In the face of expanding digital landscapes, cloud-edge computing infrastructures struggle with an ever-increasing demand for real-time data management. This demand has a direct impact on the energy consumption of cloud-edge networks, which has spiked dramatically, stressing the need for accurate time-series forecasting. As conventional machine learning models encounter difficulties in predicting volatile workloads, attention mechanisms have emerged thanks to their capability of capturing long-range dependencies. This article pioneers the exploration of attention mechanisms for time-series forecasting in cloud-edge environments, particularly focusing on a promising low-complexity attention mechanism (i.e., informer model). Through comprehensive discussions and experimental validations, we demonstrate that informers significantly outperform traditional models in the prediction accuracy of compute workload forecasting. The outcome of this work not only highlights the importance of attention mechanisms in cloud-edge scenarios but also pave the way for future optimizations, ultimately aiming at reducing the environmental impact of digital growth.

COVID-19 is an acute respiratory disease that has become a pandemic worldwide. Many studies have been conducted to enhance our understanding of COVID-19. However, the abundance of information obtained from these studies has resulted in information overload. In this study, we purposed a simple COVID-19 Knowledge Graph in Bahasa Indonesia as a way to reconstruct knowledge to combat this information overload. We used Bahasa Indonesia in our study to explore its potential for constructing a Knowledge Graph (KG). The construction of our KG involved manual curation of medical literatures and annotation of entities and relationships by the domain experts. The KG was implemented using Neo4J version 5. We successfully demonstrated our COVID-19 KG, which consists of 240 nodes and 276 relationships with 15 and 14 node and relationship labels respectively. Accessing the information within the KG is made effortless through the use of Cypher queries in Neo4J. Further research is still needed to develop the KG into a larger and better one. However, our COVID-19 KG can serve as a basis for further development.

In today’s increasingly data-driven landscape, organizations are shifting their focus toward leveraging data analytics for strategic decision-making. As data becomes a cornerstone of operational and strategic activities, the quality of this data has emerged as a non-negotiable aspect for organizations. Lack of attention to data quality can not only result in considerable revenue losses but can also cripple the effectiveness of analytics, causing misinformed decisions and strategic errors. Against this backdrop, this empirical study delves into the innovative avenue of utilizing Generative Artificial Intelligence (AI) as a mechanism for enhancing data quality. The research aims to explore multiple facets of organizational operationsâ\euro”ranging from technical infrastructure to business strategyâ\euro”to ascertain the potential advantages offered by Generative AI. Utilizing a mix of qualitative and quantitative methods, we conducted in-depth interviews, case studies, and simulations to evaluate the impact of Generative AI on data quality. Our findings reveal a multi-layered benefit structure. Notably, we found that Generative AI is not a replacement for existing, traditional methods of data quality assurance but serves as a powerful supplement. It augments traditional methods by increasing the accuracy of data, thereby offering a more reliable foundation for analytics. Additionally, the use of Generative AI can streamline workflows, enhancing productivity among various roles including solution architects and software developers. Moreover, it facilitates a more nuanced and accurate requirement gathering process, enabling businesses to fine-tune their data analytics strategies more effectively. In conclusion, our study establishes that integrating Generative AI into data quality management processes can not only resolve immediate issues surrounding data accuracy but also lead to long-term organizational benefits, such as higher efficiency and more effective decision-making. This research serves as a pioneering step in the intersection of Generative AI and data quality, setting the stage for future studies and real-world applications.

A sound field estimation method based on kernel interpolation with an adaptive kernel function is proposed. The kernel-interpolation-based sound field estimation methods enable physics-constrained interpolation from pressure measurements of distributed microphones with a linear estimator, which constrains interpolation functions to satisfy the Helmholtz equation. However, a fixed kernel function would not be capable of adapting to the acoustic environment in which the measurement is performed, limiting their applicability. To make the kernel function adaptive, we represent it with a sum of directed and residual trainable kernel functions. The directed kernel is defined by a weight function composed of a superposition of exponential functions to capture highly directional components. The weight function for the residual kernel is represented by neural networks to capture unpredictable spatial patterns of the residual components. Experimental results using simulated and real data indicate that the proposed method outperforms the current kernel-interpolation-based methods and a method based on physics-informed neural networks.

Mega satellite networks recently emerged to complement the current terrestrial infrastructure to attain global coverage and faster communication links. However, with increased congestion in the radio spectrum, migrating satellite communication to high frequencies can provide higher data rates. Nevertheless, signal fading due to weather conditions and atmospheric losses becomes significant at such high frequencies. In this paper, we leverage tools from stochastic geometry to provide an analytical framework that captures the effect of high frequency fading for satellite constellations in the downlink. The analytical framework presented exploits the spatial diversity provided by the satellite network and examines the performance of the dominant satellite (satellite providing the best quality of service). Results show a close fit to the performance of practical networks and can thus provide network designers with an analytical benchmark to assist with network tuning.

Ah, the game is afoot once more! Following the trail blazed by the enlightening tome â\euro™Comparative Analysis of Electric Cars and Diesel Cars Using Hydrotreated Vegetable Oil (HVO)â\euro™ [6], we find ourselves embarking upon a most intriguing investigation. Our quarry? No less than four of the most cunning and elusive beasts in the automotive kingdom: electric, hydrogen, hydrotreated vegetable oil (HVO), and the venerable petrol. With the meticulous eye of a detective and the precision of a scientist, we delve into the very sinews and bones of these mechanical creatures. We shall dissect their physical efficiencies with the keen blade of physics, leaving no gear unturned, no circuit unexamined. From energy conversion to fuel consumption, we shall lay bare their secrets. But, my dear Watson, the plot thickens! For we shall not stop at mere physical scrutiny. No, we shall don our economistâ\euro™s hat and weigh their worth in gold, assessing cost-effectiveness, market trends, and the long-term financial implications that would make even the Bank of England take notice. And let us not forget the environment, that great and silent witness to all our deeds. We shall examine emissions, sustainability, and ecological footprints with the thoroughness of a bloodhound on the scent. Our aim? To present an objective comparison, as clear and as illuminating as the gaslights of Baker Street, highlighting strengths, limitations, and the tantalizing possibilities that lie ahead. The findings, I have no doubt, will be of great interest to stakeholders, policymakers, and all those engaged in the grand debate on sustainable transportation. The game, as they say, is truly afoot!

Lightweight convolutional neural networks (LCNNs) are commonly quantized and deployed on edge devices to fulfill the requirements of low-power, high-performance tasks. Utilizing uniform, symmetric, per-tensor quantization with power-of-two scale factors can enhance hardware efficiency, albeit at the cost of significant accuracy degradation. In this work, we present a hardware-friendly post-training quantization (HFPTQ) framework to address this problem. HFPTQ employs a synergistic combination of established techniques, including Cross-Layer Equalization (CLE), Absorbing High Bias (AHB), and Adaptive Rounding. Furthermore, HFPTQ introduces quantization-aware equalization by optimizing the equalization scale and absorption vector to minimize block reconstruction error and network prediction difference. Additionally, HFPTQ introduces an adaptive bias correction mechanism. While optimizing weight rounding, bias term is co-optimized to rectify the mean shift in activations induced by quantization. Experimental results, based on the ImageNet dataset, demonstrate that HFPTQ significantly enhances the low-bit hardware-friendly quantization performance of lightweight networks.

This study introduces a cutting-edge digital stethoscope optimized for remote health monitoring. Integrating Micro-Electromechanical Systems (MEMS) microphones with Bluetooth Low Energy (BLE) 5, the device ensures high-fidelity, real-time audio transmission. It seamlessly connects to an Internet of Things (IoT) platform through an embedded system, highlighting its potential in remote healthcare scenarios, especially during global health emergencies. Advanced features encompass Active Noise Cancellation, extended battery life, and intricate internal sound filtration. Paired with a dedicated Android application, the stethoscope streamlines the capture, storage, and visualization of auscultation data. Crucially, its integration with Electronic Health Records (EHRs) and its capability to generate vast datasets can significantly advance diagnostic precision, leveraging Digital Signal Processing and Artificial Intelligence methodologies.Â

This paper introduces and explores the notion of intelligence as a â\euro™considered responseâ\euro™ phenomenon, shedding light on its relevance in defining and understanding human-level intelligence and its various associated facets. The concept of intelligence as a considered response offers a valuable framework for gaining clarity on essential elements of cognition and consciousness. This paper delves into its implications on the mind, self/I, awareness, self-awareness, consciousness, sentience, thoughts and feelings, free will, perception, attention, cognition, expectation, prediction, and learning. Furthermore, the paper argues that embodiment plays a pivotal role in the architecture of Artificial General Intelligence (AGI). Embodiment is proposed as an essential component for AGI to attain grounded cognition, develop a sense of self, and facilitate social learning. This achievement is made possible through direct physical experiences and mental processes, all rooted in the concept of â\euro™considered response.â\euro™ By adopting the â\euro™considered responseâ\euro™ framework, this paper provides a comprehensive perspective on intelligence and its multifaceted dimensions. It offers insights that can contribute to the development of more sophisticated AGI systems and deepen our understanding of human intelligence, paving the way for a more profound exploration of the intersection between artificial and human cognition.

Increasing the independence of individuals with tetraplegia is a challenging task. One potential solution is to allow for use of assistive robotics, specifically an assistive robotic manipulator (ARM), when solving varying tasks in personal and remote space. Allowing for remote performances has a positive influence on the independence of the user, allowing the user to be self-sufficient even when lying in bed. The control interfaces that are suitable for severely disabled individuals is lacking. The aim of this paper is twofold: to allow for remote tongue-based control of an ARM and second, to compare the effect of semi-automation on the control of a robotic ARM. Ten able-bodied individuals participated in a two-day experiment where they were asked to drive a wheelchair mounted ARM away from the participant and out of sight. Thereafter, they should either pick up a strawberry or a bottle from a table. All the participants successfully finished three trials for three different control methods: 1) manual control (MA), 2) adaptive level semi-automation (SA), and 3) fixed level semi-automation (FA). When grasping the strawberry, there was a significant decrease in the gripping time and number of used commands when using FA compared to MA. When grasping the bottle, the SA showed a significant reduction in gripping time and number of used commands compared with MA. This paper is a step in the direction of providing severely paralyzed individuals with a way to increase their independence and overall quality of life.

Explainable Artificial Intelligence (XAI) and Fair Learning have made significant strides in various application domains, including criminal recidivism predictions, healthcare settings, toxic comment detection, automatic speech detection, recommendation systems, and image segmentation. However, these two fields have largely evolved independently. Recent studies have demonstrated that incorporating explanations into decision-making processes enhances the transparency and trustworthiness of AI systems. In light of this, our objective is to conduct a systematic review of FairXAI, which explores the interplay between fairness and explainability frameworks. To commence, we propose a taxonomy of FairXAI that utilizes XAI as a means to both mitigate and evaluate bias. This taxonomy will serve as a base for machine learning researchers operating in diverse domains. Additionally, we will undertake an extensive review of existing articles, taking into account factors such as the purpose of the interaction, target audience, and domain and context. Moreover, we outline an interaction framework for FairXAI considering various fairness perceptions and propose a FairXAI wheel that encompasses four core properties that must be verified and evaluated. This will serve as a practical tool for researchers and practitioners, ensuring the fairness and transparency of their AI systems. Furthermore, we will identify challenges and conflicts in the interactions between fairness and explainability, which could potentially pave the way for enhancing the responsibility of AI systems. As the inaugural review of its kind, we hope that this survey will inspire scholars to address these challenges by scrutinizing current research in their respective domains.Â

Blood glucose is typically measured using invasive methods such as finger pricking, which although accurate are not suitable for frequent use as they cause extreme pain, and do not provide provisions for continuous glucose monitoring. Recent studies have proposed non-invasive glucometers that are based on scientific principles such as optical polarimetry, thermal emission, and electromagnetic approaches, but are expensive, highly sensitive to external noise and environmental variations, have low signal-to-noise ratio (SNR), and poor glucose selectivity. Although developments in Near-Infrared Spectroscopy (NIRS) have overcome these limitations to a certain extent, they do not produce reliable measurements due to large calibration errors that often result in incorrect glucose readings. In this paper, we propose a robust particle-swarm optimization-based artificial neural network for non-invasive continuous glucose monitoring using the principles of NIRS. We show that the PSO-ANN approach outperforms the traditional backpropagation algorithm used in ANN training and several other regression algorithms with the lowest error metrics: MAE- 1.01, MSE-2.16, RMSE-0.97, R-sqaured score -0.976 and modified R-squared score -0.973. The paper also provides insights into the circuit design, sensors used, hardware-software integration, and clinical validation alongside providing an overview of HbA1c computation.The accuracy and reliability of the proposed system are analyzed using the Clarke Error Grid (CEG) with 93.9% of the obtained readings falling within zone A and 100% of the readings falling in the clinically accepted range (zones A and B). The paper also explores potential enhancements such as miniaturization of the prototype device for wearable applications and wireless connectivity.Â

Smart roads have become an essential component of intelligent transportation systems (ITS). The roadside perception technology, a critical aspect of smart roads, utilizes various sensors, roadside units (RSUs), and edge computing devices to gather real-time traffic data for vehicle-road cooperation. However, the full potential of smart roads in improving the safety and efficiency of autonomous vehicles only can be realized through the mass deployment of roadside perception and communication devices. On the one hand, roadside devices require significant investment but can only achieve monitoring function currently, resulting in no profitability for investors. On the other hand, drivers lack trust in the safety of autonomous driving technology, making it difficult to promote large-scale commercial applications. To deal with the dilemma of mass deployment, we propose a novel smart-road vehicle-guiding architecture for vehicle-road cooperative autonomous driving,  based on which we then propose the corresponding business model and analyze its benefits from both operator and driver perspectives. The numerical simulations validate that our proposed smart road solution can enhance driving safety and traffic efficiency. Moreover, we utilize the cost-benefit analysis (CBA) model to assess the economic advantages of the proposed business model which indicates that the smart highway that can provide vehicle-guided-driving services for autonomous vehicles yields more profit than the regular highway.

Earth observation has a crucial role in understanding and monitoring our planet’s health and changes. Spaceborne Synthetic Aperture Radar (SAR) has become a valuable technology for Earth monitoring, leading to a massive expansion of satellite launches. However, within the limited radio frequency (RF) band, Radio Frequency Interference (RFI) poses a significant challenge for SAR technology. RFI can have a significant impact on the overall system performance and particularly on SAR image quality. To analyze and solve the interference problem, a simulator/emulator is required at the RF level to emulate and analyze the effects of different RFI sources on the final focused spaceborne SAR image. This paper presents an open-source RF-level SAR emulator for spaceborne applications called SEMUS. SEMUS is an integrated end-to-end framework for realistic spaceborne SAR scenarios that can generate raw RF data (Level-0) for an arbitrary scene and reconstruct the final SAR-focused image (Level-1). Moreover, the emulator is capable of injecting arbitrary RFI waveforms into the raw SAR data. The simulation results prove SEMUS’s ability to generate high-quality Level-0 SAR data above Melbourne, Australia. Affirming its capability, SEMUS is able to reconstruct Level-1 free of RFI or contaminated with interference.

Detecting Distributed Denial of Service (DDoS) attacks through the creation of a Network Intrustion Detection System (NIDS) using machine learing and convolutional neural networks.Â

Phishing involves manipulating individuals into revealing private data, e.g., user IDs, bank details, and passwords. The observed surge in fraud is related to increased deception, impersonation, and advanced online attacks. Thus, effective phishing detection methods are required to mitigate escalating global phishing threats. Existing methods (e.g., heuristics-based, signature-based, and visual similarity-based methods) attempt to detect phishing sites, and machine learning (ML) and deep learning (DL) methods are effective in the cybersecurity context in terms of learning from data, offering insights, and forecasting. However, independent ML algorithms are limited when handling complex data, and DL techniques surpass traditional ML methods in terms of performance but require more data and time. This paper introduces ``EnLeM'',  an ensemble learning model that yields excellent precision, i.e., 97.06\% and 96.36\% for before and after feature selection, respectively, compared to individual ML/DL methods. To address computational efficiency, we employ univariate feature selection. Compared to DL models, this approach yielded promising results (10.01 s for prefeature selection and 8.72 s for post-feature selection). The proposed model was assessed against five conventional ML-based classifiers and two DL-based counterparts to evaluate pre/post feature selection and execution times. The experimental results demonstrate EnLeM’s outstanding, scalable, and consistent performance.

As wireless optical communication becomes a key technology in many applications such as internet-of-underwater-things (IoWT) and inter-satellite communication, investigation of different modulation schemes has become essential. In this paper, we address the issue of whether it is possible to wirelessly transmit a modulated light signal at a frequency beyond the signal’s band-limit. We show that by using a superoscillation function as the amplitude modulating signal, it is possible to wirelessly transmit the optical signal through various media such as free-space, underwater and even turbulent underwater, and still preserve the superoscillatory nature of the signal with the property that it contains a component that oscillates faster than the signalâ\euro™s highest Fourier component. We also present cases where the received optical signal is distorted and quantify distortionÂ

In distance education programs with a large number of students, the organization and facilitation of collaborative writing projects are particularly challenging. Teachers must specify the didactical design and group formation, supervise and support distributed groups, grade, and finally evaluate the learning experiences. Distributed student groups need their own workspace including both, support for a structured writing process including necessary instructions and materials as well as tools for collaborative text editing, communication, coordination, and providing formative and summative feedback. Current approaches to support collaborative writing in education are mostly based on the use of Web 2.0 applications, such as Wikis and Weblogs, or Collaborative real-time text editors, failing to support teachers and students appropriately. As a consequence, teachers often refrain from implementing collaborative writing projects in large scale distance learning courses. We introduce a process model of a collaborative writing project aimed at creating a summary of a research paper and present the architecture and implementation of a Collaborative Learning Platform implementing Collaborative Writing Activities by an extension of a Learning Management System and integrating it with a collaboration environment. The platform supports the phases and activities of the process model and provides distributed teachers and students with integrated support throughout the collaborative writing project lifecycle. Our experience shows that the platform provides a scalable, responsive, and robust environment for collaborative writing and is accepted by teachers and students. It provides the basis for the analysis of collaborative writing behavior and further research.