Computers

Noise filtering is a crucial task in digital image processing, performing the function of preprocessing. In this paper, we propose an algorithm that employs deep convolution and soft thresholding iterative algorithms to extract and learn the features of noisy images. The extracted features are acquired through prior and sparse representation theory for image reconstruction. Effective separation of the image and noise is achieved using an end-to-end network of dilated convolution and fully connected layers. Several experiments were performed on public images subject to various levels of Gaussian noise, in order to evaluate the effectiveness of the proposed approach. The results indicated that our algorithm achieved a high peak signal-to-noise ratio (PSNR) and significantly improved the visual effects of the images. Our study supports the effectiveness of our approach and substantiates its potential to be applied to a broad spectrum of image processing tasks. Full article

Highly-skilled migrants and refugees finding employment in low-skill vocations, despite professional qualifications and educational backgrounds, has become a global tendency, mainly due to the language barrier. Employment prospects for displaced communities are mostly decided by their knowledge of the sublanguage of the vocational domain they are interested in working. Common vocational domains include agriculture, cooking, crafting, construction, and hospitality. The increasing amount of user-generated content in wikis and social networks provides a valuable source of data for data mining, natural language processing, and machine learning applications. This paper extends the contribution of the authors’ previous research on automatic vocational domain identification by further analyzing the results of machine learning experiments with a domain-specific textual data set while considering two research directions: a. prediction analysis and b. data balancing. Wrong prediction analysis and the features that contributed to misclassification, along with correct prediction analysis and the features that were the most dominant, contributed to the identification of a primary set of terms for the vocational domains. Data balancing techniques were applied on the data set to observe their impact on the performance of the classification model. A novel four-step methodology was proposed in this paper for the first time, which consists of successive applications of SMOTE oversampling on imbalanced data. Data oversampling obtained better results than data undersampling in imbalanced data sets, while hybrid approaches performed reasonably well. Full article

As more and more devices are being deployed across networks to gather data and use them to perform intelligent tasks, it is vital to have a tool to perform real-time data analysis. Data are the backbone of Machine Learning models, the core of intelligent systems. Therefore, verifying whether the data being gathered are similar to those used for model building is essential. One fantastic tool for the performance of data analysis is the 0-Dimensional Persistent Diagrams, which can be computed in a Resource-Scarce Embedded System (RSES), a set of memory and processing-constrained devices that are used in many IoT applications because they are cost-effective and reliable. However, it is challenging to compare Persistent Diagrams, and Persistent Landscapes are used because they allow Persistent Diagrams to be passed to a space where the mean concept is well-defined. The following work shows how one can perform a Persistent Landscape analysis in an RSES. It also shows that the distance between two Persistent Landscapes makes it possible to verify whether two devices collect the same data. The main contribution of this work is the implementation of Persistent Landscape analysis in an RSES, which is not provided in the literature. Moreover, it shows that devices can now verify, in real-time, whether they can trust the data being collected to perform the intelligent task they were designed to, which is essential in any system to avoid bugs or errors. Full article

Recommender systems are widely used in various fields, such as e-commerce, entertainment, and education, to provide personalized recommendations to users based on their preferences and/or behavior. Τhis paper presents a novel approach to providing customized recommendations with the use of user-centric artificial intelligence. In greater detail, we introduce an enhanced collaborative filtering (CF) approach in order to develop hybrid recommender systems that personalize search results for users. The proposed CF enhancement incorporates user actions beyond explicit ratings to collect data and alleviate the issue of sparse data, resulting in high-quality recommendations. As a testbed for our research, a web-based digital library, incorporating the proposed algorithm, has been developed. Examples of operation of the use of the system are presented using cognitive walkthrough inspection, which demonstrates the effectiveness of the approach in producing personalized recommendations and improving user experience. Thus, the hybrid recommender system, which is incorporated in the digital library, has been evaluated, yielding promising results. Full article

The Cultural Crowd–Artificial Neural Network (CC-ANN) takes the cultural dimensions of a crowd into account, based on Hofstede Cultural Dimensions (HCDs), to predict social and physical behavior concerning cohesion, collectivity, speed, and distance. This study examines the impact of applying the CC-ANN learning model on more cultures to test the effect of predicting crowd behavior and the relationships among their characteristics. Our previous work which applied the CC-ANN only included eight nations using the six HCDs. In this paper, we including the United Arab Emirates (UAE) in the CC-ANN as a new culture which aided a comparative study with four HCDs, with and without the UAE, using Mean Squared Error (MSE) for evaluation. The results indicated that most of the best-case experiments involved the UAE having the lowest MSE: 0.127, 0.014, and 0.010, which enhanced the CC-ANN model’s ability to predict crowd behavior. Moreover, the links between the cultural, sociological, and physical properties of crowds can be seen from a broader perspective with stronger correlations using the CC-ANN in more countries with diverse cultures. Full article

Smart contracts (SCs) are digital agreements that execute themselves and are stored on a blockchain. Despite the fact that they offer numerous advantages, such as automation and transparency, they are susceptible to a variety of assaults due to their complexity and lack of standardization. In this paper, we investigate the use of artificial intelligence (AI) to improve SC security. We provide an overview of Smart Contracts (SCs) and blockchain technology, as well as a discussion of possible SC-based attacks. Then, we introduce various AI categories and their applications in cybersecurity, followed by a thorough analysis of how AI can be used to enhance SC security. We also highlight the open questions and future directions of research in this field. Our research demonstrates that AI can provide an effective defense against assaults on SCs and contribute to their security and dependability. This article lays the groundwork for future research in the field of AI for SC security. Full article

The simultaneous advances in deep learning and the Internet of Things (IoT) have benefited distributed deep learning paradigms. Federated learning is one of the most promising frameworks, where a server works with local learners to train a global model. The intrinsic heterogeneity of IoT devices, or non-independent and identically distributed (Non-I.I.D.) data, combined with the unstable communication network environment, causes a bottleneck that slows convergence and degrades learning efficiency. Additionally, the majority of weight averaging-based model aggregation approaches raise questions about learning fairness. In this paper, we propose a peer-to-peer federated learning (P2PFL) framework based on Vision Transformers (ViT) models to help solve some of the above issues and classify COVID-19 vs. normal cases on Chest-X-Ray (CXR) images. Particularly, clients jointly iterate and aggregate the models in order to build a robust model. The experimental results demonstrate that the proposed approach is capable of significantly improving the performance of the model with an Area Under Curve (AUC) of 0.92 and 0.99 for hospital-1 and hospital-2, respectively. Full article

Starting in late 2019, the coronavirus SARS-CoV-2 began spreading around the world and causing disruption in both daily life and healthcare systems. The disease is estimated to have caused more than 6 million deaths worldwide [WHO]. The pandemic and the global reaction to it severely affected the world economy, causing a significant increase in global inflation rates, unemployment, and the cost of energy commodities. To stop the spread of the virus and dampen its global effect, it is imperative to detect infected patients early on. Convolutional neural networks (CNNs) can effectively diagnose a patient’s chest X-ray (CXR) to assess whether they have been infected. Previous medical image classification studies have shown exceptional accuracies, and the trained algorithms can be shared and deployed using a computer or a mobile device. CNN-based COVID-19 detection can be employed as a supplement to reverse transcription-polymerase chain reaction (RT-PCR). In this research work, 11 ensemble networks consisting of 6 CNN architectures and a classifier layer are evaluated on their ability to differentiate the CXRs of patients with COVID-19 from those of patients that have not been infected. The performance of ensemble models is then compared to the performance of individual CNN architectures. The best ensemble model COVID-19 detection accuracy was achieved using the logistic regression ensemble model, with an accuracy of 96.29%, which is 1.13% higher than the top-performing individual model. The highest F1-score was achieved by the standard vector classifier ensemble model, with a value of 88.6%, which was 2.06% better than the score achieved by the best-performing individual model. This work demonstrates that combining a set of top-performing COVID-19 detection models could lead to better results if the models are integrated together into an ensemble. The model can be deployed in overworked or remote health centers as an accurate and rapid supplement or back-up method for detecting COVID-19. Full article

There are many uses for machine learning in everyday life and there is a steady increase in the field of medicine; the use of such technologies facilitates the tiresome work of health professionals by either automating repetitive tasks or making them simpler. Bed-related disorders are a great example where tedious tasks could be facilitated by machine learning algorithms, as suggested by many authors, by providing information on the posture of a particular bedded patient to health professionals. To assess the already existing studies in this field, this study provides a systematic review where the literature is analyzed to find correlations between the various factors involved in the making of such a system and how they perform. The overall findings suggest that there is only a significant relationship between the postures considered for classification and the resulting accuracy, despite some other factors such as the amount of data available providing some differences according to the type of algorithm used, with neural networks needing larger datasets. This study aims to increase awareness in this field and give future researchers information based on previous works’ strengths and limitations while giving some suggestions based on the literature review. Full article

The Internet of Things (IoT) integrates different advanced technologies in which a wireless sensor network (WSN) with many smart micro-sensor nodes is an important portion of building various IoT applications such as smart agriculture systems, smart healthcare systems, smart home or monitoring environments, etc. However, the limited energy resources of sensors and the harsh properties of the WSN deployment environment make routing a challenging task. To defeat this routing quandary, an energy-efficient routing protocol based on grid cells (EEGT) is proposed in this study to improve the lifespan of WSN-based IoT applications. In EEGT, the whole network region is separated into virtual grid cells (clusters) at which the number of sensor nodes is balanced among cells. Then, a cluster head node (CHN) is chosen according to the residual energy and the distance between the sink and nodes in each cell. Moreover, to determine the paths for data delivery inside the cell with small energy utilization, the Kruskal algorithm is applied to connect nodes in each cell and their CHN into a minimum spanning tree (MST). Further, the ant colony algorithm is also used to find the paths of transmitting data packets from CHNs to the sink (outside cell) to reduce energy utilization. The simulation results show that the performance of EEGT is better than the three existing protocols, which are LEACH-C (low energy adaptive clustering hierarchy), PEGASIS (power-efficient gathering in sensor information systems), and PEGCP (maximizing WSN life using power-efficient grid-chain routing protocol) in terms of improved energy efficiency and extended the lifespan of the network. Full article

Recent developments, begun by the ascending spiral of the anticipated endless prospects of ChatGPT, promote artificial intelligence (AI) as an indispensable tool and commodity whose time has come. Yet the sinister specter of a technology that has hidden and unmanageable attributes that might be harmful to society looms in the background, as well as the likelihood that it will never deliver on the purported promise of artificial general intelligence (AGI). Currently, the prospects for the development of AI and AGI are more a matter of opinion than based on a consistent methodological approach. Thus, there is a need to take a step back to develop a general framework from which to evaluate current AI efforts, which also permits the determination of the limits to its future prospects as AGI. To gain insight into the development of a general framework, a key question needs to be resolved: what is the connection between human intelligence and machine intelligence? This is the question that needs a response because humans are at the center of AI creation and realize that, without an understanding of how we become what we become, we have no chance of finding a solution. This work proposes info-autopoiesis, the self-referential, recursive, and interactive process of self-production of information, as the needed general framework. Info-autopoiesis shows how the key ingredient of information is fundamental to an insightful resolution to this crucial question and allows predictions as to the present and future of AGI. Full article

This paper proposes the use of the GNS3 IP network modeling platform to study/verify whether the exchanged information between power electronic devices and a control center (Monitoring and Control Centre) is secure. For the purpose of this work, a power distribution unit (PDU) and a UPS (Uninterruptable Power Supply) that are used by internet service providers are studied. Capsa Free network analyzer and Wireshark network protocol analyzer were used as supporting tools. A working model of an IP network in GNS3 has been created through which this research has been carried out. In addition to checking whether the exchanged information is secure, a characterization of the generated traffic has been made, showing results for the generated traffic and which ports generate the most traffic. These carried-outstudies show that the exchanged information is not secure. As a way to secure the exchanged information, the use of VPN (Virtual Private Network) technology is proposed; thanks to a VPN, the exchange of information is secure. The obtained results confirm this and validate the applicability of GNS3 to test/study whether data exchange between power electronic devices and a control center is secure. Full article

In the new global scene, digital skills are a key skill for students to seize new learning opportunities, train to meet the demands of the labor market, and compete in the global market, while also communicating effectively in their everyday and academic lives. This article presents research aimed at relating the impact of personal variables on the digital competence of technical problem solving in Spanish students from 12 to 14 years old. A quantitative methodology with a cross-sectional design was employed. A sample of 772 students from 18 Spanish educational institutions was used. For data collection, an assessment test was designed (ECODIES^®) based on a validated indicator model to evaluate learners’ digital competence (INCODIES^®), taking as a model the European framework for the development of digital competence. Mediation models were used and theoretical reference models were created. The results allowed us to verify the influence of personal, technology use, and attitudinal variables in the improvement of digital skill in technical problem solving. The findings lead to the conclusion that gender, acquisition of digital devices, and regular use do not determine a better level of competence. Full article

A growing number of services and applications are developed using multimedia sensing low-cost wireless devices, thus creating the Internet of Multimedia Things (IoMT). Nevertheless, energy efficiency and resource availability are two of the most challenging issues to overcome when developing image-based sensing applications. In depth, image-based sensing and transmission in IoMT significantly drain the sensor energy and overwhelm the network with redundant data. Event-based sensing schemes can be used to provide efficient data transmission and an extended network lifetime. This paper proposes a novel approach for distributed event-based sensing achieved by a cluster of processing nodes. The proposed scheme aims to balance the processing load across the nodes in the cluster. This study demonstrates the adequacy of distributed processing to extend the lifetime of the IoMT platform and compares the efficiency of Haar wavelet decomposition and general Fourier descriptors (GFDs) as a feature extraction module in a distributed features-based target recognition system. The results show that the distributed processing of the scheme based on the Haar wavelet transform of the image outperforms the scheme based on a general Fourier shape descriptor in recognition accuracy of the target as well as the energy consumption. In contrast to a GFD-based scheme, the recognition accuracy of a Haar-based scheme was increased by 26%, and the number of sensing cycles was increased from 40 to 70 cycles, which attests to the adequacy of the proposed distributed Haar-based processing scheme for deployment in IoMT devices. Full article

Collective cell movement is an indication of phenomena such as wound healing, embryonic morphogenesis, cancer invasion, and metastasis. Wound healing is a complicated cellular and biochemical procedure in which skin cells migrate from the wound boundaries into the wound area to reconstruct the injured skin layer(s). In vitro analysis of cell migration is an effective assay for measuring changes in cell migratory complement in response to experimental inspections. Open-source segmentation software (e.g., an ImageJ plug-in) is available to analyze images of in vitro scratch wound healing assays; however, often, these tools are error-prone when applied to, e.g., low-contrast, out-of-focus, and noisy images, and require manual tuning of various parameters, which is imprecise, tedious, and time-consuming. We propose two algorithmic methods (namely log gradient segmentation and entropy filter segmentation) for cell segmentation and the subsequent measurement of the collective cell migration in the corresponding microscopic imagery. We further investigate the effects of image compression on the algorithms’ measurement accuracy, applying lossy compression algorithms (the current ISO standards JPEG2000, JPEG, JPEG-XL and AV1, BPG, and WEBP). We aim to identify the most suitable compression algorithm that can be used for this purpose, relating rate–distortion performance as measured in terms of peak signal-to-noise ratio (PSNR) and the multiscale structural similarity index (MS-SSIM) to the segmentation accuracy obtained by the segmentation algorithms. The experimental results show that the log gradient segmentationalgorithm provides robust performance for segmenting the wound area, whereas the entropy filter segmentation algorithm is unstable for this purpose under certain circumstances. Additionally, the best-suited compression strategy is observed to be dependent on (i) the segmentation algorithm used and (ii) the actual data sequence being processed. Full article

Mobile applications are developed and released to the market every day. Due to the intense usage of mobile applications, their quality matters. End users’ rejection of mobile apps increases from time to time due to their low quality and lack of proper mobile testing. This indicates that the role of mobile application testing is crucial in the acceptance of a given software product. Test engineers use automation frameworks for testing their mobile applications. Automated testing brings several advantages to the development team. For example, automated checks are used for regression testing, fast execution of test scripts, and providing quick feedback for the development team. A systematic literature review has been used to identify and collect evidence on automated testing frameworks for mobile application testing. A total of 56 relevant research papers were identified that were published in prominent journals and conferences until February 2023. The results were summarized and tabulated to provide insights into the suitability of the existing automation testing framework for mobile application testing. We identified the major test concerns and test challenges in performing mobile automation testing. The results showed that the keyword-driven testing framework is the widely used approach, but recently, hybrid approaches have been adopted for mobile test automation. On the other hand, this review indicated that the existing frameworks need to be customized using reusable and domain-specific keywords to make them suitable for mobile application testing. Considering this, this study proposes an architecture, the mobile-based automation testing framework (MATF). In the future, to address the mobile application testing challenges, the authors will work on implementing the proposed framework (MATF). Full article

Open laboratories (OpenLabs) in Cultural Heritage institutions are an effective way to provide visibility into the behind-the-scenes processes and promote documentation data collected and produced by domain specialists. However, presenting these processes without proper explanation or communication with specialists may cause issues in terms of visitors’ understanding. To support OpenLabs and disseminate information, digital media and efficient data management can be utilized. The CAnTi (Conservation of Ancient Tiryns) project seeks to design and implement virtual and mixed reality applications that visualize conservation and restoration data, supporting OpenLab operations at the Acropolis of Ancient Tiryns. Semantic Web technologies will be used to model the digital content, facilitating organization and interoperability with external sources in the future. These applications will be part of the OpenLab activities on the site, enhancing visitors’ experiences and understanding of current and past conservation and restoration practices. Full article

Due to its high transmissibility, the COVID-19 pandemic has placed an unprecedented burden on healthcare systems worldwide. X-ray imaging of the chest has emerged as a valuable and cost-effective tool for detecting and diagnosing COVID-19 patients. In this study, we developed a deep learning model using transfer learning with optimized DenseNet-169 and DenseNet-201 models for three-class classification, utilizing the Nadam optimizer. We modified the traditional DenseNet architecture and tuned the hyperparameters to improve the model’s performance. The model was evaluated on a novel dataset of 3312 X-ray images from publicly available datasets, using metrics such as accuracy, recall, precision, F1-score, and the area under the receiver operating characteristics curve. Our results showed impressive detection rate accuracy and recall for COVID-19 patients, with 95.98% and 96% achieved using DenseNet-169 and 96.18% and 99% using DenseNet-201. Unique layer configurations and the Nadam optimization algorithm enabled our deep learning model to achieve high rates of accuracy not only for detecting COVID-19 patients but also for identifying normal and pneumonia-affected patients. The model’s ability to detect lung problems early on, as well as its low false-positive and false-negative rates, suggest that it has the potential to serve as a reliable diagnostic tool for a variety of lung diseases. Full article

High mobility has promoted the concentration of people’s aggregation in urban areas. As people pursue areas with higher density, gentrification and sprawl become more serious. Disadvantaged people are then pushed out of urban centers. Conversely, as mobility increases, the disadvantaged may also migrate in pursuit of their desired density. As a result, disparities relative to density and housing may shrink. Hence, migration is a complex system. Understanding the effects of migration on disparities intuitively is difficult. This study explored the effects of mobility on disparity using an agent-based model of opinion formation. We find that as mobility increases, disparities between agents in density and diversity widen, but as mobility increases further, the disparities shrink, and then widen again. Our results present possibilities for a just city in the age of mobility. Full article