检索结果-内蒙古大学图书馆

Terrain identification and land price estimation using deep learning

AIP Conference Proceedings 2021年第1期2387卷

作者： K. Kousalya B. Krishnakumar A. S. Aswath P. S. Gowtham S. R. Vishal 1Professor Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu 638060 India 2Assistant Professor Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu 638060 India 3UG Scholar Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu 638060 India

The real estate market is becoming one of the most competitive in terms of pricing and same tends to vary significantly based on various factors. This paper focuses on identifying the type of land and estimating the price using convolutional neural network. Deep learning algorithms exhibit marvelous performance over conventional machine learning algorithms identifying the complex patterns. In this paper two Convolutional Neural Network (CNN) models are used. One is self-proposed model and another is ResNet152V2 model. Models are trained using aerial land image dataset. The ResNet152V2model showed high accuracy compared to the self proposed model. This system helps the land owner to acquire some basic essential details about the land.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Question Answering Systems for Covid-19

引用

Journal of Physics: Conference Series 2021年第1期2062卷

作者： Poonam Gupta Ruchi Garg Amandeep Kaur Assistant Professor Computer Science and Engineering Department MMEC M.M.(Deemed to be) University Mullana Ambala Haryana India guptapoonam 231 Assistant Professor Electronics and Communication Engineering Department MMEC M.M. (Deemed to be) University Mullana Ambala Haryana India Associate Professor Computer Science and Engineering DepartmentMMEC M.M. (Deemed to be) University Mullana Ambala Haryana India

In the present scenario COVID-19 pandemic has ruined the entire world. This situation motivates the researchers to resolve the query raised by the people around the world in an efficient manner. However, less number of resources available in order to gain the information and knowledge about COVID-19 arises a need to evaluate the existing Question Answering (QA) systems on COVID-19. In this paper, we compare the various QA systems available in order to answer the questions raised by the people like doctors, medical researchers etc. related to corona virus. QA systems process the queries submitted in natural language to find the best relevant answer among all the candidate answers for the COVID-19 related questions. These systems utilize the text mining and information retrieval on COVID-19 literature. This paper describes the survey of QA systems-CovidQA, CAiRE (Center for Artificial Intelligence Research)-COVID system, CO-search semantic search engine, COVIDASK, RECORD (Research Engine for COVID Open Research Dataset) available for COVID-19. All these QA systems are also compared in terms of their significant parameters-like Precision at rank 1 (P@1), Recall at rank 3(R@3), Mean Reciprocal Rank(MRR), F1-Score, Exact Match(EM), Mean Average Precision, Score metric etc.; on which efficiency of these systems relies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attendance Management System Using Face Recognition Method

引用

Journal of Physics: Conference Series 2021年第1期2089卷

作者： Syed Mansoora Giribabu Sadineni Shaik Heena Kauser P.G Scholar Department of Computer Science & Engineering PACE Institute of Technology and Sciences A.P India Associate Professor Department of Computer Science & Engineering PACE Institute of Technology and Sciences A.P India Assistant Professor Department of Computer Science & Engineering PACE Institute of Technology and Sciences A.P India

When it comes to classroom management, the attendance check is a critical component. Time-consuming, particularly when it comes to open meetings, is checking attendance by calling names or by handing around a sign-in sheet to make it easier to commit fraud. An implementation of a real-time attendance check is described in this article in great detail facial recognition system and its outcomes. The system must be able to identify a student's face in order for it to work first snap a photograph of the pupil and save it in a database as a reference for future use. During the event, there were students may be identified by using the webcam, which captures photos of their faces auto-detects faces and selects students with names that are most likely to match, and lastly, depending on the facial recognition findings, an excel file will be updated to reflect attendance. To identify faces in webcam footage, the system uses a pre-trained Haar Cascade model. As a result, a 128-bit FaceNet has been generated by training it to minimise the triplet loss. The dimensions of the facial picture. When two facial pictures have similar encodings If the two facial pictures are from the same student or different. Use of the system as part of a class, and the outcomes have been extremely positive. There has been a poll done to find out more about There are both advantages and disadvantages to using a college attendance system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experience of Truth-Telling From the Viewpoints of Family in the Intensive Care Units

引用

Hu li za zhi The journal of nursing 2020年第4期67卷 50-60页

作者： Kung, Chen-Ning Yeh, Chun-Yin Lai, Wei-Shu Chen, Chin-Ming Ko, Nai-Ying 1MSN RN Department of Nursing Chi Mei Medical Center Taiwan ROC PhD RN Postdoctoral Research Fellow Department of Computer Science and Information Engineering College of Electrical Engineering and Computer Science National Cheng Kung University Taiwan ROC PhD RN Assistant Professor Department of Nursing College of Medicine National Cheng Kung University Taiwan ROC MD Attending Physician and Professor Department of Intensive Care Medicine Chi Mei Medical Center ROC Taiwan PhD RN Distinguished Professor Department of Nursing College of Medicine National Cheng Kung University Taiwan ROC

TITLE: 從加護病房家屬觀點探究重症病情告知的經驗. 背景: 病情告知是減少醫病認知落差的重要步驟，且能減輕家屬心理壓力。現階段研究仍缺乏家屬對重症病情告知經驗及需求之探討。. 目的: 瞭解重症家屬病情告知經驗及過程需求。. 方... 详细信息

TITLE: 從加護病房家屬觀點探究重症病情告知的經驗. 背景: 病情告知是減少醫病認知落差的重要步驟，且能減輕家屬心理壓力。現階段研究仍缺乏家屬對重症病情告知經驗及需求之探討。. 目的: 瞭解重症家屬病情告知經驗及過程需求。. 方法: 採描述現象學，立意取樣5位加護病房疾病嚴重度≥ 20分的病人家屬進行深度訪談。以Giorgi現象學分析法，利用Nvivo 11分析歸納資料。. 結果: 整體經驗包含四大主題：（一）訊息聽了無法懂，希望疑問詳細解、（二）無助找尋為解答，期望護理來幫忙、（三）託付專業卻無奈，渴望醫療多些愛、（四）重重難關多牽絆，盼望見解來割斷。. 結論／實務應用: 病情告知著重傳遞結果，家屬無法理解病情變化原因。本研究建議醫療專業人員應體認家屬認知程度，並顧及其情緒反應，納入家屬需求及期待，以病人為中心提供個別化告知。.;BACKGROUND: Truth-telling is an important step toward reducing the cognitive gap between physicians and patients as well as reducing the psychological pressures applied to physicians by family members. There is a lack of research on the truth-telling experience and needs in the intensive care unit from the perspective of patient family members. PURPOSE: This study is designed to explore the experiences and needs of families in the intensive care unit. METHODS: A descriptive phenomenology method was used in this study. In-depth interviews were conducted with five participants who had family members assessed with acute physiology and chronic health evaluation II scores ≥ 20. Data were analyzed using Giorgi's phenomenological methods and Nvivo 11. RESULTS: Four experience themes were examined, including (1) nothing is clear, requires explanation;(2) helpless to find answers, need a nurse to resolve this issue;(3) professional conduct makes us feel helpless, longing for love from the medical team;(4) decisions are very difficult, hoping to get more help. CONCLUSIONS / IMPLICATIONS FOR PRACTICE: The family members expressed that they were unable to understand the underlying causes of the progression in patient condition because the medical team only presented outcomes to the family and did not discuss related causes. Thus, it is recommended that medical teams learn to recognize the cognitive processes of patient family members and consider their emotions, including their needs and expectations, in order to provide individualized explanations based on a patient's status and progress.

关键词： family needs intensive care unit phenomenology truth-telling

来源：评论

学校读者我要写书评

暂无评论

A reversible data hiding method for image protection

引用

AIP Conference Proceedings 2021年第1期2387卷

作者： S. S. Saranya C. Santhosh M. Santhiya S. Jeevana J. Dhivya A. Vanitha 1Assistant Professor Computer Tehnology UG Kongu Engineering College. Perundurai Tamil Nadu-638060 India 2Assistant Professor Department of Computer Science Engineering Nandha Engineering College Perundurai Tamil Nadu-638052 India 3UG Scholar Computer Tehnology UG Kongu Engineering College Perundurai Tamil Nadu-638060 India

Encryption is the way toward encoding given information that can't be perceived by an unapproved individual. Securing a message or a picture which is partaken in a social stage be the difficult undertaking these days. This paper proposes an account procedure to steganography by means of reversible room before encryption surface mix. Reversible room before encryption surface mix measure explore supplementary unobtrusive side picture that arranges different facet picture with a similar and relative appearance with optional dimensions. This paper networks the Reversible room before encryption surface association cycle with steganography for covering secrete data. Rather than using contemporary cover photo for covering information our figure seal the source surface picture and introduces coded message via pattern of Reversible room before encryption surface association. This licenses us to isolate the secret messages and source surface from a stego designed surface. This philosophy proffers main three focal points. Most importantly, the positioning provide data embedding furthest extended that is contrast to dimensions of surface of the stego picture. Second, a steganalytic compute not apparently to conquer steganography technique. Third, changeable capacity gained from our arrangement gives value, which grants recovery surface of the source. Exploratory results are guaranteed to provide various consignment of introducing curtailment, produce ostensibly viable surface pictures, and also recuperate fount surface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling of an Adaptive Energy Based Route Broadcasting Algorithm (AERBA) Using Route Optimization in MANET

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1084卷

作者： S B Manoojkumaar C Poongodi Assistant Professor Department of Computer Science and Engineering J.K.K.Munirajah College of Technology T.N.Palayam Professor & Head Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam

Owed to the uncertain and dynamic behaviour of nodes over Mobile Ad-Hoc Networks (MANETs), the reliable route discovery and data delivery is considered as a challenging factor. With absence of centralized infra-structure and global broadcasting nature, nodes over the distributed environment rely over the neighborhood nodes. For reliable communication, the network needs to broadcast the routing direction to chose the appropriate neighborhood partner to make the functionality effectual during packet relying. Therefore, the evaluation process is determined to be a crucial factor. Various methodologies use the trust-based concepts for choosing the route broadcasting region and neighborhood nodes. However, those methods are identified with certain limitations and the evaluation is performed over single node. The inadequate consideration of these factors leads to the wider range of network model that leads to inappropriate broadcasting. This leads to packet loss, higher energy consumption due to re-transmission of packets. In this work, an Adaptive Energy-based Route Broadcasting Algorithm (AERBA) using Route Optimization (RO) is applied along with the route optimization approach to derive the global solutions. This leads to the trust establishment among the network nodes and pretends to fulfill the constraints related to broadcasting and energy consumption. The anticipated model facilitates appropriate evaluation over the potential nodes with multiple hops for balancing the route broadcasting and energy consumption. Simulation is carried out in MATLAB environment and the results demonstrate lesser energy consumption, higher delivery ration when compared with prevailing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning approach for grading of Diabetic Retinopathy

引用

Journal of Physics: Conference Series 2021年第1期1767卷

作者： T Aswathi T R Swapna S Padmavathi Student Research Scholar Department of Computer Science Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India. Assistant Professor Department of Computer Science Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India.

There has been a wide interest in applying Deep Learning (DL) algorithms for automated binary and multi class classification of colour fundus images affected with Diabetic Retinopathy (DR). These algorithms have shown high sensitivity and specificity for detecting DR in non-clinical setup. Transfer learning has been successfully tested in many medical imaging applications like skin cancer detection, pulmonary nodule detection, Alzheimer's disease etc. This paper experiments with the different DL architectures such as VGG19, InceptionV3, ResNet50, MobileNet and NASNet for automated DR classification (binary and multi class) on Messidor dataset. The dataset is publicly available, and comprises of 1200 retinal fundus images. The images belong to four different classes of DR namely, normal (class 0), mild (class 1), moderate (class 2) and severe (class 3), graded based on the severity level of DR. In our experiment, we have enhanced the quality of input images by applying algorithms like CLAHE (Contrast Limited Adaptive Histogram Equalisation) algorithm and Powerlaw transformation as pre-processing techniques, which work on the small image patches with high accuracy, contrast limiting and image sharpening. Hyper parameter tuning on pretrained InceptionV3 architecture, resulted in enhancing the accuracy of the model. Both binary and multi class results were analysed considering inter class (one class with another class) accuracies. We achieved an accuracy of 78% between class 0 and class 1, the accuracy between class 0 and class 2 further reduced to 69%, while class 1 and class 2 showed an accuracy of 61%. Moreover, the interclass class accuracy between class 1 and class 3 was 62%, class 2 and class 3 further reduced to 49%. The accuracy further diminished between class 0 and class 3 to 32%. These experiments suggest that the pretrained models provided better results in classifying normal and mild, but they were not that much efficient in classifying moderate-severe and

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object and lane detection for autonomous vehicle using YOLO V3 algorithm

引用

AIP Conference Proceedings 2021年第1期2387卷

作者： Mohanapriya S. Natesan P. Indhumathi P. Mohanapriya S. T. P. Monisha R. 1Assistant Professor Department of Computer Science and Engineering Kongu Engineering College Perundurai Erode Tamil Nadu India 2Professor and Head Department of Computer Technology Kongu Engineering College Perundurai Erode Tamil Nadu India 3UG Scholar Department of Computer Science and Engineering Kongu Engineering College Perundurai Erode Tamil Nadu India

To detect the objects around an autonomous vehicle is very essential to operate safely. This paper presents to detect and classify the objects for assisting autonomous driving. In autonomous driving systems, the task of object detection itself is one of the most important prerequisites to autonomous navigation. Deep learning one of the computer vision tasks, perform object detection very effectively than compared to earlier methods and this project is to detect the objects like vehicles, persons, traffic lights, etc. In this work, an approach to object detection in deep learning that makes the bounding box for an image to predict is explored. Object detection is the method of detecting the objects present in a given image. Apart from detecting the number of objects present in an image it also specifies in which location that object is present in the image. The objects are detected by means of bounding boxes. In the existing system algorithm like Convolutional Neural Network (CNN) using Resnet-50 were used to detect the objects like vehicles, persons, traffic lights separately. The problem identified here is, in the existing system the camera is fixed in a particular place and it detects objects only if the objects come into the camera frames. It is not detecting both objects and lanes simultaneously when the autonomous vehicle is in motion at any location. To overcome these problems, in the proposed system object detection is performed by mounting camera in front of the moving vehicle. You Only Look Once (YOLO) V3 Algorithm is used for the process of object detection. Compared to earlier detection approaches YOLO V3 shows improvement in detection accuracy. It provides good feature extraction and detection in large-scale. The proposed YOLO al gorithm has better average precision value for detecting all objects than compared to existing CNN using Resnet-50. In addition YOLO V3 algorithm performs lane detection apart from object detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Counterfeit drugs prevention using block chain techniques

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1055卷

作者： M Arumugam S Deepa G R Sreekanth G Arun S Nilesh Assistant Professor Department of Computer Technology - PG Kongu Engineering College Perundurai Erode India Assistant Professor Department of Information Technology MP Nachimuthu M Jaganathan Engineering College Chennimalai India PG-scholar Master's degree programme in Software Systems Kongu Engineering College Perundurai Erode India

The production and distribution of counterfeit drugs is an urgent and increasingly critical worldwide issue, especially in developing countries. The pharmaceutical counterfeiting's market price has hit over billions of dollars yearly. The flawed supply chain system in the pharmaceutical industry is one of the main reasons for drug imitations. Before meeting the clients, the ownership of the medicaments shifts from suppliers to wholesalers. Knowledge is not shared between processes in modern supply chain systems; manufacturers don't even have any input at what occurs to their goods, just that the drug administration has no summary of the system; reminder programs are complex and inefficient and patients can not follow up. This project describes how in the pharmaceutical supply chains we use block chain technologies to provide the monitoring and protection of the drug supplier. The presented method will also be used by the pharmaceutical industry to track the medication from the particular time it is manufactured to the patient. The result of each drug used is recorded for future use in the database. An accepted block chain is used for storing transactions and only trusted parties can enter the network and move data in the block chain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Weight Allocation–Based Network Security and Anomaly Detection Model for Intelligent VANETs

引用

Transactions on Emerging Telecommunications Technologies 2025年第6期36卷

作者： Aadam Quraishi Rakeshnag Dasari Sushilkumar Dangiya Sateesh Kumar Nallamala Krishna Kanth Kondapaka Swaroop Reddy Gayam Isa Bayhan Uguloy Berdieva Rubal Jeet M.D. Research Cognitive and AI laboratory Interventional treatment institute Houston Texas USA Department of CSE Acharya Nagarjuna University Nagarjuna Nagar Guntur India Department of Electronics and Communication Engineering GTU – School of Engineering and Technology Ahmedabad India Independent Researcher USA Independent Researcher California USA Independent Researcher and Senior Software Engineer at TJMax USA Assistant Professor of Tourist Guiding Dept Bolu Abant Izzet Baysal University Golkoy Campus Bolu Turkey The Department of Tax and Taxation Tashkent State University of Economics Tashkent Uzbekistan Chandigarh Group of Colleges Jhanjeri Chandigarh Engineering College Department of Computer Science and Engineering Punjab India

Determining the weights of evaluation metrics is one of the key factors influencing the cybersecurity and anomaly detection of intelligent vehicular ad hoc networks (VANETs). To address the limitations of traditional weighting methods, which often overlook the impact of changes in metric attribute states on evaluation weights, this paper proposes a dynamic weight allocation–based network security and anomaly detection model. The model begins by decomposing and analyzing the security and anomaly detection objectives of VANETs, constructing a comprehensive evaluation metric system. The network security assessment model for VANETs presented in this research overcomes the drawbacks of conventional static models by utilizing a dynamic weight allocation technique. Based on current network conditions, a state variable weight method was created that dynamically computes security values by combining incentive and penalty mechanisms. A ranking-based weighting algorithm is employed to analyze the correlation between security and anomaly detection metrics. Subsequently, the proposed dynamic weight allocation algorithm calculates the dynamic weights of individual metrics within the system, enabling a robust assessment of network security and anomaly detection for intelligent VANETs. The evaluation results provide security level classifications and identify anomalies effectively. Experimental results demonstrate that the model significantly enhances the rationality and accuracy of intelligent VANET evaluations, contributing to improved cybersecurity and anomaly detection.

关键词： anomaly detection dynamic weight allocation intelligent vehicle network security VANETs

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：