检索结果-内蒙古大学图书馆

Dynamic Visible Light Positioning Based on Enhanced Visual Target Tracking

China Communications 2023年第10期20卷 276-291页

作者： Xiangyu Liu Jingyu Hao Lei Guo Song Song School of Information Science and Engineering Shenyang Ligong UniversityShenyang 110158China Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Hangzhou Institute of Advanced Technology Hangzhou 310056China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China

In visible light positioning systems,some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy,real-time performance,and ***,there are still two problems:(1)When the captured LED disappears and the uncertain LED reappears,existing tracking algorithms may recognize the landmark in error;(2)The receiver is not always able to achieve positioning under various moving *** this paper,we propose an enhanced visual target tracking algorithm to solve the above ***,we design the lightweight recognition/demodulation mechanism,which combines Kalman filtering with simple image preprocessing to quickly track and accurately demodulate the ***,we use the Gaussian mixture model and the LED color feature to enable the system to achieve positioning,when the receiver is under various moving *** results show that our system can achieve high-precision dynamic positioning and improve the system’s comprehensive performance.

关键词： visible light positioning visual target tracking gaussian mixture model kalman filtering system performance

来源：评论

学校读者我要写书评

暂无评论

Optimization Model for Machine Learning Based Intrusion Detection System (OML-IDS) in Mobile-Edge Computing 4

Optimization Model for Machine Learning Based Intrusion Dete...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Kiruthiga, R. Jeyalaksshmi, S. Vanitha, V. Khan, Abdul Azeem Pal, Souvik Kumar, Rahul SRM Institute of Science & Technology Department of Computer Applications Kattankulathur Chennai India Depart. of IT Vels Institute of Science Technology & Advanced Studies Chennai India Sri Sankara Arts and Science College Department of Computer Applications Kanchipuram India Faculty of Islamic Technology Brunei Sister Nivedita University Department of CS and Engineering Kolkata India Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR Institute of Technology and Sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

The Internet of Things (IoT) and 5G communications now primarily use mobile edge computing (MEC). The fundamental concept behind MEC is the deployment of a hierarchy of edge servers with more computational power to handle the computing duties that are being offloaded by low-end IoT edge devices. Some of the security risks in MEC pertain to the application layer, the network layer, the data, and the node. Out main aim is to protect MEC from different cyber-attacks and continuous monitoring of digital assets. The network layer security for MEC is protected by intrusion detection systems (IDSs). We need an updated IDS system capable of detecting modern cyber-attacks as well as monitoring the devices. Thus, this paper proposes an optimization model for MEC settings that functions in conjunction with an OML-IDS, a machine learning-based intrusion detection system. To begin identifying attack patterns in a MEC environment, this model first develops an optimization-based feature selection strategy for selecting an ideal subset of characteristics. For the purpose of intrusion categorization and detection, a hybrid ML algorithm is also used. Enhancing the offloading latency, synchronization time, and turnaround time is necessary if you want to be able to recognize assaults in real time. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Intelligent Kidney Abnormality Detection in CT Images Using GLCM and Neural Networks 4

Intelligent Kidney Abnormality Detection in CT Images Using ...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Bajpai, Chhavi Anitha, S. Gaur, Manish Raghini, M. Kaliappan, S. Khan, Imran Centre for Advanced Studies Aktu Department of Computer Science and Engineering Lucknow India Acs College of Engineering Department of CSE-Cyber Security Bangalore India Institute of Engineering and Technology Aktu Department of Computer Science & Engineering Lucknow India Velammal College of Engineering and Technology Department of Artificial Intell igence and Data Science Madurai India Lovely Professional University Department of Research and Development Jalandhar India Sharda School of Nursing Science and Research Sharda University Department of Medical Surgical Nursing Greater Noida India

ISBN: (纸本)9798350352931

Kidney stone illness, one of the most common medical problems worldwide, relieves pain and drives people to the ER. Diagnoses often use imaging, but educated doctors must interpret them. computer-aided diagnostics (CAD) systems help doctors discover kidney stones more accurately. The suggested technique includes preprocessing, feature extraction, and model training. Ultrasound (US) image preprocessing includes restoration, smoothness, sharpness, and contrast enhancement. The Grey Level Co-occurrence Matrices (GLCM) analyze image texture to extract characteristics. Model training uses KELM. The KELM-based model outperforms Extreme Learning Machine (ELM) and K-Nearest Neighbours (KNN) with an average accuracy of 92.54%. This accuracy demonstrates the method can detect kidney stones in ultrasound images. This proposed shows that computer-aided kidney stone detection can be fast and accurate. The combination of GLCM's texture analysis and KELM's classification skills can help medical professionals diagnose kidney stones using imaging. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

TrA-MHWR: Transformer-Enhanced Feature Extraction with Attention-Based Recognition for Offline Handwritten Malayalam Words

TrA-MHWR: Transformer-Enhanced Feature Extraction with Atten...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Anju A T Binu P Chacko Mohamed Basheer K P Department of Computer Science Sullamussalam Science College Malappuram India Department of Computer Science Prajyoti Niketan College Trisssur India Department of Computer Science Amal College of Advanced Studies Malappuram India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

The article introduces TrA-MHWR a unique methodology transformer-based model designed to facilitate the recognition of handwritten Malayalam words in an offline setting. The model features remarkable ability to transform raw pixel data into meaningful linguistic units. Utilizing the power of Vision transformers and attention units, the model offers a sophisticated framework for robust and precise identification of handwritten Malayalam words in offline contexts. This study presents a comprehensive analysis of the architecture, training methodology, and evaluation results of TrA-MHWR, demonstrating its efficacy in pushing the boundaries related to the recognition of handwritten words in relation to Malayalam language. The proposed study uses DeiT model with a multi-head self-attention layer to improve feature sensitivity and achieved 98.82% accuracy.

关键词： Training Handwriting recognition computer vision Vocabulary Accuracy computer architecture Transformers Feature extraction Data models Character recognition

来源：评论

学校读者我要写书评

暂无评论

Tracking Evolving Labels using Cone based Oracles

arXiv

引用

arXiv 2023年

作者： Acharya, Aditya Mount, David M. Department of Computer Science Institute for Advanced Computer Studies University of Maryland College ParkMD United States

The evolving data framework was first proposed by Anagnostopoulos et al.,where an evolver makes small changes to a structure behind the scenes. Insteadof taking a single input and producing a single output, an algorithmjudiciously probes the current state of the structure and attempts tocontinuously maintain a sketch of the structure that is as close as possible toits actual state. There have been a number of problems that have been studiedin the evolving framework including our own work on labeled trees. We weremotivated by the problem of maintaining a labeling in the plane, where updatingthe labels require physically moving them. Applications involve trackingevolving disease hot-spots via mobile testing units , and tracking unmannedaerial vehicles. To be specific, we consider the problem of tracking labelednodes in the plane, where an evolver continuously swaps labels of any twonearby nodes in the background unknown to us. We are tasked with maintaining ahypothesis, an approximate sketch of the locations of these labels, which wecan only update by physically moving them over a sparse graph. We assume theexistence of an Oracle, which when suitably probed, guides us in fixing ourhypothesis. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transforming Hematological Data Interpretation: A Deep Learning and NLP Framework for Blood Cancer Prognostics

Transforming Hematological Data Interpretation: A Deep Learn...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Nitya, Erupaka Nassa, Vinay Kumar Singh, Anupam Priyanka Maithili, K. Agarwal, Vartika Cvr College of Engineering Department of Csit Hyderabad India Tecnia Institute of Advanced Studies (Delhi) Department of Information Communication Technology(ICT) Delhi India Graphic Era Hill University Department of Computer Science and Engineering India Graphic Era Deemed to be University Department of Computer Science and Engineering Dehradun India University Institute of Computing Chandigarh University Gharuan Gharuan India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Raj Kumar Goel Institute of Technology Department of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350379716

In this research work, we have investigated the transformative potential of a deep learning and natural language processing framework in enriching the capabilities to prognosticate blood cancer. Specifically, we used a dataset that covers a complete range of a clinical, high-resolution blood smear, bone marrow biopsy and imaging such as CT, MRI and PET scans. To achieve our objectives, we also designed and implemented hybrid models of CNNs and LSTM networks, specifically VGG 19 + LSTM, VGG 16 + LSTM and ResNet 50 + LSTM. The results of the study showed that the VGG 19 + LSTM model achieved the highest accuracy than the VGG 16 + LSTM and ResNet 50 + LSTM models. The confusion matrix, precision, recall and F1 score metrics gave a clear indication of the fact that VGG 19 + LSTM has the highest capacity predictive capabilities. During the calculation of the confusion matrix, this model showed the minimum number of false positives and false negatives. We also noticed that all models converge during the loss and accuracy in every epoch, which suggests that the model has the potential to learn from the complex data. Through the extensive utilisation of clinical data with imaging, we designed reliable diagnostic tools that have more chances to prognosticate accurately. Moreover, it has made a significant contribution to the validation of deep learning in interpreting medical data. Most importantly, it will also give a kind of approach to future work to further extend these methods for other cancers. © 2024 IEEE.

关键词： Blood cancer prognostics deep learning medical data interpretation NLP framework VGG 19 + LSTM

来源：评论

学校读者我要写书评

暂无评论

Ornithopter- IoT Based Kamikaze Drone 11

Ornithopter- IoT Based Kamikaze Drone

引用

11th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2023

作者： Singh, Sugandha China Ramu, S. Kumar, Pawan Chinni, Pathlavath Vivekananda Institute of Professional Studies- TC Computer Science and Engineering Department Delhi India Chaitanya Bharathi Institute of Technology Computer Science and Engineering Department Hyderabad India Hyderabad Institute of Technology and Management Mechanical Engineering Department Hyderabad India Hyderabad Institute of Technology and Management Electronics and Communication Engineering Department Hyderabad India

ISBN: (纸本)9798350326147

The ornithopter drone's major objective is to address the issue of border monitoring in particular without being discovered by enemies. Many insect and bird wing variations were researched in attempt to comprehend how natural fliers generate lift by flapping their wings. Following extensive testing on many wing forms and materials, a design for the drone was created. The drone's tail is constructed in a manner reminiscent of an elevator on an airplane. The two distinct parts of the tail are controlled by two servo. Different lift and thrust computation methods are examined and evaluated. The drone is designed to seem like a bird and to hover or glide like a bird, making it more challenging for attackers to find it. The ornithopter is equipped with a variety of parts, such as battery packs, brushless motors, folding propellers, 30amp ESCs, three HS-55 servos, accelerometers, humidity sensors, GPS receivers, thermal imagers, electro-optical day cameras, and Arduino mega boards, It also has a transmitter and receiver. Primary objective is surveillance. It has the capacity to transport flying bombs as well. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Acceleration System for Scene Text Recognition 4

Heterogeneous Acceleration System for Scene Text Recognition

引用

4th International Conference on Artificial Intelligence and computer Engineering, ICAICE 2023

作者： Feng, Hua Wu, Junmin Department of Computer Science and Technology University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China

ISBN: (纸本)9798400708831

Scene text recognition has a wide range of applications. Its deep learning algorithm model is mainly CNN and RNN hybrid neural network, which can effectively identify text information in natural scenes. However, complex network models lead to longer inference time. This paper proposes a heterogeneous acceleration system for the scene text recognition neural network model CRNN. Mainly performed hardware deployment and optimization on CNN and LSTM. For CNN, blocking computation and a new data access pattern are proposed to reuse data and reduce on-chip storage. For LSTM, it is implemented in modules, and a method to overcome data dependency is proposed to improve processing efficiency. We implemented this accelerator on the Xilinx ZCU104 platform, which has good performance and low resource utilization. © 2023 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Exploring ML Methods for Sentiment Analysis in Text Data

Exploring ML Methods for Sentiment Analysis in Text Data

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Agarwal, Vishu Tayal, Ashmit Dixit, Rajani Chugh, Bharti Jain, Shikha Kiet Group of Institutions Department of Computer Science and Engineering Ghaziabad India School of Engineering and Technology Vivekananda Institute of Professional Studies- Technical Campus New Delhi India

ISBN: (纸本)9798350375237

Data Analysis has become an important part of our life, as it helps us to draw useful information, decision-making conclusions on any particular raw data. One component of digital data analysis is sentiment analysis. Sentiment analysis evaluates the emotional tone of textual data and classifies it as neutral, negative, or positive. In business, this analysis is frequently utilized for market social media monitoring, market research, consumer feedback and many more. In order to automate the procedure, machine learning models that recognize patterns in labeled data are frequently used. The objective is to derive meaningful insights from textual data so that decisions can be made with knowledge, effectively. In order to provide important insights into public opinion and behavior, this study uses machine learning techniques to investigate the sentiments conveyed in Twitter data. A wide range of Twitter posts, including ones about trending hashtags, events, and subjects, are gathered as part of the process. Sentiment analysis is done using machine learning algorithms. Sentiment analysis and examples of human language are used to train machine learning models. Following this training, machine learning is used by sentiment analysis software to evaluate and rank human language according to its previous training. The current study proposes a technique that best analyzes the sentiments of the text used in social media is gradient boosting classifier. With this method, an additive model can be built in a step-by-step, forward fashion and any differentiable loss function can be optimized. There are n-class regression trees that are fitted on the negative gradient of the loss function, which could be the multiclass log loss or the binary loss. This process is repeated in each step. In the particular case of binary classification, just one regression tree is induced. The computational results demonstrates that gradient boosting approach with an accuracy of 93.62% which outperform

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Advancements in Skin Disease Diagnosis Through Machine Learning-Driven Lesion Segmentation Techniques

Advancements in Skin Disease Diagnosis Through Machine Learn...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： M. Megala T.R. Nisha Dayana Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced-Studies (VISTAS) Chennai Tamil Nadu India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Skin diseases pose a significant global health challenge, demanding precise diagnosis and effective treatment. This survey paper delves into the realm of enhancing skin disease diagnosis via a pioneering machine learning algorithm focused on lesion segmentation. By amalgamating cutting-edge techniques like Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), this algorithm strives to elevate accuracy and efficiency in this pivotal task. The results unequivocally establish the algorithm's superiority in accurately delineating skin lesions. Timely identification and meticulous characterization of skin ailments substantially influence patient outcomes. This contribution augments the corpus of knowledge in machine learning-based medical image analysis. The amalgamation of sophisticated techniques within this algorithm unfurls new horizons for subsequent exploration and innovation in skin disease analysis. The continuous evolution of this field harbors the potential to revolutionize dermatological practice, thereby enhancing the global management of skin disorders. The machine learning algorithm for skin lesion segmentation unveils a propitious avenue for accurate and efficient skin disease diagnosis. The far-reaching impact on patient care and the broader dermatological sphere underscores the imperative of further investigation and validation of this approach.

关键词： Surveys Technological innovation Machine learning algorithms Accuracy Generative adversarial networks Skin Lesions Medical diagnosis Convolutional neural networks Diseases

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：