Victor Ikechukwu Agughasi

Dr. Victor Ikechukwu Agughasi

Computer Science and Engineering, University of Mysore, Mysore, Karnātaka, International
orcid
...trying to understandhow Machines learn. Most of my work r...

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2021 in Global Transitions Proceedings
Verified
Journal Article
Open access
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi
SMS. Murali
S. Murali
RDR. Deepu
R. Deepu
RSR.C. Shivamurthy
R.C. Shivamurthy

18 May 2023 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi
MSMurali S
Murali S
Automatic identification of salient features in large medical datasets, particularly in chest x-ray (CXR) images, is a crucial research area. Accurately detecting critical findings such as emphysema, pneumothorax, and chronic bronchitis can aid radiologists in prioritizing time-sensitive cases and screening for abnormalities. However, traditional deep neural network approaches often require bounding box annotations, which can be time-consuming and challenging to obtain. This study proposes an explainable ensemble learning approach, CX-Net, for lung segmentation and diagnosing lung disorders using CXR images. We compare four state-of-the-art convolutional neural network models, including feature pyramid network, U-Net, LinkNet, and a customized U-Net model with ImageNet feature extraction, data augmentation, and dropout regularizations. All models are trained on the Montgomery and VinDR-CXR datasets with and without segmented ground-truth masks. To achieve model explainability, we integrate SHapley Additive exPlanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) techniques, which enable a better understanding of the decision-making process and provide visual explanations of critical regions within the CXR images. By employing ensembling, our outlier-resistant CX-Net achieves superior performance in lung segmentation, with Jaccard overlap similarity of 0.992, Dice coefficients of 0.994, precision of 0.993, recall of 0.980, and accuracy of 0.976. The proposed approach demonstrates strong generalization capabilities on the VinDr-CXR dataset and is the first study to use these datasets for semantic lung segmentation with semi-supervised localization. In conclusion, this paper presents an explainable ensemble learning approach for lung segmentation and diagnosing lung disorders using CXR images. Extensive experimental results show that our method efficiently and accurately extracts regions of interest in CXR images from publicly available datasets, indicating its potential for integration into clinical decision support systems. Furthermore, incorporating SHAP and Grad-CAM techniques further enhances the interpretability and trustworthiness of the AI-driven diagnostic system.

26 December 2024 in Technologies
Verified
Journal Article
Open access
PDF file
RJReem jalloul
Reem jalloul
CHChethan H.K.
Chethan H.K.
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi
RARamez Alkhatib
Ramez Alkhatib
Breast cancer remains one of the most prevalent and deadly cancers affecting women worldwide. Early detection is crucial, particularly for younger women, as traditional screening methods like mammography often struggle with accuracy in cases of dense breast tissue. Infrared thermography offers a non-invasive imaging alternative that enhances early detection by capturing subtle thermal variations indicative of breast abnormalities. This study investigates and compares the performance of various deep learning and machine learning models in analyzing thermographic data to classify breast tissue as healthy, benign, or malignant. To maximize detection accuracy, data preprocessing, feature extraction, and dimensionality reduction were implemented to isolate distinguishing characteristics across tissue types. Leveraging advanced feature extraction and visualization techniques inspired by geospatial data methodologies, we evaluated several deep learning architectures and classical classifiers using the DRM-IR and Breast Thermography Mendeley thermal datasets. Among the tested models, the ResNet152 architecture combined with a Support Vector Machine (SVM) classifier delivered the highest performance, achieving 97.62% accuracy, 95.79% precision, 98.53% recall, 94.52% specificity, an F1 score of 97.16%, an area under the curve (AUC) of 99%, a latency of 0.06 s, and CPU utilization of 88.66%. These findings underscore the potential of integrating infrared thermography with advanced deep learning and machine learning approaches to significantly improve the accuracy and efficiency of breast cancer detection, supporting its role as a valuable tool for early diagnosis.

31 October 2022 in International Journal of Advanced Technology and Engineering Exploration
Verified
Journal Article
Closed access
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi

1 February 2024 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
SBSampoorna Bhimshetty
Sampoorna Bhimshetty
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi
The internet of things (IoT) underscores pivotal real-world applications ranging from security systems to smart infrastructure and traffic management. However, contemporary IoT devices grapple with significant challenges pertaining to battery longevity and energy efficiency, constraining the assurance of prolonged network lifetimes and expansive sensor coverage. Many existing solutions, although promising on paper, are intricate and often impractical for real-world implementations. Addressing this gap, we introduce an energy-efficient routing protocol leveraging reinforcement learning (RL) tailored for wireless sensor networks (WSNs). This protocol harnesses RL to discern the optimal transmission route from the source to the sink node, factoring in the energy profile of each intermediary node. Training of the RL algorithm is facilitated through a reward function that includes energy outflow and data transmission efficacy. The model was compared against two prevalent routing protocols, LEACH and fuzzy C-means (FCM), for a comprehensive assessment. Simulation results highlight our protocol’s superiority with respect to the active node count, energy conservation, network longevity, and data delivery efficiency.

5 August 2023
Verified
Conference Paper
Closed access
Victor Ikechukwu AgughasiVictor Ikechukwu Agughasi
Victor Ikechukwu Agughasi
MSMurali S
Murali S
HBHonnaraju B
Honnaraju B
Chronic Obstructive Pulmonary Disease (COPD) is a prevalent pulmonary condition marked by enduring respiratory symptoms and airflow limitations. Prompt diagnosis is vital for efficacious disease management and enhanced patient outcomes. This study introduces COPDNet, an explainable deep learning model founded on the ResNet50 architecture, tailored specifically for diagnosing COPD using Chest radiographic (CXR) images. COPDNet employs preprocessing techniques such as normalization, resizing, and data augmentation to boost model performance and generalization. To foster interpretability and clinician trust, explainability methods like Layer-wise Relevance Propagation (LRP) or Grad-CAM are integrated, offering visual explanations for model predictions. In addition, transfer learning is utilized by initializing the model with pre-trained weights from extensive datasets, minimizing training time and refining performance. With a recall of 98.9% on the pneumothorax CXR image, the efficacy of COPDNet in diagnosing COPD was validated, potentially leading to improved patient outcomes and supporting clinicians in making well-informed decisions.