Raed Abdulla

The aim of the project is to design an obstacle avoidance system by using neural network. The main functionality of the project is to predict the object detected and to find a path of avoidance the detected object. Due to the increase in autonomous vehicle centered around machine learning technology, expensive system which incorporates multiple sensors for the obstacle avoidance and object detection are made. To fill this gap, the project is designed to implement an object detection and obstacle avoidance system using a camera as the main component for detection. Jetson nano board is used as the main computer, NoirV2 camera is used as the main vision sensor, 3d printed structure for the body, two dc motor with a I2c based motor driver. SSD MobileNet v2 is used as the model for object detection, Jetson inference is the training guide which is used for the obstacle avoidance and object detection which is optimized to work with Jetson nano board providing a faster detection and fps. The project includes a web based Graphical user interface to control the robot and to monitor it. The project will solve the issues of expensive system and requirement of multiple sensors for object detection and obstacle avoidance.

This project is aimed at developing a general-purpose reusable glove that allows users to freely don gloves in a moment’s notice when coming in contact with contaminated surfaces in this COVID-19 pandemic. The mechanical glove is composed of three major linkages in the housing, the palm and the four long fingers fully 3D printed. The mechanism implemented to tackle the retraction and extension of the glove relies on two distinct actuation techniques: cable-driven retraction for the palm and belt-driven shafts for the fingers. The dexterity of the user while the glove is equipped is evaluated with the Kapandji test and Feix’s Grasp Taxonomy whereas the performance of the gloves is tested through a grip force setup as well as a retraction and extension mechanism time testing. The prototype developed is a product of low cost with sufficient functionalities and comfort paired with a highly reproducible retraction and extension mechanism.

In this world, it consists of a lot of people who do not know how to use power wisely. For example, especially in hostel areas, the students will keep turning on the phone or laptop charger and keep turning on the air-conditioner to keep their room at their desired temperature even when there is nobody in their room. This is a big issue, and it will cause the students to pay high electrical fees and cause the wastage of natural resources. To overcome this problem, the hostel power switching card system is implemented. In the hostel power switching card system, the students need to insert the student ID card into the energy-saving card switch to turn on the power. Without the card, the student will not be able to turn on the power of their room. After inserting the card, the power will turn on immediately and the energy meter will start measuring the unit consumption. The energy meter will transfer the data to the ESP12E NodeMcu V3, which is the microcontroller in this system, via an optocoupler. The optocoupler will measure the pulses from the energy meter. The ESP12E NodeMcu V3 will upload the data to the Blynk cloud. The students can check the unit consumption and electrical fees used through the Blynk mobile application.

The main aim of this project is to develop a cohesive methodology for heart rate monitoring and heart attack notification system for any heart patients, especially the elderly and at risk. In this proposed system, a pulse sensor is used to measure a person’s heart rate and post it on hardware as well as upload it to cloud servers through the implementation of IoT. Mobility and compactness were also considered for this system, with a strap-on container for most of the components also designed. Based on the heart rate data, the system also sends notifications on mobile as well as emails to any address about an emergency based on very high or low heart rate. Testing for the performance of this notification system, as well as general accuracy for the system, was tested to be around 96% minimum when compared to at least another commercial device with heart rate measurement capabilities. The system limitations and recommendations have also been done for the system in this report.

The main aim of this project is to develop an IoT-based security system for residents which includes biometric authentication, plate recognition, and movement detection system. In this proposed method, the programming platforms such as Python and Arduino were used to develop and demonstrate the proposed system. The performance of the developed proposed system is evaluated by testing the system with several sample tests and from there, the performance was examined. The system performed well in recognizing the different persons and is capable of returning the correct output in almost all the face samples, as well as the plate number detection, which can successfully extract the string information from the pictures. It is observed that the system has an overall accuracy of 77% after considering several important factors that may affect the system’s performance.

The main aim of this research is to design a smart hand sanitizer dispenser that dispenses the optimum amount of sanitizer based on palm image processing with enhanced IoT features. The research problem of this project is that hand sanitizer dispensers are mostly provided in manual form. This will make the hand sanitizer dispenser contaminated. The usage of the hand sanitizer is also controlled by individual behaviors. They may use it very little, which will not achieve the purpose of using it to curb infectious viruses. They may also use it too much and it can be wasted. The method used to achieve the objectives of this project is by using the Raspberry Pi B+. The system is implemented by using Haar Cascade Classifier to detect the hand palm and measure the hand by using Euclidean distance and pixels per metric. The system also consists of monitoring and alert features. The liquid level of the hand sanitizer is monitored using Node-RED. An alert system is also constructed to remind the owner to refill the hand sanitizer. Other than that, a PIR sensor is used to detect the presence of a human nearby and give out a message through a speaker to remind people to use the hand sanitizer.

The aim of this research is to develop a low-cost neonatal incubator unit with IOT functionality for use in the developing world and conflict zones which currently see 99% of all neonatal deaths due to the financial constraints in the regions preventing the adoption of conventional incubator units. The proposed system incorporated the development of a functional neonatal incubator unit incorporating various biometric sensors for assessment of the infant’s condition through the use of an IOT application developed using the Blynk IOT platform. The performance of the developed proposed system is evaluated by testing the system’s ability to create a desired microclimate within the incubator enclosure as well as assessing the accuracy of the biometric sensors used. It is observed that the incubator system is capable of creating the desired microclimate. The biometric sensors used are observed to produce comparable results to measurement taken simultaneously on medical grade equivalents. Tests conducted show the system achieves an extreme case humidity of 95% within a 5-minute period and autonomously maintain a humidity within the 90-95% range. The integration of the monitoring system with the low-cost incubator, and the numerous biometric sensors used produced a proposed system not presently available as determined by the literature reviewed.

Nowadays, less converters are preferred for higher efficiency, low size and cost. Such a converter has its own problems. The output voltage of PV arrays is relatively low, requiring a high step-up converter to obtain the DC input voltage for the converter. In this paper, a step-up DC-DC converter is analysed, designed, simulated with MATLAB Simulink and practically implemented. Besides, the performance and effectiveness of some standard and improved boost converter circuits are discussed and compared in terms of voltage gain, power loss and switch voltage stress requirement A major aim of the project is to investigate the effectiveness of this converter regarding application in Solar systems. In short, DC-DC boost converter is designed to overcome the issues faced by the conventional converters such as low conduction and switching losses. a simulation study comparing the relative efficiency performance of the low-cost selected converters with Sic and GaN power switches. The two devices will be compared in terms of efficiency and performance. From this paper all results clarify that GaN devices has better efficiency and performance compared to Si devices. the results were achieved by simulation and experimentally.

Carbon Monoxide Detection Based IoT was selected to be the title for this project. IoT platform in recent year have grown and expanded to different applications. These Carbon Monoxide Detection System was designed and implemented with the use of problem statements, investigating previous work done by other people whilst reviewing the work that was done and proposed methodology was given. The finalised design was built and thus enhanced with real environmental testing that took place in several locations. The overall system was tested and evaluated. Thus, based on the design and implementation of the system, the results were obtained.

Manhole recognition and monitoring is one of the essential needs for modern society, particularly smart city plan. The idea of this project roots in fact that missing or stolen manholes results in various road accidents and it shrinks the quality of city. The major challenge in this research is to investigate a method in recognition of manholes and further investigation on the condition of manhole on road. The report can be simultaneously updated in IOT platform which can be further used with other applications such as WAZE or Google MAP. This method uses Naïve Bayes classifier to train dataset and detect as well as recognize the missing manhole on road. This project has three main components including 1) Recognize manhole on road, 2) Detect missing manhole, and 3) Update the coordinates to IOT platform. The software used for image processing was MATLAB. The coordinates were obtained via Arduino Mega and SIM808 GSM modem to updates the missing manhole covers coordinates on BLYNK IOT. The result obtained from the accuracy of the Naïve Bayes classifier indicates that the system can perfectly detect the missing manhole with total accuracy of 85%. The True Negative Rate (TNR), Positive Predictive Value (PPV) and False Discovery Rate (FDR) were found to be 80%, 90%, and 10%, respectively. The data shows that the system results in 100% accuracy in detection for speed of below 20 KMPH. The result indicates that the camera can varied from 30 to 42 degrees while obtaining best result without any misdetection. The rate of recognition for the system with 30 fps is found to be 71.58% by dividing the total time for processing a frame over the total frame time duration). The Latency test in obtaining the coordinates indicates that the proposed system takes 4.724 seconds in average to obtain the coordinates from GSM modem.