检索结果-内蒙古大学图书馆

International Conference on Edge Computing and Applications (ICECAA)

作者： P Kanaga Priya T Vaishnavi N Selvakumar G Ramesh Kalyan A Reethika Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering SNS College of Technology Coimbatore India Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore India

Animal species classification is a fundamental task in wildlife conservation, animal behavior studies, and biodiversity research. Convolutional Neural Networks (CNNs) have become a potent technique for automatic classification tasks in recent times. This abstract presents an overview of the use of CNNs for animal species classification. The proposed approach involves pre-processing of the input images, followed by feature extraction and classification using CNN architecture. The pre-processing step involves image resizing, normalization, and augmentation to enhance the resilience of the model. The feature extraction is performed by convolutional layers, followed by max-pooling layers, and fully connected layers for classification. Transfer learning is also utilized to leverage the pre-trained CNN models and fine-tune them for specific animal species classification tasks. The proposed approach achieves high accuracy of 98% and can be extended to various animal species classification tasks. Overall, CNNs provide an effective means for automated animal species classification, enabling more efficient and accurate animal behavior studies, and wildlife conservation efforts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Learning Multi-UAV Policy for Multi-Object Tracking and Formation Control 18

On Learning Multi-UAV Policy for Multi-Object Tracking and F...

引用

18th IEEE India Council International Conference, INDICON 2021

作者： Kaushik, Prakarsh Garg, Armaan Jha, Shashi Shekhar Electronics and Communication Engineering Ajay Kumar Garg Engineering College India Computer Science and Engineering Indian Institute of Technology Ropar India

ISBN: (纸本)9781665441759

Autonomous navigation and formation control of multi-UAV systems poses a significant challenge for the robotic systems that operate in partially-observable, dynamic and continuous environments. This paper addresses the problem of multi-UAV formation control while cooperatively tracking a set of moving objects. The objective of the multi-UAV system is to maintain the moving objects under their joint coverage along with aligning themselves in an optimal formation for maximizing the overall area coverage. We develop a multi-agent reinforcement learning model to learn a cooperative multi-UAV policy for the multi-object tracking and formation control. We design a reward function to encode the objectives of tracking, formation and collision avoidance into the model. The proposed deep reinforcement learning based model is deployed and tested against a baseline controller using the Gazebo simulator. The result indicates that the proposed model is robust against the tracking and alignment errors outperforming the baseline model. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Developing a Logistic Regression Model for Predicting Chronic Kidney Disease

Developing a Logistic Regression Model for Predicting Chroni...

引用

International Conference on Trends in electronics and Informatics (ICEI)

作者： Nageswara Rao Lavuri Premkumar Borugadda Punnanpu Rama Krishna G Karthik Reddy Department of Electronics and Communication Engineering CVR College of Engineering Hyderabad India Department of Computer Science and Engineering SRM University-AP Andhra Pradesh India Department of Artificaial Intelligence and Machine Learning NRI Institute of Technology Agiripalli Andhra Pradesh India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

This study presents an optimized Logistic Regression-based predictive model for early detection of Chronic Kidney Disease (CKD) using clinical and demographic data. The framework integrates feature selection techniques and hyperparameter tuning to enhance classification accuracy and interpretability. Unlike traditional approaches, our model is evaluated against Decision Tree, Random Forest, and SVM, ensuring comparative robustness. The results show that the proposed approach achieves an accuracy of X %, outperforming existing models while maintaining low computational complexity. This research contributes to personalized healthcare by offering an early-warning system, improving decision-making for medical practitioners, and enabling timely interventions.

关键词： Analytical models Computational modeling Medical services Artificial neural networks Predictive models Data models Chronic kidney disease Glucose Artificial intelligence Slabs

来源：评论

学校读者我要写书评

暂无评论

Energy efficient machine learning based SMART-A-BLE implemented Wireless Battery Management System for both Hybrid Electric Vehicles and Battery Electric Vehicles

引用

Procedia computer science 2023年 218卷 235-248页

作者： Srikalaivani Pannerselvam VAnantha Narayanan T Gireesh Kumar Department of Electronics and Communication Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham 641112 India Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham 641112 India

Electric vehicles have a larger battery pack with more than 100's cells connected in series or parallel combinations to form many battery modules. A Battery Management system (BMS) continuously monitors Current, Voltage, and Temperature data to trigger control algorithms like cell balancing and thermal management using wired communication which is then sent to the cloud for real-time analytics [1]. Wired communication restricts the flexibility in battery module assembly and makes it difficult for battery swapping. The proposed wireless communication, along with the SMART-A-BLE algorithm for BMS in the electric vehicle, uses Bluetooth Low Energy [2], [3], [4], and [5]. SMART-A-BLE algorithm predicts the best connection interval using the Decision tree model based on the link quality factor captured based on real time latency. The model uses threshold latency, expected retransmission factor, data packet length, and the number of peripherals as input features. A look-up table-based algorithm is also proposed for resource constraint devices to achieve the optimal operating point where the slaves could transmit at both low latency and low current consumption with less congestion. SMART-A-BLE control algorithm outperforms the mathematical model-based algorithm in both ideal and interference conditions within a metallic container by maintaining robust connectivity.

关键词： WBMS Bluetooth Low Energy Machine Learning Electric Vehicle Model predictive control Battery swapping

来源：评论

学校读者我要写书评

暂无评论

Intelligent Glasses for the Visually Impaired with Google Cloud API

Intelligent Glasses for the Visually Impaired with Google Cl...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Netish V.P M.Vidhya Lakshmi Puli Venkatesh Kumar K.Durga Devi Puli Nitish Kumar Electronics and Communication Engineering SRM Institute of Science and Technology Chennai India Computer Science Engineering-Data Science St.Ann's College of Engineering and Technology Chirala India

Visually challenged people struggle in their day to day life. People face difficulty in identifying objects, reading and navigation. Canes help them to detect obstacles during traveling. The Idea of this research work is to develop an auxiliary device with sensors that could be connected to ordinary glasses. The Camera provided with the device continuously captures images from the real time environment. The Images are processed with Machine learning algorithms in google vision API. Proposed model informs the user about the obstacles they face during navigation and the travel route. The device can determine the obstacle in front of the user and notify the user about the danger. It also helps the user to read out a text from a label or a document. The API provides a speech based Interface. The user can use voice to activate the device and process the information. The device also interacts with the user through voice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

M2PAIR: A High-Quality Acoustic Impulse Response Computation Model

M2PAIR: A High-Quality Acoustic Impulse Response Computation...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhiyu Li Xinpei Zhao Jing Wang Xinyuan Qian Xiang Xie School of Information and Electronics Beijing Institute of Technology Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Acoustic Impulse Response (AIR) provides crucial spatial information about the environment, significantly enhancing audio immersion. However, achieving high perceptual quality while computing AIR in real-time for interactive audio-video media (IAVM) presents a challenging problem. This study proposes the Mesh to Parametric AIR (M2PAIR), a method for computing AIR designed for IAVM. M2PAIR integrates neural networks with psychoacoustics. It takes the 3D scene mesh, the listener positions, and the sound source positions as inputs, utilizes perceptual parameters as intermediaries, and computes the desired high-quality AIR signal based on these parameters. Experimental results demonstrate that M2PAIR improves the perceptual quality of AIR output compared to existing methods while reducing the model complexity. Additionally, it meets the requirements of IAVM, including real-time computation, high sampling rates, and flexible duration for the output AIR.

关键词： Psychoacoustics Three-dimensional displays Computational modeling Atmospheric modeling Neural networks Media Signal processing Real-time systems Psychoacoustic models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Pattern Recognition of Time-Varying Signals Using Ensemble Classifiers 5th

Pattern Recognition of Time-Varying Signals Using Ensemble C...

引用

5th International Conference on Microelectronics, Electromagnetics and Telecommunication, ICMEET 2019

作者： Subbarao, M. Venkata Terlapu, Sudheer Kumar Chakravarthy, V.V.S.S.S. Satapaty, Suresh Chandra Department of Electronics and Communication Engineering Shri Vishnu Engineering College for Women Bhimavaram India Department of Electronics and Communication Engineering Raghu Institute of Technology Visakhapatnam India Department of Computer Science and Engineering KIIT Bhubaneswar India

ISBN: (纸本)9789811538278

A new classification approach for time-varying power quality (PQ) signals using ensemble classifiers (EC) is proposed in this paper. To achieve high performance, existing expert systems require several signal features so that these systems have more computational complexity. In order to reduce the computational cost and to improve the accuracy further, a new set of features called moments and cumulants are introduced in this paper to classify PQ events. Further, the performance of various ensemble classifiers is analyzed with the proposed feature set. Moreover, the analysis is carried out with different training and testing rates. Finally, the performance comparison is made with that of the existing techniques to prove the superiority of the proposed features and classifiers. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Compact Deep Learning Architecture for Oral Cancer Classification

Compact Deep Learning Architecture for Oral Cancer Classific...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： Sivanagireddy Kalli G. Kalaimani S Sivaprakash P. Suvathi G. Kavitha C. Srinivasan Department of Electronics and Communication Engineering Sridevi Women’s Engineering College Hyderabad Telangana India Department of Computer Science and Engineering Karpagam College of Engineering Coimbatore Tamil Nadu India School of Computer Science and Engineering Vellore Institute of Technology Vellore Tamilnadu India Department of Computer Science and Engineering Muthayammal Engineering College (Autonomous) Namakkal Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

A compact deep learning model is designed to classify oral cancer based on histopathological images in this work. It has the capacity to learn varying quantities of contextual information by making use of image patches. The proposed model consists of four convolution layers and four sub-sampling layers to extract the features. It uses softmax classification in the fully connected layer for the classification. Because of its straightforward architecture, it is a lightweight model that is suitable for use in settings with limited access to resources and in which it may provide superior results in terms of the amount of space and time required. The performance is evaluated using 1224 histopathological images in two distinct resolutions. The first set has 528 images (100 x magnifications) and the second set has 696 images (400 x magnifications). Results prove that the proposed system provides an accuracy of $\sim 98.5 \%$ for both sets when data augmentation is employed.

关键词： Deep learning Accuracy Image resolution Convolution Hospitals Feature extraction Data augmentation Pattern recognition Cancer Image classification

来源：评论

学校读者我要写书评

暂无评论

Cognitive Digital Twin Systems for Predictive Security in AI-Enhanced IoT Environments

Cognitive Digital Twin Systems for Predictive Security in AI...

引用

Software, Systems and Information Technology (SSITCON), International Conference on

作者： M Ravi Kumar Upma Jain Flory Francis s Senthil Kumar Rachit Adhvaryu L Natrayan Department of Electronics and Communication Engineering Cambridge Institute of Technology Bengaluru India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Electronics and Communication Engineering Ramaiah Institute of Technology Bengaluru India Department of Mechanical Engineering R.M.K College of Engineering and Technology Thiruvallur India Department of Computer Science and Engineering Parul institute of Engineering and Technology Parul University Vadodara India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai India

ISBN: (数字)9798350352931

ISBN: (纸本)9798350352948

The Internet has grown in importance and impact over the years, causing people to become more reliant on it. The Internet has evolved into a major vector for cybercrime because to its ever-increasing user base. Over the last decade, the number of these computing systems—including desktops, laptops, smartphones, and the Internet of Things (IoT)—has skyrocketed. Among them, cell phones are practically integral to modern life. The popularity of web-based assaults has skyrocketed with the exponential growth in the number of individuals using the Internet. These web-based assaults are increasingly being combatted by security corporations. Unfortunately, new forms of these assaults are appearing all the time, making it hard for older security measures to stay up. Artificial intelligence (AI) is a source of optimism in the current cybersecurity landscape, offering a potential solution to the ever-changing digital dangers. The fast development of AI over the last decade has given rise to this optimism, because it is now impacting the expansion of every industry. With AI bringing so many advantages in every field, online security is one sector that just cannot afford to ignore it. This thesis represents progress in that direction. This thesis covers research that aims to use AI to tackle significant online security challenges. Security in Internet of Things (IoT) settings powered by artificial intelligence may be improved with the help of cognitive digital twin systems (CDTS). In order to provide proactive security measures, real-time monitoring, and predictive analysis, these systems use cutting-edge AI methods to digitally represent physical IoT devices. In order to anticipate and lessen the impact of security risks, this research introduces a new CDTS architecture that combines cognitive learning skills, anomaly detection, and machine learning models. The suggested approach reduced reaction time to security events by 87.5% and identified zero-day threats with a detection

关键词： Accuracy computer architecture NSL-KDD Vectors Digital twins Security Internet of Things Artificial intelligence Probes Network intrusion

来源：评论

学校读者我要写书评

暂无评论

The Findings of an Empirical Investigation on Cloud-Based Computation Usage as a Strategy Innovation 4

The Findings of an Empirical Investigation on Cloud-Based Co...

引用

4th International Conference on Computation, Automation and Knowledge Management, ICCAKM 2023

作者： Nagendar, Y. Kaur, Chamandeep Jahan, Noor Firdoos Aravinda, K. Devi, Kskn Venkata Ramana Nijhawan, Ginni School of Computer Science & Artificial Intelligent Sr University Telangana Warangal India Jazan University Department of Cs and It Jazan Saudi Arabia Rv Institute of Management Bangalore India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India Institute of Aeronautical Engineering Hyderabad Dundigal India Lovely Professional University Phagwara India

ISBN: (纸本)9798350393248

The current research experimentally examines the elements that influence the usage of cloud-based computation in organizations where the strategy is regarded as strategic for performing their operation. To examine the elements that impact the intent to use cloud computing, a study framework was created that incorporates the elements discovered in the technological acceptance model (TAM) with other exterior elements like high-level management assistance, firm size, training, interaction, and technical complication. The assumptions are tested using data gathered from 150 firms in Andalusia (Spain). The findings of this research demonstrate which key aspects must be examined and the way they are linked. They also demonstrate the organizational needs that should be regarded by businesses that want to use an actual management paradigm tailored to the digital financial system, particularly those associated with cloud computing. © 2023 IEEE.

关键词： Cloud computing

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：