December 30 ~ 31, 2023, Virtual Conference
Patrick Ansah1, Sumit Kumar Tetarave2, Ezhil Kalaimannan2 and Caroline John2, 1School of Computer Application, Kalinga Institute of Industrial Technology, India, 2Department of Cybersecurity, University of West Florida, FL 32514, USA
Tomato plants' susceptibility to diseases imperils agricultural yields. About 30% of the total crop loss is attributable to plants with disease. Detecting such illnesses in the plant is crucial to avoid significant output losses. This study introduces "data fusion" to enhance disease classification by amalgamating distinct disease-specific traits from leaf halves. Data fusion generates synthetic samples, fortifying a TensorFlow Keras deep learning model using a diverse tomato leaf image dataset. Results illuminate the augmented model's efficacy, particularly for diseases marked by overlapping traits. Enhanced disease recognition accuracy and insights into disease interactions transpire. Evaluation metrics (accuracy 0.95, precision 0.58, recall 0.50, F1 score 0.51) spotlight balanced performance. While attaining commendable accuracy, the intricate precision-recall interplay beckons further examination. In conclusion, data fusion emerges as a promising avenue for refining disease classification, effectively addressing challenges rooted in trait overlap. The integration of TensorFlow Keras underscores the potential for enhancing agricultural practices. Sustained endeavours toward enhanced recall remain pivotal, charting a trajectory for future advancements.
Disease Fusion, Deep Learning Classification, Tomato Leaf Diseases, TensorFlow Keras, Disease Recognition.
Peprah Obed Adjei1, Sumit Kumar Tetarave1, Parthasarathi Pattnayak1 and Caroline John2, 1School of Computer Applications, Kalinga Institute of Industrial Technology, India, 2Department of Cybersecurity, University of West Florida, FL 32514, USA
This research delves into network anomaly detection by harnessing the power of K-Nearest Neighbours (KNN) within Digital Twins. The study capitalizes on the remarkable performance of the model, characterized by impeccable precision, recall, and F1-score, as indicated by the classification report. The confusion matrix further highlights the model's robustness, showcasing minimal Type-I and Type-II errors. The research aims to amplify the robustness and adaptability of KNN-based Digital Twins dedicated to network anomaly detection. The exploration encompasses dynamic learning mechanisms for real-time adaptation, extension to edge computing environments, multi-modal data fusion for comprehensive insights, and resilience against adversarial attacks. The proposed continuous evaluation framework ensures the model's perpetual relevance, while integrated explainability tools provide transparency in decision-making for network administrators. Cross-domain generalization is scrutinized to assess the model's adaptability to diverse network landscapes. This research underscores the potential of KNN-enhanced Digital Twins as a potent tool in the network security arsenal, paving the way for reliable and agile anomaly detection across various domains and network environments.
Network Anomaly Detection, K-Nearest neighbours (KNN), Digital Twins, Robustness and Adaptability.
Tabea Hirzel, Independent Researcher & Educator, Department of Culture/ Founder & Developer, Learning4Tech, Tomelloso City Council, Ciudad Real, Spain
Economy 5.0 signifies a transformative era with profound implications for human development and education. This article examines emerging learning models underpinning Economy 5.0, exploring their impact on politics, personal growth, and global education ecosystems. The paradigm shift in economic evolution prompts a reevaluation of the nexus between politics and personal development, with learning acting as a catalyst for societal and individual transformation. A global perspective on AI in education policies underscores the geopolitical significance of AI-related technologies, reshaping knowledge dissemination through innovative learning platforms and Learning DAOs. Blockchain-based Agile Learning DAOs (BALD) are introduced as a mechanism that revolutionizes content creation with transparency and ethical considerations. Ethical learning, privacy, and addressing information bias emerge as central themes, with AI enhancing personhood. The roles of educators as guides remain pivotal. The future of learning in Economy 5.0 necessitates a balanced partnership between humanity and technology, grounded in ethics and human potential.
Economy 5.0, Learning models, Machine learning, Ethical learning, Technology in education.