Browsing by Author "Islam, Rakibul"

Now showing 1 - 20 of 33

A domain and noise adversarial bird tune classification pipeline using deep neural network
(BRAC University, 9/29/2022) Riya, Aparna Sarker; Roy, Arpita; Fahim, Md. Abrar; Tasnim, Zarin; Islam, Rakibul; Mostakim, Moin; Reza, Md Tanzim
Birds are an important category of animals that ecologists keep track of utilizing autonomous recording units as a key indication of environmental health. Because of the consequences of climate change and the rising number of endangered species, many experts suggested developing an animal species recognition system to help them in specialized research. Researchers can improve their ability to assess the state of biodiversity and its patterns in crucial ecosystems by precise sound detection and categorization, which is supported by machine learning, allowing them to better support global conservation efforts. However, producing analysis outputs with high precision and recall remains a difficulty. Due to a lack of appropriate methods for efficient and accurate extraction of interest signals, the vast bulk of data remains unexplored (e.g., bird calls). Moreover, due to strong source-domain specific features and artificial/natural noises, these acquired raw data create different distributions in datasets. So, to ensure a generalized feature learning, domain adaptation [1] techniques will be implemented in this work to make the networks familiar towards both acquisition sensor noises and background noises without having to do intensive dataset specific augmentations. We used 3 popular and powerful DNN models, including CNN, VGG19 and ResNet50. Out of them, for the bird species classification task VGG19 achieved the best accuracy of 96.02% in testing and 94.01% in training. To the best of our knowledge, this will guide towards convenient and deployable in real life models which will allow future works into the pipeline to ensure better coverage.
A Fine Tune Robust Transfer Learning Based Approach for Brain Tumor Detection Using Vgg-16
(Institute of Electrical and Electronics Engineers Inc., 2023-12-15) Islam, Rakibul; Akhi, Amatul Bushra; Akter, Farzana
Brain tumor recognition by magnetic resonance imaging (MRI) is crucial because it improves survival rates and allows them to plan treatments accordingly. An accumulation of abnormal cells known as a brain tumor can spread to nearby tissues and endanger the patient. Magnetic resonance imagery is the primary imaging technique which determines the extent of brain tumors. Deep learning techniques rapidly grew in computer vision due to ample data for model training and improved designs on applications. MRI has shown promising results when using deep learning approaches to identify and classify brain tumors. This study uses MRI data and a convolutional neural network (CNN) to create a reliable transfer learning model that classifies tumors under four classes. Brain tumors' unwanted parts are excised, the quality is improved, and the cancer is coloured. By eliminating artefacts, decreasing noise, and boosting the image. The number of MRI images has increased using two augmentation techniques. A number of CNN architectures, including VGG19, VGG16, MobileNet, InceptionV3, and MobileNetV2 analyzed the augmented dataset. Where VGG-16 provides the accuracy of highest level. The best model underwent a hyperparameter ablation investigation, which led to the suggested hyper-tuned VGG16 obtaining 99.21% test and validation accuracy and 99.01% test accuracy.
A Fine Tune VGG16 Model Based on Ablation Study for Diagnosing Brain Tumor from MRI Images
(Daffodil International University, 23-01-29) Islam, Rakibul
Brain tumor recognition by magnetic resonance imaging (MRI) is crucial because it improves survival rates and allows them to plan treatments accordingly. The patient is at risk if a tumour in the brain, which is made up of a cluster of abnormal cells, spreads to nearby tissues. MRI is the primary technique of imaging which is used for determining the extent of brain tumours. Deep Learning techniques have rapidly expanded in popularity in computer vision applications due to the abundance of data available for training models and advancements in designing models that provide more accurate estimations. When using deep learning techniques to recognize and categorize brain tumors, magnetic resonance imaging (MRI) has produced satisfactory performance. In this paper, we develop a strong deep-learning model which classifies brain tumors into four groups depending on MRI scans using a CNN. Unsolicited areas of brain tumours are deleted with the help of artefact removal, lowering noise, and quality-enhanced images. With improved image quality the cancer is tinted. The number of MRI images has increased using two augmentation techniques. The augmented dataset was analyzed by a number of CNN architectures, including VGG19, MobileNetV2, InceptionV3, VGG16, and Mobile Net. In this situation, VGG-16 offers the highest level of accuracy. The best model was then chosen, and a ablation study was performed on it based on the hyperparameters. The best outcomes were achieved by the hyper-tuned VGG16, which had test accuracy of 98.56% and validation and test accuracy of 99.23%.
A Priority-Based Process Scheduling Algorithm in Cloud Computing
(Springer Nature Singapore Pte Ltd., 2018-12-12) Haque, Misbahul; Islam, Rakibul; Kabir, Md. Rubayeth; Nur, Fernaz Narin; Moon, Nazmun Nessa
Nowadays, cloud computing is in demand as it provides progressive pliable resource allocation, for unfailing and guaranteed services in the pay-as-you-use scheme, to cloud service users. So, there is a dispensation that all resources are made available to requesting users in an efficient manner to satisfy their needs. Process scheduling has become the key issue in cloud computing. In this paper, we have presented a priority-based process scheduling (PRIPSA) algorithm, which is developed with the block-based queue in cloud computing. It concentrates on the preemptive part as well as it calculates the energy consumption and reducing starvation of process for scheduling the process in the cloud. We provide a priority-based algorithm which considered preempt able task scheduling with block-based queue using burst time and lead time. This job is being performed by the dynamic voltage and frequency scaling (DVFS) controller in our algorithm. The load management, energy consumption, reducing the starvation problem of the processes, and maximizing the revenue are the key motives of our consideration.
A Priority-Based Process Scheduling Algorithm in Cloud Computing
(Scopus, 2020) Haque, Misbahul; Islam, Rakibul; Kabir, Md. Rubayeth; Nur, Fernaz Narin; Moon, Nazmun Nessa
Nowadays, cloud computing is in demand as it provides progressive pliable resource allocation, for unfailing and guaranteed services in the pay-as-you-use scheme, to cloud service users. So, there is a dispensation that all resources are made available to requesting users in an efficient manner to satisfy their needs. Process scheduling has become the key issue in cloud computing. In this paper, we have presented a priority-based process scheduling (PRIPSA) algorithm, which is developed with the block-based queue in cloud computing. It concentrates on the preemptive part as well as it calculates the energy consumption and reducing starvation of process for scheduling the process in the cloud. We provide a priority-based algorithm which considered preempt able task scheduling with block-based queue using burst time and lead time. This job is being performed by the dynamic voltage and frequency scaling (DVFS) controller in our algorithm. The load management, energy consumption, reducing the starvation problem of the processes, and maximizing the revenue are the key motives of our consideration.
A Software Development Documentation Internship With Smart Enterprise Software
(Daffodil International University, 2019-11) Islam, Rakibul
This report discusses my experience as a software development documentation intern at Smart-Enterprise, from August 2018 to December 2018. I worked on short and longterm projects at Smart-Enterprise. Smart-Enterprise is a fully integrated ERP solution meets all business needs and enables to achieve a faster, accountable, centralize and smooth-up operation for organization. It helps to streamline and automate business processes by providing functionality across a variety of areas. It has the modules that completely automate and run business; Purchasing, Accounting, Production, Inventory Control, Sales, and more. This application has been developed by content management system using Java script, Bootstrap4 and written in C# (.Net Framework MVC Pattern) and Sql Server Database
Aligning Education with Market Demands: A Case Study of Marketing Graduates from Daffodil International University
(Scopus, 2024) Abir, Tanvir; Islam, Rakibul; Ullah, Anowar; Rahman, Siddiqur
This study conducted a comprehensive tracer analysis of 197 graduates from Daffodil International University’s Marketing bachelor program between 2019 and 2022. The main objective was to evaluate the program's alignment with labor market requirements and its effectiveness in equipping students with the necessary skills to navigate the complexities of the global market. A cross-sectional descriptive design was employed, utilizing a survey questionnaire as the primary data collection instrument. The target population consisted of graduates of the marketing program, selected through purposive sampling to ensure the inclusion of individuals with relevant experience. Data were analyzed using descriptive statistics to identify trends and percentages. Key findings revealed a significant gender disparity, with more male graduates than female, and high unemployment rates, which highlighted ongoing employment difficulties. While 75.5% of graduates affirmed the curriculum’s relevance to their professional roles, a gap was noted between the theoretical knowledge imparted and its practical application. The study suggests integrating comprehensive career preparation and extensive networking opportunities into the curriculum to mitigate employment barriers. Additionally, enhancing the curriculum to support entrepreneurial ventures is recommended. The findings emphasize the importance of ongoing curriculum revisions and the development of dynamic career support services to improve graduate employability and adapt to the evolving demands of the marketing profession. This research provides valuable insights for policymakers, curriculum developers, and educational researchers to enhance the relevance of higher education to the workforce, facilitating successful transitions into the labor market.
Aligning Education with Market Demands: A Case Study of Marketing Graduates from Daffodil International University
(Society for Research and Knowledge Management, 2024-08-15) Abir, Tanvir; Islam, Rakibul; Ullah, Anowar; Rahman, Siddiqur
This study conducted a comprehensive tracer analysis of 197 graduates from Daffodil International University’s Marketing bachelor program between 2019 and 2022. The main objective was to evaluate the program's alignment with labor market requirements and its effectiveness in equipping students with the necessary skills to navigate the complexities of the global market. A cross-sectional descriptive design was employed, utilizing a survey questionnaire as the primary data collection instrument. The target population consisted of graduates of the marketing program, selected through purposive sampling to ensure the inclusion of individuals with relevant experience. Data were analyzed using descriptive statistics to identify trends and percentages. Key findings revealed a significant gender disparity, with more male graduates than female, and high unemployment rates, which highlighted ongoing employment difficulties. While 75.5% of graduates affirmed the curriculum’s relevance to their professional roles, a gap was noted between the theoretical knowledge imparted and its practical application. The study suggests integrating comprehensive career preparation and extensive networking opportunities into the curriculum to mitigate employment barriers. Additionally, enhancing the curriculum to support entrepreneurial ventures is recommended. The findings emphasize the importance of ongoing curriculum revisions and the development of dynamic career support services to improve graduate employability and adapt to the evolving demands of the marketing profession. This research provides valuable insights for policymakers, curriculum developers, and educational researchers to enhance the relevance of higher education to the workforce, facilitating successful transitions into the labor market.
Assessing Early Stage Design of a mHealth App for Gestational Diabetes Mellitus Management in Bangladeshi Women
(The International Diabetes Federation (IDF), 2023, 2023-10) Islam, Ashraful; AHMED, ESHTIAK; Zaman, Marzia; Rangon, Fairy Hasan; Amin, M Ashraful; Islam, Rakibul
There is significant concern over the rising incidence of Gestational Diabetes Mellitus (GDM) among expectant mothers in Bangladesh [1]. Limited healthcare facilities in rural areas hinder prompt diagnosis and efficient management of GDM in Bangladesh. Despite mHealth's benefits, there is a lack of GDM management apps in Bangla, the native language of Bangladeshi citizens. To assess the viability of the first GDM management mHealth app in Bangla, users were asked about its early designs and functionalities. The app features a blood glucose tracker, food diary, medication reminder, educational resources, activity tracker, and personalized recommendations. 30 women with pre-existing GDM who were visiting a clinic in Dhaka, Bangladesh, were freely recruited during July 2023, and participation was anonymized. Participants ranged in age from 24 to 43 years (mean 33.43, SD 5.4). Following a briefing on the app's features and functionalities, participants were shown early sketches of the app. Later, they were prompted with a series of questions to provide feedback on the initial design and features. The majority (n=24) participants exhibited a positive response towards the app, expressing a wish that they had such a tool during their experience with GDM. However, 2 participants viewed the app as an impractical tool, while 3 were uncertain, expressing concerns about the accuracy of the information and guidance provided by the app. Beyond a textual interface, 1 participant suggested the inclusion of voice-based interaction to accommodate users who are illiterate, unfamiliar with using apps or having visual impairments. All participants appreciated the interface's use of the Bangla language and its cultural tailoring. 9 participants specifically highlighted the culturally tailored dietary recommendation feature as particularly praiseworthy. The app can play a crucial role in managing GDM in Bangladesh based on the early-stage evaluation feedback. However, further research is warranted to evaluate the real-world effectiveness and feasibility of it with a high-fidelity prototype for in-situ evaluation with the target users.
Bangla Speaker Accent Variation Detection by MFCC Using Recurrent Neural Network Algorithm
(Springer, 2020-03-04) Mamun, Rezaul Karim; Abujar, Sheikh; Islam, Rakibul; Been Md. Badruzzaman, Khalid; Hasan, Mehedi
There are a number of languages accent differential applications that detect the different accents in assorted languages. The studies which have done before most of them are based on the English language and different languages throughout the world. A few researches have been performed in Bangla regional language accent differential applications, which is not conclusive for the system to be able to manage Bangla accented speakers. In this paper, we report regional language accent detection experiments of different types of Bangladesh. We demonstrate a strategy to observe Bangladeshi different accents which exploit Mel frequency cepstral coefficient (MFCC) and recurrent neural network (RNN). Listening from the people of different places in Bangladesh creates an accent differentiation results performed by the speakers. This experimental result shows the adaptation of the people to adapt of the regional languages.
Determinants of Students Satisfaction at Higher Educational Institution in Bangladesh: Evidence from Private and Public Universities
(Malaysian Online Journal of Education, 2019) Hossain, Mohammad Emdad; Hoq, Mohammad Nazmul; Sultana, Israth; Islam, Rakibul; Hassan, Md. Zahid
The purpose of this study is to identify the relative importance of factors that influence the students’ satisfaction at private and public universities in Bangladesh. Moreover, the study examines different demographic and socio-economic variables that also affect stakeholders’ satisfaction at university. Quantitative method research design was conducted for the study and a sample of 182 students was taken from different private and public universities in Bangladesh. The results showed that students were mostly satisfied with teachers’ expertise and design of course curriculum in both categories of universities in Bangladesh while food facilities had the lowest positive response factor of the students. The exceptionality of this study is to use binary logistic regression analysis to identify the most important demographic determinants regarding satisfaction. It is found that female students were less likely to be satisfied overall on their respective institutions than their male counterparts. In addition, students from the urban area and also from middle-class economic condition had more likely to be satisfied than any other counterparts. Understanding these variables could assist educational institutions with bettering their strategies to achieve their desired goal. Moreover, the strategy of development of strong personal relations with students and faculty members can definitely alleviate the dissatisfaction of the students.
Determination of Strong Ion Difference and Anion Gap from blood biochemical parameters in Lactating Cow
(Chattogram Veterinary and Animal Sciences University Khulshi, Chattagram-4225, Bangladesh, 2021-11) Islam, Rakibul
The objectives of this study are to determine serum strong ion differences (SID) and anion gap (AG) of 8 high yielding lactating dairy cows with a history of inappetence and drop of milk production. Blood biochemical data of 8 cows were collected from diagnostic reports done at the Department of Physiology, Biochemistry and Pharmacology, Chattogram Veterinary and Animal Sciences University. Concentrations of quantitatively important strong ions (Na+, K+, Ca2+, Mg2+, Cl-) and nonvolatile buffer ions (total protein and phosphate) were determined and a fixed L-lactate value was used. Mean (±SD) of Strong ion difference (SID) was determined by calculating the differences between measured strong anion and cation concentrations (SID3, 37.56 mEq/L; SID4, 37.02 mEq/L; SID6, 40.14 mEq/L). Mean value of Atot, total plasma concentration of nonvolatile weak acids was calculated (Atot, 28.10 mmol/L) and this value along with a fixed value of Ka, effective dissociation constant for plasma weak acids and pH is then used to calculate concentrations of HCO3-. Anion Gap is then determined and the mean value of anion gap (AG) is 16.62 mEq/L, which is within the normal reference range. Although acid-base abnormalities are frequently present in sick animals. Measuring SID and AG will not only help in explaining the underlaying disease mechanisms of Acid-base disorders but also will help in proper treatment protocols.
Effect of E-Banking on the Performance of Commercial Banks: A Case Study on Selected Banks of Bangladesh.
(HAJEE MOHAMMAD DANESH SCIENCE AND TECHNOLOGY UNIVERSITY, DINAJPUR., 2016-06) Islam, Rakibul; Saiful Islam
In this present world, we are always interacting with Information & Technologies and always trying to keep pace with using new & newer Information & Technologies (IT) and IT related devices. E-Banking is one of the parts to become a digital Bangladesh and also it is being tried to adapt this in various organizations. As apparently, it can be assumed that the adaptation of E-Banking can produce good results for the organizations. This paper is a result of survey on the impact of E-Banking on the performance of commercial banks, particularly some banks in Dinajpur area. Continuous technological development, particularly information technology revolution of the decades has forced the banks to introduce the E-Banking operations for their sustainable growth in expanded competitive environment. E-Banking has made financial transactions easier for the participants and has introduced wide range of financial products and services. The main focus of this research is to present the scenario, prospects & the impact of E-Banking on the performance of commercial banks. The study is descriptive in nature and data were gathered both through direct observation and reaching at the websites of different banks, conversation with bankers and interview by structured questionnaires through random sampling technique with current customers of different banks. To measure operating performance, I have analyzed questionnaire data from respondents those are primary in nature. It indicates that operating performance of the banks is much more satisfied due to E-Banking systems. Again, ROE, ROCE and ROA are also calculated to measure financial performance with specified formulas data from annual reports. The result of this measurement shows that E-Banking has a negative effect on the performance of the commercial banks. Primary data analysis has produced commendable effect on the performance of banks. But secondary data analyses have provided the result that is after adaptation of E-Banking, Banking performance has been declined. And for this, only EBanking system is not liable. As we are in primary stage of adaptation process and our people are not well accustomed with the system that occur increase in operating expenses or more investment that didn’t provide required return. Again political instability and also the effect of economic slowdown may cause for this result. If everything remains better, we hope this system may provide a good result in near future. The study also highlights some constraints and steps of overcoming those constraints of E-Banking in banking sector of Bangladesh.
Evaluating the Performance of Piled Raft Foundations on Soft Soil Using PLAXIS 2D
(Daffodil International University, 2024-12-08) Islam, Rakibul
A large number of building projects have been built on soft soil in recent years. Differential settlements can occur in structures built on soft soil because of its properties. The raft foundation is one way to lessen differential settling. It may result in excessive settling even when it has a sufficient bearing capacity. A piled raft foundation system is one that uses piles in conjunction with a raft foundation. The analysis of piled raft foundations in soft soil conditions presents a critical challenge in geotechnical engineering due to the complexities associated with soil-structure interactions and settlement behavior. This study employs PLAXIS 2D, a finite element analysis software, to investigate the performance of piled raft foundations subjected to varying load conditions on soft soil. The research aims to optimize the design by examining the contribution of piles to load sharing and settlement reduction. Key parameters such aspile length, pile spacing, and raft thickness are analyzed to evaluate their impact on the overall foundation behavior. Results from numerical simulations highlight the significant influence of pile arrangement and soil properties on the settlement response and load distribution efficiency. The findings provide a comprehensive understanding of the piled raft system, offering insights for the effective design of foundations in challenging soft soil environments, enhancing stability and reducing excessive settlement. Based on the permitted settlements, the ideal amount of piles for a piled raft foundation system must be taken into account for an economical design.
Film Editing
(Daffodil International University, 2019-12-11) Islam, Rakibul
Unite also to fulfill my Want to start my own and also a Drama Generation had to execute my intern once I had a chance to start my profession in spring 17, I opted to do it and you will find reasons for this creation. The episodes appeared transferred in reality and actualities. Interesting actualities look in movies and engage us. Movies are imperative on the reasons are the medium that is perfect. Movies can be enlightening. Films can be persuasive. Pictures can achieve A change from the eye in people' psyches. Movies make us feel items that are different, distress, pride and enthusiasm. We think what the characters feel and most of us know the characters do what they do in the movies. Films show somebody's ability and transfer our very own significant scale. Help us comprehend the behavior that's human. We are pushed by fantasy films. Films help us recall background Career. Movies are crucial Films are not allas a foundation certain, of entertainment . . . but movies can be study material. Movies are important that is why I decided to is a mind function of art. There's a wonderful combination Image and audio and content are the fundamental. There's mild, acting, narrative writing, changing and so on. Information is granted by films at Contained in Necessity.
Identification of molecular biomarkers and pathways of NSCLC
(Journal of Genetic Engineering and Biotechnology, Springer, 2021-03-19) Islam, Rakibul; Ahmed, Liton; Paul, Bikash Kumar; Ahmed, Kawsar; Bhuiyan, Touhid; Ali Moni, Mohammad
Background Worldwide, more than 80% of identified lung cancer cases are associated to the non-small cell lung cancer (NSCLC). We used microarray gene expression dataset GSE10245 to identify key biomarkers and associated pathways in NSCLC. Results To collect Differentially Expressed Genes (DEGs) from the dataset GSE10245, we applied the R statistical language. Functional analysis was completed using the Database for Annotation Visualization and Integrated Discovery (DAVID) online repository. The Differential Net database was used to construct Protein–protein interaction (PPI) network and visualized it with the Cytoscape software. Using the Molecular Complex Detection (MCODE) method, we identify clusters from the constructed PPI network. Finally, survival analysis was performed to acquire the overall survival (OS) values of the key genes. One thousand eighty two DEGs were unveiled after applying statistical criterion. Functional analysis showed that overexpressed DEGs were greatly involved with epidermis development and keratinocyte differentiation; the under-expressed DEGs were principally associated with the positive regulation of nitric oxide biosynthetic process and signal transduction. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway investigation explored that the overexpressed DEGs were highly involved with the cell cycle; the under-expressed DEGs were involved with cell adhesion molecules. The PPI network was constructed with 474 nodes and 2233 connections. Conclusions Using the connectivity method, 12 genes were considered as hub genes. Survival analysis showed worse OS value for SFN, DSP, and PHGDH. Outcomes indicate that Stratifin may play a crucial role in the development of NSCLC
Impact of Working Capital Management on Corporate ProfitabilityEmpirical Evidence from Pharmaceutical Industry of Bangladesh
(Canadian Center of Science and Education, 2018) Islam, Rakibul; Hossain, Mohammad Emdad; Hoq, Mohammad Nazmul; Alam, Md. Morshedul
Working capital management plays centric role in enhancing operational efficiency and their ultimate profitability. Globally financial managers have been searching the proper way on how to utilize working capital components which prolong profitability. The purpose of this study is to assess the impact of working capital components on profitability indicators of selected pharmaceutical firms in Bangladesh. The paper used financial data of 9 pharmaceutical firms listed in Dhaka stock exchange (DSE) covered 2011-2015. Two methods were used in this study for analysis data set. Firstly, to measure the relationship between selected variables Pearson Correlation matrix was used. Secondly, multiple regression analysis was used to investigate the impact working capital components on profitability of selected pharmaceutical firms. The study also conducted Durbin Watson test to assess autocorrelation of selected variables. In this study the correlation matrix identified a negative correlation between working capital components and profitability, whereas regression analysis found number of days account receivable (AR) had significant positive and current ratio (CR) and debt ratio (DR) had appeared a significant negative impact on profitability.
Mutual fund performance: an analysis of mutual funds’ return compare to the market return (DSEX).
(BRAC University, 1/14/2015) Islam, Rakibul; Afiruzzaman, S. M.
Mutual Fund is a Capital Market Investment Vehicle. In Bangladesh there are 48 Mutual Funds under 17 Asset Management Companies. This paper focused on evaluating the performance of 48 growth oriented mutual funds on the basis of weekly returns compared to market returns. Risk adjusted performance measures suggested by Jenson, Treynor, Sharpe and statistical models are employed. It is found that, most of the mutual funds have performed better according to Jenson and Treynor measures but not up to the benchmark on the basis of Sharpe ratio. However, most of the mutual funds are diversified and have reduced its unique risk. The growth oriented funds have performed better in terms of total risk and the funds are offering advantages of diversification and professionalism to the investors. So, mutual funds perform better with their expertise.
Performance Analysis of Chronic Kidney Disease through Machine Learning Approaches
(Daffodil International University, 2021-01-28) Emon, Minhaz Uddin; Imran, Md. Al Mahmud; Islam, Rakibul
Machine learning and data mining play a vital role in health care and also medical information and detection, Now a day machine learning techniques use awareness of some major health risks such as diabetic prediction, brain tumor detection, covid 19 detections, and many more. The kidney is the most important organ of our body and if it has any problem then the impact is more dangerous to our body. Chronic kidney disease (CKD), otherwise referred to as renal disease. Chronic kidney disease requires disorders that damage and reduce the capacity of our kidneys to keep us healthy. So, we need to be concerned about kidney disease to our very primary stage. We take a few attributes to measure our analysis about chronic kidney disease and this attribute is one of the major occurrences of chronic kidney disease. Therefore 8 machine learning classifier are used to measure analysis using weka tools namely: Naive Bayes(NB), Logistic Regression(LG), Multilayer Perceptron(MLP), Stochastic Gradient Descent(SGD), Adaptive Boosting(Adaboost), Bagging, Decision Tree(DT), Random Forest(RF) classifier are used. We feature extraction of all attributes using principal component analysis(PCA). We gain the highest accuracy from the Random Forest(RF) and it is 99% and ROC(receiver operating characteristic) curve value is also highest from other algorithms
Performance Analysis of Chronic Kidney Disease through Machine Learning Approaches
(Scopus, 2021) Emon, Minhaz Uddin; Imran, Al Mahmud; Islam, Rakibul; Keya, Maria Sultana; Zannat, Raihana; Ohidujjaman, Ohidujjaman
Data mining and machine learning play a vital role in health care and also medical information and detection, Now a day machine learning techniques use awareness of some major health risks such as diabetic prediction, brain tumor detection, covid 19 detections, and many more. The kidney is the most important organ of our body and if it has any problem then the impact is more dangerous to our body. Chronic kidney disease (CKD), otherwise referred to as renal disease. CKD requires disorders that damage and reduce the capacity of our kidneys to keep us healthy. So, it is required to be concerned about kidney disease to our very primary stage. We take a few attributes to measure our analysis about chronic kidney disease and this attribute is one of the major occurrences of chronic kidney disease. Therefore 8 machine learning classifier are used to measure analysis using weka tools namely: Logistic Regression (LG), Naive Bayes (NB), Multilayer Perceptron (MLP), Stochastic Gradient Descent (SGD), Adaptive Boosting (Adaboost), Bagging, Decision Tree (DT), Random Forest (RF) classifier are used. We feature extraction of all attributes using principal component analysis (PCA). We gain the highest accuracy from the Random Forest (RF) and it is 99 % and ROC (receiver operating characteristic) curve value is also highest from other algorithms.