检索结果-内蒙古大学图书馆

A Novel approach for the screening and the classification of Macular Ischemia caused by Diabetic Retinopathy Disease using Retinal Image Datasets 7

A Novel approach for the screening and the classification of...

引用

7th International Conference on Emerging Trends in Engineering & Technology (ICETET)

作者： Patil, W. V. Daigavane, Prema GH Raisoni Coll Engn Dept Elect Engn Nagpur Maharashtra India

ISBN: (纸本)9781467383059

Diabetic Retinopathy (DR) is the retinal disease which is caused due to change in the micro retinal blood vascular structure. It may cause change in the diameter or the blockage of the blood vascular structure which leads to the occurrence of serious macular ischemia disease. The early detection of the blockage area in the vascular system is necessary otherwise it may result in loss of vision. The ophthalmologist screening of the retinal images differ from person to person and hence there requires the need of the automated system program for the analysis and classification of the fundus images. Here an automated system is proposed for the detection and the classification of the Macular Ischemia based on a graph trace method for automatic A/V (Arteries and Veins) classification by extracting the graph from the segmented vascular structure. The A/V classification is done by measuring the intensity features of the segmented blood vessels. knn classifier is then used to extract the thickness feature of the vascular structure to allocate the blockage of the veins in the retinal blood vessels. For Grading of the disease severity, SVM algorithm is use. In this methodology, the concept of evaluating two database at the same time is used in order to reduce the computational time i.e., two patients fundus images can be evaluated at the same time. The performance of the proposed system is evaluated or calculated by testing it on Drive database using parameter such as sensitivity, specificity and accuracy.

关键词： Graph trace method knn algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Collaborative filtering algorithm based on rating prediction and user characteristics 17

Collaborative filtering algorithm based on rating prediction...

引用

IEEE Int Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking (ISPA/BDCloud/SocialCom/SustainCom)

作者： Song, Na Lu, Qin Zhang, Zhihao Qilu Univ Technol Sch Comp Sci & Technol Jinan Shandong Peoples R China

ISBN: (纸本)9781728143286

Collaborative filtering directly predicts potential favorite items of user based on user's behavior records. It is one of the key technologies in personalized recommendation systems. The traditional similarity measurement method relies on user's rating data in the case of data sparseness, which causes a decrease in the recommendation quality of recommendation systems. To solve this problem, this paper proposes a collaborative filtering algorithm based on item rating prediction and user characteristics. The first step is to select the k nearest neighbor sets of the item using the knn algorithm, and then calculate the similarity between the items using the improved similarity measurement method, and initially predict the user's rating on the unrated item to improve the sparsity problem. The second step considers the user characteristics when predicting the similarity between users according to the item ratings. Finally, the algorithm combining item-based rating prediction and user characteristics is adopted to make recommendations for the user. The experimental results on MovieLens and Douban datasets show that the proposed collaborative filtering algorithm based on rating prediction and user characteristics can effectively improve the quality of recommendation system compared with the traditional algorithm.

关键词： collaborative filtering rating prediction user characteristics knn algorithm sparsity

来源：评论

学校读者我要写书评

暂无评论

Optimizing Latency in Secure Reliable Transport (SRT) Protocol through Machine Learning for Video Streaming Applications 10

Optimizing Latency in Secure Reliable Transport (SRT) Protoc...

引用

10th IEEE International Conference on Electronics, Computing and Communication Technologies (IEEE CONECCT)

作者： Rao, Rahul V. Sushmita, B. N. Nayak, Manjunath S. Akilesh, N. S. Ramya, S. Baliga, Shwetha Karjee, Jyotirmoy RVCE Elect & Commun Dept Bangalore Karnataka India RVCE Comp Sci & Engn Dept Bangalore Karnataka India Samsung R&D Inst Bangalore Karnataka India

ISBN: (纸本)9798350385939;9798350385922

The increasing demand for live video streaming, especially using protocols like MPEG-TS and UDP/RTP, faces challenges of high latency and bandwidth overhead. Secure Reliable Transport (SRT) protocol, a superior open-source technology, optimizes streaming over unpredictable networks by managing packet loss, jitter, and bandwidth fluctuations, ensuring high-quality video. However, SRT struggles with latency issues due to packet delivery times, clock discrepancies, time drift, and Round-Trip Time (RTT) fluctuations. This paper introduces a machine learning approach to enhance streaming efficiency by predicting the optimal codec (MPEG4, H264, VP8) using K-means clustering to categorize codec groups and K-nearest neighbors algorithm for training the prediction model. This system significantly enhances bandwidth and reduces latency, jitter, and packet loss, achieving a testing accuracy of 98%. The results indicate a substantial improvement in latency optimization through machine learning in the SRT protocol, highlighting potential bandwidth and performance gains.

关键词： SRT MPEG-4 H264 VP8 knn algorithm K-means clustering latency jitter bandwidth

来源：评论

学校读者我要写书评

暂无评论

EntropyVis: Malware Classification 10

EntropyVis: Malware Classification

引用

10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Ren, Zhuojun Chen, Guang Donghua Univ Coll Informat Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9781538619377

Malware writers often develop malware with automated measures, so the number of malware has increased dramatically. Automated measures tend to repeatedly use significant modules, which form the basis for identifying malware variants and discriminating malware families. Thus, we propose a novel visualization analysis method for researching malware similarity. This method converts malicious Windows Portable Executable (PE) files into local entropy images for observing internal features of malware, and then normalizes local entropy images into entropy pixel images for malware classification. We take advantage of the Jaccard index to measure similarities between entropy pixel images and the k-Nearest Neighbor (knn) classification algorithm to assign entropy pixel images to different malware families. Preliminary experimental results show that our visualization method can discriminate malware families effectively.

关键词： malware visualization entropy Jaccard index knn algorithm

来源：评论

学校读者我要写书评

暂无评论

Real Time Face Recognition using LBP Features

Real Time Face Recognition using LBP Features

引用

3rd International Conference on Computing, Communication, Control and Automation (ICCUBEA)

作者： Kulkarni, O. S. Deokar, S. M. Chaudhari, A. K. Patankar, S. S. Kulkarni, J. V. Vishwakarma Inst Technol Dept Instrumentat Pune Maharashtra India

ISBN: (纸本)9781538640081

Facial identication is important these days, Methods are required must be fast and accurate enough to work realtime. So research in methods for face recognition seems ever growing. The measurements of an individuals data is inherent part of FR techniques. In biomedical verification and identification requires the dataset such as iris, finger prints etc. While for FR, cameras are replacing the cards at places like ATMs. It helps capturing facial images of customers, and compare these photos to the images of account holders database of banks to verify the customers identity. This paper proposes way for face recognition. Shape and texture of facial images are studied for representation. The face is Firstly divided into tiny regions. Which are used to get LBPH. These histograms merged in one partially enhanced histogram, by which we get face images effciently. knn classier does the classication and not just effciency but the simplicity of manner allows very fast feature extraction.

关键词： Face Recognition Features Extraction LBPH algorithm knn algorithm Raspberry pi3

来源：评论

学校读者我要写书评

暂无评论

Understanding Labor Market Dynamics in Urban India Amidst the Pandemic: A Study Employing Supervised Learning Methods

引用

JOURNAL OF QUANTITATIVE ECONOMICS 2024年第4期22卷 883-909页

作者： Roy, Namrata Singha Ghosh, Niladri Christ Univ Dept Econ Hosur Rd Bengaluru 560029 India

This study provides insights into the dynamic job ladder and challenges in the Indian labor market, particularly when facing external shock. It examines the fluidity of job transitions among the 'employed', 'unemployed', and those 'not in the laborforce', focusing on the urban labor market of India during the COVID-19 pandemic. Using data from the 2020-21 Periodic Labour Force Survey, a longitudinal panel dataset was created to track individuals across four quarters, enabling the monitoring of their activity status. Employing K-Nearest Neighbour classification, the study identifies vulnerabilities in labor market engagement. It further explores factors driving transitions among the three states of labor market involvement, using a multinomial logistic model adjusted for selection bias. The research reveals significant movement within the labor force, with notable shifts between employment statuses. Even those currently employed are often vulnerable, at risk of detachment from the labor force at any time. Women were disproportionately affected, with evidence of discouraged worker effect, as many ceased jobs search duo to perceived job scarcity or unavailability of decent jobs. The study raised concerns about the sustainability of self-employment and the security of regular jobs. These findings expose enduring structural challenges exacerbated by the pandemic, calling for urgent action to address widespread unemployment, low female participation, and prevailing inequalities in the labor market.

关键词： Employment COVID-19 Labor market transition knn algorithm Multinomial logistic regression Urban India

来源：评论

学校读者我要写书评

暂无评论

Discrimination of unknown complex network based on the information of local nodes 40

Discrimination of unknown complex network based on the infor...

引用

40th Chinese Control Conference (CCC)

作者： Liu, Siyuan Jin, Yue Wu, Yongjun Li, Kun Zhang, Jianlei Nankai Univ Coll Artificial Intelligence Dept Automat Tianjin 300071 Peoples R China Nankai Univ Tianjin Key Lab Intelligent Robot Tianjin 300071 Peoples R China Tiangong Univ Sch Math Sci Tianjin 300387 Peoples R China Hebei Univ Technol Sch Civil & Transportat Engn Tianjin 300401 Peoples R China

ISBN: (纸本)9789881563804

At present, the study on complex network and game theory has been spread across the fields of science and engineering. The research contents on these topics mainly focus on the evolution results of structured populations based on the determined network structures and game types, which may not be open information to the interacting players. Therefore, how to obtain the maximum benefit in an unfamiliar game environment for an individual new to the population is a topic that has received little attention but is of great significance. In this paper, we explore how to use the minimum amount of known information available to realize the identification of large-scale unknown networks. We simulate real large structured populations with five classical large complex networks and hide their real structures. Then, we propose an improved k-nearest neighbor (knn) algorithm, which can infer the real network structures with high accuracy only based on the degree and clustering coefficient information of a few local nodes on the network. The results and method presented here provide some hints about the study on the evolutionary game process and swarm intelligence in networked populations.

关键词： Complex network Structured population Game theory knn algorithm Classification

来源：评论

学校读者我要写书评

暂无评论

knnR:K-Nearest Neighbour Classification based Routing Protocol for Opportunistic Networks 10

KNNR:K-Nearest Neighbour Classification based Routing Protoc...

引用

10th International Conference on Contemporary Computing (IC3)

作者： Sharma, Deepak Kumar Aayush Sharma, Abhishek Kumar, Jaideep Univ Delhi Netaji Subhas Inst Technol Div Informat Technol Delhi India

ISBN: (纸本)9781538630778

Opportunistic Networks (OppNets) are an extension of Mobile Adhoc Networks (MANETs), where no assumption is made regarding the preexistent path between the source and the destination node. Hence, the nodes in OppNets are required to rely upon intermediate nodes for successful message delivery. Therefore, the biggest challenge in OppNets for a carrier node is to make a decision whether the neighbour node will be a good carrier for the message in the future or not. Hence, in this paper a new routing protocol called K-Nearest Neighbour based Routing protocol (knnR) is proposed which judicially forwards the message through intermediate nodes towards the destination. The proposed protocol initially stores the past behaviour of nodes in a dataset. Whenever a decision has to be made related to an intermediate node, the protocol studies this dataset and finds instances that closely resemble the intermediate node based on their network parameters using K-Nearest Neighhbour (knn) algorithm. To evaluate the efficiency of the proposed protocol simulation results are compared with the existing routing protocols i.e. Epidemic, HBPR and ProPHET. It was observed that the knnR protocol efficiently reduces average latency, overhead ratio and average hop count while at the same time increases the message delivery probability.

关键词： MANETs ProPHET knn algorithm Opportunistic network routing protocol ONE simulator

来源：评论

学校读者我要写书评

暂无评论

Research on Indoor Positioning algorithm Based on Neighborhood Partitioning 3

Research on Indoor Positioning Algorithm Based on Neighborho...

引用

3rd IEEE International Conference on Information Communication and Signal Processing (ICICSP)

作者： Shan, Zhilong Zhang, Fan Lv, Na Xiang, Wan South China Nounal Univ Sch Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9781728188232

In order to solve the problem of long matching time caused by a large number of reference fingerprints and inaccurate positioning caused by knn algorithm alone. A method based on knn partitioning is proposed in this paper. Firstly, the fingerprint space is clustered, and then the K nodes closest to the unknown node are obtained in the clustered area according to knn algorithm. Secondly, the maximum and minimum coordinates of K fingerprints are used to determine the region, and then the region is divided by Newton interpolation method to form a virtual fingerprint matrix. Finally, knn algorithm is used to re-determine the region, and then particle swarm optimization algorithm is used to find the optimal location node in this region iteratively. Experiments show that the algorithm can improve the positioning accuracy and reduce the matching time effectively, especially when the reference fingerprints are sparse.

关键词： fingerprint library knn algorithm K-Means newton interpolation particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Principal Component Analysis on k-Nearest Neighbors and Naive Bayes Classification algorithms 29th

Analyzing the Impact of Principal Component Analysis on k-Ne...

引用

29th International Conference on Information and Software Technologies (ICIST)

作者： Macionczyk, Rafal Moryc, Michal Buchtyar, Patryk Silesian Tech Univ Fac Appl Math Kaszubska 23 PL-44100 Gliwice Poland

ISBN: (纸本)9783031489808;9783031489815

Principal Component Analysis (PCA) is a well-known dimensionality reduction technique that has been widely used in various machine learning algorithms. This includes knn and Naive Bayes algorithms which can be time-consuming. The reduction of dimensions can have positive effects on those two algorithms by reducing the number of related types of data and decreasing the data they need to analyze. Here we present detailed findings about how the PCA algorithm affects them both in time efficiency and accuracy. All calculations regarding those values were carried out in Python programming language. The dataset used in research is the Titanic dataset, on which data cleaning and normalization were done. The data in this paper suggests that it is possible to maintain the same level of accuracy with great improvement in time efficiency. For the knn algorithm reducing the number of dimensions by one resulted in a 31.09% increase in accuracy and for the Naive Bayes algorithm an 18.18% increase while having an imperceptible effect on accuracy.

关键词： PCA algorithm knn algorithm Naive Bayes Classification algorithms analyze impact effect

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：