| Annals of Emerging Technologies in Computing (AETiC) |
|
| IAER
| AETiC
| Editorial Board
| Instructions
| Indexing
| Submit Paper
| Special Issues
| Archives
| Contact Us
|
|
 |
|
|
|
Beam Prediction for mmWave V2I Communication aided by Geolocation and Machine Learning Sherif Adeshina Busari, Ifiok Otung, Muhammad Ali and Raed Abd-Alhameed Abstract: Millimetre wave (mmWave) systems require high beamforming gains to overcome the unfavourable impacts of high path losses at mmWave frequencies. Large antenna arrays enable such gains through highly directive narrow beams which then require multiple beams to cover the spatial directions of interest. The required beam management for such systems, particularly for mobile use cases such as the vehicle-to-infrastructure (V2I) scenarios, is challenging. Real-time optimal beam selection from codebooks consumes radio resources and incurs large training overheads. As a result, geolocation side information and machine learning (ML) algorithms are being explored to address beam management challenges. However, prior works have mostly applied their solutions using simulations that are based on synthetic datasets. Recently, real-world datasets based on extensive mmWave measurements have become available. Leveraging the real-world datasets, in this work, we evaluate and compare the performance of three ML (i.e., k-nearest neighbours, support vector machine and decision tree) algorithms on mmWave V2I beam selection aided by global positioning system latitude and longitude coordinates as the only two features for the ML. The results show the impact of codebook sizes on the accuracies of the ML algorithms under ten different scenarios. The results also reveal the limitations of the geolocation-aided beam prediction as average accuracy could go below 30% in some scenarios, and higher than 90% in other scenarios. These performance results point to the need for multi-modal approaches (involving a combination of different sensors' data) for efficient mmWave V2I beam prediction. Keywords: Beam Prediction; Decision Tree; GPS; K-Nearest Neighbour; Machine learning; mmWave; Support Vector Machine; V2I. |
Mohammad Zahangir Alam, Khandoker Ashik Uz Zaman and Mahdi H. Miraz Abstract: Retrieval-Augmented Generation (RAG) shows significant promise in knowledge-intensive tasks by improving domain specificity, enhancing temporal relevance and reducing hallucinations. However, applying RAG to finance encounters critical challenges: restricted access to proprietary datasets, limited retrieval accuracy, regulatory constraints and sensitive data interpretation. We introduce AstuteRAG-FQA an adaptive RAG framework tailored for Financial Question Answering (FQA), leveraging task-aware prompt engineering to address these challenges. The framework uses a hybrid retrieval strategy integrating both open-source and proprietary financial data whilst maintaining strict security protocols and regulatory compliance. A dynamic prompt framework adapts in real time to query complexity, improving precision and contextual relevance. To systematically address diverse financial queries, we propose a four-tier task classification: explicit factual, implicit factual, interpretable rationale and hidden rationale involving implicit causal reasoning. For each category, we identify key challenges, datasets and optimisation techniques within the retrieval and generation process. The framework incorporates multi-layered security mechanisms including differential privacy, data anonymisation and role-based access controls to protect sensitive financial information. Additionally, AstuteRAG-FQA implements real-time compliance monitoring through automated regulatory validation systems that verify responses against industry standards and legal obligations. We evaluate three data integration techniques — contextual embedding, small model augmentation and targeted fine-tuning — analysing their efficiency and feasibility across varied financial environments. Our experimental results show that the framework improves response accuracy by 23% and enhances regulatory compliance by 18%, compared to the baseline systems. Furthermore, qualitative case studies illustrate the robustness of the system in handling complex financial queries whilst maintaining transparency and preserving confidentiality. This study presents a scalable, secure and domain-adaptive solution for sensitive and regulated financial environments. Keywords: Causal Reasoning; Explainable AI; Financial Question Answering (FQA); Hybrid Retrieval; Proprietary Data; RAG; Regulatory Compliance; Sensitive Data; Small Model Augmentation; Task-Aware Prompt Engineering. |
SRR-Based RF Sensor for Non-Invasive Detection of Static Bone Fracture States Prince O. Siaw, Ebenezer Adjei, Ahmad Aldelemy, Aslan N. Moqadam, Mohammed Lashab and Raed A. Abd-Alhameed Abstract: This study presents the design and simulation of a metamaterial-based radio frequency (RF) sensor employing Split-Ring Resonator (SRR) structures for the non-invasive detection of static bone fracture states. Traditional imaging modalities such as X-ray, CT, and MRI, though widely used, often face limitations in accessibility, cost, radiation exposure, and sensitivity to micro-fractures. To address these gaps, the proposed sensor operates within the 1–3 GHz frequency range and leverages dual SRRs to enhance field confinement and sensitivity to dielectric changes caused by bone discontinuities. Full-wave simulations were conducted using CST Microwave Studio on a multilayer femur phantom comprising realistic anatomical layers, including skin, fat, muscle, cortical bone, and blood. The sensor demonstrated a strong response to variations in dielectric properties associated with fracture conditions, achieving detection of fracture features as small as 0.10 mm in width and 20 mm in depth beneath a 5.00 mm thick cortical layer. Reflection coefficient analysis (|S11|) revealed distinct resonance shifts between healthy, fractured, and healed bone states, with frequency deviations up to 47 MHz and quality factors exceeding 80. An iterative antenna design process led to an optimised SRR configuration (ANT 5), exhibiting high Q-factor, enhanced electromagnetic confinement, and excellent impedance matching. The findings highlight the sensor’s potential as a compact, non-ionising, and wearable diagnostic tool for orthopaedic applications. Keywords: Biological tissues; Dielectric material; Fracture detection; Metamaterial; Microwave sensor; Split-ring resonator. |
Kavita Agrawal, Padala Prasad Reddy and Suresh Chittineni Abstract: Securing the edge layer is essential in modern cybersecurity architectures, particularly for the Internet of Things (IoT), where resource-constrained devices require robust yet lightweight protection mechanisms. This paper introduces a novel Neural Cryptography Secure Router (NCSR) framework that integrates Tree Parity Machine (TPM)-based neural key generation with AES encryption, OpenWRT-based firewalling, and a virtualized intrusion detection/prevention system. The architecture is implemented using Raspberry Pi devices at the edge and a Fedora-based host for virtualization and centralized security processing. The framework features two Raspberry Pi units: the first simulates an IoT node, encrypting sensor data with TPM-generated keys before transmission via SSH/SCP; the second operates as a secure router, running OpenWRT and nftables for real-time packet filtering. The Fedora host functions as a multi-layered security hub, hosting virtual machines (pfSense and Security Onion) for firewalling, deep packet inspection, and threat analysis via Snort and Suricata. This integrated model eliminates the need for pre-shared keys while ensuring end-to-end confidentiality and dynamic session key exchange. Empirical evaluations demonstrate strong performance with minimal resource consumption: 1.2 ms/KB encryption time, 1.1 ms/KB decryption time, 25% CPU utilization, 95.5% firewall drop efficiency, and a 7% false positive rate. Comparative analysis with existing solutions confirms the model’s advantages in terms of security, scalability, and computational efficiency, establishing NCSR as a practical and novel security solution for IoT edge networks. Keywords: AES Encryption; Edge Layer Security; Firewall; Intrusion Detection and Prevention System (IDS/IPS); Neural Cryptography. |
Clinical Text Augmentation and Generation Using RAG for Large Language Models Nasreen Fathima and Kavitha Ganesh Abstract: Large Language Models (LLM) are becoming more essential in clinical text generation, where use of synthetic medical data is environmentally accurate and applicable for real-world healthcare applications. Existing LLMs often lack in specialized optimization and clarity, leading to incorrect outputs. These restrictions can make their references unreliable, particularly for sensitive clinical data. To overcome these problems, this research work suggests integrating generative adversarial networks with LLM to improve clinical data accuracy and reduce hallucinations. LLMs like LLaMA, BERT and GPT are broadly used in clinical settings for tasks such as summarizing patient notes and answering medical queries. Generative Adversarial Networks (GANs) are used to generate realistic synthetic clinical data, aiding privacy and data augmentation. The LDA model is added with GAN to identify the underlying topics in clinical documents, ensuring the synthetic text is coherent and thematically relevant. The use of Retrieval Augmented Generation (RAG) dynamically retrieves current medical knowledge and provides grounding responses with real-time evidence and minimizes outdated information. The first phase focuses on generating and validating synthetic clinical data using GANs and LDA to ensure high quality and domain alignment; the second phase focus on user interaction, where RAG retrieves relevant information in real time to answer queries, and an interactive interface enables seamless engagement and feedback. Continuous evaluation of NLP metrics demonstrates that the proposed Clinical Augmentation Generation and Retrieval Augmented Generation (CAG-RAG) framework outperforms the existing DALL-M approach in generating synthetic clinical text. For diagnosis-related data, the proposed CAG-RAG method achieves improvements of 15.7% in BLEU, 17% in ROUGE-1, and 17% in ROUGE-L scores. For medication-related data, the improvements were 20.8% in BLEU, 17.1% in ROUGE-1, and 17.25% in ROUGE-L. These results highlight the reliability, adaptability, and contextual accuracy for clinical applications. Keywords: Large Language Models; Retrieval Modules; Synthetic Clinical Data; Data Augmentation; Synthetic Text; NLP Metrics; Generative Adversarial Network; Retrieval Augmented Generation. |
Kavita Agrawal, Padala Prasad Reddy and Suresh Chittineni Abstract: The rapid growth of the Internet of Things (IoT) and edge computing has revolutionized real-time data processing through decentralized decision-making. However, ensuring the security of resource-constrained edge devices, particularly against emerging quantum threats, presents a significant challenge. Traditional encryption schemes such as RSA and AES, though robust, impose considerable computational and memory overhead, making them unsuitable for low-power IoT environments. Moreover, many existing solutions prioritize network-level security while neglecting device-level cryptographic constraints. This paper introduces the Chaotic-Lattice Feistel Cipher (CLFC), a lightweight and post-quantum secure cryptographic framework tailored for IoT edge devices. CLFC integrates an Extended Generalized Feistel Network (EGFN) for efficient data diffusion, a novel chaotic 5-bit S-box for enhanced non-linearity in key scheduling, and Ring-Learning with Errors (Ring-LWE) for quantum-resilient master key generation. Experimental results show that CLFC reduces execution time by up to 19% compared to Ascon and 45% compared to Elephant, while requiring zero heap memory allocation—making it well-suited for constrained environments. Security analysis confirms that CLFC achieves strong resistance against classical cryptanalytic techniques, including linear, differential, and meet-in-the-middle (MitM) attacks. These findings position CLFC as a computationally efficient, memory-optimized, and quantum-resistant encryption scheme for securing next-generation IoT and edge computing systems. Keywords: Chaotic Substitution Box (S-box); Extended Generalized Feistel Network (EGFN); Internet of Things (IoT) Security; Lightweight Cryptography; Post-Quantum Security; Ring Learning with Errors (Ring-LWE). |
From Sentiment to Search Volume: Impact Assessment of Video Branding Campaign Gangmin Li Abstract: In the growing reliance on social media for brand campaigns, this study aims to identify efficient and reliable methodologies for evaluating their success. Using a quantitative approach, we investigated two key metrics: sentiment analysis (via VADER) and Brand Search Volume (BSV) via Google Trends. We employed an OLS regression model to examine how sentiment scores and negative-to-positive comment ratios influence BSV. The findings reveal strong positive correlations between sentiment scores, total comment counts, and BSV changes in the subsequent month (28.3% increase per sentiment score unit) and year (6.57% increase). Higher negative-to-positive comment ratios were significantly associated with BSV declines, with negative sentiments showing persistent short- and long-term impacts. The study highlights the need to integrate emotional response metrics (e.g., sentiment analysis) with behavioural indicators (e.g., BSV) to assess campaigns’ effects on consumer attitudes and behaviour. It emphasises that managers and policymakers must ensure campaigns secure initial positive reception and maintain long-term relevance. Keywords: Brand search volume; OLS regression; Sentiment analysis; Social media evaluation; Video branding campaigns. |
Adaptive Deep Learning for Multimodal Cardiac Risk Prediction: A Feature Fused Multichannel Approach Krishna Priya Remamany, Anju S Pillai and Ahmed Al Shahri Abstract: Cardiovascular disease (CVD) continues to be a leading global cause of death and requires advanced models and personalized risk prediction algorithms. This research presents an adaptive deep learning framework that combines feature selection and signal fusion to improve individual level cardiac risk prediction. The adaptive deep learning model collects multimodal physiological signals, including Electrocardiogram (ECG), photoplethysmogram (PPG), and other bio-signals, to create an overall health profile for each patient. The feature selection component of the adaptive model enhances the model performance by reducing noise and dimensionality of the input, enhancing learning efficiency. To enhance data representativeness, a multi-signal or multi-channel fusion paradigm was applied, taking advantage of feature correlations across multiple signals to result in a more accurate and robust representation of cardiovascular health status. The proposed predictive architecture combines convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to efficiently analyse both spatial and temporal dependencies present in the signals. In testing using a public, benchmark dataset containing over 10,000 patient records, the model achieved an accuracy of 94.5%, precision of 93.8%, recall of 92.3%, and an F1 score of 93.0%. The entire diagnostic system enables remote monitoring and highly accurate and predictive results in real-time. The proposed research represents the first adaptive deep learning approach to signal fusion for robust and personalized CVD risk prediction, while addressing existing challenges within predictive health care systems. Keywords: Cardiac Risk Forecasting; Deep Learning; ECG; Feature Selection; Health Monitoring; Signal Fusion. |
ROBUST Project: Advancing Ubiquitous eHealth Solutions for Fracture Orthopaedic Rehabilitation Joaquim Bastos, Raed A. Abd-Alhameed, Evanthia Karavatselou, Jorge Martins and Valdemar Monteiro Abstract: The ROBUST (Ubiquitous eHealth Solution for Fracture Orthopaedic Rehabilitation) project represents a pioneering research and innovation initiative. This position paper presents the project's comprehensive approach to revolutionizing bone fracture care through the development of an innovative mobile eHealth platform that integrates advanced RF-based sensing technologies, secure IoT infrastructure, and artificial intelligence-driven rehabilitation protocols. Europe's rapidly ageing population presents unprecedented challenges to healthcare systems, with osteoporosis alone causing over 3.2 million leg and hip fractures annually in those aged 50 and above, with up to 10% becoming non-unions that lead to prolonged immobility, repeated hospital visits, and soaring healthcare costs. ROBUST addresses this critical societal need by developing a smart, connected eHealth solution that enables remote monitoring of patients' healing processes while preserving control, safety, and privacy through reliable and energy-efficient mechanisms. After the first 30 months of execution, the project has achieved significant milestones including the development of active RF-based sensors for non-invasive bone density monitoring, implementation of secure body area network with advanced cybersecurity mechanisms, creation of prototype mobile application for patient-centred care, and establishment of a comprehensive system architecture that encompasses telemonitoring and telerehabilitation functionalities. The consortium's interdisciplinary approach combines expertise from five leading European institutions spanning academia and industry, fostering knowledge transfer and innovation through a structured secondment program that has facilitated cross-sector collaboration and skills development. This research contributes to the advancement of digital health technologies by providing evidence-based solutions that could save hundreds of millions of euros in annual healthcare costs through reduced hospital stays and readmissions, while supporting personalized at-home guidance that enhances solution adoption and reduces caregiver burden. The project's outcomes establish a foundation for scalable, multidisciplinary bone fracture care with broad benefits for Europe's ageing population and demonstrate the potential for mobile applications in healthcare to address pressing societal challenges. Keywords: Bone fracture monitoring; Cybersecurity; eHealth; Internet of Things (IoT); RF-based sensing; Telerehabilitation. |
|