检索结果-内蒙古大学图书馆

Data Science and Business Systems (ICDSBS), International Conference on

作者： Vanitha N Vivekanandan G Nehashree G Sasmitha S Keerthana M Laashya Lakshmi M Computer Science and Engineering Sri Sairam Institute of Technology Chennai India Electronics and Communication Engineering St. Joseph's Institute of Technology Chennai India

ISBN: (数字)9798331585600

ISBN: (纸本)9798331585617

The disposal of street waste is a complicated task in smart cities owing to preposterous waste management practices. The paper proposes an integrated system architecture, utilizing the YOLOv8 algorithm for real time classification of street garbage, citizen collaboration with incentives, and vendor-based integration with note for segregation and distribution. The dustbins are embedded with sensors to measure the fill level and send an alarm if it is surpassed. The citizens are updated centrally using a web application on the current state of cleanliness coupled with the collection progress of the waste. Proper disposal of waste is rewarded, and vendors are provided with segregated garbage for recycling, solving the problem of poor waste management.

关键词： Waste management Smart cities Surveillance Current measurement Systems architecture Collaboration Data science Real-time systems Recycling Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Agriculture Productivity and Automation of Agriculture using IoT 6

Enhancement of Agriculture Productivity and Automation of Ag...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Seetha, J. Senthil Kumar, S. Nruthya, K. Rao, Nynalasetti Kondala Kameswara Leela Rani, D. Department of Computer Science and Business Systems Panimalar Engineering College Chennai India Department of Mechanical Engineering R.M.K College of Engineering and Technology Thiruvallur India Department of Civil Engineering Indian Institute of Science Bengaluru India Department of Computer Science and Engineering Sagi Rama Krishnam Raju Engineering College Bhimavaram India Department of Electronics and Communication Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798350398496

The utilisation of sensor networks in agriculture monitoring is the invention that benefits Indians the most. Given that agriculture is the primary source of revenue, it is essential to boost production while decreasing expenses, inputs of time, and labour. Information gathered from agricultural areas is stored in a database, which may be monitored via the Internet of Things (IoT). Connecting Raspberry Pi with IoT and sensors to increase agricultural activity productivity is the challenging task in the Farm Management System for secure agriculture. Temperature, humidity, soil moisture content, and any field fires are tracked as a challenge's outcome. Specifications like temperature, moisture content, and fire are currently detected manually in farm systems. This technique automates the completion of watering. It used to lighten the workload for farmers. Any type of crop productivity is feasible. This method's drawbacks include an increase in labour costs, increased time requirements, and the inability to do continuous monitoring. © 2023 IEEE.

关键词： Wages

来源：评论

学校读者我要写书评

暂无评论

The three dimensional dosimetry imaging for automated eye cancer classification using transfer learning model 14

The three dimensional dosimetry imaging for automated eye ca...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Mohammed, Murtuza Ali Mohammed, Vazeer Ali Ramakrishnan, Rakesh Mohammed, Mehmood Ali Logeshwaran, J. Maheswaran, S. Lewis University Department of Computer & Information System IL United States University of the Cumberlands Department of Information Technology Union CityCA United States University of the Cumberlands Department of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Electronics and Communication Engineering Tamil Nadu Erode India

ISBN: (纸本)9798350335095

computer vision methods utilizing transfer learning can offer a promising approach for automated eye cancer diagnosis with three-dimensional dosimetry imaging. The latest advances in AI have encouraged researchers to use deep learning models for automated cancer classification. This paper presents a novel approach using three-dimensional dosimetry imaging for automated ocular cancer classification using transfer learning. The approach uses a combination of dataset augmentation methods. The approach is adapted from the popular Inception V3 CNN architecture. Two different feature extraction approaches, namely mean and maximum pooling, are compared while extracting features from the output of the CNN layers. The extracted features are fed to the classifier which uses the SVM with a linear kernel as its decision system. The effectiveness of this method is evaluated on a set of 20 healthy ocular images and 26 suspicious ocular images. The overall classification accuracy achieved with this approach is 94.85%. The results obtained demonstrate that this approach has a promising potential for automated ocular cancer classification with an appropriate transfer learning model. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Automation of Traffic Signal for Better Commutation of Vehicles

Automation of Traffic Signal for Better Commutation of Vehic...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Aarzoo Vaghela Padaya Maruf Naorem Yaipharenba Meitei Laiphrakpam Dolendro Singh Department of Computer Science and Engineering National Institute of Technology Silchar Assam India NineLabs Electronics & Electrical Engineering Indian Institute of Technology Guwahati Assam India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Traffic congestion poses a significant challenge in urban areas globally, resulting in wasted time, increased fuel consumption, and heightened pollution levels. Traditional traffic light systems often rely on fixed timers, failing to adjust to fluctuating traffic patterns and causing unnecessary delays. To tackle this issue, an adaptive traffic signal timer is designed to dynamically respond to real-time traffic conditions. The proposed system harnesses live camera feeds from traffic junctions and employs object detection techniques to analyze traffic density accurately. The proposed method represents a proactive approach to addressing urban congestion challenges, promising more efficient traffic management and improved commuting experiences for residents and commuters. A comprehensive simulation platform is developed to validate our system’s efficacy and facilitate comparative analysis with existing static systems.

关键词： Pollution Urban areas Object detection Traffic control Real-time systems Fuels Vehicle dynamics Junctions Intelligent systems Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

An innovation prediction of DNA damage of melanoma skin cancer patients using deep learning 14

An innovation prediction of DNA damage of melanoma skin canc...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Ramakrishnan, Rakesh Mohammed, Mehmood Ali Mohammed, Murtuza Ali Mohammed, Vazeer Ali Logeshwaran, J. Maheswaran, S. University of the Cumberlands Department of Information Technology Union CityCA United States University of the Cumberlands Department of Information Technology WilliamsburgKY United States Lewis University Department of Computer & Information System IL United States Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Electronics and Communication Engineering Tamil Nadu Erode India

ISBN: (纸本)9798350335095

There are now a variety of intriguing options for the study of genetic data thanks to recent developments in artificial neural networks and deep learning. In this study, we use a deep learning-based prediction model to find possible DNA damage in individuals with melanoma skin cancer. We create a convolutional neural network (CNN) model to forecast the DNA damage susceptibility of melanoma cancer cells using a publically available genome sequencing dataset. This model preprocesses the genomic data, extracts features, and categorises them. Comparing the results of our CNN model with those of a traditional logistic regression model, we find that our CNN reported superior performance in identifying differences between healthy and cancerous samples with an accuracy of nearly 96%. The model can be used to augment the standard clinical diagnosis of melanoma, which only uses visual assessment and histology. By intervening sooner, clinicians can put forward more personalized and informed plans of care and surveillance for each melanoma patient, reducing medical costs and improving the quality of patient diagnosis. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Secure Data Reduplication System with Efficient and Reliable Multi-Key Management in Cloud Storage 3

Secure Data Reduplication System with Efficient and Reliable...

引用

3rd International Conference on Innovative Practices in technology and Management, ICIPTM 2023

作者： Jayaram, B. Suguna, T. Fairooz, Shaik Arul Selvam, P. Vimal, S. Rmk Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavaraipettai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Malla Reddy Engineering College Department of Cse -AIML Telangana Secunderabad India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350336238

Malicious hackers may compromise hundreds or millions of machines with little effort, allowing them to shut down networks, steal sensitive data, and compromise critical infrastructure. Data is stolen and used for malicious purposes by hackers who exploit security flaws in the network. And the sophisticated technology they use, like the bucks they do, are continually feeding them the information they needed, not just once. Moreover, even if Internet firewalls have improved, cybercrime has been on the rise. Then, we have a long way to go before we approach the limit, what with all the different kinds of cloud server devices that can connect to the internet nowadays. It's certain that in the future, little devices, no matter how helpful they are really in our everyday lives, will become the preferred tool of villains. In this research, we offer a novel security technique for protecting sensitive data on cloud servers. This intelligent cloud server was protected from any hacking with the aid of this algorithm. The system's output was measured against those of pre-existing algorithms. More than 96% of inputs are authenticated by the proposed technique, while password cracking operations are reduced by about 3%. The source code security management is improved to 99% and the updating issues for various devices entries is reduced 0.02%, and further the privacy breach is reduced up to 0.32%. Hence the proposed method was more secured from cyber security issues. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Automatic Facial Expression Recognition Employing CNN-Inception and the ResNet 50

Automatic Facial Expression Recognition Employing CNN-Incept...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Krishnakumari, K. Padmapriya, S. Abirami, N. Kanaghadhara, N.E. Arul, P. Department of Computer Science and Engineering name of organization A.V.C. College of Engineering Mayiladuthurai India Department of Information Technology R.M.D. Engineering College Chennai India Department of Electronics and Communication Engineering R.M.D. Engineering College Chennai India

ISBN: (纸本)9798350305708

The ability of computers to accurately determine the human state of mind can be improved with the help of the recognition of human facial expressions that reflect emotions. This will make it possible for workplace interactions to be more tailored to the individual. We will be able to recognize the emotions by paying attention to the placement of the brows and eyes, as well as the position of the mouth and the various changes that occur in the facial features. Using a deep learning Convolutional Neural Network (CNN)-INCEPTION and RESNET50 network model, we examine the recognition of human face expressions. The system utilizes a labeled data set that has around 32, 298 photos with a variety of facial expressions. This data set is used for both training and testing purposes. A CNN model is trained using the dataset's grayscale photos to categorize facial expressions into one of five categories: happy, sad, neutral, fearful, or furious. The use of batch normalization and dropout helps to increase the accuracy of the model while also preventing it from becoming overfit. © 2023 IEEE.

关键词： CNN Facial Expressions Inception Normalization ResNet50

来源：评论

学校读者我要写书评

暂无评论

An Improved Fingerprint-based Document Image Retrieval using Multi-resolution Histogram of Oriented Gradient Features

引用

International Journal of engineering, Transactions A: Basics 2022年第4期35卷 750-759页

作者： Dixit, U.D. Shirdhonkar, M.S. Department of Electronics and Communication Engineering BLDEA's V. P. Dr. P. G. Halakatti College of Engineering & Technology Vijayapura India Department of Computer Science and Engineering BLDEA's V. P. Dr. P. G. Halakatti College of Engineering & Technology Vijayapura India

Recently most of the documents are authenticated by using a latent fingerprint impression. Examples of such documents are property registration, banking transactions, insurance documents, etc. The fingerprint-based document retrieval (FPDIR) has emerged to provide an easier way of accessing, browsing, or searching such document images. This paper proposes efficient fingerprint-based document image retrieval by employing multi-resolution Histogram of Oriented Gradient (HOG) features. The preprocessing technique presented in this paper employs a combination of top-hat and bottom-hat filtering operations to enhance the detected fingerprint image. Multi-resolution HOG features are constructed from horizontal, vertical and diagonal directional components of the enhanced fingerprint image. Finally, a standardized Euclidean distance metric is used as a tool for matching, ranking and retrieval of the document images. The proposed system is assessed by experimenting with a dataset of 1200 images. The precision and recall results obtained using the proposed research work have given an improvement of 8% to 14% in retrieval performance compared to earlier methods. © 2022 Materials and Energy Research Center. All rights reserved.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

KDProg: A Knowledge distillation graph neural network for cancer prognosis prediction and analysis

KDProg: A Knowledge distillation graph neural network for ca...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Xiong, Shuwen Wang, Zixuan Zhang, Junming Luo, Hong Zhang, Yongqing Zou, Quan Chengdu University of Information Technology School of Computer Science Chengdu China Sichuan University College of Electronics and Information Engineering Chengdu China University of Electronic Science and Technology of China Institute of Fundamental and Frontier Sciences Chengdu China

ISBN: (纸本)9798350337488

Accurately predicting cancer prognosis remains challenging, owing to the combination of computational and practical challenges. This study proposes KDProg, a knowledge distillation-based graph learning framework for predicting cancer prognosis and exploring downstream tasks. The framework includes a novel feature distillation paradigm that compresses a multi-layer complex teacher model to a single-layer simple student by using the teacher model's middle-layer feature representations and outputs as supervision information to improve the student model's performance. In addition, instead of introducing a unified temperature hyperparameter, KDProg adopts a novel strategy to parameterize the distillation temperature and combine it with the Cox partial log-likelihood function. So the model can learn the appropriate temperature. Furthermore, considering multi-omics data of patients are often complex to obtain in practical cancer prognosis, this paper uses different input data for the teacher and student models, respectively. The input data for the teacher model are multi-omics data (mRNA, CNV, and DNA methylation), clinical data, and KEGG pathways. The input data for the student model are mRNA, clinical data, and KEGG pathways. Extensive experiments on 15 real-world datasets from TCGA demonstrated the effectiveness and efficiency of the proposed method in predicting cancer prognosis. The results suggest that the proposed model can guide clinical decision-making. © 2023 IEEE.

关键词： cancer prognosis graph neural networks knowledge distillation multi-omics data survival risk prediction

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Efficiency in Smart Healthcare Systems using an Improved Enumeration Algorithm for 5G-IoT

Optimizing Energy Efficiency in Smart Healthcare Systems usi...

引用

Distributed Computing and Electrical Circuits and electronics (ICDCECE), IEEE International Conference on

作者： Aby K Thomas A. Jeraldine Viji Gunavardini V Bhukya Balakrishna Suman Mishra Amit Lathigara Department of Electronics and Communication Engineering Alliance School of Applied Engineering Alliance University Bengaluru India Department of Electrical and Electronics Engineering Mailam Engineering College Villupuram India Department of Computer Science and Engineering Bannari Amman Institute of Technology (Autonomous) Erode India Department of Computer Science and Engineering(Data Science) MLR Institute of Technology Hyderabad India Department of Electronics and Communication Engineering CMR Engineering College Hyderabad India Department of Computer Science and Engineering School of Engineering RK University Rajkot India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

High-power radio connection, such as that provided by the Fifth Generation (5G) in the transmission of data, is necessary for IoT devices in order to provide immediate surveillance on patients. In the field of healthcare, the fast implementation of IoT equipment that is allowed by 5G has brought about a revolution by giving capabilities to measure and diagnostics that are both efficient and real-time. These issues include the fact that there is not a standard structure for dealing with the apps, that there is not enough of resource improvement, which results in the waste of bandwidth on the networks, that there is a lack of resources that are environmentally conscious, and that the primary worry is the lack of fraudulent information or the privacy of private healthcare information. For the purpose of enhancing the thermal effectiveness in uplink transfer, an enhanced Optimal Enumeration Algorithm (OEA) with Proximity based Service (ProSe) has been suggested for use in Device-to-Device (D2D) communications. Furthermore, the findings of the simulator demonstrate that the better outcomes are achieved with greater energy utilization and reduced computing difficulty that is achieved. Outperforming both OEA and Round Robin, the Improved OEA (Proposed Method) attains an accuracy of 92.89%.

关键词： 5G mobile communication Surveillance Supply chains Standards organizations Medical services Real-time systems Device-to-device communication Internet of Things Velocity measurement Uplink

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：