检索结果-内蒙古大学图书馆

International Conference on Inventive Computation technologies (ICICT)

作者： S R Raja Hemlata Arya Ramya.D S Sivakumar Arun Kumar Arigela Nookala Venu Department of Computer Science Saveetha College of Liberal Arts and Science Saveetha Deemed University SIMATS Chennai Department of Computer Science & Engineering Madhav Institute of Technology & Science (MITS) (A Govt.Aided UGC Autonomous Institute) Gwalior Madhya Pradesh India Electrical and Electronics Engineering Sathyabama Institute Of Science and Technology Chennai Department of Electrical and Electronics Engineering Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Chennai Tamilnadu India Department of CSIT Marri Laxman Reddy Institute of Technology and Management (MLRITM) Hyderabad Telangana India Centre for IoT Madhav Institute of Technology & Science (MITS) Gwalior Madhya Pradesh India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

This study investigates the use of Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) to improve power utilization in green data centers. The study examines each model's individual capabilities in addressing key concerns about energy efficiency and sustainability. SVM is extremely accurate in workload prediction and resource allocation, whereas CNN excels in real-time monitoring and cooling system efficiency. RNN contributes by anticipating fluctuations in energy use and adapting to dynamic workload changes over time. The research uses ten hypothetical trials to demonstrate the models' consistent performance across multiple measures. These results suggest that SVM, CNN, and RNN have transformative potential in the development of flexible, efficient, and sustainable green data centers. The study adds to the larger discussion about green computing by emphasizing the role of powerful machine learning models in shaping the future of ecologically responsible data center operations.

关键词： Support vector machines Data centers Recurrent neural networks biological system modeling Computational modeling Green products Machine learning

来源：评论

学校读者我要写书评

暂无评论

Jellyfish Search Optimizer with Deep Learning Driven Cervical Cancer Recognition and Classification Model on biomedical Images

Jellyfish Search Optimizer with Deep Learning Driven Cervica...

引用

International Conference on Advances in Information technology (ICAIT)

作者： M. Suresh Anand S. Venkatramulu Sesha Vidhya S W T Chembian Yashaswini b M Magesh Kumar b Department of Computing Technologies School of Computing SRM Institute of Science & Technology Kattankulathur Department of CSE kakatiya Institute of Technology and science Warangal Department of ECE RMK College of Engineering and Technology Department of CSE Vel Tech High Tech Dr Rangarajan Dr Sakuntala Engineering College Morai Avadi Electronics & Communication Engineering JSS Academy of Technical Education JSSATE-B Campus Bengaluru Karnataka Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam Erode

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The emergence of Cervical Cancer (CC) Recognition and Classification Model for biomedical Images is a main advancement in fields of medical imaging and diagnostics. Leveraging state-of-the-art image processing and machine learning algorithms, this model can accurately detect and classify CC-related abnormalities in medical images, namely colposcopy or Pap smear images. by providing automated and precise assessments, the model empowers medical experts to make timely and informed decisions, which leads to earlier interference and potential life-saving treatment. With its potential to improve diagnostic accuracy and reduce human error, the model holds great promise in the fight against CC, especially in resource-constrained healthcare settings where medical practitioners may be limited. This study presents a Jellyfish Search Optimizer with Deep Learning Driven CC Recognition and Classification (JSODL-CCRC) model on biomedical Images. The JSODL-CCRC technique is mainly developed to investigate the medical images for detection and classification of CC. The JSODL-CCRC approach comprises median filtering (MF) for noise reduction, followed by feature extraction utilizing Inceptionv3 to derive complex image patterns. besides, the JSO based hyperparameter selection process is performed for the Inception v3 model. At last, Extreme Learning Machine (ELM) algorithm is applied to categorize the images which validates efficacy in handling complex biomedical image data. The experimental results stated that the JSODL-CCRC model enables effective detection results over other models.

关键词： Deep learning Image recognition Jellyfish biological system modeling Noise reduction Medical services Feature extraction Medical diagnostic imaging Cervical cancer Tuning

来源：评论

学校读者我要写书评

暂无评论

Data-driven visual analytics of Human Mobility data and green cover using Image Processing for Smart Cities

Data-driven visual analytics of Human Mobility data and gree...

引用

Intelligent technologies (CONIT), International Conference on

作者： Sivasubramanian Ramanathan Kulsoom Syed Tejaswini Chavan SVKMs NMIMS Navi Mumbai B. Tech Computer Science & Business Systems Mumbai India SVKMs NMIMS Navi Mumbai School of Technology Management & Engineering Mumbai India

This research paper presents an approach to data-driven visual analytics of human mobility data using Kernel Density Estimation visualized through heatmaps, highlighting the need for exploration of forecasting methods and intuitive visualizations using the ARIMA model. A specific geographic area is chosen for the demonstration of the scope of the proposed system. The system is a web application developed using Streamlit, an open-source python framework. To effectively implement the smart city concept, it is crucial to integrate diverse iot systems, data sources, data streams, and analytical tools into a unified and seamless platform that facilitates the collection, analysis and presentation of information related to urban systems and subsystems. We propose taking into consideration several attributes when analyzing human mobility patterns, such as vehicle/traffic density, modes of transport, transport data, demographics, latitude, and longitude. Additionally, the system utilizes image processing as an efficient method for calculating urban green cover using morphological operations that are computationally cheaper and easy to use as compared to traditional surveys that are time and resource intensive. This information is used to develop smart plans to sustain or increase green cover in select areas, leading to the creation of sustainable and green smart cities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empowering Safety: Designing of an iot based Women Protective System using Artificial Intelligence enabled Smart Sensors

Empowering Safety: Designing of an IoT based Women Protectiv...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： R. Sonia T Rubesh Kumar G. Naresh S. Durga Devi N Juliet Department of Computer Applications B S Abdur Rahman Crescent Institute of Science and Technology Vandalur Chennai Department of Biomedical Engineering Rajalakshmi Engineering College Chennai Department of ECE Mohan Babu University (Erstwhile SreeVidyanikethan Engineering College) Tirupati Andhra Pradesh Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Avadi Chennai Department of Master of Computer Applications S.A. Engineering College Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Worldwide, women endure a great deal of unethical forms of domestic violence. The lack of an efficient tracking mechanism is speeding this up. An AI-based system that provides protection to vulnerable women was the subject of this research. In critical situations, this framework can respond appropriately automatically and manually. No place is secured for women, but they are more at risk when venturing out on their own into remote areas and unfamiliar roads. After recognizing danger, current women’s handheld safety gadgets require human involvement to activate (e.g., pushing a button or shaking the device). We provide an approach that aims to provide women with false proof safety while also attempting to address the shortcomings of current systems. This system showcases an Arduino-powered wearable safety gadget designed specifically for women. This gadget is designed to protect ladies from harm in case they encounter any risk. The gadget is able to converse and deliver alerts using a wireless sensor network. The user’s precise whereabouts can be sent to designated authorities and stored contacts through the use of GPS and GSM. In the event of an emergency, the device’s switch can be used as a panic button to get a shock; when pressed, the buzzer and laser diode will both activate. This research presents a novel approach to women’s safety, the iot Powered Women Protection (iotPWP), and evaluates its efficacy by cross-validating it with the usual model, the bluetooth enabled Women Safety System (bWSS). We also believe that shows with built-in cameras that record electric shock and broadcasting real-time footage can have an effect on women’s lives through the medium of digital technology.

关键词： Wireless sensor networks technological innovation Electric shock Pressing Switches Watches Real-time systems

来源：评论

学校读者我要写书评

暂无评论

iot and Cloud based Face detection application design for Surveillance systems using Deep Learning 22

IoT and Cloud based Face detection application design for Su...

引用

6th International Conference on Cloud and big Data Computing, ICCbDC 2022

作者： Patil, Gouri bethu, Srikanth bhavani, Y.V.K. Durga Harikrishna, b. Vijayalakshmi, Adluri b Sankara babu Department of It Muffakham Jah College of Engg and Tech Telangana Hyderabad500034 India Department of Cse - Aiml and Iot Vnrvjiet Telangana Hyderabad500090 India Department of Cse National Institute of Technology Telangana Warangal506004 India Department of It Vijaya Institute of Technology for Women VijayawadaAP-521108 India Department of Cse Mallareddy Engineering College Telangana Hyderabad500100 India Department of Cse B v Raju Institute of Technology Telangana Hyderabad502313 India Department of Computer Science and Engineering Griet Telangana Hyderabad500090 India

ISBN: (纸本)9781450396578

Semantic Index, Human Action Detection, and Event Detection are video surveillance packages that assist automate surveillance tasks. Video surveillance structures have entered the generation of virtual surveillance structures in which virtual video is used to traverse the course of different virtual facts. Advances in storage, telecommunications, and facts compression have enabled the increase of more than one technology in virtual surveillance structures. Using more than one video surveillance fashion in risky conditions extends the competencies of rule implementation organizations. In addition, video surveillance enables the form of a motion to carry out in one-of-a-kind conditions. In addition, spotting a particular man or woman in a video is essential for added security, multimedia, and multimedia packages, including offline, seek, and online monitoring of involved humans within the video. The proposed iot- Cloud based Face detection application is designed to find a person from a huge size dataset and that can generate more accurate results. This application uses Deep Learning methods to find exactness when classifying the images. iot here is used for liveness detection by comparing all the images present in cloud systems. For results comparison, we used Haar Cascade and DenseNet architectures. © 2022 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Individual Privacy Protection in Cybersecurity Using Data Analytics and Machine Learning

Individual Privacy Protection in Cybersecurity Using Data An...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： M. Arun bhavadharani K b. R. Supreeth Sumit Pundir K Pradeepa K. Abdul Razak Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering V.S.B. Engineering College Karur Tamil Nadu India Department of Computer Science Oxford Degree and PG College Bangalore India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Artificial Intelligence and Data Science KPR College of Arts Science and Research Coimbatore Tamil Nadu Department of Mathematics K. Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Traditional cybersecurity addresses struggle to keep up with the ever-changing nature of cyber threats and usually fail to detect new privacy breaches. The paper proposes a proactive protection mechanism that employs data analytics and machine learning (ML) to promote individual privacy in the digital realm. The system analyzes several data sources, including system events, network traffic, and user activity logs, using advanced ML methods like Random Forests (RF), Support Vector Machines (SVM), and Neural Networks (NN), to detect and prevent privacy violations. Ensemble learning techniques, feature engineering, and real-time monitoring enable adaptability in the face of shifting threats. According to the results, the proposed system surpassed the existing system in terms of accuracy (0.92), recall (0.89), precision (0.91), and F1 score (0.90). Its ability to detect unlawful access, unusual logins, and irregular data requests is proved by anomaly detection rates utilizing One-Class SVMs (91%) and Isolation Forest (89%). The system's low false positive rate of 5% demonstrates how effectively it can detect privacy breaches, resulting in stronger cybersecurity and greater privacy protection for both individuals and enterprises.

关键词： Support vector machines Data privacy Data analysis Accuracy Scalability Telecommunication traffic Data collection Privacy breach Protection computer security

来源：评论

学校读者我要写书评

暂无评论

A Recommendation System for Crop Prediction Under Diverse Weather Conditions

A Recommendation System for Crop Prediction Under Diverse We...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： P ShunmugaLakshmi V Ram Kishore Pillai Pratham Ramachandran S Santhi S Kalaiselvi B.Tech Information Technology National Engineering College Kovilpatti Tamil Nadu Dept. of Information Technology National Engineering College Kovilpatti Tamil Nadu Dept. of Computer Science and Engineering National Engineering College Kovilpatti Tamil Nadu

In order to develop strategic initiatives in agricultural belonging for trading protocol and tripling countrymen earnings, early and accurate agricultural output estimation is pivotal in computable and commercial decision at the territory plane. Crop production forecasting, which is done to foresee a greater crop output, is the impressive difficulty in the agronomic division. To help farmers increase agricultural yield, this study has collected and evaluated data on N, P, K, temperature, humidity, ph, rainfall and soil_moisture. The superior values of this work are to recommend the crop to cultivate, suggest the appropriate fertilizers to use and predict the disease of a crop. A python environment is used to perform initial preprocessing on the data. KNN classification is used for developing the recommendation system. The link between the count, nutrients, temperature, humidity, pH, rainfall, and crop, are visualized using bar graphs and scatter plots. The tensor and torch were used to forecast crop disease and also to suggest appropriate fertilizer based on the data. The application was developed using Python Flask. This Classification was compared with other algorithms such as SVM, DT , RF and K-means.

关键词： Support vector machines Temperature sensors Linear regression Crops Humidity Prediction algorithms Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Predicting the Quantity of Municipal Solid Waste using XGboost Model 3

Predicting the Quantity of Municipal Solid Waste using XGBoo...

引用

3rd International Conference on Inventive Research in Computing Applications, ICIRCA 2021

作者： Jayaraman, Vaishnavi Parthasarathy, Saravanan Lakshminarayanan, Arun Raj Singh, Hiran Kumar B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9780738146270

The quantity of Municipal Solid Waste (MSW) gets intensified, based on various factors such as population growth, monetary status and consumption patterns. The insufficiency of elementary trash data is a critical problem for managing the MSW. In this study, the goal is to forecast the MSW generation of Northern Ireland. A precise model was developed to estimate the total amount of waste produced for every quarter of the year, by employing the Machine Learning techniques. The seasonal ARIMA (s-ARIMA) and Extreme Gradient boosting (XGboost) models were employed to estimate the amount of waste produced. On comparing both the models, XGboost performed better. Thus, the parameters of the XGboost were tuned to yield the optimal outcome. The XGboost with the tuned hyperparameters achieved an optimum result with the higher coefficient of determination (R2) value as 0.5325 and lower RMSE value of 13215.97. The prediction of the MSW weight would help the decision-makers in treating and disposing solid waste appropriately. © 2021 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Non-Rigid Registration with Volumetric Mesh for Liver Surgery

SSRN

引用

SSRN 2024年

作者： Zhang, Yanying Liu, Peter xiaoping Hou, Wenguo School of Mechanical Engineering Zhejiang Sci-Tech University Zhejiang Hangzhou China School of Information Science and Engineering Zhejiang Sci-Tech University Zhejiang Hangzhou China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Department of Systems and Computer Engineering Carleton University OttawaONKIS 5B6 Canada

In image-guided liver surgery, the registration of preoperative reconstructed liver model with intraoperative captured surfaces is extremely challenging, due to the limited visibility of liver surfaces and the impact of soft tissue deformation. In order to solve this problem, this paper presents a novel nonrigid registration method that achieves accurate alignment between the preoperative reconstructed volumetric liver mesh and a portion of the intraoperative captured liver surface. A deformation subspace is incorporated to characterize the deformation of volumetric liver mesh during registration, ensuring volume preservation of the liver mesh. The proposed method enables to capture both surface and inside deformation of the liver, thus improving the flexibility and accuracy of the *** majorization-minimization (MM) algorithm with limited-memory broyden fletcher goldfarb shanno (L-bFGS) is introduced to solve the optimization problem in the registration process, thereby effectively improves the computational efficiency of the non-rigid registration. The experimental results show that the volume relative error is less than 2% and the registration error is less than 1mm. The proposed method can reduce mesh distortion, and maintain organ volume. It provides a promising solution for aligning the liver mesh between preoperative and intraoperative periods. © 2024, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Identification of Advanced breast Cancer by Using Aggregate Deep Learning Method

Identification of Advanced Breast Cancer by Using Aggregate ...

引用

Communication, Computing and Energy Efficient technologies (I3CEET), International Conference on

作者： V. J. Chakravarthy Sangeetha Varadhan Sridevi Sakhamuri R. Vijayabharathi Fathima S. K Saritha K Faculty of Computer Applications Dr. M.G.R. Educational and Research Institute Chennai India Department of Computer Applications Dr. M.G.R. Educational and Research Institute Maduravoyal Department of IoT Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Andhra Pradesh Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology(Deemed to be University) Chennai Department of CSE Sona College of Technology Salem Department of Computer Applications Muthoot Institute of Technology and Science Kochi

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

Metastasis is the main factor contributing to death in breast cancer patients. Faster and more accurate deep learning algorithms are being researched as potential replacements for the current, labor-intensive techniques used to diagnose metastases from lymph nodes. For testing and training purposes, a total of 220025 whole-slide pictures representing the lymph nodes of two cohorts of patients were identified. In order to detect metastatic cancer, we used a hybrid convolutional neural network model. A total of 57458 unlabeled images were utilized in order to verify the accuracy, sensitivity, specificity, and P-value of our diagnostic method. The DL-based approach was created to automatically and selectively assess and identify metastasizing lymph nodes. In the quantification procedure, accuracy was 98.84%. Moreover, the accuracy rates for VGG16 and Recall were 92.42% and 91.25%, respectively. The differentiation levels of metastatic cancer may have an impact on recognition performance, according to later study. Our devised diagnostic complex showed a high degree of efficacy and accuracy for lymph node diagnosis. Patients with breast cancer may find it simpler to perform pathological screening for metastases thanks to our innovative DL-based method.

关键词： Deep learning Training Pathology Accuracy Sensitivity Convolution breast cancer Metastasis Convolutional neural networks Lymph nodes

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：