Browsing by Author "Md. Shahriar Karim"

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    Open Access
    A Weather Station for Collecting Local Climate and Environmental Data and Predicting Weather
    (North- south University, 2020-12-31) Mahadiul Islam Shakib; Ishtiaq Ahmed Chowdhury; Md. Shahriar Karim; 1511080645; 1610253642
    Weather is one of the most important environmental constraints in every phase of our lives on the earth. Prediction requires accurate classification of data. To predict things that are going to happen in future we need to do analysis on the factors that are related directly or indirectly. So as to make every day plans we have to rely on weather and need to know weather conditions beforehand, which could be achieved by predicting the weather condition such as humidity, rainfall, temperature, rain etc. And thus helps ourselves protect from abnormal conditions and avoids unnecessary delays. Besides, weather plays the most important role in the field of agriculture. Knowing weather conditions beforehand will help to plan harvesting to produce the maximum and avoid the loss and damages due to natural calamities. That’s why we are introducing a device for collecting local weather data and predicting the weather. It will predict the temperature, humidity and precipitation of any date past, present or future. The predictions will allow the people specially farmers to take preventive measures and make better decisions for the future
  • Thumbnail Image
    Item
    Open Access
    Blockchain Based E Voting System
    (North South University, 2021) Mehedi Hasan; Ishtiaque Shahriar; Umma Habiba Sultana; Md. Shahriar Karim; 1610882042; 1511814642; 1620421042
    Voting is a very important issue which can be beneficial in terms of choosing the right leader in an election. So people want a trust worthy voting system. The goal of our project is to replace the traditional pen and paper election with a new election system which has the ability to limit fraud and improve voting system by increasing security and decreasing the cost of hosting a nationwide election. We discussed the characteristics of our proposed Blockchain-Based Electronic Voting protocol in this paper. We implement this Blockchain system to turn election protocol into an automated control system without relying any single point of authority. This paper gives a comprehensive overview of our proposed system. We used Hyperledger Fabric framework in this project. As this framework is very flexible in term of cryptography, it was very suitable for our area. For the main functionality implementation we used Java. This system will ease the voting process and make people willing to participate in this new technology.
  • Thumbnail Image
    Item
    Open Access
    Early Detection of Mental Health over Social Media Using Machine Learning
    (North South University, 2020) Sabbir Hasan; Md. Tashfiq H. Choudhury; Md. Shahriar Karim; 1411107042; 1611508042
    In this project, we have worked on the use of machine learning algorithms that may indicate the mental state or sentiment of the users of social media. The current linguistic research on tweets or statuses shows distinct language patterns talks much about the sentiments of the users. As such, we are encouraged to use the available social media dataset repository for performance analysis of the supervised learning models generally applied in the case of large datasets. We have captured the texts and preprocessed the text data using Python tools for feature selection that provides clues to sentiment and subsequently, the subjective sentences are classified as positive or negative. We built machine learning (ML) models out of the classified text features for random forest and LSTM algorithms. The accuracy of the classification in both cases is encouraging, particularly the LSTM algorithm. The whole work is carried out using rich libraries of Python machine language modules. A prototype web application is developed with a front end (input and output) and back end (ML models and classification) using a rapid prototype web application framework for testing the algorithms that enable us to check the mental status of a social media user to determine if they may require medical or emotional support. Social media emerges as the most critical source of information, reflecting people's expressions and communication through textual content. This work contributes to the application of machine learning to further enhance the early detection of the mental health of users.
  • Thumbnail Image
    Item
    Open Access
    Find The Best Product in Your Local Market
    (North South University, 2019) Sadman Kabir Soumik; Md. Azwad Hasan Chowdhury; Asif Mahmud; Md. Shahriar Karim; 1511109042; 1430125042; 1610255042
    This project demonstrates a price comparison based application that can be used for price evaluations and online retailer choice in the local market. Consumer behavior on the internet has a diverse impact on the development of e-commerce websites as the users have many alternatives today. As much as the opportunities have opened for the users, the more indecisive it gets when it comes to comparing the same product from different retailers. To make the user experience better, an aggregated application can help users to filter the same product from different retailers based on the price. Price distributions independently influence price evaluations.
  • Thumbnail Image
    Item
    Open Access
    Floating Photovoltaic Dual Axis Solar Tracker: Wave Model and Its Effect on the Tilt Angle
    (North South University, 2021) Shahriar Ahmed Khan Kaif; Md. Abdullah Al- Hamim; Nazifa Reza; Fatin Anwar; Md. Shahriar Karim; 1721492043; 1712678643; 1631304043; 1620901043
    This report presents the design and practical implementation of a cost-effective floating active photovoltaic dual-axis solar tracker (PV DAST) that can keep track of the sun’s movement every hour from sunset to sunrise. The performance of a solar panel is maximum when the incident solar radiation is normal on the surface of the panel. For obtaining the best results, in terms of collected energy, the PV DAST must first be appropriately aligned towards the sun and tilted at the optimum angle. The optimization of the tilt angle of the solar panels aims to maximize the solar energy collected, thus reducing the active solar-thermal surface with the constant maintenance of thermal energy production, installation, maintenance cost, etc. In our project, we mainly focused on the rotating and floating structures of the plant. This system is mainly based on following a light source by angling the PV panel through two servo motors, ideally in the direction of sunlight rays. For higher efficiency, the solar panel has to track in two axes, the elevation and altitude axis. Hence, dual-axis tracking system. DASTs move along with the two fundamental directions, horizontal and vertical, making them more flexible and adaptable in constantly following the moving sun in any direction, whether from east to west or seasonal, without losing any sunlight. Our main objective was to study the effect of water waves on the tilt angle of the solar PV panel and overall produced energy from the system. This paper discusses the development of a floating dual-axis mechanism that absorbs shock from incoming wind and water waves and, in turn, keeps its initial resting angle constant. The floating PV (FPV) can adjust with the wind and wave partition to find the best tilt angle.
  • Thumbnail Image
    Item
    Open Access
    Plant Disease Detection and Solution for Rural Farmers Using Computer Vision, Cloud Computing and Android Platform
    (North South University, 2019) Mohammad Rashedul Alam; Sakib Mukter; Aminul Islam; Md. Shahriar Karim; 1511384042; 1520268042; 1520523042
    Bangladesh is a densely populated country with considerably low per capita arable land, which makes a daunting task to grow sufficient food grains for about its 160 million people. Diseases prevalence and the lack of close monitoring often results in crop loss as high as 30% in some cases. For instance, rice production reduces by about 10% because of diseases, whereas potato and tomato production decreases by 37% and 43% respectively because of leaf infection. Early and accurate detection of these diseases can prevent a large-scale yield loss. However, detection of these diseases is hard for farmers without the direct help of skilled people. To provide the farmers with the initial information, we develop a voice assisted mobile app that can predict a possible set of diseases from the images of leaf-infection. The App is optimized against low-resolution images and includes voice assistance at its every step to ensure usability for the farmers, who are generally are uncomfortable with digital platforms. Also, the App also suggests possible remedies for the affected crops, and the information of sellers and distributors of pesticides, fertilizers, and other relevant commodities. Together, this App attempts to increase crops yield and is expected to act as the bridge between the sellers, distributors and the farmers living in the farthest corner of our country.
  • Thumbnail Image
    Item
    Open Access
    SAVIOUR, THE SURVEILLANCE BOT
    (North South University, 2019) MD. Shaiful Alam Turza; Sharmina Islam Surmi; Meraj Jannat; Md. Shahriar Karim; 1420652042; 1420116042; 1420052042
    This report represents a survivor robot model motivated by the physique of a spider which may be used for search and rescue operations. Various types of walking algorithm took place to make this survivor robot and have been tested on the robot too. Control of this robot is done by the use of RC remote AT 9s. This spider robot is based on six leg system and this is expected to be well suited for navigation in rough terrains. To move the robot into rough fields we have put some functional algorithm on to it. Moreover, these algorithms provide varieties of speed parameters to the robot which is based on the structure of the robot leg system. Each leg is joined by three servo motors that are controlling the limbs from every joint. In addition, we have developed a prototype for the experimental purpose.
  • Thumbnail Image
    Item
    Open Access
    SENTIMENT ANALYSIS AND EMOTION DETECTION FROM SOCIAL MEDIA COMMENTS IN BENGALI LANGUAGE
    (North-south University, 2021-08-30) Sananda Saha; Tanvir Hossain Pion; Faysal Mahmud Nahiyan; Md. Shahriar Karim; 1711496042; 1110992045; 1712699402
    In the last decade social media sites like Facebook, Twitter, YouTube, Instagram and TikTok have truly integrated in our life. However, due to this mass popularity and apparent anonymity, the number of negative comments like violence, gender discrimination, spam and depression have increased dramatically. As there are few datasets about these kinds of topics in Bangla language, detecting such comments is very difficult. So, in this paper we are creating a new dataset of 13000 Bangla comments from Bangladeshi Facebook celebrity pages. We will use the SVM model for baseline evaluation and several deep learning models for increasing accuracy to detect such negative comments. Our core contribution will be to make this dataset accessible to all for future research in these topics. Finally, we will use the best model to analyze the trend of these negative comments in Bangladeshi Facebook celebrity pages in recent times.
  • Thumbnail Image
    Item
    Open Access
    Virtual Responsive Learning Assistance- A Learning Aid for Primary Level Education
    (North South University, 2019) Shimanto Haque; Devasish Ghosh; Mohammad Khurshed Alam; Md. Shahriar Karim; 1331333042; 1431154642; 1420799042
    This paper deals with recognizing characters written on thin air. The aim of this project was to enhance the learning method of primary school education in learning alphabets and numbers and counting. Children of primary level can draw characters in thin air, and see three dimensional or two dimensional images of the characters they write on the screen as a means of Augmented Reality, and also see examples associated with the characters and numbers. This is done by identifying a certain gesture of the hand as a pointer and then tracking that pointer as a means of drawing a character. The detection of the pointer is done with one single-lens web camera and without the usage of any motion sensors or any other external devices. Google’s Tensorflow module was used for training the pointer, and the entire project is done with simple python libraries such as OpenCV, numpy and others. The system requires the minimum manual involvement, and operates within three keystrokes.