Information, Volume 15, Issue 5 (May 2024) – 48 articles

Lightweight convolutional neural networks are widely used for face detection due to their ability to learn local representations through spatial induction bias and translational invariance. However, convolutional face detectors have limitations in detecting faces under challenging conditions like occlusion, blurring, or changes in facial poses, primarily attributed to fixed-size receptive fields and a lack of global modeling. Transformer-based models have advantages on learning global representations but are insensitive to capture local patterns. To address these limitations, we propose an efficient face detector that combines convolutional neural network and transformer architectures. We introduce a bi-stream structure that integrates convolutional neural network and transformer blocks within the backbone network, enabling the preservation of local pattern features and the extraction of global context. To further preserve the local details captured by convolutional neural networks, we propose a feature enhancement convolution block in a hierarchical backbone structure. Additionally, we devise a multiscale feature aggregation module to enhance obscured and blurred facial features. Experimental results demonstrate that our method has achieved improved lightweight face detection accuracy with an average precision of 95.30%, 94.20%, and 87.56% across the easy, medium, and hard subdatasets of WIDER FACE, respectively. Therefore, we believe our method will be a useful supplement to the collection of current artificial intelligence models and benefit the engineering applications of face detection. Full article

Named Data Networking (NDN) stands out as a prominent architectural framework for the future Internet, aiming to address deficiencies present in IP networks, specifically in the domain of security. Although NDN packets containing requested content are signed with the publisher’s signature which establishes data provenance for content, the NDN domain still requires more holistic frameworks that address consumers’ identity verification while accessing protected contents or services using producer/publisher-preapproved authentication servers. In response, this paper introduces the NDN One-Time Authentication (NDNOTA) framework, designed to authenticate NDN online services, applications, and data in real time. NDNOTA comprises three fundamental elements: the consumer, producer, and authentication server. Employing a variety of security measures such as single sign-on (SSO), token credentials, certified asymmetric keys, and signed NDN packets, NDNOTA aims to reinforce the security of NDN-based interactions. To assess the effectiveness of the proposed framework, we validate and evaluate its impact on the three core elements in terms of time performance. For example, when accessing authenticated content through the entire NDNOTA process, consumers experience an additional time overhead of 70 milliseconds, making the total process take 83 milliseconds. In contrast, accessing normal content that does not require authentication does not incur this delay. The additional NDNOTA delay is mitigated once the authentication token is generated and stored, resulting in a comparable time frame to unauthenticated content requests. Additionally, obtaining private content through the authentication process requires 10 messages, whereas acquiring public data only requires two messages. Full article

The Internet of Medical Things (IoMT) extends the concept of eHealth and mHealth for patients with continuous monitoring requirements. This research concentrates on the use of wearable devices based on the use of inertial measurement units (IMUs) that account for a gait analysis for its use in three health cases, equilibrium evaluation, fall prevention and surgery recovery, that impact a large elderly population. We also analyze two different scenarios for data capture: supervised by clinicians and unsupervised during activities of daily life (ADLs). The continuous monitoring of patients produces large amounts of data that are analyzed in specific IoMT platforms that must be connected to the health system platforms containing the health records of the patients. The aim of this study is to evaluate the factors that impact the cost of the deployment of such an IoMT solution. We use population data from Catalonia together with an IoMT deployment model for costs from the current deployment of connected devices for monitoring diabetic patients. Our study reveals the critical dependencies of the proposed IoMT platforms: from the devices and cloud cost, the size of the population using these services and the savings from the current model under key parameters such as fall reduction or rehabilitation duration. Future research should investigate the benefit of continuous monitoring in improving the quality of life of patients. Full article

A measurement performed on a quantum system is an act of gaining information about its state. However, in the foundations of quantum theory, the concept of information is multiply defined, particularly in the area of quantum reconstruction, and its conceptual foundations remain surprisingly under-explored. In this paper, we investigate the gain of information in quantum measurements from an operational viewpoint in the special case of a two-outcome probabilistic source. We show that the continuous extension of the Shannon entropy naturally admits two distinct measures of information gain, differential information gain and relative information gain, and that these have radically different characteristics. In particular, while differential information gain can increase or decrease as additional data are acquired, relative information gain consistently grows and, moreover, exhibits asymptotic indifference to the data or choice of Bayesian prior. In order to make a principled choice between these measures, we articulate a Principle of Information Increase, which incorporates a proposal due to Summhammer that more data from measurements leads to more knowledge about the system, and also takes into consideration black swan events. This principle favours differential information gain as the more relevant metric and guides the selection of priors for these information measures. Finally, we show that, of the symmetric beta distribution priors, the Jeffreys binomial prior is the prior that ensures maximal robustness of information gain for the particular data sequence obtained in a run of experiments. Full article

Clinical characteristics of COVID-19 patients have been mostly described in hospitalised patients, yet most are managed in an outpatient setting. The COVID-19 pandemic transformed healthcare delivery models and accelerated the implementation and adoption of telemedicine solutions. We employed a modular remote monitoring system with multi-modal data collection, aggregation, and analytics features to monitor mild COVID-19 patients and report their characteristics and symptoms. At enrolment, the patients were equipped with wearables, which were associated with their accounts, provided the respective in-system consents, and, in parallel, reported the demographics and patient characteristics. The patients monitored their vitals and symptoms daily during a 14-day monitoring period. Vital signs were entered either manually or automatically through wearables. We enrolled 162 patients from February to May 2022. The median age was 51 (42–60) years; 44% were male, 22% had at least one comorbidity, and 73.5% were fully vaccinated. The vitals of the patients were within normal range throughout the monitoring period. Thirteen patients were asymptomatic, while the rest had at least one symptom for a median of 11 (7–16) days. Fatigue was the most common symptom, followed by fever and cough. Loss of taste and smell was the longest-lasting symptom. Age positively correlated with the duration of fatigue, anorexia, and low-grade fever. Comorbidities, the number of administered doses, the days since the last dose, and the days since the positive test did not seem to affect the number of sick days or symptomatology. The i-COVID platform allowed us to provide remote monitoring and reporting of COVID-19 outpatients. We were able to report their clinical characteristics while simultaneously helping reduce the spread of the virus through hospitals by minimising hospital visits. The monitoring platform also offered advanced knowledge extraction and analytic capabilities to detect health condition deterioration and automatically trigger personalised support workflows. Full article

In recent years, many deep learning-based object detection methods have performed well in various applications, especially in large-scale object detection. However, when detecting small targets, previous object detection algorithms cannot achieve good results due to the characteristics of the small targets themselves. To address the aforementioned issues, we propose the small object algorithm model MCF-YOLOv5, which has undergone three improvements based on YOLOv5. Firstly, a data augmentation strategy combining Mixup and Mosaic is used to increase the number of small targets in the image and reduce the interference of noise and changes in detection. Secondly, in order to accurately locate the position of small targets and reduce the impact of unimportant information on small targets in the image, the attention mechanism coordinate attention is introduced in YOLOv5’s neck network. Finally, we improve the Feature Pyramid Network (FPN) structure and add a small object detection layer to enhance the feature extraction ability of small objects and improve the detection accuracy of small objects. The experimental results show that, with a small increase in computational complexity, the proposed MCF-YOLOv5 achieves better performance than the baseline on both the VisDrone2021 dataset and the Tsinghua Tencent100K dataset. Compared with YOLOv5, MCF-YOLOv5 has improved detection AP_small by 3.3% and 3.6%, respectively. Full article

Aim: Biofields combine many physiological levels, both spatially and temporally. These biofields reflect naturally resonant forms of synaptic energy reflected in growing and spreading waves of brain activity. This study aims to theoretically understand better how resonant continuum waves may be reflective of consciousness, cognition, memory, and thought. Background: The metabolic processes that maintain animal cellular and physiological functions are enhanced by physiological coherence. Internal biological-system coordination and sensitivity to particular stimuli and signal frequencies are two aspects of coherent physiology. There exists significant support for the notion that exogenous biologically and non-biologically generated energy entrains human physiological systems. All living things have resonant frequencies that are either comparable or coherent; therefore, eventually, all species will have a shared resonance. An organism’s biofield activity and resonance are what support its life and allow it to react to stimuli. Methods: As the naturally resonant forms of synaptic energy grow and spread waves of brain activity, the temporal and spatial frequency of the waves are effectively regulated by a time delay (T) in inter-layer signals in a layered structure that mimics the structure of the mammalian cortex. From ubiquitous noise, two different types of waves can arise as a function of T. One is coherent, and as T rises, so does its resonant spatial frequency. Results: Continued growth eventually causes both the wavelength and the temporal frequency to abruptly increase. Two waves expand simultaneously and randomly interfere in an area of T values as a result. Conclusion: We suggest that because of this extraordinary dualism, which has its roots in the phase relationships of amplified waves, coherent waves are essential for memory retrieval, whereas random waves represent original cognition. Full article

Opportunistic Networks (OppNets) are characterized by intermittently connected nodes with fluctuating performance. Their dynamic topology, caused by node movement, activation, and deactivation, often relies on controlled flooding for routing, leading to significant resource consumption and network congestion. To address this challenge, we propose the Adaptive Clustering-based Routing Protocol (ACRP). This ACRP protocol uses the common member-based adaptive dynamic clustering approach to produce optimal clusters, and the OppNet is converted into a TCP/IP network. This protocol adaptively creates dynamic clusters in order to facilitate the routing by converting the network from a disjointed to a connected network. This strategy creates a persistent connection between nodes, resulting in more effective routing and enhanced network performance. It should be noted that ACRP is scalable and applicable to a variety of applications and scenarios, including smart cities, disaster management, military networks, and distant places with inadequate infrastructure. Simulation findings demonstrate that the ACRP protocol outperforms alternative clustering approaches such as kRop, QoS-OLSR, LBC, and CBVRP. The analysis of the ACRP approach reveals that it can boost packet delivery by 28% and improve average end-to-end, throughput, hop count, and reachability metrics by 42%, 45%, 44%, and 80%, respectively. Full article

Security and efficiency remain a serious concern for Internet of Things (IoT) environments due to the resource-constrained nature and wireless communication. Traditional schemes are based on the main mathematical operations, including pairing, pairing-based scalar multiplication, bilinear pairing, exponential operations, elliptic curve scalar multiplication, and point multiplication operations. These traditional operands are cost-intensive and require high computing power and bandwidth overload, thus affecting efficiency. Due to the cost-intensive nature and high resource requirements, traditional approaches are not feasible and are unsuitable for resource-limited IoT devices. Furthermore, the lack of essential security attributes in traditional schemes, such as unforgeability, public verifiability, non-repudiation, forward secrecy, and resistance to denial-of-service attacks, puts data security at high risk. To overcome these challenges, we have introduced a novel signcryption algorithm based on hyperelliptic curve divisor multiplication, which is much faster than other traditional mathematical operations. Hence, the proposed methodology is based on a hyperelliptic curve, due to which it has enhanced security with smaller key sizes that reduce computational complexity by 38.16% and communication complexity by 62.5%, providing a well-balanced solution by utilizing few resources while meeting the security and efficiency requirements of resource-constrained devices. The proposed strategy also involves formal security validation, which provides confidence for the proposed methodology in practical implementations. Full article

This research paper presents a comprehensive study on optimizing the critical artificial intelligence (AI) factors influencing cost management in civil engineering projects using a multi-criteria decision-making (MCDM) approach. The problem addressed revolves around the need to effectively manage costs in civil engineering endeavors amidst the growing complexity of projects and the increasing integration of AI technologies. The methodology employed involves the utilization of three MCDM tools, specifically Delphi, interpretive structural modeling (ISM), and Cross-Impact Matrix Multiplication Applied to Classification (MICMAC). A total of 17 AI factors, categorized into eight broad groups, were identified and analyzed. Through the application of different MCDM techniques, the relative importance and interrelationships among these factors were determined. The key findings reveal the critical role of certain AI factors, such as risk mitigation and cost components, in optimizing the cost management processes. Moreover, the hierarchical structure generated through ISM and the influential factors identified via MICMAC provide insights for prioritizing strategic interventions. The implications of this study extend to informing decision-makers in the civil engineering domain about effective strategies for leveraging AI in their cost management practices. By adopting a systematic MCDM approach, stakeholders can enhance project outcomes while optimizing resource allocation and mitigating financial risks. Full article

Decentralized execution is a widely used framework in multi-agent reinforcement learning. However, it has a well-known but neglected shortcoming, redundant computation, that is, the same/similar computation is performed redundantly in different agents owing to their overlapping observations. This study proposes a novel method, the locally centralized team transformer (LCTT), to address this problem. This method first proposes a locally centralized execution framework that autonomously determines some agents as leaders that generate instructions and other agents as workers to act according to the received instructions without running their policy networks. For the LCTT, we subsequently propose the team-transformer (T-Trans) structure, which enables leaders to generate targeted instructions for each worker, and the leadership shift, which enables agents to determine those that should instruct or be instructed by others. The experimental results demonstrated that the proposed method significantly reduces redundant computations without decreasing rewards and achieves faster learning convergence. Full article

Situation awareness (SA) describes an individual’s understanding of their surroundings and actions in the near future based on the individual’s comprehension and understanding of the surrounding inputs. SA measurements can be applied to improve system performance or human effectiveness in many fields of study, including driving. However, in some scenarios drivers might need to drive in unfamiliar traffic regulations (UFTRs), where the traffic rules and vehicle configurations are a bit different from what the drivers are used to under familiar traffic regulations. Such driving conditions require drivers to adapt their attention, knowledge, and reactions to safely reach the destination. This ability is influenced by the degree of handedness. In such tasks, mixed-/left-handed people show better performance than strong right-handed people. This paper aims to explore the influence of the degree of handedness on SA when driving under UFTRs. We analyzed the SA of two groups of drivers: strong right-handed drivers and mixed-/left-handed drivers. Both groups were not familiar with driving in keep-left traffic regulations. Using a driving simulator, all participants drove in a simulated keep-left traffic system. The participants’ SA was measured using a subjective assessment, named the Participant Situation Awareness Questionnaire PSAQ, and performance-based assessment. The results of the study indicate that mixed-/left-handed participants had significantly higher SA than strong right-handed participants when measured by performance-based assessment. Also, in the subjective assessment, mixed-/left-handed participants had significantly higher PSAQ performance scores than strong right-handed participants. The findings of this study suggest that advanced driver assistance systems (ADAS), which show improvement in road safety, should adapt the system functionality based on the driver’s degree of handedness when driving under UFTRs. Full article

In smart education, adaptive e-learning systems personalize the educational process by tailoring it to individual learning styles. Traditionally, identifying these styles relies on learners completing surveys and questionnaires, which can be tedious and may not reflect their true preferences. Additionally, this approach assumes that learning styles are fixed, leading to a cold-start problem when automatically identifying styles based on e-learning platform behaviors. To address these challenges, we propose a novel approach that annotates unlabeled student feedback using multi-layer topic modeling and implements the Felder–Silverman Learning Style Model (FSLSM) to identify learning styles automatically. Our method involves learners answering four FSLSM-based questions upon logging into the e-learning platform and providing personal information like age, gender, and cognitive characteristics, which are weighted using fuzzy logic. We then analyze learners’ behaviors and activities using web usage mining techniques, classifying their learning sequences into specific styles with an advanced deep learning model. Additionally, we analyze textual feedback using latent Dirichlet allocation (LDA) for sentiment analysis to enhance the learning experience further. The experimental results demonstrate that our approach outperforms existing models in accurately detecting learning styles and improves the overall quality of personalized content delivery. Full article

Social media has become more popular in the last few years. It has been used in public health development and healthcare settings to promote healthier lifestyles. Given its important role in today’s culture, it is necessary to understand its current trends and future directions in public health. This review aims to describe and summarize how public health professionals have been using social media to improve population outcomes. This review highlights the substantial influence of social media in advancing public health objectives. The key themes explored encompass the utilization of social media to advance health initiatives, monitor diseases, track behaviors, and interact with communities. Additionally, it discusses potential future directions on how social media can be used to improve population health. The findings show how social media has been used as a tool for research, implementing health campaigns, and health promotion. Social media integration with artificial intelligence (AI) and Generative Pre-Trained Transformers (GPTs) can impact and offer an innovative approach to tackle the problems and difficulties in health informatics. The research shows how social media will keep growing and evolving and, if used effectively, has the potential to help close public health gaps across different cultures and improve population health. Full article

Automated crowd counting is a crucial aspect of surveillance, especially in the context of mass events attended by large populations. Traditional methods of manually counting the people attending an event are error-prone, necessitating the development of automated methods. Accurately estimating crowd counts across diverse scenes is challenging due to high variations in the sizes of human heads. Regression-based crowd-counting methods often overestimate counts in low-density situations, while detection-based models struggle in high-density scenarios to precisely detect the head. In this work, we propose a unified framework that integrates regression and detection models to estimate the crowd count in diverse scenes. Our approach leverages a routing strategy based on crowd density variations within an image. By classifying image patches into density levels and employing a Patch-Routing Module (PRM) for routing, the framework directs patches to either the Detection or Regression Network to estimate the crowd count. The proposed framework demonstrates superior performance across various datasets, showcasing its effectiveness in handling diverse scenes. By effectively integrating regression and detection models, our approach offers a comprehensive solution for accurate crowd counting in scenarios ranging from low-density to high-density situations. Full article

Identifying stress in older adults is a crucial field of research in health and well-being. This allows us to take timely preventive measures that can help save lives. That is why a nonobtrusive way of accurate and precise stress detection is necessary. Researchers have proposed many statistical measurements to associate stress with sensor readings from digital biomarkers. With the recent progress of Artificial Intelligence in the healthcare domain, the application of machine learning is showing promising results in stress detection. Still, the viability of machine learning for digital biomarkers of stress is under-explored. In this work, we first investigate the performance of a supervised machine learning algorithm (Random Forest) with manual feature engineering for stress detection with contextual information. The concentration of salivary cortisol was used as the golden standard here. Our framework categorizes stress into No Stress, Low Stress, and High Stress by analyzing digital biomarkers gathered from wearable sensors. We also provide a thorough knowledge of stress in older adults by combining physiological data obtained from wearable sensors with contextual clues from a stress protocol. Our context-aware machine learning model, using sensor fusion, achieved a macroaverage F-1 score of 0.937 and an accuracy of 92.48% in identifying three stress levels. We further extend our work to get rid of the burden of manual feature engineering. We explore Convolutional Neural Network (CNN)-based feature encoder and cortisol biomarkers to detect stress using contextual information. We provide an in-depth look at the CNN-based feature encoder, which effectively separates useful features from physiological inputs. Both of our proposed frameworks, i.e., Random Forest with engineered features and a Fully Connected Network with CNN-based features validate that the integration of digital biomarkers of stress can provide more insight into the stress response even without any self-reporting or caregiver labels. Our method with sensor fusion shows an accuracy and F-1 score of 83.7797% and 0.7552, respectively, without context and 96.7525% accuracy and 0.9745 F-1 score with context, which also constitutes a 4% increase in accuracy and a 0.04 increase in F-1 score from RF. Full article

Amidst an unprecedented period of technological progress, incorporating digital platforms into diverse domains of existence has become indispensable, fundamentally altering the operational processes of governments, businesses, and individuals. Nevertheless, the swift process of digitization has concurrently led to the emergence of cybercrime, which takes advantage of weaknesses in interconnected systems. The growing dependence of society on digital communication, commerce, and information sharing has led to the exploitation of these platforms by malicious actors for hacking, identity theft, ransomware, and phishing attacks. With the growing dependence of organizations, businesses, and individuals on digital platforms for information exchange, commerce, and communication, malicious actors have identified the susceptibilities present in these systems and have begun to exploit them. This study examines 28 research papers focusing on intrusion detection systems (IDS), and phishing detection in particular, and how quickly responses and detections in cybersecurity may be made. We investigate various approaches and quantitative measurements to comprehend the link between reaction time and detection time and emphasize the necessity of minimizing both for improved cybersecurity. The research focuses on reducing detection and reaction times, especially for phishing attempts, to improve cybersecurity. In smart grids and automobile control networks, faster attack detection is important, and machine learning can help. It also stresses the necessity to improve protocols to address increasing cyber risks while maintaining scalability, interoperability, and resilience. Although machine-learning-based techniques have the potential for detection precision and reaction speed, obstacles still need to be addressed to attain real-time capabilities and adjust to constantly changing threats. To create effective defensive mechanisms against cyberattacks, future research topics include investigating innovative methodologies, integrating real-time threat intelligence, and encouraging collaboration. Full article

The progress in machine learning during the last decade has had a considerable impact on many areas of science and technology, including quantum technology. This work explores the application of reinforcement learning (RL) methods to the quantum control problem of state transfer in a single qubit. The goal is to create an RL agent that learns an optimal policy and thus discovers optimal pulses to control the qubit. The most crucial step is to mathematically formulate the problem of interest as a Markov decision process (MDP). This enables the use of RL algorithms to solve the quantum control problem. Deep learning and the use of deep neural networks provide the freedom to employ continuous action and state spaces, offering the expressivity and generalization of the process. This flexibility helps to formulate the quantum state transfer problem as an MDP in several different ways. All the developed methodologies are applied to the fundamental problem of population inversion in a qubit. In most cases, the derived optimal pulses achieve fidelity equal to or higher than 0.9999, as required by quantum computing applications. The present methods can be easily extended to quantum systems with more energy levels and may be used for the efficient control of collections of qubits and to counteract the effect of noise, which are important topics for quantum sensing applications. Full article

Cyclic air braking is a key factor affecting the safe operation of trains on long downhill sections. However, a train’s cycle braking strategy is constrained by multiple factors such as driving environment, speed, and air-refilling time. A Q-learning algorithm-based cyclic braking strategy for a heavy haul train on long downhill sections is proposed to address this challenge. First, the operating environment of a heavy haul train on long downhill sections is designed, considering various constraint parameters, such as the characteristics of special operating routes, allowable operating speeds, and train tube air-refilling time. Second, the operating status and braking operation of a heavy haul train on long downhill sections are discretized in order to establish a Q-table based on state–action pairs. The training of algorithm performance is achieved by continuously updating Q-tables. Finally, taking the heavy haul train formation as the study object, actual line data from the Shuozhou–Huanghua Railway are used for experimental simulation, and different hyperparameters and entry speed conditions are considered. The results show that the safe and stable cyclic braking of a heavy haul train on long downhill sections is achieved. The effectiveness of the Q-learning control strategy is verified. Full article

This study aims to present a comparative analysis of the Bayesian regularization backpropagation and Levenberg–Marquardt training algorithms in neural networks for the metrics prediction of damaged archaeological artifacts, of which the state of conservation is often fragmented due to different reasons, such as ritual, use wear, or post-depositional processes. The archaeological artifacts, specifically laminar blanks (so-called blades), come from different sites located in the Southern Levant that belong to the Pre-Pottery B Neolithic (PPNB) (10,100/9500–400 cal B.P.). This paper shows the entire procedure of the analysis, from its normalization of the dataset to its comparative analysis and overfitting problem resolution. Full article

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose. Full article

Artificial intelligence (AI) and blockchain technology have emerged as increasingly prevalent and influential elements shaping global trends in Information and Communications Technology (ICT). Namely, the synergistic combination of blockchain and AI introduces beneficial, unique features with the potential to enhance the performance and efficiency of existing ICT systems. However, presently, the confluence of these two disruptive technologies remains in a rather nascent stage, undergoing continuous exploration and study. In this context, the work at hand offers insight regarding the most significant features of the AI and blockchain intersection. Sixteen outstanding, recent articles exploring the combination of AI and blockchain technology have been systematically selected and thoroughly investigated. From them, fourteen key features have been extracted, including data security and privacy, data encryption, data sharing, decentralized intelligent systems, efficiency, automated decision systems, collective decision making, scalability, system security, transparency, sustainability, device cooperation, and mining hardware design. Moreover, drawing upon the related literature stemming from major digital databases, we constructed a timeline of this technological convergence comprising three eras: emerging, convergence, and application. For the convergence era, we categorized the pertinent features into three primary groups: data manipulation, potential applicability to legacy systems, and hardware issues. For the application era, we elaborate on the impact of this technology fusion from the perspective of five distinct focus areas, from Internet of Things applications and cybersecurity, to finance, energy, and smart cities. This multifaceted, but succinct analysis is instrumental in delineating the timeline of AI and blockchain convergence and pinpointing the unique characteristics inherent in their integration. The paper culminates by highlighting the prevailing challenges and unresolved questions in blockchain and AI-based systems, thereby charting potential avenues for future scholarly inquiry. Full article

In response to the challenges introduced by global warming and increased eutrophication, this paper presents an innovative modeling and simulation (M&S)-driven model for developing an automated inland water monitoring system. This system is grounded in a layered Internet of Things (IoT) architecture and seamlessly integrates cloud, fog, and edge computing to enable sophisticated, real-time environmental surveillance and prediction of harmful algal and cyanobacterial blooms (HACBs). Utilizing autonomous boats as mobile data collection units within the edge layer, the system efficiently tracks algae and cyanobacteria proliferation and relays critical data upward through the architecture. These data feed into advanced inference models within the cloud layer, which inform predictive algorithms in the fog layer, orchestrating subsequent data-gathering missions. This paper also details a complete development environment that facilitates the system lifecycle from concept to deployment. The modular design is powered by Discrete Event System Specification (DEVS) and offers unparalleled adaptability, allowing developers to simulate, validate, and deploy modules incrementally and cutting across traditional developmental phases. Full article

The existing deep learning-based detection of fake information focuses on the transient detection of news itself. Compared to user category profile mining and detection, transient detection is prone to higher misjudgment rates due to the limitations of insufficient temporal information, posing new challenges to social public opinion monitoring tasks such as fake user detection. This paper proposes a multimodal aggregation portrait model (MAPM) based on multi-model joint representation for social media platforms. It constructs a deep learning-based multimodal fake user detection framework by analyzing user behavior datasets within a time retrospective window. It integrates a pre-trained Domain Large Model to represent user behavior data across multiple modalities, thereby constructing a high-generalization implicit behavior feature spectrum for users. In response to the tendency of existing fake user behavior mining to neglect time-series features, this study introduces an improved network called Sequence Interval Detection Net (SIDN) based on Sequence to Sequence (seq2seq) to characterize time interval sequence behaviors, achieving strong expressive capabilities for detecting fake behaviors within the time window. Ultimately, the amalgamation of latent behavioral features and explicit characteristics serves as the input for spectral clustering in detecting fraudulent users. The experimental results on Weibo real dataset demonstrate that the proposed model outperforms the detection utilizing explicit user features, with an improvement of 27.0% in detection accuracy. Full article

In South Korea, the rapid proliferation of smartphones has led to an uptick in messenger phishing attacks associated with electronic communication financial scams. In response to this, various phishing detection algorithms have been proposed. However, collecting messenger phishing data poses challenges due to concerns about its potential use in criminal activities. Consequently, a Korean phishing dataset can be composed of imbalanced data, where the number of general messages might outnumber the phishing ones. This class imbalance problem and data scarcity can lead to overfitting issues, making it difficult to achieve high performance. To solve this problem, this paper proposes a phishing messages classification method using Biased Discriminant Analysis without resorting to data augmentation techniques. In this paper, by optimizing the parameters for BDA, we achieved exceptionally high performances in the phishing messages classification experiment, with 95.45% for Recall and 96.85% for the BA metric. Moreover, when compared with other algorithms, the proposed method demonstrated robustness against overfitting due to the class imbalance problem and exhibited minimal performance disparity between training and testing datasets. Full article

This research confronts the persistent challenge of data scarcity in medical machine learning by introducing a pioneering methodology that harnesses the capabilities of Generative Pre-trained Transformers (GPT). In response to the limitations posed by a dearth of labeled medical data, our approach involves the synthetic generation of comprehensive patient discharge messages, setting a new standard in the field with GPT autonomously generating 20 fields. Through a meticulous review of the existing literature, we systematically explore GPT’s aptitude for synthetic data generation and feature extraction, providing a robust foundation for subsequent phases of the research. The empirical demonstration showcases the transformative potential of our proposed solution, presenting over 70 patient discharge messages with synthetically generated fields, including severity and chances of hospital re-admission with justification. Moreover, the data had been deployed in a mobile solution where regression algorithms autonomously identified the correlated factors for ascertaining the severity of patients’ conditions. This study not only establishes a novel and comprehensive methodology but also contributes significantly to medical machine learning, presenting the most extensive patient discharge summaries reported in the literature. The results underscore the efficacy of GPT in overcoming data scarcity challenges and pave the way for future research to refine and expand the application of GPT in diverse medical contexts. Full article

In this systematic literature review, we delve into the realm of intention recognition within the context of digital forensics and cybercrime. The rise of cybercrime has become a major concern for individuals, organizations, and governments worldwide. Digital forensics is a field that deals with the investigation and analysis of digital evidence in order to identify, preserve, and analyze information that can be used as evidence in a court of law. Intention recognition is a subfield of artificial intelligence that deals with the identification of agents’ intentions based on their actions and change of states. In the context of cybercrime, intention recognition can be used to identify the intentions of cybercriminals and even to predict their future actions. Employing a PRISMA systematic review approach, we curated research articles from reputable journals and categorized them into three distinct modeling approaches: logic-based, classical machine learning-based, and deep learning-based. Notably, intention recognition has transcended its historical confinement to network security, now addressing critical challenges across various subdomains, including social engineering attacks, artificial intelligence black box vulnerabilities, and physical security. While deep learning emerges as the dominant paradigm, its inherent lack of transparency poses a challenge in the digital forensics landscape. However, it is imperative that models developed for digital forensics possess intrinsic attributes of explainability and logical coherence, thereby fostering judicial confidence, mitigating biases, and upholding accountability for their determinations. To this end, we advocate for hybrid solutions that blend explainability, reasonableness, efficiency, and accuracy. Furthermore, we propose the creation of a taxonomy to precisely define intention recognition, paving the way for future advancements in this pivotal field. Full article

Ransomware poses a significant threat by encrypting files or systems demanding a ransom be paid. Early detection is essential to mitigate its impact. This paper presents an Uncertainty-Aware Dynamic Early Stopping (UA-DES) technique for optimizing Deep Belief Networks (DBNs) in ransomware detection. UA-DES leverages Bayesian methods, dropout techniques, and an active learning framework to dynamically adjust the number of epochs during the training of the detection model, preventing overfitting while enhancing model accuracy and reliability. Our solution takes a set of Application Programming Interfaces (APIs), representing ransomware behavior as input we call “UA-DES-DBN”. The method incorporates uncertainty and calibration quality measures, optimizing the training process for better more accurate ransomware detection. Experiments demonstrate the effectiveness of UA-DES-DBN compared to more conventional models. The proposed model improved accuracy from 94% to 98% across various input sizes, surpassing other models. UA-DES-DBN also decreased the false positive rate from 0.18 to 0.10, making it more useful in real-world cybersecurity applications. Full article

Understanding local history is fundamental to fostering a comprehensive global viewpoint. As technological advances shape our pedagogical tools, Virtual Reality (VR) stands out for its potential educational impact. Though its promise in educational settings is widely acknowledged, especially in science, technology, engineering and mathematics (STEM) fields, there is a noticeable decrease in research exploring VR’s efficacy in arts. The present study examines the effects of VR-mediated interventions on cultural education. In greater detail, secondary school adolescents (N = 52) embarked on a journey into local history through an immersive 360° VR experience. As part of our research approach, we conducted pre- and post-intervention assessments to gauge participants’ grasp of the content and further distributed psychometric instruments to evaluate their reception of VR as an instructional approach. The analysis indicates that VR’s immersive elements enhance knowledge acquisition but the impact is modulated by the complexity of the subject matter. Additionally, the study reveals that a tailored, context-sensitive, instructional design is paramount for optimising learning outcomes and mitigating educational inequities. This work challenges the “one-size-fits-all” approach to educational VR, advocating for a more targeted instructional approach. Consequently, it emphasises the need for educators and VR developers to collaboratively tailor interventions that are both culturally and contextually relevant. Full article