检索结果-内蒙古大学图书馆

A Factor Based Multiple Imputation Approach to Handle Class Imbalance

Procedia computer science 2023年 218卷 103-112页

作者： Pranita Baro Malaya Dutta Borah Dept. of Computer Science and Engineering National Institute of Technology Silchar Silchar-788010 India

Class imbalance and incompleteness are the two most serious problems faced in data science and machine learning when working on real-life datasets. Both of these cases have severe implications on the ability of classification algorithms to make accurate predictions. When a dataset used for training classifiers is both imbalanced as well as incomplete, the traditional approach is to address the missing data first and then handle class imbalance but it could lead to some issues such as overfitting as well as amplification of some errors due to random duplication. In this paper, an alternate factor-based multiple imputation oversampling method (FB-MIO) is proposed to handle class imbalance as well as missing values in the training dataset at the same time. First, a new factor is presented to evaluate the density of missing values belonging to the majority class with respect to the minority class in a particular region. With the help of this factor, an oscillator is developed to guide how imputation based oversampling should be carried out. Then the training set is divided into multiple smaller subsets and used the oscillator to determine whether missing values for the majority class belonging to that subsets should be imputed or not. This would help in preventing exaggerated duplication when not needed. Experiments were carried out on 27 imbalanced datasets after random addition of missing value and the F1 and AUROC scores of FB-MIO were compared to other dataset level resampling methods such as SMOTE, ADASYN, B-SMOTE etc. The effectiveness of the proposed method has been validated after experiments on benchmark datasets and the comparative results are presented in the form of average rank and number of wins.

关键词： class imbalance overfitting oversampling imputation missing value

来源：评论

学校读者我要写书评

暂无评论

Real-Time Network Monitoring: A Big Data Approach

Real-Time Network Monitoring: A Big Data Approach

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Kunisetty Jaswanth S Sruthi Pranav Ramachandrula S. Saravanan Dept. of Computer Science Engineering Amrita School of Computing Bengaluru India Dept. of Computer Science Engineering Amrita School of Computing Chennai India

Real-time network monitoring is a critical requirement for tracking user activities and ensuring optimal network performance. In this paper, we propose a big data approach to real-time network monitoring that leverages the capabilities of Apache Spark, MongoDB, and Apache Kafka with Python. Our approach utilizes distributed stream processing of network data, enabling real-time analytics for user activity monitoring and network performance optimization. Our approach demonstrates the effectiveness of our system through experiments with real network traffic data, showing how it can identify and track user activities in real-time. Our system can be used by network administrators and IT professionals to optimize network performance, improve user experience, and enhance security through real-time monitoring and analysis of user activity data. This approach can also be opted as a feature in SDNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Code Smell Detection using Hybrid Machine Learning Algorithms

Code Smell Detection using Hybrid Machine Learning Algorithm...

引用

International Conference on Inventive Research in Computing applications (ICIRCA)

作者： D Mahalakshmi Prabakaran Kasinathan D. Elangovan C. Rohith Bhat M Balamurugan S. Sivakumar Dept. of Information Technology Panimalar Engineering College Dept. of CSE School of Computing Veltech Rangarajan Dr. Sagunthula R & D Institute of Science and Technology Dept. of CSE Panimalar Engineering College Institute of computer science and engineering Saveetha School of engineering (SIMATS) Chennai Dept. of CSE Sri Sairam Engineering College Affiliated to Anna University Dept. of Computer Applications Lakshmi Bangaru Arts and Science College melmaruvathur

Code smells frequently leads to the discovery of decreased code quality, drains on application resources, or even critical security vulnerabilities embedded within the application's code. While code smells may not always indicate a particularly serious problem, it do often lead to the discovery of these issues. Software's structural characteristics lead to a design issue that makes it challenging to manage and maintain code refactoring. The goal of the current research is to create methods for identifying code smells. The machine learning algorithm is a reliable method for individualized smell detection, but there aren't many studies on how well it works for different developers. In this proposed work used two different deep learning algorithms and five different machine learning ensembles to detect suspicious code. Investigation of the Data class, God class, Feature-envy, and Long-method datasets revealed that each contained various levels of code smells. Although there is room for improvement, the outcomes of prior publications' applications of machine learning and stacking ensemble learning methods to this dataset were satisfactory. A class balancing method (SMOTE) was implemented to address the problem of class imbalance within the datasets. While the Feature- envy dataset with the selected dozen metrics produced the lowest accuracy (91.45%) for the Max voting method, the Long-method dataset with the various chosen metrics produced the highest accuracy (100%) for all five methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measurement of Ocular Torsion Using Feature Matching on the Iris and Sclera

Measurement of Ocular Torsion Using Feature Matching on the ...

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Arthur Bell Richard Green Aluna Everitt Dept. of Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

The tracking of torsional eye movements, where the eye rotates about the axis of vision, is important for the diagnosis of certain vestibular disorders, but presents additional challenges when compared to the tracking of linear eye movements. This paper proposes a method for the measurement of ocular torsion that combines techniques from several previous studies, attempting to make the measurement robust to a highly off-axis centre of vision and obscurations of the pupil and iris. The proposed method detects feature points across a region of interest (ROI) including both the iris and the sclera (the white part of the eye surrounding the iris), using the Affine-SIFT (ASIFT) feature detection method, and tracks the feature points across frames using the Lucas-Kanade Optical Flow Method. The proposed method was only able to achieve an average error of 0.42 degrees compared to 0.17 degrees achieved in prior research. However, an additional 23.5% of feature points were able to be tracked compared to feature matching on the iris alone, showing that the proposed method has the potential to provide more accurate tracking than conventional methods. Future improvements proposed to the method include a deep segmentation method to automatically determine the ROI in each frame, and further testing with a calibration step to determine the source of error in the method.

关键词： Iris Image segmentation Accuracy Tracking Feature detection Feature extraction Calibration Pupils Optical flow Testing

来源：评论

学校读者我要写书评

暂无评论

Advancements in Breast Cancer Detection: A Comprehensive Review of Deep Learning Techniques

Advancements in Breast Cancer Detection: A Comprehensive Rev...

引用

Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： Drishti Arora Shruti Gupta Jashekam Singh Chawla Rakesh Garg Dept. of Computer Science and Engineering Amity University Uttar Pradesh India Dept. of Computer Science and Engineering Amity University Uttar Pradesh India

This paper addresses the pressing issue of breast cancer-related mortality by comprehensively analyzing six distinct deep learning models utilized in the past decade. With a focus on timely and precise diagnosis, the study evaluates the performance metrics of each model across diverse datasets, image modalities, and methodologies. The primary goal is to identify the most efficient and precise deep learning architecture tailored to classify breast cancer tumors, with potential implications for optimizing early detection strategies and advancing clinical decision-making processes. The findings hold significant implications for refining clinical decision-making processes, potentially leading to more efficacy in timely detection strategies. This research emphasizes on the broader field of image analysis and its role in combating breast cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Alzheimer's Disease using Deep Learning Algorithms

Prediction of Alzheimer's Disease using Deep Learning Algori...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： P Praveen Koleti Srilatha Masabathini Sathvika Edulapuram Nishitha Madduri Nikhil Dept. of Computer Science and Artificial Intelligence SR University Warangal India Dept. of Computer Science Engineering SR Engineering College Warangal India

Throughout the world, at least five crore individuals are thought to have the disease of Alzheimer. This Alzheimer's disease is the most well-known and prevalent kind of dementia (AD). Since the modest but significant advancements in Alzheimer's disease (AD) treatment, the diagnostic emphasis has progressively switched to the precise identification of the disease's earliest stage. In numerous attempts at clinical classification, the difficulty of differentiating pre-clinical AD from changes associated with normal aging or developed AD has been recognized. Alzheimer's disease is a neurological and brain disorder that eventually makes it difficult to do even the most fundamental tasks. It gradually destroys memory and thinking skills. It is a neurological degenerative disorder that causes both brain cell shrinkage and degeneration. The most typical reason of dementia is a gradual loss of cognitive ability, behavioral, and social abilities, limiting their capacity to operate independently. It causes both brain cell shrinkage and degeneration. As people live longer, there are more concerns about aging. Damage to brain cells can be avoided with an early diagnosis of this disease. Early detection can considerably slow or stop the growth of this disease because there is no cure for it. To stop the progression of Alzheimer's disease, early detection is essential. As a result, experts can initiate preventive care as soon as possible. They call for prompt and precise Alzheimer's disease detection in its initial and most elusive stages. The only accurate approach for diagnosis is magnetic resonance imaging (MRI) brain imaging, although exams like the Mini-Mental State Examination (Fol stein 1975), or MMSE, are routinely used for earlier diagnosis. The main objective of this research work is to devise a technique for accurately identifying and staging diseases in magnetic resonance imaging (MRI). Deep learning excels at analyzing images and predicting diseases. A growing body o

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction Model for Suicidal Behavior Disorder Risk Analysis by Correlating Cyber and Real World Data

Prediction Model for Suicidal Behavior Disorder Risk Analysi...

引用

Emerging Techniques in Computational Intelligence (ICETCI), International Conference on

作者： Gone Neelakantam Dept. Computer Science and Engineering Ecole Centrale School of Engineering Mahindra University Hyderabad India

ISBN: (数字)9798350387063

ISBN: (纸本)9798350387070

In the era of internet of things (IoT), people are attentive to express their non verbal behavior on cyber world such as social media by using smart phone, laptop or tablet. People are more active in sharing their daily activities status such as current activity the person is into and personal life situations such as achievement, problem, stress and even any hazardous desire (i.e. suicide). In contrast with real world such as smart home environment, people generally spent their non verbal behavior in term of Activity Daily Livings (ADLs) in associating with smart home sensors. Based on non verbal and verbal behaviors, data are generated from both Cyber and Real world, which are big in volume and variety. However, there is lack of investigating Cyber and Real world data especially in analyzing the risk of committing suicide, considering suicide is a big issues and threats in the society. Therefore, it motivate us to propose prediction model to determine high and low risk of committing suicide by combining two separate approaches such as Activity Recognition (AR) for real world and Sentiment Analysis (SA) for cyber world.

关键词： Analytical models Sentiment analysis Social networking (online) Smart homes Predictive models Activity recognition Data models Risk analysis Internet of Things Stress

来源：评论

学校读者我要写书评

暂无评论

Graph Based Keywords Extraction from Crime Data

Graph Based Keywords Extraction from Crime Data

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Priyanka Das Anuvab Munshi Annwesha Naha Adrija Dey Sriparno Chakraborty Dept. of Computer Application and Science Institute of Engineering & Management Kolkata University of Engineering and Management Kolkata

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

It takes a lot of work to gather a large amount of data to help in criminal investigation and prevention of crimes. The most effective methods for reporting crimes are insufficient for both civilians and law enforcement. The police and witness narrative summaries are frequently deemed to be too lengthy to read. Hence, there exists many research works that represents summary of those descriptive reports. But to make it easier, there should be certain phrases or words so that Police investigators can quickly understand criminal scenarios saving them from having to read the entire report. This can be accomplished with the use of criminal information extraction. Here, the proposed study uses a graph-based methodology and natural language processing techniques to extract crime-related keywords from in-dept. police and witness narrative descriptions. Initially, the suggested work selected nouns, verbs, and adjectives from the crime reports and evaluated their importance scores. Based on the words' importance scores, a graph partitioning technique has been applied; following repeated runs of the algorithm, the words are classified into clusters. Each cluster in this instance, together with the words that reside within it, represent a different aspect of crime. These clustered words are considered as the keywords for representing the crime.

关键词： Law enforcement Prevention and mitigation Clustering algorithms Information retrieval Natural language processing Partitioning algorithms Classification algorithms Data mining Communication networks Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Integrated Gradients Demystified: An MRI Case Study on Aβ-T Protein Localization 3

Integrated Gradients Demystified: An MRI Case Study on Aβ-T...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Dolci, Giorgio Morasso, Cristian Cruciani, Federica Brusini, Lorenza Pini, Lorenzo Calhoun, Vince D. Galazzo, Ilaria Boscolo Menegaz, Gloria University of Verona Dept. of Engineering for Innovation Medicine Verona Italy University of Verona Dept. of Computer Science Verona Italy Padua Neuroscience Center University of Padua Padua Italy Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States

ISBN: (纸本)9798350378009

Explainability in Artificial Intelligence is gaining increasing importance, especially in critical fields. In biomedical applications, attribution maps are particularly relevant for their inherent spatial localization property. Features that are relevant for a given task (e.g., classification of cases versus controls) can then be associated to specific regions, revealing disease-specific modulations and enabling ad-hoc post-hoc validation. Among these, baseline-dependent methods require a neutral image (called baseline) for computing the feature importance. The choice of the baseline is critical in that it determines the relevance map. In this work, we focused on a classification task, that is, subject stratification based on the amyloid-β and τ status in controls and patients in the Alzheimer's disease continuum, and employed Integrated Gradients to extract the attribution maps. This allowed identifying relevant brain regions driving the classification. Aware of the dependence of the outcomes from the chosen baseline, post-hoc statistical analysis was performed for validating the results confirming their plausibility. This puts forth the need to systematically assess the impact of the baseline for the correct interpretation of the corresponding outcomes. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Inferring Message Flows From System Communication Traces

arXiv

引用

arXiv 2024年

作者： Nadimi, Bardia Zheng, Hao Dept. Computer Science and Engineering University of South Florida Tampa United States

This paper proposes a novel method for automatically inferring message flow specifications from the communication traces of a system-on-chip (SoC) design that captures messages exchanged among the components during a system execution. The inferred message flows characterize the communication and coordination of components in a system design for realizing various system functions, and they are essential for SoC validation and debugging. The proposed method relieves the burden of manual development and maintenance of such specifications on human designers. Our method also uses a new accuracy metric, acceptance ratio, to evaluate the quality of the mined specifications instead of the specification size often used in the previous work, enabling more accurate specifications to be mined. Furthermore, this paper introduces the concept of essential causalities to enhance the accuracy of the message flow mining and accelerate the mining process. The effectiveness of the proposed method is evaluated on both synthetic traces and traces generated from executing several system models in GEM5. In both cases, the proposed method achieves superior accuracies compared to a previous approach. Additionally, this paper includes some practical use cases. Copyright © 2024, The Authors. All rights reserved.

关键词： System-on-chip

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：