检索结果-内蒙古大学图书馆

Explainable deep stacking ensemble model for accurate and transparent brain tumor diagnosis

computers in biology and Medicine 2025年 191卷 110166-110166页

作者： Haque, Rezaul Khan, Mahbub Alam Rahman, Hamdadur Khan, shakil siddiqui, Md Ismail Hossain Limon, Zishad Hossain swapno, s M Masfequier Rahman Appaji, Abhishek Department of Computer Science and Engineering East West University A 2 Jahurul Islam Ave Dhaka1212 Bangladesh Department of Management Information System Pacific State University 3424 Wilshire Blvd. 12th Floor Los Angeles CA90010 United States Department of Management of Information System International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Business Analytics International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Engineering/Industrial Management Westcliff University IrvineCA92614 United States Department of Computer Science Westcliff University IrvineCA92614 United States Department Of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur-2 Dhaka1216 Bangladesh Department of Medical Electronics Engineering B.M.S. College of Engineering Bangalore560019 India Maastricht University University Eye Clinic Maastricht Maastricht Netherlands

Early detection of brain tumors in MRI images is vital for improving treatment results. However, deep learning models face challenges like limited dataset diversity, class imbalance, and insufficient interpretability. Most studies rely on small, single-source datasets and do not combine different feature extraction techniques for better classification. To address these challenges, we propose a rob.s. and explainable stacking ensemble model for multiclass brain tumor classification. To address these challenges, we propose a stacking ensemble model that combines EfficientNetb0, MobileNetV2, GoogleNet, and Multi-level CapsuleNet, using Catboost as the meta-learner for improved feature aggregation and classification accuracy. This ensemble approach captures complex tumor characteristics while enhancing rob.s.ness and interpretability. The proposed model integrates EfficientNetb0, MobileNetV2, GoogleNet, and a Multi-level CapsuleNet within a stacking framework, utilizing Catboost as the meta-learner to improve feature aggregation and classification accuracy. We created two large MRI datasets by merging data from four sources: braTs, Msoud, br35H, and sARTAJ. To tackle class imbalance, we applied borderline-sMOTE and data augmentation. We also utilized feature extraction methods, along with PCA and Gray Wolf Optimization (GWO). Our model was validated through confidence interval analysis and statistical tests, demonstrating superior performance. Error analysis revealed misclassification trends, and we assessed computational efficiency regarding inference speed and resource usage. The proposed ensemble achieved 97.81% F1 score and 98.75% PR AUC on M1, and 98.32% F1 score with 99.34% PR AUC on M2. Moreover, the model consistently surpassed state-of-the-art CNNs, Vision Transformers, and other ensemble methods in classifying brain tumors across individual four datasets. Finally, we developed a web-b.s.d diagnostic tool that enables clinicians to interact with the proposed mo

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Level prediction of preterm birth using risk factor analysis and electrohysterogram signal classification 2

Level prediction of preterm birth using risk factor analysis...

引用

2nd International Conference on Computing and Communications Technologies, ICCCT 2017

作者： Pari, R. sandhya, M. shankar, sharmila Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai India

ISBN: (纸本)9781509062201

As per the reports published by World Health Organization (WHO) in November, 2012, every year more than 15 million babies are born preterm and this number is rising [1]. Preterm labor is the major cause of neonatal deaths. Every year, pre term birth (PTb) complications leads to the death of almost 1 million babies [2][3]. Predicting the preterm labor well in advance can reduce the neonatal death considerably. There are some commonly attributed risk factors associated with preterm birth [4][5]. 33% of the women who deliver their babies prematurely have one or more of these risk factors. We propose to predict PTb by analyzing the historical data of patients who had one or more of the above risk factors. In addition to this, historic data of the patients who did not have any of the above risk factors but had PTb is also analyzed. Electrohysterogram (EHG) is the most commonly used clinical procedure which can reveal few indicators of preterm labor [6]. We analyze the EHG signals to predict the pre term labor by applying Feature Extraction coupled with semi-supervised learning (ssL). Predicting the preterm labor helps the health care professionals to make decisions about the treatment [7]. Hence the expectant mother undergoes minimal or no complications of preterm labor. On the other hand it also helps to avoid unnecessary hospitalization and treatment for women who are having a false labor pain. © 2017 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Tag detection in RFID system b.s.d on RssI technique for LF and HF passive tags

Tag detection in RFID system based on RSSI technique for LF ...

引用

2016 International Conference on Communication and signal Processing, ICCsP 2016

作者： bagirathi, s. sankar, sharmila sandhya Computer Science and Engineering Department B.S. Abdur Rahman University Chennai India

ISBN: (纸本)9781509003969

Radio-Frequency Identification (RFID) is the use of radio waves to read and capture information stored on a tag attached to an object. RFID can be used to solve localization problems effectively. A number of novel methods have been proposed in the recent years for tag detection. In some cases it is not possible for the reader to identify all the tags which results in missing of those tags. One of the reasons may be increase in read range between tag and the reader. Read range depends on a number of factors like the frequency of the radio waves used for reader - tag communication, the size of the tag antenna, the signal strength of the receiver antenna, transmitting power output of the reader and the type of tags that is deployed in the system. To determine the tags effectively without any loss the proposed method uses Received signal strength indicator (RssI) method to calculate the distance between the reader and all the tags in the RFID environment. The transmitter power of the Readers' antenna is adjusted b.s.d upon the RssI value. Hence through this proposed framework the tags which are out of vicinity from the reader's coverage area could be tracked and identified efficiently. © 2016 IEEE.

关键词： Radio waves

来源：评论

学校读者我要写书评

暂无评论

Measurement process and multi-dimensional metric model for evaluating KM systems

Measurement process and multi-dimensional metric model for e...

引用

2011 International Conference on Research and Innovation in Information systems, ICRIIs'11

作者： Venkata subramanian, D. Hussain, Mohammed K. Geetha, Angelina Department of Computer Science and Engineering TJ Institute of Technology Chennai India Department of Computer Applications B.S. Abdur Rahman University Chennai India Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai India

ISBN: (纸本)9781612842950

Knowledge Management (KM) system plays a crucial role in every industry as well as Higher Learning Institutions where capturing, sharing, managing & archiving knowledge assets are important for increasing knowledge workers or users productivity at the same token utilizing the available KM infrastructure effectively. b.s.d on the research works, we have identified that there are challenges in measuring and evaluating the effectiveness of the Knowledge Management systems. The primary goal of this research paper is to design and develop a domain-independent multi-dimensional metric model which can be helpful to build a metric datab.s. or toolset for evaluating the effectiveness of the Knowledge Management systems (KMs). In this proposed work, we first list out some of the ways to conduct the evaluation of KMs and describe a suitable measurement process which can be helpful to conduct an evaluation experiment against the knowledge management systems. secondly we describe the importance of the prime quality factors, key attributes and outcome metrics for designing and developing a metric model. b.s.d on the in-depth study and comparison with various software quality models, we have come up with a design of multi-dimensional metric model for evaluating any KMs. Finally, we discuss how this process and model will be helpful to map to mathematical model and also to build the metric datab.s. for generating metric report for analyzing the gaps, effectiveness and benefits of the knowledge management systems. © 2011 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Enhanced Adaptive data cache invalidation approach for mobile ad hoc network

Enhanced Adaptive data cache invalidation approach for mobil...

引用

International Conference on Electronic computer Technology

作者： Fatima, N. sabiyath Khader, P. sheik Abdul Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai Tamil Nadu India Department of Computer Applications B.S. Abdur Rahman University Chennai Tamil Nadu India

ISBN: (纸本)9781424486779

A mobile ad-hoc network (MANET) is a collection of mobile nodes communicating within a transmission range and it is a self-configuring network of mobile routers. The concept of caching frequently accessed data provides efficient communication among mobile nodes. The main objective is to avoid the stale data using invalidation policy b.s.d on TTL. In this paper we introduce an Enhanced Adaptive TTL (EATTL) algorithm in which each 1-hop distance node's to data cache node maintain a hash table for cache invalidation. Data item name is used as key and TTL used as its value. simulations are carried out in Ns-2 to evaluate the performance of the proposed scheme. The simulation results showed that EATTL algorithm can cut the query delay by a factor of 3 and double the throughput compared to the Adaptive TTL. © 2011 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Precise diagnosis of Alzheimer’s disease using Recursive Feature Elimination (RFE) method

International Journal of Systematic Innovation

引用

International Journal of systematic Innovation 2022年第3期7卷 27-36页

作者： Ansari, Gufran Ahmad sivakani, R. srisakthi, s. Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Tamilnadu VandalurChennai India Department of Computer Application B.S. Abdur Rahman Crescent Institute of Science and Technology Tamilnadu VandalurChennai India

One of the prevalent diseases that the elderly tend to have patients has been Alzheimer's disease (AD). It is a neurological disease where the brain cells start to deteriorate. As the disease progresses it eventually leads to the death of the brain cells. Death in brain cells results in various problems like memory loss change in behavior patterns and many more. The most challenging problem has been in predicting an early diagnosis of AD in patients. The importance of the disease is that it is detected early. If early detection is done, the death of brain cells can be reduced. The disease is predicted b.s.d on the various features of the patient. Feature selection has been one of the important steps in predicting the disease. This paper takes the OAsIs data set and implements the different algorithms and proposes a model. The proposed model identifies the salient feature by recursively considering smaller and smaller sets of the features. The classification has been done for evaluating the feature selection. The result has been compared before the feature selection method and after the feature selection method. The performance metrics show improved scores after applying the feature section concept. © 2022,International Journal of systematic Innovation. All Rights Reserved.

关键词： Alzheimer Early diagnosis Feature selection Recursive feature elimination

来源：评论

学校读者我要写书评

暂无评论

Ontology b.s.d clustering algorithm for information retrieval

Ontology based clustering algorithm for information retrieva...

引用

2013 4th International Conference on Computing, Communications and Networking Technologies, ICCCNT 2013

作者： Ravishankar, T. Nadana shriram, R. Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai-48 India

ISBN: (纸本)9781479939268

The explosive growth of mobile devices has increased the need for information on the move. As the number of web users through mobile devices is increasing day by day, it is very challenging for the search engines to provide the specific result in response to user query. We present a clustering algorithm which is b.s.d on decision tree structure in order to improve the clustering results and visualize only the relevant results to the user. In this paper, the objective is to integrate domain ontology as background knowledge and study the clustering performance. We have computed multiple clusters using standard K-means b.s.d on various similarity metrics as well. Our results are compared with previous b.s.line approaches to find the performance and overheads. The experimental results show that more refinement to be done in the clustering technique to retrieve documents with fewer navigations and less data traffic, which is important especially for mobile devices. © 2013 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Grammar rule-b.s.d sentiment categorisation model for classification of Tamil tweets

Grammar rule-based sentiment categorisation model for classi...

引用

作者： Ravishankar, Nadana shriram, R. Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai600048 India

The advent of social media has enabled people to easily and publicly express their ideas on a movie/product in such a way that it reaches millions of people within no time. This research aims to implement a tool that would be helpful in predicting the genre of the movies as perceived by the audience through linguistic rules and natural language processing (NLP) tool kit. This paper focuses on development of rule-b.s.d sentiment categorising tool for Tamil tweets and a tool has been developed using Python and NLP tool kit. Furthermore, a model is designed to determine the opinion along with genre classification of Tamil movies. For this work, a set of genres are selected from Tamil movies with public tweets b.s.d on sentiment analysis. We find that the tool classifies the genre of a particular movie provided by user tweets and validated our approach with domain experts and b.s.line models. © 2018 Inderscience Enterprises Ltd.

关键词： sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Chennai Water Crisis—Data Analysis 5th

Chennai Water Crisis—Data Analysis

引用

5th International Conference on Intelligent Computing and Applications, ICICA 2019

作者： shankar, Deepak Rehman, N. Aaftab.s.nkar, sharmila banu, Aisha sandhya, M. Department of Computer Science & Engineering B.S. A Crescent Institute of Science & Technology Chennai India

ISBN: (纸本)9789811555657

Chennai is a coastal city and is the capital city of the Indian state of Tamil Nadu. It is densely populated and currently facing a severe drought as of June 2019. Chennai mainly depends on reservoir water, i.e., metro water and its groundwater resources to meet its water needs. The four main reservoirs of the city are Red Hills, Chembarambakkam, Cholavaram, and Poondi. With a combined total capacity of 11,057 Mcft, these act as the major source of water for the inhabitants of the city. With the ever-increasing population and the added effects of climate change which induces a decreasing rate of total rainfall, the situation of drought is likely to increase over the upcoming years. This project aims to explain the severity of drought in Chennai and how it can get worse in the upcoming years with the help of data analysis to find the per capita water that is currently present for a civilian, and how this has changed over the years due to various factors. This project also aims to create awareness and provide scope for possible solutions and measures that can be taken to mitigate the situation of drought in upcoming years. © 2021, springer Nature singapore Pte Ltd.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Enhancing speech Emotional Recognition through a Multi-Layer Perceptron Model 2

Enhancing Speech Emotional Recognition through a Multi-Layer...

引用

2nd International Conference on Trends in Electrical, Electronics and computer engineering, TEECCON 2023

作者： Lakshminarayanan, Arun Raj singh Rathna balaji, Inderpaal Hussain, sheik Taaha Jayaraman, Vaishnavi Anwar, Chintakunta shaik B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350339949

Detecting emotions in audio speech files is a significant challenge for machines, despite the natural skill of humans in this area. While computers excel at comprehending informational content, deciphering underlying emotions remains a formidable challenge. At this juncture, the speech Emotion Recognition system (sERs) emerges as an important component of the solution. To reliably categorize audio speech data into distinct emotional categories such as happiness, sorrow, anger, and neutrality, a specific model called sERs was developed. It has a wide range of potential uses, from healthcare to contact centers. In this study, the following Machine Learning models were utilized support Vector Machine (sVM), k-nearest neighbors (KNN), and Decision Tree (DT). These models yielded lower accuracy rates when categorizing emotions. Thus, to improve the accuracy rate three crucial audio features such as Mel, chroma, and MFCC are applied by the constructed sERs and analyzed by utilizing a grid search-b.s.d Multi-Layer Perceptron (MLP) classifier for accurate results. The proposed model produced 75.97% accuracy rate, which is quite remarkable. © 2023 IEEE.

关键词： Emotion Recognition

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：