http://196.220.128.81:8080/xmlui/handle/123456789/159 Sun, 26 Apr 2026 22:01:27 GMT 2026-04-26T22:01:27Z http://196.220.128.81:8080/xmlui/handle/123456789/5311 MOTION PATH PLANNING OF MOBILE ROBOT USING REINFORCEMENT LEARNING ALGORITHM OSHO, ADENIKE BILIKISU Path planning has applications in many areas, for example, industrial robotics, autonomous systems, virtual prototyping, and computer-aided drug design. Much research has been done on path planning especially in the robotic field. This thesis presents a new framework for path planning using the Soft Actor-Critic (SAC) algorithm of reinforcement learning. The Soft Actor Critics Algorithms is an offpolicy Reinforcement Learning which uses the policy gradient method that incorporates the entropy measure of the policy into the reward to encourage exploration. The agent learns policy that acts as randomly as possible while still succeeding in performing a task. CoppeliaSim (formerly known as VREP) was used to simulate the environment. The result shows that the proposed SAC-based motion planning method is feasible and practicable in path planning and obstacle avoidance. It also shows that it is more efficient than Deep Deterministic Policy Gradient (DDPG) algorithm using the same hyperparameter. M.TECH THESIS Fri, 01 Oct 2021 00:00:00 GMT http://196.220.128.81:8080/xmlui/handle/123456789/5311 2021-10-01T00:00:00Z http://196.220.128.81:8080/xmlui/handle/123456789/5310 GEOFENCE-BASED SYSTEM FOR THE PREVENTION OF HUMAN KIDNAPPING OGUNFEITIMI, OLAYINKA, OLUWASEUN M.TECH THESIS Sat, 01 May 2021 00:00:00 GMT http://196.220.128.81:8080/xmlui/handle/123456789/5310 2021-05-01T00:00:00Z http://196.220.128.81:8080/xmlui/handle/123456789/5309 FUZZY LOGIC MODEL FOR CANDIDATE RATING AND SELECTION IN FINANCIAL INSTITUTION RECRUITMENT PROCESSES IDOWU, AYOWOLE OLUWATAYO The traditional ways of candidate selection and recruitment are prone to subjectivity, imprecision and vagueness. With a view to achieving objective and precise selection and recruitment while keeping up with technological improvement and changes, this research proposes a fuzzification-based technique for candidate rating and selection by financial institutions. The technique comprises a Fuzzy Logic component that is an extension of Boolean logic and used for establishing accurate selection process and precise solutions to multi-variable problems. There is a knowledge base component which forms the database of multi-level information and rule base which comprises a set of if-then statements for decision making. Its Inference Engine applies a pre-defined procedure on input from the rule base and fuzzy logic interfaces for final recommendations. The proposed methodology performs pre-defined procedures that are based on some input sets which store multi-level information derived from several pre-specified scores. Results from the implementation of the proposed technique established its practical function as well as its superior performances over some of the existing models for the same purpose M.TECH THESIS Mon, 01 Nov 2021 00:00:00 GMT http://196.220.128.81:8080/xmlui/handle/123456789/5309 2021-11-01T00:00:00Z http://196.220.128.81:8080/xmlui/handle/123456789/5308 A LATTICE CRYPTOGRAPHY AND FOG COMPUTING-BASED MODEL FOR PRIVACY PRESERVATION OF MEDICAL BIG DATA FATOKUN, YEMI TUNRAYO The expanding success of cloud computing in the management of Electronic Health Records (EHRs) also comes with loads of challenges, especially those that bothers on the preservation of users’ privacy, personal data integrity, and even reduction in computational resource demand. Today, there is explosive growth in concerns for security of data exchanged between edge node devices (users) and the cloud server. Almost all the existing proposed methods for overcoming these privacy issues have significant shortcomings such as, ineffectiveness or inefficiencies, as well as their lack of the lightweight property required by resource constrained devices used by users at the edge of the network. This current research work is therefore motivated to develop a lattice cryptography-based quantum attack-resistant security system for preserving privacy and ensuring data integrity in health cloud big data. The lattice encryption algorithm is used to encrypt medical records or data before uploading them on to the storage servers. For every file uploaded to the cloud server, a decoy (or fake equivalent) file is generated and stored in the decoy medical files repository that resides on a decoy server (in the fog facility). This honeypot security paradigm is used here for deceiving/luring potential attackers (unauthorized), to leaving trails behind each time they make attempt to access secured medical records. This chemistry adds multiple layers of security and satisfy requirements such as capacity, security and robustness for secure medical data transmission in a fog-cloud computing environment. The proposed health cloud data security solution was implemented using PHP/Python programming language, on a Windows 10 Operating System running on a PC characterized by 8GB of RAM, 2TB of Hard Disk, Intel Core i7. Comparative evaluation of the proposed solution was then carried out using standard metrics such as time consumption/computation time, throughput, memory requirement, and bandwidth consumption. Results obtained reveals that the developed system performed better than existing ones in terms of having robustness, requiring far lesser computation time, and the lightweight property M.TECH THESIS Sun, 01 Aug 2021 00:00:00 GMT http://196.220.128.81:8080/xmlui/handle/123456789/5308 2021-08-01T00:00:00Z