Browsing by Author "Hasan, Md. Mehedi"

Now showing 1 - 20 of 94

A Comparative Study on Prediction of Hepatitis B Virus (HBV) Using Machine Learning Algorithm
(Daffodil International University, 2021-01-31) Musabbir, Muhammad; Hasan, Md. Mehedi
The Hepatitis B virus (HBV) can cause acute and chronic liver infections. It is transmitted through infected blood products, unprotected sex, infected items such as needles, razor blades, dental or medical equipment, unscreened blood transfusions, or from mother to child at birth. Despite a considerable body of published research on hepatitis B in Bangladesh, researchers continue to lament the lack of reliable information about hepatitis B virus (HBV) infection epidemiology. The present review aims to provide a comprehensive survey of the literature with particular focus on a number of epidemiological questions, as well as a commentary on the trends of hepatitis B research as it has taken place in Bangladesh. it is difficult to provide conclusive estimates about HBV prevalence in the general population of Bangladesh. So, the aim of this piece of research work is to analysis the symptoms of Hepatitis B and Hepatitis C fever and early prediction of the symptoms that can be seen in years ahead. For predicting the symptoms two different Machine Learning algorithms have used. Support vector machine (SVM) and random forest classifier algorithm have been used. Finally, the accurate of these two has been evacuated and the confusion matrix has been shown and then we have talked about the algorithm which is better for our dataset.
A Computer Vision System for the Categorization of Citrus Fruits Using Convolutional Neural Network
(2021 International Symposium on Electronics and Smart Devices (ISESD), IEEE, 2021-08-12) Hasan, Md. Mehedi; Salehin, Imrus; Moon, Nazmun Nessa; Kamruzzaman, T. M.; -Ul-Islam, Baki; Hasan, Mehedi
The recognition of citrus fruit is one of the most challenging and crucial measures in citrus yield mapping. Several artificial vision systems have been proposed to solve the issue of fruits recognition problem with sundry effects. In this study, we developed an automated system to categorize citrus fruit images using Convolutional Neural Network. We categorized two different citrus fruits, Orange (Citrus Sinensis) and Kinnow (Citrus Reticulate). Firstly the images of Orange and Kinnow were collected and preprocessed. Secondly, the fruit images and their background were segmented by image segmentation and edge detection. Four main features of Orange and Kinnow fruit were extracted based on image segmentations such as fruit size, surface color fruit shape and fruit surface defects. These features were examined through Convolutional Neural Network. We implemented three separate Convolutional Neural Network models to further experiment and tested recognition rates for different parameters. We have used the classical measurements including precision, recall, F1 score, ROC and accuracy for performance evaluation. Among the three experimented models, the third model was outperformed by 92.25% percent accuracy.
A Continuous Word Segmentation of Bengali Noisy Speech
(Springer, 2020-11-28) Hossain, Md. Fahad; Hasan, Md. Mehedi; Ali, Hasmot; Abujar, Sheikh
Human voice is an important concern of efficient and modern communication in the era of Alexa, Siri, or Google Assistance. Working with voice or speech is going to be easy by preprocessing the unwanted entities when real speech data contains a lot of noise or continuous delivery of a speech. Working with Bangla language is also a concern of enriching the scope of efficient communication over Bangla language. This paper presented a method to reduce noise from speech data collected from a random noisy place, and segmentation of word from continuous Bangla voice. By filtering the threshold of noise with fast Fourier transform (FFT) of audio frequency signal for reduction of noise and compared each chunk of audio signal with minimum dBFS value to separate silent period and non-silent period and on each silent period, segment the signal for word segmentation.
A Continuous Word Segmentation of Bengali Noisy Speech
(Scopus, 2021) Hossain, Md. Fahad; Hasan, Md. Mehedi; Ali, Hasmot; Abujar, Sheikh
Human voice is an important concern of efficient and modern communication in the era of Alexa, Siri, or Google Assistance. Working with voice or speech is going to be easy by preprocessing the unwanted entities when real speech data contains a lot of noise or continuous delivery of a speech. Working with Bangla language is also a concern of enriching the scope of efficient communication over Bangla language. This paper presented a method to reduce noise from speech data collected from a random noisy place, and segmentation of word from continuous Bangla voice. By filtering the threshold of noise with fast Fourier transform (FFT) of audio frequency signal for reduction of noise and compared each chunk of audio signal with minimum dBFS value to separate silent period and non-silent period and on each silent period, segment the signal for word segmentation.
A Cross-sectional Analysis of Undergraduate Pharmacy Students' Knowledge and Attitudes about the Use of Generic Medications
(©Daffodil International University, 2021-07-18) Hasan, Md. Mehedi
Background: Some people are worried about generic medicines because this are much cheaper than brand-name medicines. They think that generic medicine compromises in terms of quality and effectiveness because it is cheap. But according to the FDA's (U.S. Food and drug administration) requirements, generic medicines must be as safe and effective as brand-name medicines. In fact, generic medicines are much cheaper because manufacturers do not have to spend extra money to develop and market a new drug. Upon expiration of the patent, manufacturers may apply to the FDA to produce and sell generic versions of the drug. Although the production and sale of generic versions of medicines are already in vogue in different countries of Europe and America, India is also doing well in this sector. In Bangladesh most of the company manufacture generic medicine but in ground level people doesn’t have much more good knowledge. That’s why people may have various misconceptions and rumours, so the main purpose of this study is to know the attitudes of people towards generic medicine, to take their feedback and to analyse them. Objectives: The aim of this study was to assess and analysis of undergraduate pharmacy students’ knowledge and attitudes about the use of generic medications. Method: A cross-sectional online based survey preform form March to May 2021, among the undergraduate pharmacy students at Daffodil International University in Bangladesh. A 25-item questionnaire was developed, validated and administered on the participant. 100 students are responded to this survey. Results: The majority of person (93%) claimed that they knew about generic drugs. And most person (47%) get information from their teachers. There was a misconception among respondents about the concepts of "efficacy", "safety", "bio-equivalence", and "manufacturing standards" of generic medications, 76% believed that generic medications are bioequivalent to brand-name medicines. One the other hand 29% said that generic medications are less effective than brand-name medicines. 71% believe that a standard guidance required for both GPs and pharmacists on the brand substitution process. Furthermore, advertisements and product bonuses offered by pharmaceutical industry, patient’s socio-economic factors also as credibility of manufacturers were factors reported to influence their selection of medicine. Conclusion: Although it has emerged that students have widely accept the use of generic medicine, they still have concerns about the reliability and quality of such products. Students need to be educated and reassured about bio-equivalence, quality and safety of generic product approval system in Bangladesh. The current research has important implications for establishing generic medicine policies in Bangladesh.
A Deep Learning Approach to Recognize Bangladeshi Shrimp Species
(Independent University, Bangladesh, 2023-07) Hasan, Md. Mehedi; Nishi, Jubiria Subrin; Habib, Md. Tarek; Islam, Mohammad Monirul; Ahmed, Farruk
Shrimp, the most popular shellfish in Bangladesh, is a good source of protein, minerals, vitamin D, and iodine that promote a healthy body and balanced nutrition. In Bangladesh shrimp is referred to as white gold. It consumes about 70% of exported agricultural food. In our country, about 56 species of shrimp are found. Most people do not know all of the species very well. Ordinary people even the fisherman are sometimes confused about different species because of looking like the same. To solve the problem in this work we introduced an intelligence mahine that can help people to concede Shrimp species accurately. We expect this work also help the export sector to differentiate the shrimp species monitoring. To achieve the goal, we build a custom CNN algorithm for image processing and feature extraction. We build three different CNN architectures and differentiate them by hyperparameter and number of convolutional layers. Model 1 and Model 3 both obtain an accuracy of 99.01%, however Model 3 was chosen as the final model for Computer Vision integration. Though both models generated the best accuracy why do we use model 3 as the final model? In this work, we will also describe with appropriate reason.
A localized adaptive architecture for dynamic wireless sensor networks
(BRAC University, 2020-10) Hussain, Sajjd; Ahmed, Muntasir; Joy, Kishanu Roy; Hasan, Md. Mehedi; Chakrabarty, Amitabha
IoT is seen as the next big thing in the world to come. Previously people were less connected with the internet. But in recent years, IoT has seen substantial research and innovation in many technology areas, and uses of the internet are increasing day by day. In the near foreseeable future, the vast number of devices connected together will result in highly complex networks that would cause an exponential increase in computation times, latency and power consumption. In this paper, we take a modular approach to dealing with the issue. We propose a Weight-based Adaptive Neighbor Localization (WANLoc) Algorithm that creates a highly opti- mized network based on localized network architecture that is network independent. This means that the sensor nodes in this network do not need to communicate with any cluster head or sink in order to function. In addition, WANLoc is intended to function in a dynamic wireless sensor network where nodes enter and exit the network regularly. This also means that it is exceptionally good at handling node failures. Nodes in this network only communicate with their immediate neighbors, maintained in a set of dynamic tables designed to reduce lookup times when deciding whom to forward data to. This also means that nodes can now be configured with minimum transmission capabilities, saving a lot of precious energy in the process.
A Machine Learning Approach to Recognize Speakers Region of the United Kingdom from Continuous Speech Based on Accent Classification
(IEEE, 2020-12) Hossain, Md. Fahad; Hasan, Md. Mehedi; Ali, Hasmot; Rasel Sarker, Md Rahmatul Kabir; Hassan, Md. Toukirul
Speech is one of the primary modes of communication with a lot of identical features for measuring performance and behavior of human voice. Accent is an important element and can play a vital role in spoken language. In this paper, we propose a region detection approach of UK citizens by recognizing their accent from continuous speech. The ultimate goal of this paper is to detect the region of UK citizens from which region among Ireland, Midland, Northern England, Scotland, Southern England and Wales he/she belongs using continues speech. Firstly, we use Mel Frequency Cepstral Coefficient (MFCC) for extracting the feature from continuous speech. Then we applied several Machine Learning classifiers to train and test our model. After evaluating performance we find that k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and Random Forest classifier provide comparatively better accuracy than others. We also perform a comparative analysis of these three algorithms. We got the best accuracy of 98.48% by applying k-NN classifier.
A Noble Deep Learning Approach to Recognize Speaker’s Identity from Bengali Speech
(Daffodil International University, 2021-06-01) Hossain, Md. Fahad; Ali, Hasmot; Hasan, Md. Mehedi
Speech is the most suitable form of communication. Speech-based applications are playing a vital role in modern technology for the last few decades. Because it has a lot of identical features for measuring performance and behavior of human voice. Speech-based application is not only the trend of modern and efficient technology but also a new shift of information and technology paradigm. Several research works have been completed on voice-based applications because it has more practical application than any other form of communication. In this work, we tried to recognize the feature of voice in term of identify the speakers from Bengali speech. We consider speakers Age, Division, Height, Weight, Gender, Occupation as the parameter to identify a speaker. But here we presenting the application of recognizing Bangladeshi speaker’s age and division from Bengali Speech. We used our own dataset containing 16730 samples. Each sample is a wav format audio of 8-10 seconds duration. We consider MFCC, Delta, Delta-Delta, LSF, Spectral Bandwidth and mel spectrogram features to train our model. We tried some traditional Machine Learning algorithms early but we understand that the huge number of data does better with Deep Learning algorithms. We tried different Deep Learning algorithms such as Artificial Neural Network, Convolutional Neural Network, Region Based Convolutional Neural Network, Long Short-Term Memory with different types of features but ended with Artificial Neural Network with 85% accuracy for Division recognition and Convolutional Neural Network with 78% accuracy for Age recognition.
"A Report on Internship Experience Gained from Working in the General Banking Division of Pubali Bank PLC.”
(Daffodil International University, 2025-12-14) Hasan, Md. Mehedi
My internship report shows my experience during a three (03)-months internship experience at Pubali Bank PLC, focusing on the analysis of general banking operations and how I honed my skills throughout the internship. I've structured the internship report into five sections. The first (01) chapter provides an introduction, while the second chapter shows a concise overview of Pubali Bank PLC, encompassing its history, vision, mission, and departmental layout. Chapter three outlines my day-to-day activities at Pubali Bank PLC, detailing the tasks, responsibilities, and lessons I encountered. Chapter four delves into my initial expectations regarding banks and the practical experiences I gained during my internship. Finally, the concluding chapter five presents an overall assessment regarding me throughout analyses of the banking activities of J Pubali Bank.
A Smart Polluted Water Overload Drainage Detection and Alert System
(2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC),IEEE, 2021-06-09) Salehin, Imrus; Islam, Baki-Ul-; Noman, S. M.; Hasan, Md. Mehedi; Dip, Sadia Tamim; Hasan, Mehedi
A smart city constructed through the Internet of Things is a great and best medium nowadays. In our study, we have designed an advanced and automated device that can identify overloaded polluted drainage, which is responsible for water-borne disease and unexpected floods. We are using a smart ultrasonic sensor with an Ethernet shield integrated Arduino UNO. This proposed model's most vital side is the remote data access system using IP address and the webserver. This research is adequate for city corporations to advance their city, Develop their city to be more delighter, and reduce their fund used for extra human resources of city corporations cleaner. For data access methods, we are using the city Wi-Fi router and a monitoring station. We also proposed a separate web page designed to show the report. Materials used here are very uncomplicated and inexpensive but adequate to make an advanced automation intelligence system. In this modern scientific era, to lead a comfortable life, an automation system has helped develop a city more than the old system.
A Technical and Financial Study of Solar Home System in Bangladesh : Prospects , Challenges , Constrains
(Daffodil International University, 2019-01) Hasan, Md. Mahmudul; Hasan, Md. Mehedi
Power is one of the most important factors in developing country and for sustainable economy. Like the rest of the countries of the planet, in Bangladesh the demand for power is increasing day by day. The main aim of our research is to find out the irradiation of sun in Dhaka city in the month of September so that the power production by the solar panel can be estimated and, we collect the solar irradiation and the maximum power data in Dhaka for (September)0ne month and analyze the data to get average irradiation and find the relationship between solar irradiation and power and by using this data we can easily understand the electricity production by solar home system and create a standard form of power production of solar home system in 2018.This research is an endeavor to analyze the socio economic impact by using solar Home system and also test the feasibility of maximum power can be generated from the panel. Social and Economic development from SHS and their prospects , challenges and constrains can be estimated by specific method named SWOT analysis. This research is basically for rural area where grid electricity is not available. Our research have done be a remote village named “Monpura” situated in the district of “Bhola. So to be a part of this modern world, electricity is the basic needs... Solar Home system (SHS) is very effective for any remote villages like monpura. Other hand this renewable electricity system not only performs Electrification but also perform social and economic development for any society. By using this Solar Home System (SHS) people can be benefited. Their income has increased, their education status has increased, and they are socially active.
A Web-Based Gents Parlour Management System
(Daffodil International University, 2019-04) Hasan, Md. Mehedi; Nahar, Yasmin; Sheikh, Md. Al-Mamun
This project titled “A Web-based Gents Parlour Management System” is fully responsive parlour management application with appointment scheduling functionality. In this system user can make appointment in online. Because of responsive design, all device like desktop, laptop, mobile will support this application properly. Using this application customers can see all the services of gents parlour shop. Then they can choose their service which they want. For taking services they will book an online appointment as their free time slot. This application also provide customer to buy beauty instruments through online. Customer can buy their desire product in online .Then admin has the authority to access all appointments and all orders that customers placed. Admin can confirm pending appointment and send notification to customer. He has also manage all the orders from customers. When booking an appointment from customer they can also select stylist whose they want to get service. The basis of the project is make the people sense that nowadays all services are going to ICT based, so in the sector of parlour management it should be applied for every people for their welfare. We think it will become more comfortable for every user.
An AHP Approach for Cold Storage Warehouse Site Selection
(Daffodil International University, 2020-10-07) Hasan, Md. Mehedi; Chakma, Martina
Business investors are frequently faced with complex decisions, such as selecting the location of cold storage warehouses based on multiple inconsistent criteria. An inappropriate site selection imposes excessive effects on both customers and investors of urban areas. Nowadays, multi-attributes decision-making approaches are recommended to apply to progress exactness of decision making and lessen additional adverse. This work proposes a decision support framework for location selection of cold storage warehouses using the analytic hierarchy process (AHP) model. An efficient case study is evaluated in Bangladesh considering several factors using the Analytic Hierarchy Process. This paper also describes the necessity for setting up cold storage warehouse. In this study, we have considered 6 attributes and 18 sub attributes among 3 different locations in Bangladesh as alternatives. The alternative relative importance has been calculated by using AHP. The ultimate decision is prepared based on the arithmetical scores snatched by the alternatives. For finalizing the optimal solution both the AHP result and the benchmark deduction have been taken into account. A numerical study is presented to demonstrate the possible alternative of the proposed methodology.
An Analysis of Training and Development Practices of Uttara Finance and Investments
(Daffodil International University, 2020-01-30) Hasan, Md. Mehedi
This report is prepared as a requirement of the internship phase of BBA program of Daffodil International University. This report focuses three months working experience at Uttara Finance and Investments Limited. This report will give a clear idea about the Training & Development practices in Bogra Branch of Uttara Finance and Investments Limited. Here in the first chapter basically discuss about the origin of the report, objectives and methodology used in preparation of the report and limitation faced at preparation and is overview of Uttara Finance and Investments Limited. In the chapter two, historical background of United Finance Limited, its mission, vision, structure of the Uttara Finance and Investments Limited. For preparing this report the main objective is to focus on the activities related with Training and Development practices in the Uttara Finance and Investments Limited. From my experience, observation and discussions with the employees, I have learned about the Training and Development practices and use of these in the organization. In chapter three, about Training and Development practices like as their training process, types of training programs, training techniques, training materials and evaluation of training etc. are in the Uttara Finance and Investments Limited are described as much as possible. The chapter four of the report analyzes the Strengths, Weaknesses, Opportunities and Threats of Uttara Finance and Investments Limited. I have tried to find out the Training and Development practices implementation in this branch in chapter three. As an intern, it is really difficult to give recommendation based on whatever I have learnt from my experience I have elaborately stated them in chapter three. From 1995 to 2020 it has been more than 19 years of long journey of Uttara Finance and Investments Limited. They have made strong initiatives in non-bank financial sector. I hope that the authority are always concerned about their employees so they can provide excellence service with efficiency, accuracy and proficiency to the clients and meet the ultimate objectives of Uttara Finance and Investments Limited. Uttara Finance and Investments Limited can function to the fullest by overcoming the following problems are under HRM, specifically how HRM should or can support to achieve the mission or objective by identifying what kind of competencies are needed; training from the inside and outside experts having needed competencies; and identifying more suitable experts internally or by training the staff in important fields.
An Artificial Intelligence Based Rainfall Prediction Using LSTM and Neural Network
(IEEE, 2020-12) Salehin, Imrus; Talha, Iftakhar Mohammad; Hasan, Md. Mehedi; Dip, Sadia Tamim; Saifuzzaman, Mohd.; Moon, Nazmun Nessa
The most difficult task of meteorology is to predict rainfall. In our study, we proposed an amount of rainfall prediction model that can be easily determined using artificial intelligence and LSTM techniques. This is an advanced method to find out the rainfall. The deep learning approach is most valuable for this type of method implementation and its accuracy finds out. A long short-term memory algorithm is applied to memory sequence data measurement and calculate previous data very fast and create the best prediction. The people of this country are mostly dependent on agriculture so that this prediction system is very necessary. Timely rainfall assessment will increase crop yields and reduce costs in agriculture. Considering all these factors, we have created our model which will help us to determine the amount of rainfall. We have collected data from 6 regions to do this. To predict, we have taken 6 parameters (temperature, dew point, humidity, wind pressure, wind speed, and wind direction). After analyzing all our data, we got 76% accuracy in our work. We also focus on a vast dataset in long time weather for the better result.
An assessment on social welfare activities of Islami bank Bangladesh Ltd.
(2014-12-11) Hasan, Md. Mehedi
Bangladesh is a developing country. Financial Organization like Bank can play a vital role in economic development. Banking constitutes an important segment of the financial infrastructure of any country. Banking means deposit mobilization and development of that deposit into advances in different sectors. Thus, Bank takes part in socio-economic development of country, attainment of their own profit. The internship report titled “An Assessment on social welfare activities of Islami Bank Bangladesh Ltd” is expected to give a clear idea about the overall banking as well as the performance of Islami Bank Bangladesh Limited (IBBL) over the years. I have started my analysis from discussing the basic issues regarding for any depository financial institution. First I had discussed the general part of Islami Bank Bangladesh Limited. Then I have focused on the feature those are the core variables for the Bank to success and failure. I have also discussed the mission, objective and goal of IBBL. During the short span of its operation the bank has successfully positioned itself as a acclaimed by business community, from small businessmen or entrepreneurs to large traders and industrial conglomerates, including the top rated corporate borrowers for forward looking business outlook and innovative financing solutions. Although IBBL was established just 10 years ago, it has made a strong position in banking sector of Bangladesh. In the next part of the report I have discussed different topics regarding its general bankingdeposit policy specifically pointing on its different types of deposit as well as different types of loan and advances. In this part I have focused on different day-to-day operation of Islami Bank Bangladesh Limited. I have mentioned the bank’s policy as well as procedure of the Islami Bank Bangladesh Limited.
Analysis of Student Sentiment During Video Class with Multilayer Deep Learning Approach
(Daffodil International University, 2022-08-08) Salehin, Imrus; Moon, Nazmun Nessa; Talha, Iftakhar Mohammad; Hasan, Md. Mehedi; Nur, Farnaz Narin; Hakim, Md. Azizul; Haque, Farhan Al
The modern education system is an essential part of the rise of technology. The E-learning education system is not just an experimental system; it is a vital learning system for the whole world over the last few months. In our research, we have developed our learning method in a more effective and modern way for students and teachers. For significant implementation, we are implementing convolutions neural networks and advanced data classifiers. The expression and mood analysis of a student during the onlineclass is the main focus of our study. For output measure, we divide the final output result as attentive, inattentive, understand, and neutral. Showing the output in real-time online class and for sensory analysis, we have used support vector machine(SVM)and OpenCV. The level of 5*4 neural network is created for this work. An advanced learning medium is proposed through our study. Teachers can monitor the live class and different feelings of a student during the class period through this system.
Android Application on Daily Activity Management
(Daffodil International University, 2021-05-29) Hasan, Md. Tasnimul; Hasan, Md. Mehedi; Khan, Md. Shakhawat
A budget tracker application is either web or smartphone based and can help you track a scope of costs. You enter approaching and active cash and the application can help you store and track that data. It can help you track your spending plan, track your speculations, use diagrams and graphs to show your advancement, and keep your business and individual costs discrete. Cost tracker applications can likewise follow your ways of managing money and give you accommodating experiences to more readily assist you with understanding where you're spending and how you can scale back. Cost trackers can be utilized in a hurry and distinctive applications are useful for various sorts of cost following.
Application of lean tools in Hams Garments Ltd. of Hams Group
(BRAC University, 2022-05) Hasan, Md. Mehedi; Uddin, Md. Muslim; Hossain, Afzal
A 100% export oriented leading garments industry starts journey in 2001 with 2 sewing lines and total of 350 workforces at Sreepur area in Gazipur city in Bangladesh. Now it's quite 12,000 workforces with 153 sewing lines within different project of HAMS Group in Gazipur. It expands business into knit, woven, and lingerie products. Industrial Engineering (IE) is a branch of engineering which deals with man, machine and material to illustrate maximum efficiency. IE team provide SMV by using IE tools which is used to calculating CM, minute cost of factory, efficiency of the factory. Lean manufacturing is a Japanese technology and KAIZEN is a lean tools which works for continuous improvement. Basically, lean identify non value added work from process and suggest to eliminate that added more value for the company.