Stephen Opoku Oppong

Work place: Department of Computer Science, KNUST, Ghana



Research Interests: Image Processing, Network Security, Computational Learning Theory


Stephen Opoku Oppong received his Bsc degree in Actuarial Science from Kwame Nkrumah University of Science and Technology (KNUST), Ghana in 2012 and Masters of Philosophy (MPhil) degree in Information Technology also from KNUST in 2015. He is a Lecturer in the Department of Information Technology, Faculty of Technology at Academic City College, Accra Ghana He. His research areas include statistical modeling, algorithms and image processing.

Author Articles
Error Detection and Correction in Wireless Sensor Networks Using Enhanced Reverse Conversion Algorithm in Healthcare Delivery System

By Prince Modey Dominic Asamoah Stephen Opoku Oppong Emmanuel Kwesi Baah

DOI:, Pub. Date: 8 Oct. 2022

Wireless Sensor Network (WSN) is a group of sensors connected within a geographical area to communicate with each other through wireless media. Although WSN is very important in data collection in the world today, error may occur at any stage of data processing and transmission within WSNs due to its architecture. This study presents error detection and correction in WSNs using a proposed ‘pair wise’ Residue Number System (RNS) reverse converter in a health care delivery system. The proposed RNS reverse converter required (10n+3)_FAbit hardware resources for its implementation making it suitable for sensors. The proposed scheme outperformed Weighted Function and Base Extension algorithms and Field Programmable Analog Arrays using Kalman-filter algorithm schemes in terms of its hardware requirements.

[...] Read more.
Business Decision Support System based on Sentiment Analysis

By Stephen Opoku Oppong Dominic Asamoah Emmanuel Ofori Oppong Derrick Lamptey

DOI:, Pub. Date: 8 Jan. 2019

Since organizational decisions are vital to organizational development, customers’ views and feedback are equally important to inform good decisions. Given this relevance, this paper seeks to automate a sentiment analysis system - SentDesk- that can aid tracking sentiments in customers’ reviews and feedback. The study was contextualised in some business organisations in Ghana. Three business organizational marketers were made to annotate emotions and as well tag sentiments to each instance in the corpora. Kappa and Krippendoff coefficients were computed to obtain the annotation agreement in the corpora. The SentDesk system was evaluated in the environment alongside comparing the output to that of the average sentiments tagged by the marketers. Also, the SentDesk system was evaluated in the environment by the selected marketers after they had tested the platform. By finding the average kappa value from the corpora (CFR + ISEAR), the average kappa coefficient was found to be 0.40 (40%). The results of evaluating the SentDesk system with humans shows that the system performed as better as humans. The study also revealed that, while annotating emotions and sentiments in the datasets, counsellor’s own emotions influences their perception of emotions.

[...] Read more.
Achieving Confidentiality in Electronic Health Records using Cloud Systems

By Robert French-Baidoo Dominic Asamoah Stephen Opoku Oppong

DOI:, Pub. Date: 8 Jan. 2018

Currently, existing methods for enforcing access to records in an Electronic Health Record system relies on a single Trusted Server which stores health records and mediates access. Such Trusted Severs employ either a Ciphertext-Policy Attribute-Based Encryption (CP-ABE) or Key-Policy Attribute-Based Encryption (KP-ABE) method for storing and controlling access. However, Trusted Server storage of health records is susceptible to single-point-of-threat attack and a successful attack invariably leads to compromising the integrity of records on the server. In this research work. This paper presents a methodology that defines and creates simple Access Structures and eliminates need for private keys during encryption and/or decryption of health records which is the Enhanced Ciphertext-Policy Attribute-Based Encryption (ECP-ABE). The ECP-ABE yields high cryptographic performance creates simple Access Structures, eliminates need for private keys and presents an implementation architecture that makes cloud-based EHR system secure and confidential. The ECP-ABE also performs cryptographic functions using less CPU time, minimal computer memory and produces high encryption and decryption throughput especially with increasing file sizes.

[...] Read more.
Optimizing Memory using Knapsack Algorithm

By Dominic Asamoah Evans Baidoo Stephen Opoku Oppong

DOI:, Pub. Date: 8 May 2017

Knapsack problem model is a general resource distribution model in which a solitary resource is allocated to various choices with the aim of amplifying the aggregate return. Knapsack problem has been broadly concentrated on in software engineering for a considerable length of time. There exist a few variations of the problem. The study was about how to select contending data/processes to be stacked to memory to enhance maximization of memory utilization and efficiency. The occurrence is demonstrated as 0 – 1 single knapsack problem. In this paper a Dynamic Programming (DP) algorithm is proposed for the 0/1 one dimensional knapsack problem. Problem-specific knowledge is integrated in the algorithm description and assessment of parameters, with a specific end goal to investigate the execution of finite-time implementation of Dynamic Programming.

[...] Read more.
Other Articles