elderly users. Experimental results demonstrate high accuracy in object recognition and question answering, with positive feedback from user trials. Specifically, the system accurately identified objects in various environments and provided relevant answers to user queries. This study highlights the powerful potential of AR and AI technologies in creating support tools for the elderly. It suggests directions for future improvements and applications, such as enhancing the system’s adaptability to different user needs and expanding its functionality to cover more aspects of daily living. © 2024 Copyright held by the owner/author(s).

关键词： Augmented reality

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：