Browsing by Author "K. M. A. Salam"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Open Access
    Bus Fare Collection System Using Smart Card
    (North South University, 2021) SK Kamal Hossain; Shaifur Rahman Shawon; Mohammad Sifat Hasan; K. M. A. Salam; 1712573042; 1712760642; 1721748042
    Now, it is the public transportation system, likely the metro, that is well advanced. Passenger safety, convenience, and the need to improve the performance of existing public transportation are driving demand for intelligent transportation systems in the market. The paper-based ticket system for collecting the bus fare has been found to be a source of major financial loss in Bangladesh. It is difficult to ensure the purchase of a ticket by each and every passenger. An automatic bus fare collection system is implemented using a smart card. A smart card is given to the passenger, and when the passenger gets into the bus, he/she has to swipe the card in the RFID reader, and the device will automatically calculate the fare and deduct the money automatically. The manual fare collection system has many issues that are overcome by our proposed system. An automated fare collection system for public transport using GPS is an innovative idea that reduces manpower. The ticketing systems using RFID can be merged to solve the above-mentioned problems. This project actually suggests a much more public-friendly, automated system of ticketing with the use of RFID-based tickets. This project actually suggests a much more public-friendly, automated system of ticketing with the use of RFID-based tickets.
  • Thumbnail Image
    Item
    Open Access
    Cerebral Stroke Prediction Using Machine Learning Algorithms
    (North South University, 2023) Asif Rahman; Faisal Bin Abdur Rahman; Anharul Islam; Ifrat Jahan; K. M. A. Salam; 1821214042; 1912038042; 1912541042; 1812274042
    Cerebral stroke is on the rise, which may kill, disable, and destroy the brain. In this situation, it is important to predict a cerebral stroke early to prevent or lessen the damage caused by a stroke. A cerebral stroke occurs when brain tissue is deprived of oxygen and nutrients due to decreased or blocked blood flow. Currently, machine-learning-based systems are widely used as an effective method for predicting and reducing the potential damage of various diseases. The goal of this research is to find the early signs of a cerebral stroke so that people can take steps to stop more damage. Here, a dataset is used with 5026 points of data, 11 features about stroke, and the five best machine learning models trained for making predictions: decision tree, random forest, KNN, XGBoost, and a neural network model. Compared to the other machine learning models, the random forest and XGBoost models performed better. The accuracy of Random Forest was 97.11%, whereas that of XGBoost was 97%. Thus, the most accurate model, Random Forest, is used to forecast the chance of a stroke. A hosted web application and a mobile app are created to make the system accessible. By facilitating early prediction and intervention, this study can improve the medical system's capacity to prevent the damage of cerebral stroke.
  • Thumbnail Image
    Item
    Open Access
    Deep Learning Based Diabetic Retinopathy Detection from Fundus Images with Mobile Application & Web Solution
    (North South University, 2020) Zillur Rahman; Nusrat Jahan Khan Shila; K. M. A. Salam; 1510154642; 1512879642
    Diabetic retinopathy is one of the leading causes of blindness today, and the number of patients is growing at an unprecedented rate as the world’s population increases. At the time of the first diagnosis of diabetes, up to 21% of people with type 2 diabetes have been screened for diabetic retinopathy. As the number of patients grows exponentially, it poses two challenges for the future. The challenges are: access to traditional screening tests will be limited if any modern innovative technology does not bridge the demand-supply gap, and if the traditional system attempts to accommodate a larger number of patients with fewer resources, there is a possibility of error and failing to comply with health guidelines and standards. A deep learning-based, scalable software solution may be a game changer in dealing with those unprecedented challenges. As deep learning achieves state-of-the-art performance in many fields, even outperforming experts, it will ultimately restrict inaccurate and faulty diagnoses, and a robust software solution will democratize access to this health technology. This paper proposes a deep neural network or deep learning-powered automated system for screening and grading diabetic retinopathy with 88% accuracy using 299x299 pixel fundus images using a modular android smartphone application.
  • Thumbnail Image
    Item
    Embargo
    Design of a low voltage digital thermostat using LM35 and PIC Microcontroller
    (North South University, 2013) Kaiser Alam; K. M. A. Salam; 072163045
    This system is about the design of a low cost temperature sensing and control system (thermostat) with the use of PIC microcontroller and LM35 temperature sensor. The system is relatively inexpensive to make and can be integrated with temperature control systems such as air conditioners and fans. Apart from making temperature control systems more affordable for everyone, this system also helps save energy by automatically switching the devices on or off at the appropriate temperatures. In this project the LM35 and PIC16f877a microcontroller have been used to make a digital thermostat that is programmed to switch on and off a fan automatically when the temperature rises above or falls below a certain threshold value. The device also includes a LCD display to indicate the ambient temperature to the user. The threshold temperature can be programmed into the PIC microcontroller using a PIC programmer. The device as a whole works as a digital thermostat. Commercially available digital thermostats work at 24V AC typically. Some versions use a low voltage as low as 6V or as high as 30V. In this project the thermostat design allows it to operate at only 5V, making it more energy efficient than currently commercially available digital thermostats. The versatility of the system allows it to integrate with many different devices. Apart from air conditioners, furnaces and fans, this system can be used to build incubators or to maintain a constant temperature in your refrigerator at home.
  • Thumbnail Image
    Item
    Open Access
    Smart Insecticide Spraying Agricultural Robot
    (North South University, 2020) Abdul Ahad; Sadakat Muntaha Eshan; Shoumitra Mojumder; K. M. A. Salam; 1530681643; 1520446643; 1111168043
    In this project, a unique application of robotics in the field of agriculture has been presented. Bangladesh is a developing country, and the importance of agriculture for this country is indisputable. For agricultural work, it is very important for farmers to use insecticides. In a country like Bangladesh, most farmers are not properly trained or equipped for the use of insecticides. Using human labor to handle the spraying of insecticide can lead to many problems, such as health issues and a lack of efficiency. A solution to these problems is our smart insecticide spraying agricultural robot. This robot will aid in pest and disease control applications. The robot is able to move, spray insecticide, and detect obstacles. The ability of the robot to move and spray insecticide will increase the efficiency of agricultural work, increase crop production, and reduce labor costs. The robot is able to move forward, backward, left, and right while avoiding obstacles, and it can spray the insecticide evenly to cover the plants. There is a special spraying arm mechanism in the robot that enables it to change the direction of insecticide spraying. Our robot is made in such a way that it is possible to control the robot remotely with any Bluetooth-enabled smartphone. A smartphone app is used to take input from the user and send commands to the robot. The robot does not need any external power due to the use of a solar panel. A prototype has been designed using low-cost parts such as microprocessors, motors, solar panels, batteries, and other equipment to help the farmers and effectively increase productivity in the agricultural field.
  • Thumbnail Image
    Item
    Open Access
    Under Water Rescue Drone
    (North South University, 2020) Al Shakline khan; Fahmida Alam Usha; Mohammad Momin; Mahmudur Rashid Remon; K. M. A. Salam; 1712095043; 1721645643; 1711370645; 1711224043
    Remotely operated underwater vehicles (ROVs) are remote-controlled underwater robots driven by an individual on the surface. These robots are tethered by a series of wires that send signals between the operator and the ROV. All ROVs are equipped with a video camera, propulsion system, and lights. Other equipment is added depending on the specifications required. These include a manipulator arm, a water sampler, instruments that measure clarity, light penetration, temperature, and depth. Team Dubori was determined to recreate such an ROV in order to fulfill a specific mission. By using the system, an organization such as the military can explode mines underwater and also take real-time data of the river, which is also very helpful for rescue teams to identify the position of boats after any accident. The system has been designed in such a manner that it takes care of all the needs of a typical rescue team, and it is capable of providing easy and correct information about things underwater.