Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Scientific Journal of Computer Science
Nura Muhammad Sani
Federal Polytechnic Kaltungo
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Deep Learning for Venomous and Non-Venomous Snakes Classification Yakubu Abubakar Lidani; Abdullahi Musa Yola; Abu Tasiu; Nura Muhammad Sani; Sulaiman Muhammad Gidado
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.463

Abstract

Snakes are a major health threat in various communities, specifically where human and snake encounters are frequent. When a snake is not identified correctly, healthcare providers often administer the wrong treatment, this can worsen patient recovery outcomes or even prove fatal to the victim. Therefore, a fast, proper and accurate distinction between venomous and nonvenomous snakes is vital for proper antivenom administration. This study proposes a hybrid deep learning system combining a CNN and an LSTM model for snake image classification through feature extraction from visual data. The CNN extracts key spatial features such as colour and scale patterns, texture, and body shape, whereas the LSTM captures sequential dependencies across these features, by helping distinguish visual similarity amongst the species. The model was trained and evaluated on a dataset of 6,798 snake images from diverse sources. The system achieved a performance of 97% accuracy, 97% precision, 96% recall, an F1-score of 97%, and a ROC-AUC of 0.97. These results demonstrate that integrating CNN and LSTM is moderately effective for snake classification. The proposed system has practical applications in the area of emergency healthcare, wildlife management, as well as mobile based identification tool. With 97% accuracy, this model can improve emergency responders first aid, enhance a safer treatment administration and help make safer decisions on the use of antivenom, by reducing treatment delays and improving patient survival prognosis. This model has the potential to save lives and minimize the consequences of snakebite envenoming.
Secure, Intelligent, and Energy-Efficient Architectures for Next-Generation Smart Homes: A Review Haruna Kawuwa; Nura Muhammad Sani; Ninyikiriza Deborah Lynn; Mohammed Mansur Ibrahim; Mustapha Ismail; Musbahu Bala Ibrahim
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.479

Abstract

The fast adoption of Internet of Things (IoT) technologies in smart home has driven the demand for secure, smart and energy efficient homes. However, findings from previous research were limited. This study aims at addressing the growing demand for common and scalable solutions in next generation smart home environments by performing a systematic literature review of smart home systems featuring IoT. The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA 2020) framework was used in the study. The literature was collected from major peer-reviewed academic databases. The Assessments published during the period 2021-2026 were selected for qualitative synthesis after screening, eligibility and quality evaluation. The five main dimensions were analyzed: architectural trends, communication trends, security and privacy mechanisms, Human Activity Recognition (HAR) and intelligent automation, energy management strategies, and research challenges. Results reveal that smart home systems are increasingly multi-layer and hybrid edge-cloud systems based on technologies like Wireless Fidelity (Wi-Fi), ZigBee, Bluetooth Low Energy (BLE), Long Range (LoRa), and Z-Wave. Typical applications for Machine Learning (ML) and Deep Learning (DL) include energy optimisation (forecasting, reinforcement learning), as well as intrusion detection, automation, and context-aware decision making. Challenges faced are interoperability issues, cyber security concerns, computational problems, device variations, and lack of real-world testing. The aim of the study is to create an integrated synthesis and comparative taxonomy that can guide the future development of scalable, secure and intelligent smart home ecosystems.
Hybrid Deep Learning Model for Fake News Detection on Social Media Using CNN-GRU on X formerly known as Twitter Lawan Jibril Muhammad; Isa Umar Mohammed; Nura Muhammad Sani
Scientific Journal of Computer Science Vol. 2 No. 1 (2026): June
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i1.2026.400

Abstract

The spread of fake news on social media platforms has created a dilemma for the world community by spreading false information and eroding public confidence. Fake news spreads quickly and seriously harms society. Predicting and identifying fake news is crucial for preserving the integrity of information ecosystems in the wake of an epidemic of multiple high-profile disinformation efforts. In order to detect fake news, this work suggests a hybrid deep learning algorithm called Convolutional Neural Network - Gated Recurrent Unit (CNN-GRU), which combines the Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) learning algorithms in an efficient manner. Models for identifying fake news were developed using deep learning-based methods, such as CNN, GRU, and CNN-GRU deep learning algorithms. Four standard performance metrics—accuracy, precision, recall, and F1-score—were used to evaluate the models. Nevertheless, the CNN-GRU deep learning-based detection model outperformed models created with CNN and GRU, achieving the maximum accuracy of 98.77%, 98.68%, 98.73%, and 98.71% for precision, recall, and F1-score, respectively. With a combined accuracy of 98.77%, precision of 98.68%, recall of 98.73%, and F1-score of 98.71%, the CNN-GRU deep learning-based false news detection model performs better than the two other deep learning-based models.
Fuzzy-Based Model for Respiratory Disease Classification Auwal Umar; Abdullahi Musa Yola; Musbahu Bala Ibrahim; Muawiyya Modibbo Musa; Habimana Jean Bosco; Haruna Kawuwa; Nura Muhammad Sani; Rutarindwa Jean Pierre
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.480

Abstract

Respiratory diseases remain a major global health concern, highlighting the need for accurate and interpretable computer-aided diagnostic systems. This study proposes a Mamdani Fuzzy Inference System (FIS) for the classification of four respiratory disease categories: Chronic Obstructive Pulmonary Disease (COPD), Asthma, Infected, and Healthy Control (HC). The proposed model utilizes the original variables provided in the Exasens dataset, including dielectric permittivity measurements (Real Permittivity Minimum, Real Permittivity Average, Imaginary Permittivity Minimum, and Imaginary Permittivity Average) together with demographic attributes (Age, Gender, and Smoking Status). A stratified subset of 100 records was selected from the publicly available Exasens dataset and preprocessed using min–max normalization before fuzzification with triangular and trapezoidal membership functions. Expert-defined fuzzy IF–THEN rules were employed within a Mamdani inference framework, and centroid defuzzification was used to obtain the final disease classification. The proposed model was evaluated using stratified 10-fold cross-validation and achieved an overall classification accuracy of 93.00%, with a macro-average F1-score of 91.87%. The experimental results demonstrate that the proposed Mamdani FIS provides accurate, transparent, and interpretable respiratory disease classification while preserving methodological reproducibility. These findings indicate its potential as a decision support tool for respiratory disease diagnosis.
Co-Authors Abdullahi Musa Yola Abdullahi Musa Yola Abu Tasiu Auwal Umar Habimana Jean Bosco Haruna Kawuwa Isa Umar Mohammed Lawan Jibril Muhammad Mohammed Mansur Ibrahim Muawiyya Modibbo Musa Musbahu Bala Ibrahim Mustapha Ismail Ninyikiriza Deborah Lynn Rutarindwa Jean Pierre Sulaiman Muhammad Gidado Yakubu Abubakar Lidani