Information, Volume 14, Issue 1 (January 2023) – 56 articles

Orthopairs (pairs of disjoint sets) have points in common with many approaches to managing vaguness/uncertainty such as fuzzy sets, rough sets, soft sets, etc. Indeed, they are successfully employed to address partial knowledge, consensus, and borderline cases. One of the generalized versions of orthopairs is intuitionistic fuzzy sets which is a well-known theory for researchers interested in fuzzy set theory. To extend the area of application of fuzzy set theory and address more empirical situations, the limitation that the grades of membership and non-membership must be calibrated with the same power should be canceled. To this end, we dedicate this manuscript to introducing a generalized frame for orthopair fuzzy sets called “$(m,n)$-Fuzzy sets”, which will be an efficient tool to deal with issues that require different importances for the degrees of membership and non-membership and cannot be addressed by the fuzzification tools existing in the published literature. We first establish its fundamental set of operations and investigate its abstract properties that can then be transmitted to the various models they are in connection with. Then, to rank $(m,n)$-Fuzzy sets, we define the functions of score and accuracy, and formulate aggregation operators to be used with $(m,n)$-Fuzzy sets. Ultimately, we develop the successful technique “aggregation operators” to handle multi-criteria decision-making problems in the environment of $(m,n)$-Fuzzy sets. The proposed technique has been illustrated and analyzed via a numerical example. Full article

Deep learning has significantly boosted the performance improvement of automatic speech recognition (ASR) with the cooperation of large amounts of data resources. For minority languages, however, there are almost no large-scale data resources, limiting the development of ASR technologies in these languages. In this paper, we publish a free Kirghiz speech database accompanied by associated language resources. The entire database involves 128 h of speech data from 163 speakers and corresponding transcriptions. To our knowledge, this is the largest Kirghiz speech database that is dedicated to the ASR task and is publicly free so far. In addition, we also provide several baseline systems based on Kaldi and WeNet to demonstrate how these public data resources can be used to facilitate the Kirghiz ASR research. This publication is a part of the M2ASR project, and all the resources can be downloaded at the project webpage. Full article

Educational data mining is capable of producing useful data-driven applications (e.g., early warning systems in schools or the prediction of students’ academic achievement) based on predictive models. However, the class imbalance problem in educational datasets could hamper the accuracy of predictive models as many of these models are designed on the assumption that the predicted class is balanced. Although previous studies proposed several methods to deal with the imbalanced class problem, most of them focused on the technical details of how to improve each technique, while only a few focused on the application aspect, especially for the application of data with different imbalance ratios. In this study, we compared several sampling techniques to handle the different ratios of the class imbalance problem (i.e., moderately or extremely imbalanced classifications) using the High School Longitudinal Study of 2009 dataset. For our comparison, we used random oversampling (ROS), random undersampling (RUS), and the combination of the synthetic minority oversampling technique for nominal and continuous (SMOTE-NC) and RUS as a hybrid resampling technique. We used the Random Forest as our classification algorithm to evaluate the results of each sampling technique. Our results show that random oversampling for moderately imbalanced data and hybrid resampling for extremely imbalanced data seem to work best. The implications for educational data mining applications and suggestions for future research are discussed. Full article

Machine learning (ML) techniques discover knowledge from large amounts of data. Modeling in ML is becoming essential to software systems in practice. The accuracy and efficiency of ML models have been focused on ML research communities, while there is less attention on validating the qualities of ML models. Validating ML applications is a challenging and time-consuming process for developers since prediction accuracy heavily relies on generated models. ML applications are written by relatively more data-driven programming based on the black box of ML frameworks. All of the datasets and the ML application need to be individually investigated. Thus, the ML validation tasks take a lot of time and effort. To address this limitation, we present a novel quality validation technique that increases the reliability for ML models and applications, called MLVal. Our approach helps developers inspect the training data and the generated features for the ML model. A data validation technique is important and beneficial to software quality since the quality of the input data affects speed and accuracy for training and inference. Inspired by software debugging/validation for reproducing the potential reported bugs, MLVal takes as input an ML application and its training datasets to build the ML models, helping ML application developers easily reproduce and understand anomalies in the ML application. We have implemented an Eclipse plugin for MLVal that allows developers to validate the prediction behavior of their ML applications, the ML model, and the training data on the Eclipse IDE. In our evaluation, we used 23,500 documents in the bioengineering research domain. We assessed the ability of the MLVal validation technique to effectively help ML application developers: (1) investigate the connection between the produced features and the labels in the training model, and (2) detect errors early to secure the quality of models from better data. Our approach reduces the cost of engineering efforts to validate problems, improving data-centric workflows of the ML application development. Full article

Drowning is one of the top five causes of death for children aged 1–14 worldwide. According to data from the World Health Organization (WHO), drowning is the third most common reason for unintentional fatalities. Designing a drowning detection system is becoming increasingly necessary in order to ensure the safety of swimmers, particularly children. This paper presents a computer vision and deep learning-based early drowning detection approach. We utilized five convolutional neural network models and trained them on our data. These models are SqueezeNet, GoogleNet, AlexNet, ShuffleNet, and ResNet50. ResNet50 showed the best performance, as it achieved 100% prediction accuracy with a reasonable training time. When compared to other approaches, the proposed approach performed exceptionally well in terms of prediction accuracy and computational cost. Full article

This research study aims to examine the possibilities of Hyperledger Fabric (HLF) in the healthcare sector. The study addresses the gap in the knowledge base through developing customization techniques to enable the simplicity and efficacy of Electronic Medical Records (EMR) adoption for healthcare industry applications. The focus of this research explores methods of using blockchain technology that prioritise users. The investigation of several concepts used in developing web applications has been determined. The study identified that an open-source project, known as Hyperledger Fabric, can be utilised to construct a novel method of storing EMRs. The framework provides a test network that can be customised to satisfy the need of several projects, including storing medical records. This research additionally outlines the difficulties encountered and problems that need to be resolved before Hyperledger Fabric can be successfully implemented in healthcare systems. Considering all types of blockchains available, the needs are met by Hyperledger Fabric, which offers a distributed and secure environment for healthcare systems. Blockchain has the potential to transform healthcare by putting the patient at the centre of the system and enhancing health data protection and interoperability. Also, by using grant and revoke access mechanisms, patients have complete control over their medical information as well as authorized doctors who are allowed to view records. This functionality is made possible by the chaincode defined in the blockchain platform. The research study has both practitioner and research implications for the development of secure blockchain-based EMRs. Full article

Spot welding is a critical joining process which presents specific challenges in early defect detection, has high rework costs, and consumes excessive amounts of materials, hindering effective, sustainable production. Especially in automotive manufacturing, the welding source’s quality needs to be controlled to increase the efficiency and sustainable performance of the production lines. Using data analytics, manufacturing companies can control and predict the welding parameters causing problems related to resource quality and process performance. In this study, we aimed to define the root cause of welding defects and solve the welding input value range problem using machine learning algorithms. In an automotive production line application, we analyzed real-time IoT data and created variables regarding the best working range of welding input parameters required in the inference analysis for expulsion reduction. The results will help to provide guidelines and parameter selection approaches to model ML-based solutions for the optimization problems associated with welding. Full article

To date, information retrieval methods in the medical field have mainly focused on English medical reports, but little work has studied Chinese electronic medical reports, especially in the field of obstetrics and gynecology. In this paper, a dataset of 180,000 complete Chinese ultrasound reports in obstetrics and gynecology was established and made publicly available. Based on the ultrasound reports in the dataset, a new information retrieval method (IKAR) is proposed to extract key information from the ultrasound reports and automatically generate the corresponding ultrasound diagnostic results. The model can both extract what is already in the report and analyze what is not in the report by inference. After applying the IKAR method to the dataset, it is proved that the method could achieve 89.38% accuracy, 91.09% recall, and 90.23% F-score. Moreover, the method achieves an F-score of over 90% on 50% of the 10 components of the report. This study provides a quality dataset for the field of electronic medical records and offers a reference for information retrieval methods in the field of obstetrics and gynecology or in other fields. Full article

The group testing idea is an efficient infection identification approach based on pooling the test samples of a group of individuals, which results in identification with less number of tests than individually testing the population. In our work, we propose a novel infection spread model based on a random connection graph which represents connections between n individuals. Infection spreads via connections between individuals, and this results in a probabilistic cluster formation structure as well as non-i.i.d. (correlated) infection statuses for individuals. We propose a class of two-step sampled group testing algorithms where we exploit the known probabilistic infection spread model. We investigate the metrics associated with two-step sampled group testing algorithms. To demonstrate our results, for analytically tractable exponentially split cluster formation trees, we calculate the required number of tests and the expected number of false classifications in terms of the system parameters, and identify the trade-off between them. For such exponentially split cluster formation trees, for zero-error construction, we prove that the required number of tests is $O\left({log}_{2}n\right)$. Thus, for such cluster formation trees, our algorithm outperforms any zero-error non-adaptive group test, binary splitting algorithm, and Hwang’s generalized binary splitting algorithm. Our results imply that, by exploiting probabilistic information on the connections of individuals, group testing can be used to reduce the number of required tests significantly even when the infection rate is high, contrasting the prevalent belief that group testing is useful only when the infection rate is low. Full article

The largest source of information in healthcare during the present epidemic is radiological imaging, which is also one of the most difficult sources to interpret. Clinicians today are forced to rely heavily on therapeutic image analysis that has been filtered and sometimes performed by worn-out radiologists. Transmission of these medical data increases in frequency due to patient overflow, and protecting confidentiality, along with integrity and availability, emerges as one of the most crucial components of security. Medical images generally contain sensitive information about patients and are therefore vulnerable to various security threats during transmission over public networks. These images must be protected before being transmitted over this network to the public. In this paper, an efficient SCAN and chaotic-map-based image encryption model is proposed. This paper describes pixel value and pixel position manipulation based on SCAN and chaotic theory. The SCAN method involves translating an image’s pixel value to a different pixel value and rearranging pixels in a predetermined order. A chaotic map is used to shift the positions of the pixels within the block. Decryption follows the reverse process of encryption. The effectiveness of the suggested strategy is evaluated by computing the histogram chi-square test, MSE, PSNR, NPCR, UACI, SSIM, and UQI. The efficiency of the suggested strategy is demonstrated by comparison analysis. The results of analysis and testing show that the proposed program can achieve the concept of partial encryption. In addition, simulation experiments demonstrate that our approach has both a faster encryption speed and higher security when compared to existing techniques. Full article

In this paper, aiming at the severe problems of UWB positioning in NLOS-interference circumstances, a complete method is proposed for NLOS/LOS classification, NLOS identification and mitigation, and a final accurate UWB coordinate solution through the integration of two machine learning algorithms and a hybrid localization algorithm, which is called the C-T-CNN-SVM algorithm. This algorithm consists of three basic processes: an LOS/NLOS signal classification method based on SVM, an NLOS signal recognition and error elimination method based on CNN, and an accurate coordinate solution based on the hybrid weighting of the Chan–Taylor method. Finally, the validity and accuracy of the C-T-CNN-SVM algorithm are proved through a comparison with traditional and state-of-the-art methods. (i) Focusing on four main prediction errors (range measurements, maxNoise, stdNoise and rangeError), the standard deviation decreases from 13.65 cm to 4.35 cm, while the mean error decreases from 3.65 cm to 0.27 cm, and the errors are practically distributed normally, demonstrating that after training a SVM for LOS/NLOS signal classification and a CNN for NLOS recognition and mitigation, the accuracy of UWB range measurements may be greatly increased. (ii) After target positioning, the proposed method can realize a one-dimensional X-axis and Y-axis accuracy within 175 mm, and a Z-axis accuracy within 200 mm; a 2D ($X,Y$) accuracy within 200 mm; and a 3D accuracy within 200 mm, most of which fall within (100 mm, 100 mm, 100 mm). (iii) Compared with the traditional algorithms, the proposed C-T-CNN-SVM algorithm performs better in location accuracy, cumulative error probability (CDF), and root-mean-square difference (RMSE): the 1D, 2D, and 3D accuracy of the proposed method is 2.5 times that of the traditional methods. When the location error is less than 10 cm, the CDF of the proposed algorithm only reaches a value of 0.17; when the positioning error reaches 30 cm, only the CDF of the proposed algorithm remains in an acceptable range. The RMSE of the proposed algorithm remains ideal when the distance error is greater than 30 cm. The results of this paper and the idea of a combination of machine learning methods with the classical locating algorithms for improved UWB positioning under NLOS interference could meet the growing need for wireless indoor locating and communication, which indicates the possibility for the practical deployment of such a method in the future. Full article

Heterogeneous test processes concerning test goals and test script languages are an integral part of mechatronic systems development in supply chains. Here, test cases are written in a multitude of different test script languages. The translation between test script languages is possible, a joint understanding and a holistic view of the mechatronic system as a system under test is only achieved in the minds of experienced test engineers. This joined-up information is called test knowledge and is the key input for test automation and in turn, it is essential for reducing the cost of product development. Persisted test knowledge enables the search for patterns semi-automatically without reading countless test cases and enables the auto-completion of essential parts of test cases. In this paper, we developed a knowledge graph that aggregates all the test knowledge automatically and integrates it into the test processes. We derived an explorative search that simplifies the test case creation. For that purpose, a corresponding user-friendly query language, and unidirectional translation capabilities were developed that translates a test case into a graph tailored to the target audience of test engineers. We demonstrated the usage and impact of this approach by evaluating it on test cases from aircraft cabin doors. Full article

We consider the storage–retrieval rate trade-off in private information retrieval (PIR) systems using a Shannon-theoretic approach. Our focus is mostly on the canonical two-message two-database case, for which a coding scheme based on random codebook generation and the binning technique is proposed. This coding scheme reveals a hidden connection between PIR and the classic multiple description source coding problem. We first show that when the retrieval rate is kept optimal, the proposed non-linear scheme can achieve better performance over any linear scheme. Moreover, a non-trivial storage-retrieval rate trade-off can be achieved beyond space-sharing between this extreme point and the other optimal extreme point, achieved by the retrieve-everything strategy. We further show that with a method akin to the expurgation technique, one can extract a zero-error PIR code from the random code. Outer bounds are also studied and compared to establish the superiority of the non-linear codes over linear codes. Full article

Governments are altering how they operate to enhance the provision of public services, be more successful and efficient in their plans, and accomplish goals such as greater transparency, interoperability, and citizen pleasure. There are, however, limited studies about how public sector managers are currently identifying digital transformation in their own day-to-day practices, how they are implementing digital transformation projects, and what their expected results are, aside from the reports provided by consulting firms. The aim of this article is to present a case study in order to gain an understanding of the current expectations that public managers have regarding the implementation of digital transformation projects, as well as the outcomes that they anticipate these projects will produce. A qualitative analysis was conducted based on experts who were involved in digital transformation projects with a thorough understanding of government decisions and in-depth knowledge of execution procedures. Based on the results derived from interviews, this paper aims to support managers in examining the barriers of digital transformation in the public sector in order to improve this process. Full article

Penang Youth Development Corporation took the “Penang Young Digital Talent Program” initiative to bridge the gap between Malaysian youth’s current digital skills and emerging technologies market demands. The program comprises different online courses such as web design, digital marketing, etc. The objective of this study is to understand the level of participants’ digital competency and, secondly, investigate the impact of participants’ digital competency on their perceived employability and examine the mediating role of course quality. This study employed a cross-section design method, and data were collected using purposive sampling. The participants (Nn= 385) of this program range from 18 to 22 years old, either born in Penang or have resided in Penang for a minimum of 3 years. The data were analyzed using Smart PLS 3.0. Post-online course findings show that digital content creation, information and data literacy, and problem-solving have a significant and positive relationship with perceived employability. Moreover, course quality significantly mediates the impact of communication and collaboration, digital safety and information and data literacy on the perceived employability of Malaysian youth. The findings of this research have implications for policymakers responsible for education, emphasizing youth’s acquisition of digital skills to help them succeed in the current workplace. Full article

Owing to the prevalence of the Internet of things (IoT) devices connected to the Internet, the number of IoT-based attacks has been growing yearly. The existing solutions may not effectively mitigate IoT attacks. In particular, the advanced network-based attack detection solutions using traditional Intrusion detection systems are challenging when the network environment supports traditional as well as IoT protocols and uses a centralized network architecture such as a software defined network (SDN). In this paper, we propose a long short-term memory (LSTM) based approach to detect network attacks using SDN supported intrusion detection system in IoT networks. We present an extensive performance evaluation of the machine learning (ML) and deep learning (DL) model in two SDNIoT-focused datasets. We also propose an LSTM-based architecture for the effective multiclass classification of network attacks in IoT networks. Our evaluation of the proposed model shows that our model effectively identifies the attacks and classifies the attack types with an accuracy of 0.971. In addition, various visualization methods are shown to understand the dataset’s characteristics and visualize the embedding features. Full article

Location-Aware Beamforming (LAB) in Ultra-Dense Networks (UDN) is a breakthrough technology for 5G New Radio (NR) and Beyond 5G (B5G) millimeter wave (mmWave) communication. Directional links with narrow antenna half-power beamwidth (HPBW) and massive multiple-input multiple-output (mMIMO) processing systems allows to increase transmitter and receiver gains and thus facilitates to overcome high path loss in mmWave. Well known problem of pencil beamforming (BF) is in construction of precoding vectors at the transmitter and combining vectors at the receiver during directional link establishing and its maintaining. It is complicated by huge antenna array (AA) size and required channel state information (CSI) exchange, which is time consuming for vehicle user equipment (UE). Knowledge of transmitter and receiver location, UE or gNodeB (gNB), could significantly alleviate directional link establishment and space division multiple access (SDMA) implementation. Background of SDMA is in efficient maintenance of affordable level of interference, and the purpose of this research is in signal-to-interference ratio (SIR) evaluation in various 5G UDN scenarios with LAB. The method, used to evaluate SIR, is link level simulation, and results are obtained from publicly released open-source simulator. Contribution of research includes substantiation of allowable UE density, working with LAB. Practical implications include recommendations on terrestrial and angular separation of two UE in 5G UDN scenarios. Full article

Information security issues have triggered both academic and practical circles to think about operation management and the sustainable development of information systems. Based on the theory of framing effect, this study constructs a theoretical model of the presentation framework of security notice information on users’ compliance willingness and empirically tests the proposed research hypotheses using a combination of behavioral experiments and questionnaires to analyze the mechanism of the information presentation framework on compliance willingness. The results show that (1) the information presentation framework has a significant effect on users’ decision to comply, but it varies according to specific frameworks. While the attribute and risk frameworks have a significant effect on users’ decision to comply, the goal framework does not have a significant effect on users’ decision to comply. (2) The security notice situation moderates the relationship between the security notice information presentation frame and users’ compliance willingness, but this varies according to the specific situation of the specific framework. The security notice situation moderates the relationship between the attribute framework, the risk framework, and users’ compliance willingness but not the relationship between the goal framework and users’ compliance willingness. (3) Information security cognition has a moderating effect on the relationship between the security notice presentation framework and users’ compliance willingness, but it varies by the specific frameworks. Information security cognition moderates the relationship between attribute frames, risk frames, and users’ compliance willingness but not the relationship between goal frames and users’ compliance willingness. Full article

Extended Reality (XR) technology represents an innovative tool to address the challenges of the present, as it allows for experimentation with new solutions in terms of content creation and its fruition by different types of users. The potential to modulate the experience based on the target audience’s needs and the project’s objectives makes XR suitable for creating new accessibility solutions. The “Includiamoci” project was carried out with the aim of creating workshops on social inclusion through the combination of art and technology. Specifically, the experimentation involved ten young people between the ages of 28 and 50, with cognitive disabilities, who participated in Extended Reality workshops and Art Therapy workshops. In the course of these activities, the outputs obtained were two: a virtual museum, populated by the participants’ works, and a digital set design for a theatrical performance. Through two tests, one on user experience (UX) and one on the degree of well-being, the effectiveness of the entire project was evaluated. In conclusion, the project demonstrated how the adopted solutions were appropriate to the objectives, increasing our knowledge of UX for a target audience with specific user needs and using XR in the context of social inclusion. Full article

A multichannel interaction service is a practice whereby organizations communicate and interact with their existing customers and potential new customers through different channels. This article presents a brief case study of multichannel interaction in healthcare services, which studies the viability of continuous multichannel interaction for personalized healthcare services to enable health professionals to follow up and monitor patients in home-based care. Furthermore, this study aims to explore the possibility of the continuity and complementarity of the interactions across different communication channels with the patients. The data used for this study was gathered during the first wave of the COVID-19 pandemic. This study showed that despite this type of interaction being relatively new in healthcare services, it has considerable potential for improving the relationship between patients, health professionals, and care providers. Upon completion of the data analysis, several conclusions were drawn. One such conclusion was the ability to maintain continuity of interaction across multiple channels, as well as the synergy between the different channels of interaction available to patients and the impact this has on the way patients and health professionals interact. Additionally, it was determined that the complementarity of different interaction channels is crucial when implementing multichannel interaction services. Furthermore, the implementation of this solution resulted in improved communication between patients and health professionals. Also, it has decreased health professional’s workload and reduced care providers costs regarding remote patient follow-up. Full article

Diabetic foot ulcer (DFU) is one of the major complications of diabetes and results in the amputation of lower limb if not treated timely and properly. Despite the traditional clinical approaches used in DFU classification, automatic methods based on a deep learning framework show promising results. In this paper, we present several end-to-end CNN-based deep learning architectures, i.e., AlexNet, VGG16/19, GoogLeNet, ResNet50.101, MobileNet, SqueezeNet, and DenseNet, for infection and ischemia categorization using the benchmark dataset DFU2020. We fine-tune the weight to overcome a lack of data and reduce the computational cost. Affine transform techniques are used for the augmentation of input data. The results indicate that the ResNet50 achieves the highest accuracy of 99.49% and 84.76% for Ischaemia and infection, respectively. Full article

The emergence of artificial intelligence (AI) and its derivative technologies, such as machine learning (ML) and deep learning (DL), heralds a new era of knowledge management (KM) presentation and discovery. KM necessitates ML for improved organisational experiences, particularly in making knowledge management more discoverable and shareable. Machine learning (ML) is a type of artificial intelligence (AI) that requires new tools and techniques to acquire, store, and analyse data and is used to improve decision-making and to make more accurate predictions of future outcomes. ML demands big data be used to develop a method of data analysis that automates the construction of analytical models for the purpose of improving the organisational knowledge. Knowledge, as an organisation’s most valuable asset, must be managed in automation to support decision-making, which can only be accomplished by activating ML in knowledge management systems (KMS). The main objective of this study is to investigate the extent to which machine learning applications are used in knowledge management applications. This is very important because ML with AI capabilities will become the future of managing knowledge for business survival. This research used a literature review and theme analysis of recent studies to acquire its data. The results of this research provide an overview of the relationship between big data, machine learning, and knowledge management. This research also shows that only 10% of the research that has been published is about machine learning and knowledge management in business and management applications. Therefore, this study gives an overview of the knowledge gap in investigating how ML can be used in KM for business applications in organisations. Full article

Social media usage for news, feedback on services, and even shopping is increasing. Hotel services, food cleanliness and staff behavior are also discussed online. Hotels are reviewed by the public via comments on their websites and social media accounts. This assists potential customers before they book the services of a hotel, but it also creates an opportunity for abuse. Scammers leave deceptive reviews regarding services they never received, or inject fake promotions or fake feedback to lower the ranking of competitors. These malicious attacks will only increase in the future and will become a serious problem not only for merchants but also for hotel customers. To rectify the problem, many artificial intelligence–based studies have performed discourse analysis on reviews to validate their genuineness. However, it is still a challenge to find a precise, robust, and deployable automated solution to perform discourse analysis. A credibility check via discourse analysis would help create a safer social media environment. The proposed study is conducted to perform discourse analysis on fake and real reviews automatically. It uses a dataset of real hotel reviews, containing both positive and negative reviews. Under investigation is the hypothesis that strong, fact-based, realistic words are used in truthful reviews, whereas deceptive reviews lack coherent, structural context. Therefore, frequency weight–based and semantically aware features were used in the proposed study, and a comparative analysis was performed. The semantically aware features have shown strength against the current study hypothesis. Further, holdout and k-fold methods were applied for validation of the proposed methods. The final results indicate that semantically aware features inspire more confidence to detect deception in text. Full article

Deep convolutional neural networks (DCNNs) have manifested significant performance gains for single-image super-resolution (SISR) in the past few years. Most of the existing methods are generally implemented in a fully supervised way using large-scale training samples and only learn the SR models restricted to specific data. Thus, the adaptation of these models to real low-resolution (LR) images captured under uncontrolled imaging conditions usually leads to poor SR results. This study proposes a zero-shot blind SR framework via leveraging the power of deep learning, but without the requirement of the prior training using predefined imaged samples. It is well known that there are two unknown data: the underlying target high-resolution (HR) images and the degradation operations in the imaging procedure hidden in the observed LR images. Taking these in mind, we specifically employed two deep networks for respectively modeling the priors of both the target HR image and its corresponding degradation kernel and designed a degradation block to realize the observation procedure of the LR image. Via formulating the loss function as the approximation error of the observed LR image, we established a completely blind end-to-end zero-shot learning framework for simultaneously predicting the target HR image and the degradation kernel without any external data. In particular, we adopted a multi-scale encoder–decoder subnet to serve as the image prior learning network, a simple fully connected subnet to serve as the kernel prior learning network, and a specific depthwise convolutional block to implement the degradation procedure. We conducted extensive experiments on several benchmark datasets and manifested the great superiority and high generalization of our method over both SOTA supervised and unsupervised SR methods. Full article

The topological structure in vehicular communication networks presents challenges for sustaining network connectivity on the road. Highway dynamics, for example, encourage the need for an adaptive and flexible structure to handle the rapid events of vehicles joining and leaving the road. Such demand aligns with the advancement made in software-defined networks and related dynamic network re-orchestration. This paper discusses the development of a virtual model that represents the operation of an autonomous vehicular network. It also investigates the ability to re-orchestrate the topology through software definition while running the various operational phases. Network self-formation, network expansion, retraction via vehicular members joining and leaving, and network self-healing when a topological rupture occurs as a result of a key member leaving the network are the key grouping phases. The communication approach is analyzed based on the status of network members and their ability to assume the various network roles. The concept is tested using both a Contiki–Cooja network simulator and a MATLAB analytical modeling tool to reflect the operation and performance of the grouping approach under various road scenarios. The outcome of the analysis reflects the ability of the group to be formulated within a measured latency considering the various network parameters such as communication message rate. The approach offers tools for managing the dynamic connectivity of vehicular groups and may also be extended to assume the function of an on-road network digital twin during the lifetime of a given group. Full article

Despite the efforts of the World Health Organization, blood transfusions and delivery are still the crucial challenges in blood supply chain management, especially when there is a high demand and not enough blood inventory. Consequently, reducing uncertainty in blood demand, waste, and shortages has become a primary goal. In this paper, we propose a smart platform-oriented approach that will create a robust blood demand and supply chain able to achieve the goals of reducing uncertainty in blood demand by forecasting blood collection/demand, and reducing blood wastage and shortage by balancing blood collection and distribution based on an effective blood inventory management. We use machine learning and time series forecasting models to develop an AI/ML decision support system. It is an effective tool with three main modules that directly and indirectly impact all phases of the blood supply chain: (i) the blood demand forecasting module is designed to forecast blood demand; (ii) blood donor classification helps predict daily unbooked donors thereby enhancing the ability to control the volume of blood collected based on the results of blood demand forecasting; and (iii) scheduling blood donation appointments according to the expected number and type of blood donations, thus improving the quantity of blood by reducing the number of canceled appointments, and indirectly improving the quality and quantity of blood supply by decreasing the number of unqualified donors, thereby reducing the amount of invalid blood after and before preparation. As a result of the system’s improvements, blood shortages and waste can be reduced. The proposed solution provides robust and accurate predictions and identifies important clinical predictors for blood demand forecasting. Compared with the past year’s historical data, our integrated proposed system increased collected blood volume by 11%, decreased inventory wastage by 20%, and had a low incidence of shortages. Full article

If Diabetic Retinopathy (DR) patients do not receive quick diagnosis and treatment, they may lose vision. DR, an eye disorder caused by high blood glucose, is becoming more prevalent worldwide. Once early warning signs are detected, the severity of the disease must be validated before choosing the best treatment. In this research, a deep learning network is used to automatically detect and classify DR fundus images depending on severity using AlexNet and Resnet101-based feature extraction. Interconnected layers helps to identify the critical features or characteristics; in addition, Ant Colony systems also help choose the characteristics. Passing these chosen attributes through SVM with multiple kernels yielded the final classification model with promising accuracy. The experiment based on 750 features proves that the proposed approach has achieved an accuracy of 93%. Full article

The estimation of an image geo-site solely based on its contents is a promising task. Compelling image labelling relies heavily on contextual information, which is not as simple as recognizing a single object in an image. An Auto-Encode-based support vector machine approach is proposed in this work to estimate the image geo-site to address the issue of misclassifying the estimations. The proposed method for geo-site estimation is conducted using a dataset consisting of 125 classes of various images captured within 125 countries. The proposed work uses a convolutional Auto-Encode for training and dimensionality reduction. After that, the acquired preprocessed input dataset is further processed by a multi-label support vector machine. The performance assessment of the proposed approach has been accomplished using accuracy, sensitivity, specificity, and F1-score as evaluation parameters. Eventually, the proposed approach for image geo-site estimation presented in this article outperforms Auto-Encode-based K-Nearest Neighbor and Auto-Encode-Random Forest methods. Full article

We present a data-driven approach to discover and extract patterns in textual genres with the aim of identifying whether there is an interesting variation of linguistic features among different narrative genres depending on their respective communicative purposes. We want to achieve this goal by performing a multilevel discourse analysis according to (1) the type of feature studied (shallow, syntactic, semantic, and discourse-related); (2) the texts at a document level; and (3) the textual genres of news, reviews, and children’s tales. To accomplish this, several corpora from the three textual genres were gathered from different sources to ensure a heterogeneous representation, paying attention to the presence and frequency of a series of features extracted with computational tools. This deep analysis aims at obtaining more detailed knowledge of the different linguistic phenomena that directly shape each of the genres included in the study, therefore showing the particularities that make them be considered as individual genres but also comprise them inside the narrative typology. The findings suggest that this type of multilevel linguistic analysis could be of great help for areas of research within natural language processing such as computational narratology, as they allow a better understanding of the fundamental features that define each genre and its communicative purpose. Likewise, this approach could also boost the creation of more consistent automatic story generation tools in areas of language generation. Full article

One of the most important components of intelligent transportation systems (ITS) is the automotive self-organizing VANET network (vehicular ad hoc network). Its nodes are vehicles with specialized onboard units (OBU) installed on them. Such a network can be subject to various attacks. To reduce the effectiveness of a number of attacks on the VANET, it is advisable to use authentication protocols. Well-known authentication protocols support a security policy with full trust in roadside unit (RSU) base stations. The disadvantage of these authentication protocols is the ability of the RSU to track the route of the vehicle. This leads to a violation of the privacy and anonymity of the vehicle’s owner. To eliminate this drawback, the article proposes an adaptive authentication protocol. An advantage of this protocol is the provision of high imitation resistance without using symmetric and asymmetric ciphers. This result has been achieved by using a zero-knowledge authentication protocol. A scheme for adapting the protocol parameters depending on the intensity of the user’s traffic has been developed for the proposed protocol. The scientific novelty of this solution is to reduce time spent on authentication without changing the protocol execution algorithm by reducing the number of modular exponentiation operations when calculating true and “distorted” digests of the prover and verifying the correctness of responses, as well as by reducing the number of responses. Authentication, as before, takes place in one round without changing the bit depth of the modulus used in the protocol. To evaluate the effectiveness of the adaptive authentication protocol, the VANET model was implemented using NS-2. The obtained research results have shown that the adaptation of the authentication protocol in conditions of increased density of vehicles on the road makes it possible to increase the volume of data exchange between OBU and RSU by reducing the level of confidentiality. In addition, a mechanism for verifying the authority of the vehicle’s owner for provided services has been developed. As a result of the implementation of this mechanism, vehicle registration sites (VRS) calculate the public key of the vehicle without using encryption and provide necessary services to the owner. Full article