Browsing by Author "Tasnim, Zarrin"

Now showing 1 - 20 of 31

A Convolutional Neural Network Based Classification Approach for Breast Cancer Detection
(IEEE, 2023-05-24) Rashid, Md Harun Or; Shahriyar, S. M.; Shamrat, F M Javed Mehedi; Mahbub, Tanzil; Tasnim, Zarrin; Ahmed, Md Zunayed
Thousands of women worldwide are diagnosed with breast cancer yearly, which may be fatal if not treated. The diagnosis of the condition may take years, by which time the patient has little choice except to have the affected breast removed. Early diagnosis and treatments are the best ways to stop this disease's spread. In this study, the authors presented a Computer Aided Diagnosis (CAD) system to assist in breast cancer diagnosis. The study uses the Wisconsin breast cancer dataset to classify benign and malignant data. For the classification, three pre-trained Deep learning algorithms: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), were used. A novel CNN model that exceeds the performance efficiency of three pre-trained models and requires minimal compilation time is proposed. A number of evaluation matrices are used to analyze the models' classification abilities. Upon closer inspection, it has been established that the proposed CNN model outperforms CNN, LSTM, and MLP models with validation accuracy of 97.85%. CNN and LSTM performed with accuracies of 94.12% with the Adagrad optimizer and 93.5% with the Adam optimizer, respectively. Furthermore, MLP performance with 92.44% accuracy using the Adam optimizer. The proposed CNN model achieves the lowest Loss value and compilation time. In addition, the models' recall value, precision, and f1-score are computed to pick out the most effective model for diagnosing breast cancer on numeric data.
A Deep Learning-Based Waste Classification Using Ensemble and Vision Transformer Models
(Daffodil International University, 2025-05-14) Ahmmed, Sayem; Tasnim, Zarrin
This research presents a deep learning approach for waste categorization using three pre-trained models such as MobileNetV2, DenseNet121, and ResNet50, a transformer model (Vision Transformer or ViT), and an ensemble model. The seven-class waste dataset was used, which is publicly available, with the preprocessing steps including resizing, normalization, augmentation, and class balancing. Hyperparameter tuning was applied to all models using Grid Search, Random Search, and Bayesian Optimization. Among them, the ensemble model had a test accuracy of 97.52%, surpassing single models by synergistically combining their predictions by weighted averaging soft voting. The models were made robust using label smoothing, mix-up augmentation, and class weighting. Evaluation was carried out on accuracy, precision, recall, F1-score, and confusion matrices. Issues such as class imbalance and intra-class visual similarity in visual waste classification are addressed by the study. The future work will use the system in an IoT-capable intelligent dustbin for actual implementation.
A Web Based Application for Agriculture
(International Journal of Emerging Trends in Engineering Research, 2020-06) Shamrat, F. M. Javed Mehedi; Asaduzzaman, Md; Ghosh, Pronab; Sultan, Md Dipu; Tasnim, Zarrin
Bangladesh is predominantly an agricultural country, where agriculture sector plays a vital role in accelerating the economic growth. Agriculture remains the most important sector of Bangladeshi economy, contributing 19.6 percent to the national GDP and providing employment for 63 percent of the population. A National Agricultural Census report has said Bangladesh is currently home to 16.5 million farmer families. The report also highlighted the fact that there over four million landless farmers, with near 6.8 million farmers cultivating other people's land. To help the farmers and improve in agricultural sector, we design and develop a web based application "Smart Farming System". Farmers of Bangladesh can learn and share various knowledge and problem facing during farming through this system. Farmers can acquire information around various diseases and resolver on their problems. They can get support in various agricultural activities, by the help of the consultants and doctors through the "Smart Farming System". To develop this system we used HTML5, CSS, Bootstrap, and JavaScript. In addition, the PHP framework is used to manage the MySQL database. In testing phase, we tested it with a community based social media on Facebook and its work great with expecting output, peoples are expecting these services to be interesting.
An Automated Embedded Detection and Alarm System for Preventing Accidents of Passengers Vessel Due to Overweight
(Scopus, 2019-10-23) Shamrat, F. M. Javed Mehedi; Ahmed, Md. Razu; Nobel, Naimul Islam; Tasnim, Zarrin
One of the prominent transport system in Bangladesh is rivers and seas. Vessel overloading is found in Bangladesh as the main cause of accidents on the rivers and seas. Therefore, there must be a role to play in ensuring passenger safety on the vessels. In Bangladesh, the researchers are more focusing on the data collection related to vessel overloading and sinking. However, there is a need to overcome vessel overloading. This paper design and develop an embedded automated system which able to identify overweight and detect the location of a vessel. The proposed system segregated into three modules such as, the Location Detection Module (LDM) always tracks the current location of the vessel for monitoring; the Overweight Detection Module (ODM) measure the exceed water level of the vessel to identify the overweight issue; the Notification Module (NM) is responsible for generating message service (SMS) to notify nearby coast guard to stop the vessel. The result shows the successful overweight detection, location tracking, and instant notification send up-to-the-10 seconds. It can be noted that our proposed prototype can be embedded with any type of vessels including passenger vessel, general cargo vessel, etc.
An Effective Implementation of Web Crawling Technology to Retrieve Data from the World Wide Web (WWW)
(International Journal of Scientific and Technology Research, 2020) Shamrat, F. M. Javed Mehedi; Tasnim, Zarrin; Rahman, A.K.M Sazzadur; Nobel, Naimul Islam; Hossain, Syed Akhter
: Internet (or just the web) is enormous, well off, best, easily accessible and proper wellspring of data and its clients are expanding quickly now daily. To rescue data from the web, web indexes are utilized which access pages according to the prerequisite of the clients. The size of the web is exceptionally wide and contains organized semi-organized and unstructured information. The greater part of the information present on the web is unmanaged so it is absurd to expect to get to the entire web without a moment's delay in a solitary endeavor, so web crawlers use web crawlers. A web crawler is a fundamental piece of the web search tool. Data Retrieval manages to look and recovering data inside the reports and it likewise looks through the online databases and the web. In this paper, discussed, developed and programmed a web crawler to fetch the information from the internet and filter data for useable and graphical purpose for users.
An exploratory study on parents’ perception of online learning for preschoolers
(BRAC University, 2021-12) Tasnim, Zarrin; Khan, Mohammad Safayet
During the COVID-19 pandemic online learning has been one of the key methods of education for children as they have spent most of their time at home. This study explored the perception of parents on online learning for the preschoolers where 203 parents from English medium schools in Dhaka city of Bangladesh participated in an online survey. The data collected was analyzed in SPSS (version 20) and descriptive statistics was used to describe the findings. For parents, online learning is a means of keeping their children active during the pandemic but it is not an effective tool for education. Parents did not believe online learning was beneficial to their children. They also seemed to be concerned about the harmful effects of increased screen time on children.
An Offline and Online-based Android Application ―travelhelp to Assist the Travelers Visually And Verbally for Outing
(International Journal of Scientific and Technology Research, 2020) Shamrat, F.M. Javed Mehedi; Rahman, A.K.M Sazzadur; Tasnim, Zarrin; Hossain, Syed Akhter
TravelHelp" is an android application thatwill be developed mainly to help tourists who are eager to visit Dhaka city. The application is mainly featured to be an offline app so that the user can use the app without any hassle to acquire data services. Both English and Bangla language are supported so that not only foreigners but also the local people can also use the app flexibly. The app is developed to be user-friendly and to support different screen sizes of various mobile and tablet devices. It has features like details about the point of attractions and map of the Dhaka city. Other features include a language translator in the app. This paper details the development process of the travel application. Thisthesis is intending to design & development the idea of a user-friendly android-based offline mobile and web-based application. The travel application will be developed to provide information about the point of attractions and map of the Dhaka city. The map will consist of the regional main attractions, traveling path and assumed expense. An extension of the work is including an instant voice translator in the app which might be very helpful for the foreign travelers who are traveling the Dhaka city. An automatic voice responder based on AI (artificial intelligence) is also planned to be included in the application. By using this tool, the foreigner can be easily able to communicate with the local people which will lead to a very convenient travel.
Application of K-Means Clustering Algorithm to Determine the Density of Demand of Different Kinds of Jobs
(International Journal of Scientific and Technology Research, 2020) Shamrat, F. M. Javed Mehedi; Tasnim, Zarrin; Mahmud, Imran; Jahan, Ms. Nusrat; Nobel, Naimul Islam
In the current competitive job market, information is the most powerful tool. As a job, the seeker looks for a job, and he must have the insight of what kind of competition he is about to face. This information will allow the job seeker to improve himself from the rest in the market. To determine the demand for any field of job among job seekers, with the help of the unsupervised k-means machine learning algorithm, the data of job interests can be clustered in different groups based on their kinds. The visual representation of the clusters in a scatter plot gives the information on which variety of jobs are in more or less demand among job seekers with the density of the groups. This study provides insight into the current jobmarket.
Caregivers’ perception on children learning self-regulation in daycare
(BRAC University, 2024-05) Sultana, Kawsar; Tasnim, Zarrin
This study looks into carers' perceptions of 3-5-year-old children learning self-regulation in the daycare and their parents' involvement. This study also looks into the challenges that carers face in daycare settings while practicing self-regulation with the children. Numerous studies highlight the significance of self-regulation for children's cognitive and behavioral development, allowing them to act freely, manage themselves, and interact according to social standards without adult supervision. In this case, carers play an important role in assisting students to develop self-control through activities. The study included 13 participants who took part in seven in-depth interviews and a focus group discussion at four nursery facilities. This study revealed that carers have a general understanding of self-regulation and its importance in early childhood. The study additionally found that one daycare center offers learning opportunities for all types of children, with different activities tailored to their cognitive and developmental stages. Carers' positive understanding of giving children words of importance and offering alternative options fosters a supportive environment. The study suggests incorporating self-regulation skills into daycare curricula and providing teachers with additional training in child development facts. The findings also suggested that more research into parents' perspectives and direct assessments of children's abilities is needed to gain a better understanding of this study.
Classification of Breast Cancer Cell Images using Multiple Convolution Neural Network Architectures
(Scopus, 2021) Tasnim, Zarrin; Shamrat, F. M. Javed Mehedi; Islam, Md Saidul; Rahman, Md.Tareq; Aronya, Biraj Saha; Muna, Jannatun Naeem; Billah, Md. Masum
Abstract: Breast cancer is a malignant tumor that affects women. It is the most prevalent cancer in women, affecting about 10% of all women at any point in their lives. The development of breast cancer begins in the lobules or ducts of the cells. Early detection and prevention are the best ways to stop this cancer from spreading. In this study, five Convolution Neural Network (CNN) models are used to process image data of breast cells. Alex Net, InceptionV3, GoogLeNet, VGG19 and Exception models are used for the classification of Invasive Ductal Carcinoma, IDC and Non-Invasive Ductal Carcinoma (Non-IDC) cells. The models are trained and tested at different epochs to record the learning rate. It is observed from the study that with higher epochs, the data loss decreases and accuracy increases. The accuracy of InceptionV3 and Exception is 92.48% and 90.72% respectively. Likewise, VGG19 and Alex Net have fairly close accuracy of 94.83% and 96.74%. However, GoogLeNet dominates over the other implemented models with the highest accuracy of 97.80%. The GoogLeNet model performs with high accuracy and precision in detecting IDC cells responsible for breast cancer.
Comparative analysis of Dhaka Bank Limited
(BRAC University, 5/2/2017) Tasnim, Zarrin; Khan, Tanzin
Dhaka Bank Limited has diversified its service coverage during last twenty two years by opening new branches at different strategically important locations across the country by offering various services with a commitment of ensuring excellence in banking. Like Dhaka Bank Limited City Bank Limited, Southeast Bank Limited & Prime Bank is also doing a good job in a long run. Four of these companies shares some same features as they all are private banks and controlled under Bangladesh Bank itself. Among them account opening, DPS, FDR, locker service, card service, customer care, loan, shanchayapatra, remittance, payment order, internet & mobile banking are some common service area. Rather than these common services, all of these banks provide some unique services to sustain in the long run. As this report is about comparative analysis of Dhaka Bank Limited along with other three private limited banks, the most comparative areas among these four banks contains i) unique service features, ii) ATM booth service, iii) Locker service iv) Turnover ratio, v) Debit/Credit card service, vi) Branches & location. In these services four banks shows some different numbers in data, service type, service volume and specialties. After all of the data comparison the ultimate result states that, City Bank & Dhaka Bank is doing comparatively better than Southeast Bank and Prime Bank considering customer service & and financial structure wise. After All, though these banks contain different identity and service they all can consider some simple suggestion to sustain and improve. By focusing more on ATM booth service, customer care service, marketing & media, branch expansion and campaigning all of these banks can achieve their ultimate and desired goal.
Deep Learning Predictive Model for Colon Cancer Patient using CNN-based Classification
(Scopus, 2021) Tasnim, Zarrin; Chakraborty, Sovon; Shamrat, F. M. Javed Mehedi; Chowdhury, Ali Newaz; Nuha, Humaira Alam; Karim, Asif; Zahir, Sabrina Binte; Billah, Md. Masum
In recent years, the area of Medicine and Healthcare has made significant advances with the assistance of computational technology. During this time, new diagnostic techniques were developed. Cancer is the world's second-largest cause of mortality, claiming the lives of one out of every six individuals. The colon cancer variation is the most frequent and lethal of the numerous kinds of cancer. Identifying the illness at an early stage, on the other hand, substantially increases the odds of survival. A cancer diagnosis may be automated by using the power of Artificial Intelligence (AI), allowing us to evaluate more cases in less time and at a lower cost. In this research, CNN models are employed to analyse imaging data of colon cells. For colon cell image classification, CNN with max pooling and average pooling layers and MobileNetV2 models are utilized. To determine the learning rate, the models are trained and evaluated at various Epochs. It's found that the accuracy of the max pooling and average pooling layers is 97.49% and 95.48%, respectively. And MobileNetV2 outperforms the other two models with the most remarkable accuracy of 99.67% with a data loss rate of 1.24.
Design and Investigation of PCF based Highly Sensitive Surface Plasmon Resonance Biosensors
(Department of Electrical and Electronic Engineering, Islamic University of Technology (IUT) The Organization of Islamic Cooperation (OIC) Board Bazar, Gazipur-1704, Bangladesh, 2021-03-30) Tasnim, Zarrin; Islam, Rakina; Khan, Raisa Labiba; Moazzam, Ehtesam
Due to SPR based PCF possessing numerous advantages, researchers have focused on improving the design of these sensors. As a result, sensors with better sensing performances are discovered and some are on the way to be discovered. While designing the sensors researches focused on choosing the appropriate plasmonic material, easier fabrication process, better sensing approach. Their main concerns were to design such sensors which could be practically implemented. In order to get better sensing performance, the sensor design becomes complex. So difficulty while fabricating can be faced. We tried to propose three designs for our thesis paper which gave us satisfying results .We also tried to focus on reducing the problems faced. In our first design, we proposed a circular lattice structure with gold coating. Our proposed design was surrounded with a thin PML layer. We tried to optimize various parameters like gold, PML, airholes and chose the values which gave us the best result. In our second design we proposed a highly sensitive SPR based PCF biosensor in which we used gold as the plasmonic material. We adapted stack and draw method for designing the propose sensor so that fabrication becomes easier. For this proposed design also we tried to optimize various parameters and chose the values which gave us the best results. In our last proposed design we tried to explore the sensitivity performance as well as the temperature sensitivity performance. In all cases we used COMSOL Multiphysics 5.3a and Matlab for our researched work. The sensing outputs of the proposed designs were explored by Finite Element Method (FEM). Our first proposed design gave the amplitude sensitivity of 1779 RIU-1 , 407 RIU-1 and wavelength sensitivity of 3000 nm/RIU, 2000 nm/RIU in x and y polarization modes respectively. In this case analyte refractive index (RI ) was varied from 1.32 to 1.37 accordingly. This design gave a minimum amplitude sensor resolution of 5.6210-6 and a minimum wavelength sensor resolution of 3.3310-5 . We also obtained a birefringence of 0.0049 and FOM value of 187.5..The second proposed sensor gave us the maximum wavelength sensitivity of 14,500 nm / RIU in X-polarization mode and the maximum amplitude sensitivity of 4738.9 RIU-1 for Y-polarized mode, respectively .The RI was varied in the range of 1.35–1.41 .This sensor gave the lowest wavelength sensor resolution of 6.9×10-6RIU and the lowest amplitude sensor resolution of 2.11×10-6RIU for Y-polarized mode with FOM of 387 and 364 for X and Y polarization. Our last proposed sensor gave us the amplitude sensitivity of 1432 RIU-1 and 1291 RIU-1 in X and Y polarized mode, respectively. It gave a wavelength sensitivity of 13,500 and 13,000 in X and Y polarized mode respectively. Sensor resolutions of 7.407×10-8 and 7.692310-8 were obtained using wavelength interrogation method and 6.983210-6 , 7.7459310-6 were obtained by using amplitude interrogation method in Y and X polarized mode respectively. FOM value of 521.4601 and 546.93 were obtained for X and Y polarization method. Birefringence of 1.5×10-3 was found for the proposed sensor. Temperature sensitivity for temp range (-114 to 78℃) was 4.5833 nm/℃. So after observing the results of our proposed sensors we can say that our sensors can be used for sensing purposes.
Early Prediction of Chronic Kidney Disease
(Daffodil International University, 22-08-29) Mondol, Chaity; Shamrat, F. M. Javed Mehedi; Hasan, Md. Robiul; Alam, Saidul; Ghosh, Pronab; Tasnim, Zarrin; Ahmed, Kawsar; Bui, Francis M.; Ibrahim, Sobhy M.
Chronic kidney disease (CKD) is one of the most life-threatening disorders. To improve survivability, early discovery and good management are encouraged. In this paper, CKD was diagnosed using multiple optimized neural networks against traditional neural networks on the UCI machine learning dataset, to identify the most efficient model for the task. The study works on the binary classification of CKD from 24 attributes. For classification, optimized CNN (OCNN), ANN (OANN), and LSTM (OLSTM) models were used as well as traditional CNN, ANN, and LSTM models. With various performance matrixes, error measures, loss values, AUC values, and compilation time, the implemented models are compared to identify the most competent model for the classification of CKD. It is observed that, overall, the optimized models have better performance compared to the traditional models. The highest validation accuracy among the tradition models were achieved from CNN with 92.71%, whereas OCNN, OANN, and OLSTM have higher accuracies of 98.75%, 96.25%, and 98.5%, respectively. Additionally, OCNN has the highest AUC score of 0.99 and the lowest compilation time for classification with 0.00447 s, making it the most efficient model for the diagnosis of CKD.
Exploring parental perception on fathers’ involvement in child development for 0-3 years old children
(BRAC University, 2024-05) Akter, Rahima; Tasnim, Zarrin
Research suggests that, it is now established that fathers play an essential role in the upbringing of their children. And they are as sensitive and nurturing to their children as mothers can be. A father's nurturing presence can benefit children and help them develop cognitively, socially, and emotionally as they grow. The purpose of the study is to explore parental perception on fathers’ involvement in child development for 0-3 years old children. Data were collected through in-depth-interviews and group discussions. First, the study discovered that most of the participants have the clear idea about child development and fathers' involvement. They tried to explain about child development by saying it is a holistic growth and development that covers physical, mental and social development of a child and it starts from birth. Second, the study's findings revealed that fathers have been doing different kinds of activities in supporting their children's holistic development. Fathers gave emphasis on spending quality time with their children. They also help their children in their daily activities. Third, all participants mentioned that fathers face various challenges regarding their involvement in child development; they try to mitigate the challenges in many ways and get involved in child caring and development. Finally, the report concludes with directions for future research and calls for more comprehensive and exploratory research in this area. For more activities, training, workshop, and different programs can be undertaken to promote the importance of ECD.
Father's perception on their involvement for 0-3 years old children’s cognitive development in urban area
(BRAC University, 2025-09) Mahbub, Fatema; Tasnim, Zarrin
The early cognitive development of children is significantly influenced by parental involvement, particularly that of fathers. Nevertheless, the importance of fathers' involvement in the early years (0–3) is frequently overlooked in both research and practice, particularly in urban settings of developing countries. In Dhaka, Bangladesh, this investigation investigates the perspectives of fathers regarding their involvement in their children's cognitive development. Data were collected through semi-structured in-depth interviews (IDI) and focus group discussions (FGD) with a diverse group of urban fathers residing in varying socio-economic neighborhoods of the city, utilizing a qualitative research design. Research indicates that although the majority of fathers acknowledge the significance of their involvement in early stimulation activities, including storytelling, problem-solving, and playing, they frequently encounter difficulties in reconciling their professional obligations with their children's quality time. The extent of their involvement is also influenced by cultural expectations and traditional gender roles. However, there is a progressive transition in attitudes as a result of the growing recognition of the longterm advantages of father-child interaction. The study underscores the necessity of policy support, parental education, and increased advocacy to promote active fatherhood in early childhood development. These insights have the potential to enhance the development outcomes of children in urban Bangladesh by informing family-centered interventions.
Human Face Recognition Using Eigenface, SURF Method
(Springer, 2022-01-01) Shamrat, F.M. Javed Mehedi; Ghosh, Pronab; Tasnim, Zarrin; Khan, Aliza Ahmed; Uddin, Md. Shihab; Chowdhury, Tahmid Rashik
One such complicated and exciting problem in computer vision and pattern recognition is identification using face biometrics. One such application of biometrics, used in video inspection, biometric authentication, surveillance, and so on, is facial recognition. Many techniques for detecting facial biometrics have been studied in the past three years. However, considerations such as shifting lighting, landscape, the nose being farther from the camera, the background being farther from the camera creating blurring, and noise present renders the previous approaches bad. To solve these problems, numerous works with sufficient clarification on this research subject have been introduced in this paper. This paper analyzes the multiple methods researchers use in their numerous researches to solve different types of problems faced during facial recognition. A new technique is implemented to investigate the feature space to the abstract component subset. Principle component analysis (PCA) is used to analyze the features and uses speed up robust features (SURF) technique, eigenfaces, identification, and matching is done, respectively. Thus, we get improved accuracy and almost similar recognition rate from the acquired research results based on the facial image dataset, which has been taken from the ORL database.
Implementation of a Smart Embedded System for Passenger Vessel Safety
(Communications in Computer and Information Science, Springer, 2020-03-05) Shamrat, F. M. Javed Mehedi; Nobel, Naimul Islam; Tasnim, Zarrin; Ahmed, Razu
An automated embedded system with overweight and location detection of a vessel has been planned, developed and executed. To eliminate overweight issues and able to locate the vessel for stopping accidents, an embedded system has been developed. Based on “Archimedes Principle Formula” an algorithm has been formed, it works on data that have been collected by the “water floating switch sensor”. A sensor called “Water floating switch” used to detect the exceeding water level and send the data to the server purpose of monitoring an overweight issue. Programming language (python) with its default library has been utilized to code and some hardware components (Like raspberry pi B, microcontroller, water floating switch, GPS antenna, monitor, etc) are used for the significant execution of the algorithm. This embedded system can be accomplished in any type of vessel, utilize this system above the vessel as well as a passenger vessel, general cargo vessel, etc.
Implementation of an Intelligent Online Job Portal Using Machine Learning Algorithms
(Scopus, 2021) Tasnim, Zarrin; Shamrat, F. M. Javed Mehedi; Allayear, Shaikh Muhammad; Ahmed, Khobayeb; Nobel, Naimul Islam
Business intelligence and analytics are data management solutions implemented in companies and enterprises to collect historical and present data, while using statistics and software to analyze raw information, and deliver insights for making better future decisions. In the circumstances of today’s world, to survive and established own business need an analytical and find an easiest way or intelligence business model. The main objective is to examine the performance of various Machine Learning algorithms in order to perform with the system of an online job portal. This proposed module integrated with three phase such as, the Clusters similar kind of job search phase (CSK) is a way of knowing the demand is to create a visual graph showing clusters of similar kinds of job searched by the job seekers in the website of the job portal, the email notifications send phase (ENS) is responsible to send email notifications to the job seekers when a job circular is posted in the website, extract the job circular phase (EJC) is the way to extract the job circular post from the career section of each of the company’s website. The result shows the successful clustering of similar job search, email notification send to specific people and extracts the information from the web.
Intelligence Business Model for Skill.jobs with Machine Learning Approaches
(Daffodil International University, 2019-12) Tasnim, Zarrin
Business intelligence and analytics are data management solutions implemented in companies and enterprises to collect historical and present data, while using statistics and software to analyze raw information, and deliver insights for making better future decisions. In the circumstances of today’s world, to survive and established own business need an analytical and find an easiest way or intelligence business model. This study is on “Intelligent business model for skill. Jobs with machine learning approach”. The main objective is to examine the performance of various Machine Learning algorithms in order to perform with the system of skill.jobs. This proposed module integrated with three phase such as, the Clusters similar kind of job search phase (CSK) is a way of knowing the demand is to create a visual graph showing clusters of similar kinds of job searched by the job seekers in the website of skill. jobs, the email notifications send phase (ENS) is responsible to send email notifications to the job seekers when a job circular is posted in the website of skill.jobs, extract the job circular phase (EJC) is the way to extract the job circular post from the career section of each of the company’s website. The result shows the successful clustering of similar job search, email notification send to specific people and extracts the information from the web.