Search

Recent developments using extended reality (XR) technologies have allowed for increased use in healthcare in the last few years. This review paper explores how XR applications are utilized in home-based nursing education, in particular, to identify future challenges and opportunities. The systematic literature review evaluates relevant extracted papers based on publication information, XR technology used for education purposes, target users, and study design and evaluation, including sample size. The results show potential for using XR technologies in home-based nursing education. In particular, Virtual Reality (VR) has become quite popular and the most used to date. However, Augmented Reality (AR) has also emerged as an alternative for the future.

Recent developments using extended reality (XR) technologies have allowed for increased use in healthcare in the last few years. This review paper explores how XR applications are utilized in home-based nursing education, in particular, to identify future challenges and opportunities. The systematic literature review evaluates relevant extracted papers based on publication information, XR technology used for education purposes, target users, and study design and evaluation, including sample size. The results show potential for using XR technologies in home-based nursing education. In particular, Virtual Reality (VR) has become quite popular and the most used to date. However, Augmented Reality (AR) has also emerged as an alternative for the future.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

In recent years, with the rise of the ageing population worldwide, the health of the elderly has attracted increasing attention. This study explored existing extended reality (XR) game applications aiming at physical exercise for the elderly. Through the review of 1847 papers from the Scopus database, 17 articles were included. Based on these papers, we explored the existing contributions of exercise XR games for the elderly, the development opportunities and challenges of such games, and their special considerations in adapting to the characteristics and requirements of the target user. The results were organized into several perspectives: publication information and keywords, immersive technologies and game concepts, teamwork and social games, evaluation, opportunities and challenges, and adapting designs. We found the elderly interested in and accepted using XR games. The reported research results proved positive effects on such games’ physical and mental health. XR exercise games for the elderly should considerately adapt to the elder’s cognition, behaviour, and demand. Although problems existed, such as simulator sickness, safety risks, device problems, and cost, there were opportunities and space for research and future developments. Researchers and developers could refer to this paper for XR exercise games for the elderly and create or enhance future XR applications by learning from existing work. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

Recent developments using extended reality (XR) technologies have allowed for increased use in healthcare in the last few years. This review paper explores how XR applications are utilized in home-based nursing education, in particular, to identify future challenges and opportunities. The systematic literature review evaluates relevant extracted papers based on publication information, XR technology used for education purposes, target users, and study design and evaluation, including sample size. The results show potential for using XR technologies in home-based nursing education. In particular, Virtual Reality (VR) has become quite popular and the most used to date. However, Augmented Reality (AR) has also emerged as an alternative for the future.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

Recent developments using extended reality (XR) technologies have allowed for increased use in healthcare in the last few years. This review paper explores how XR applications are utilized in home-based nursing education, in particular, to identify future challenges and opportunities. The systematic literature review evaluates relevant extracted papers based on publication information, XR technology used for education purposes, target users, and study design and evaluation, including sample size. The results show potential for using XR technologies in home-based nursing education. In particular, Virtual Reality (VR) has become quite popular and the most used to date. However, Augmented Reality (AR) has also emerged as an alternative for the future.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

Recent developments using extended reality (XR) technologies have allowed for increased use in healthcare in the last few years. This review paper explores how XR applications are utilized in home-based nursing education, in particular, to identify future challenges and opportunities. The systematic literature review evaluates relevant extracted papers based on publication information, XR technology used for education purposes, target users, and study design and evaluation, including sample size. The results show potential for using XR technologies in home-based nursing education. In particular, Virtual Reality (VR) has become quite popular and the most used to date. However, Augmented Reality (AR) has also emerged as an alternative for the future.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

During the last decade we have witnessed how artificial intelligence (AI) have changed businesses all over the world. The customer life cycle framework is widely used in businesses and AI plays a role in each stage. However,implementing and generating value from AI in the customerlife cycle is not always simple. When evaluating the AI against business impact and value it is critical to consider both themodel performance and the policy outcome. Proper analysis of AI-derived policies must not be overlooked in order to ensure ethical and trustworthy AI. This paper presents a comprehensive analysis of the literature on AI in customer lifecycles (CLV) from an industry perspective. The study included 31 of 224 analyzed peer-reviewed articles from Scopus search result. The results show a significant research gap regardingoutcome evaluations of AI implementations in practice. This paper proposes that policy evaluation is an important tool in the AI pipeline and empathizes the significance of validating bothpolicy outputs and outcomes to ensure reliable and trustworthy AI., This work was funded by Telenor Sverige AB.

The COVID-19 pandemic has induced dramatic effects in all areas of society worldwide. It has led to drastic restrictions on academic exchanges and caused research projects to be put on hold. The need to maintain social distancing has severely affected the research communities that rely on in-person studies. In particular, Quality of Experience (QoE) research relies heavily on user studies and in-person subjective tests as means of obtaining ground truths for system designs. In this position paper, we focus on the impact of COVID-19 on conducting subjective tests for digital media quality assessment. An overview of the related discussions that take place in associated research communities is provided. A number of challenges are posed in terms of hygiene, ethics, standardization, and research quality issues. Opportunities for consolidating QoE research under COVID-19 and beyond are put forward, including alternative experimental designs and adaptation of research methodologies. Numerous enablers are suggested and discussed, revealing various avenues that can be followed to assist in conducting subjective tests under pandemic conditions. We believe that this position paper will be helpful for researchers and practitioners relying on in-person studies to keep abreast about the potential measures that support coming out of the COVID-19 pandemic strong and being prepared for future endeavors. © 2021 IEEE.

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

As a rule, modern approaches to protecting against cyberattacks do not guarantee the impossibility of compromising applications and operating systems. Therefore, detection and identification of vulnerabilities, and actions to avoid or mitigate their impact on businesses and cybersecurity processes are critical for the operation of information systems and the information security management system. To identify a possible attack vector, as a rule, the following methods could be applied: either those that allow detecting abuses or that allow detecting anomalies. This paper investigates the possibility of identifying the alleged attack vector based on the entropy analysis of cybersecurity events. The research results presented in the paper allow us to determine the required width of the sliding window and confirm that such entropy analysis detects exceeding security thresholds and anomalies in the operation of operating systems and applications and, accordingly, probable attack vectors. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Augmented Reality (AR) and 3D printing have increasingly been used in archaeological and cultural heritage to make artifacts and environments accessible to the general public. This paper presents the case study of the Ljungaviken dog, an archaeological find of dog skeleton remains dated around 8000 years ago. The dog remains have been digitized using 3D scanning and displayed in an AR application. A physical replica has also been created with 3D printing. Both the AR application and the 3D printed copy have been shown in a temporary museum exhibition. In this paper, we present the visitors’ experience evaluation based on a study with 42 participants. Aspects being evaluated are related to the realism, enjoyment, and easiness of use of the AR application. Moreover, the two media are compared in terms of understanding, visual quality, and experience satisfaction. The results show an overall positive experience for both the display solutions, with slightly higher scores for the AR application in the comparison. When asked about overall preference, the participants reported similar results between both media. Due to issues of displaying fragile objects in a museum setting, as well as recent restrictions following pandemic closures and availability, the results presented in this paper show a positive alternative towards using digital artifacts to showcase our cultural heritage. © 2022, Springer Nature Switzerland AG.

The paper provides an overview of network softwarization. This refers to network changes and adaptations regarding the convergence to Software Defined Networking and Network Function Virtualisation as well as moving the network control to Data Centers and Mobile Edge. For doing this, basic concepts and elements used in the performance provision in softwarized networking environments are used. Adequate performance frame-works can be defined, including relevant metrics and models, to be used in the development, deployment and operation of cloud and edge computing architectures as well as 5G network slicing. The paper provides an overview of network slicing, backbone of 5G technology, as well. © 2022 IEEE.

Anomaly detection is an important part of machine learning. Detection of outliers in the field of transportation can provide valid data for future traffic predictions or traffic flow analysis. This paper builds a model based on XGBoost to detect outliers in IoT data. The data is preprocessed first, followed by model building. Then we use the grid search to adjust the parameters and substitute the optimal parameters into the building model. To validate the model, we cross-checked it with two benchmark models, iFroset and Random Forest. The final experimental results show that the model constructed in this paper can accurately detect outliers in traffic flow and the accuracy is better than that of the baseline model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Virtual reality, augmented reality, and mixed reality (VR/AR/MR) as information and communication technologies have been recognised and implemented in healthcare in recent years. One of the popular application ways is games, due to the potential benefits of providing an engaging and immersive experience in a virtual environment. This study presents a systematic literature review that evaluates the state-of-the-art on VR/AR/MR game applications in healthcare by collecting and analysing related journal and conference papers published from 2014 through to the first half of 2020. After retrieving more than 3,000 papers from six databases, 88 articles, from both computer science and medicine, were selected and analysed in the review. The articles are classified and summarised based on their (1) publication information, (2) design, implementation, and evaluation, and (3) application. The presented review is beneficial for both researchers and developers interested in exploring current research and future trends in VR/AR/MR in healthcare. © 2022 Association for Computing Machinery.

This paper proposes a novel multi-stream clustering algorithm, MultiStream EvolveCluster (MS-EC), that can be used for continuous and distributed monitoring and analysis ofevolving time series phenomena. It can maintain evolving clustering solutions separatelyfor each stream/view and consensus clustering solutions reflecting evolving interrelationsamong the streams. Each stream behavior can be analyzed by different clustering techniques using a distance measure and data granularity that is specially selected for it. Theproperties of the MultiStream EvolveCluster algorithm are studied and evaluated withrespect to different consensus clustering techniques, distance measures, and cluster evaluation measures in synthetic and real-world smart building datasets. Our evaluation resultsshow a stable algorithm performance in synthetic data scenarios. In the case of real-worlddata, the algorithm behavior demonstrates sensitivity to the individual streams’ data quality and the used consensus clustering technique.

The recent advances in immersive technologies have been essential in the development of a wide range of novel standalone and networked immersive media applications. The concepts of virtual reality, augmented reality, and mixed reality relate to different compositions of real and computer-generated virtual objects. In this context, 360° video streaming has become increasingly popular offering improved immersive experiences when viewed on a head-mounted display (HMD). An important component in the development of novel immersive media systems are subjective tests in which participants assess the quality of experience of representative test stimuli. In this paper, the annotated ACR360 dataset is presented which is publicly available on GitHub. The ACR360 dataset contains a wide range of psychophysical and psychophysiological data that was collected in Subjective tests on 360° video quality. The test stimuli were shown on an HMD and rated according to the absolute category rating (ACR) and modified ACR (MACR) methods. To support an easy exploration and utilization of the ACR360 dataset by the research community, its structure on GitHub is described and a comprehensive illustration of analysis options are provided for each data category. The ACR360 dataset may be used for conducting meta-analysis in combination with other datasets to improve precision and to pursue research questions that cannot be answered by an individual study. © 2023 IEEE.

Chacha20 is a widely used stream cipher known for using permutation functions to enhance resistance against cryptanalysis. Although the existing literature highlights its strengths, it is worth further exploring its potential susceptibility to differential attacks. This paper proposes an Extended Chacha20 (EChacha20) stream cipher, which offers a slight improvement of Chacha20. It incorporates enhanced Quarter Round Functions QR-F with 32-bit input words and Add , Rotate , and XOR (ARX) operations on 16, 12, 8, 7, 4, and 2 constants. Using these improved QR-Fs , we expect EChacha20 to be more secure and effective against attacks than Chacha20. The threat model leveraged in this paper considers attacker assumptions based on the Bellare-Rogaway Model (B-RM) and the Chosen Plaintext Attack (CPA) to assess the potential security weaknesses. Then, the study analyzes the EChacha20 cipher using the NIST Statistical Test Suite (NSTS) and demonstrates its effectiveness against differential cryptanalysis. A differential attack addresses this challenge, where the study comprehensively analyses the differences between original and flipped bits. The NSTS has been used to statistically analyze the outcome for uniformity and evaluate the randomness of generating sequences of tests considering 1000 tests based on a range of [{0,1}]. Uniformity is evaluated based on the p-values test against a battery of passing sequences, and 100% is achieved from Runs and Serial (2): Test 1 , respectively. The performance evaluation metrics leveraged include encryption speed, decryption speed, and memory usage. Based on the test conducted, it has been observed that with increased QR-F , EChacha20 maintains a good balance in speed although slightly higher than Chacha20; however, with also slightly high memory usage compared to Chacha20. Despite that, a comparative study has been conducted against state-of-the-art studies, and the outcome has been reported to show the significance of the current stu

This paper proposes a novel multi-stream clustering algorithm, MultiStream EvolveCluster (MS-EC), that can be used for continuous and distributed monitoring and analysis ofevolving time series phenomena. It can maintain evolving clustering solutions separatelyfor each stream/view and consensus clustering solutions reflecting evolving interrelationsamong the streams. Each stream behavior can be analyzed by different clustering techniques using a distance measure and data granularity that is specially selected for it. Theproperties of the MultiStream EvolveCluster algorithm are studied and evaluated withrespect to different consensus clustering techniques, distance measures, and cluster evaluation measures in synthetic and real-world smart building datasets. Our evaluation resultsshow a stable algorithm performance in synthetic data scenarios. In the case of real-worlddata, the algorithm behavior demonstrates sensitivity to the individual streams’ data quality and the used consensus clustering technique.

This paper proposes a novel multimodal deep weakly-supervised learning framework, SinkholeNet, to classify and localize sinkhole(s) in high-resolution RGB-slope aerial images. The SinkholeNet first employs a multimodal Convolutional Neural Network (CNN) architecture that simultaneously extracts features from the input RGB image and ground slope map and then fuses the extracted features. It then uses an improved ShuffleNet architecture on the fused features to classify patches as sinkholes or non-sinkholes. Finally, the last extracted feature maps, belonging to the sinkhole class, are used as input of gradient-weighted class activation mapping (Grad-CAM) to localize sinkhole(s) in a weakly-supervised setting. The proposed weakly-supervised framework intends to increase the available labeled data for training and decrease the cost of human annotation. We also introduce a novel publicly available weakly labeled sinkhole dataset comprising RGB-slope paired image patches to support reproducible research. The experimental results on the newly introduced dataset show that the SinkholeNet outperforms the other methods considered in this paper both for sinkhole classification and localization. © 2023 National Authority of Remote Sensing & Space Science

Fifth-generation (5G) mobile networks have already marked their presence globally, revolutionizing entertainment, business, healthcare, and other domains. While this leap forward brings numerous advantages in speed and connectivity, it also poses new challenges for security protocols. Machine learning (ML) and deep learning (DL) have been employed to augment traditional security measures, promising to mitigate risks and vulnerabilities. This paper conducts an exhaustive study to assess ML and DL algorithms’ role and effectiveness within the 5G security landscape. Also, it offers a profound dissection of the 5G network’s security paradigm, particularly emphasizing the transformative role of ML and DL as enabling security tools. This study starts by examining the unique architecture of 5G and its inherent vulnerabilities, contrasting them with emerging threat vectors. Next, we conduct a detailed analysis of the network’s underlying segments, such as network slicing, Massive Machine-Type Communications (mMTC), and edge computing, revealing their associated security challenges. By scrutinizing current security protocols and international regulatory impositions, this paper delineates the existing 5G security landscape. Finally, we outline the capabilities of ML and DL in redefining 5G security. We detail their application in enhancing anomaly detection, fortifying predictive security measures, and strengthening intrusion prevention strategies. This research sheds light on the present-day 5G security challenges and offers a visionary perspective, highlighting the intersection of advanced computational methods and future 5G security. © 2023 by the authors.

In this paper, we consider a downlink scenario in which a base station (BS) communicates with user equipment (UE) that move with high speed. Orthogonal time frequency space (OTFS) modulation is used to overcome the effects of high Doppler shifts inherent with high-mobility scenarios. To increase spectral efficiency, power-domain non-orthogonal multiple access (NOMA) is combined with OTFS to form an OTFS-NOMA system. The K-means clustering algorithm is deployed which partitions the coverage area of the BS into clusters such that the UEs within a cluster have a shorter distance to the respective cluster center than to the centers of the other clusters. The cluster centers act as simultaneous multiple users on which basis power-domain NOMA selects the power allocation coefficients to reduce the mutual interference among UEs. OTFS can control the resolution of the delay-Doppler domain to more accurately compensate for propagation delays and Doppler shifts. The performance of this OTFS-NOMA system with K-means clustering of the UEs is assessed in terms of sum rate. The numerical results illustrate that the successive interference cancellation of power-domain NOMA significantly improves sum rate. Additional improvements are obtained by choosing a sufficiently large size of the delay-Doppler grid of OTFS which effectively copes with the high Doppler shifts of the considered high-mobility scenario. © 2023 IEEE.

Fifth-generation (5G) mobile networks have already marked their presence globally, revolutionizing entertainment, business, healthcare, and other domains. While this leap forward brings numerous advantages in speed and connectivity, it also poses new challenges for security protocols. Machine learning (ML) and deep learning (DL) have been employed to augment traditional security measures, promising to mitigate risks and vulnerabilities. This paper conducts an exhaustive study to assess ML and DL algorithms’ role and effectiveness within the 5G security landscape. Also, it offers a profound dissection of the 5G network’s security paradigm, particularly emphasizing the transformative role of ML and DL as enabling security tools. This study starts by examining the unique architecture of 5G and its inherent vulnerabilities, contrasting them with emerging threat vectors. Next, we conduct a detailed analysis of the network’s underlying segments, such as network slicing, Massive Machine-Type Communications (mMTC), and edge computing, revealing their associated security challenges. By scrutinizing current security protocols and international regulatory impositions, this paper delineates the existing 5G security landscape. Finally, we outline the capabilities of ML and DL in redefining 5G security. We detail their application in enhancing anomaly detection, fortifying predictive security measures, and strengthening intrusion prevention strategies. This research sheds light on the present-day 5G security challenges and offers a visionary perspective, highlighting the intersection of advanced computational methods and future 5G security. © 2023 by the authors.

This paper proposes a novel multimodal deep weakly-supervised learning framework, SinkholeNet, to classify and localize sinkhole(s) in high-resolution RGB-slope aerial images. The SinkholeNet first employs a multimodal Convolutional Neural Network (CNN) architecture that simultaneously extracts features from the input RGB image and ground slope map and then fuses the extracted features. It then uses an improved ShuffleNet architecture on the fused features to classify patches as sinkholes or non-sinkholes. Finally, the last extracted feature maps, belonging to the sinkhole class, are used as input of gradient-weighted class activation mapping (Grad-CAM) to localize sinkhole(s) in a weakly-supervised setting. The proposed weakly-supervised framework intends to increase the available labeled data for training and decrease the cost of human annotation. We also introduce a novel publicly available weakly labeled sinkhole dataset comprising RGB-slope paired image patches to support reproducible research. The experimental results on the newly introduced dataset show that the SinkholeNet outperforms the other methods considered in this paper both for sinkhole classification and localization. © 2023 National Authority of Remote Sensing & Space Science

Chacha20 is a widely used stream cipher known for using permutation functions to enhance resistance against cryptanalysis. Although the existing literature highlights its strengths, it is worth further exploring its potential susceptibility to differential attacks. This paper proposes an Extended Chacha20 (EChacha20) stream cipher, which offers a slight improvement of Chacha20. It incorporates enhanced Quarter Round Functions QR-F with 32-bit input words and Add , Rotate , and XOR (ARX) operations on 16, 12, 8, 7, 4, and 2 constants. Using these improved QR-Fs , we expect EChacha20 to be more secure and effective against attacks than Chacha20. The threat model leveraged in this paper considers attacker assumptions based on the Bellare-Rogaway Model (B-RM) and the Chosen Plaintext Attack (CPA) to assess the potential security weaknesses. Then, the study analyzes the EChacha20 cipher using the NIST Statistical Test Suite (NSTS) and demonstrates its effectiveness against differential cryptanalysis. A differential attack addresses this challenge, where the study comprehensively analyses the differences between original and flipped bits. The NSTS has been used to statistically analyze the outcome for uniformity and evaluate the randomness of generating sequences of tests considering 1000 tests based on a range of [{0,1}]. Uniformity is evaluated based on the p-values test against a battery of passing sequences, and 100% is achieved from Runs and Serial (2): Test 1 , respectively. The performance evaluation metrics leveraged include encryption speed, decryption speed, and memory usage. Based on the test conducted, it has been observed that with increased QR-F , EChacha20 maintains a good balance in speed although slightly higher than Chacha20; however, with also slightly high memory usage compared to Chacha20. Despite that, a comparative study has been conducted against state-of-the-art studies, and the outcome has been reported to show the significance of the current stu

The recent advances in immersive technologies have been essential in the development of a wide range of novel standalone and networked immersive media applications. The concepts of virtual reality, augmented reality, and mixed reality relate to different compositions of real and computer-generated virtual objects. In this context, 360° video streaming has become increasingly popular offering improved immersive experiences when viewed on a head-mounted display (HMD). An important component in the development of novel immersive media systems are subjective tests in which participants assess the quality of experience of representative test stimuli. In this paper, the annotated ACR360 dataset is presented which is publicly available on GitHub. The ACR360 dataset contains a wide range of psychophysical and psychophysiological data that was collected in Subjective tests on 360° video quality. The test stimuli were shown on an HMD and rated according to the absolute category rating (ACR) and modified ACR (MACR) methods. To support an easy exploration and utilization of the ACR360 dataset by the research community, its structure on GitHub is described and a comprehensive illustration of analysis options are provided for each data category. The ACR360 dataset may be used for conducting meta-analysis in combination with other datasets to improve precision and to pursue research questions that cannot be answered by an individual study. © 2023 IEEE.

This paper proposes a novel multi-stream clustering algorithm, MultiStream EvolveCluster (MS-EC), that can be used for continuous and distributed monitoring and analysis ofevolving time series phenomena. It can maintain evolving clustering solutions separatelyfor each stream/view and consensus clustering solutions reflecting evolving interrelationsamong the streams. Each stream behavior can be analyzed by different clustering techniques using a distance measure and data granularity that is specially selected for it. Theproperties of the MultiStream EvolveCluster algorithm are studied and evaluated withrespect to different consensus clustering techniques, distance measures, and cluster evaluation measures in synthetic and real-world smart building datasets. Our evaluation resultsshow a stable algorithm performance in synthetic data scenarios. In the case of real-worlddata, the algorithm behavior demonstrates sensitivity to the individual streams’ data quality and the used consensus clustering technique.

Fifth generation (5G), beyond 5G (B5G), and future sixth generation (6G) mobile networks are foreseen to increasingly account for heterogeneous networks toward ubiquitous communications with non-terrestrial networks (NTNs). Furthermore, in 5G mobile networks, massive machine type communications has been introduced for Internet of Things (IoT) applications aiming at low energy consumption, low to medium data rates, burst transmissions, and massive connectivity. It is expected that IoT communications will take an even larger portion in B5G and 6G mobile networks. Robust communications in such high-mobility NTN deployments including unmanned aerial vehicles (UAVs), airborne platforms, and satellite systems, need novel modulation waveforms that can deal with the induced severe Doppler effects. Orthogonal time frequency space (OTFS) modulation has gained tremendous interest in recent years as an effective technology for coping with high Doppler channels. OTFS essentially transforms a time-varying fading channel into a quasi-static channel in the delay-Doppler domain. In this paper, for the first time, an overview on OTFS modulation for NTNs is provided including basic concepts and applications in UAVs, airborne networks, and satellite systems. A case study related to an application in high Doppler airborne communication networks is also provided to illustrate the potential of OTFS modulation in providing robust transmission links in high-mobility scenarios. This survey will be helpful for researchers and practitioners to keep abreast about the potential of OTFS modulation in NTNs. © 2023 IEEE., Riktad luftdatalänk

The recent advances in immersive technologies have been essential in the development of a wide range of novel standalone and networked immersive media applications. The concepts of virtual reality, augmented reality, and mixed reality relate to different compositions of real and computer-generated virtual objects. In this context, 360° video streaming has become increasingly popular offering improved immersive experiences when viewed on a head-mounted display (HMD). An important component in the development of novel immersive media systems are subjective tests in which participants assess the quality of experience of representative test stimuli. In this paper, the annotated ACR360 dataset is presented which is publicly available on GitHub. The ACR360 dataset contains a wide range of psychophysical and psychophysiological data that was collected in Subjective tests on 360° video quality. The test stimuli were shown on an HMD and rated according to the absolute category rating (ACR) and modified ACR (MACR) methods. To support an easy exploration and utilization of the ACR360 dataset by the research community, its structure on GitHub is described and a comprehensive illustration of analysis options are provided for each data category. The ACR360 dataset may be used for conducting meta-analysis in combination with other datasets to improve precision and to pursue research questions that cannot be answered by an individual study. © 2023 IEEE.

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase

Sixth-generation (6G) networks are considered as key enablers in the development of the intelligent information society offering ultra-reliable low-latency communications in the context of massive machine-type communications and the emergence of the Internet-of-everything. In this paper, we consider a short-packet cooperative nonorthogonal multiple access (C-NOMA) communication system that uses the K-means algorithm for user clustering. The short-packet component of the system facilitates low-latency communications. In addition, C-NOMA using decode-and-forward relays allows extended coverage in terms of user equipment (UE) clusters and spectral efficiency in terms of sum rate. Given the trend toward irregular deployment of heterogeneous infrastructure elements in 6G networks and massive amounts of UEs, the K-means algorithm is used to generate clusters of UEs around the locations of the relays that assist the communication between the base station and the UEs. Analytical expressions of the block error rate (BLER) and sum rate are derived allowing a performance assessment of the short-packet C-NOMA communication system. Numerical results are provided revealing the impact of the number of channel uses and the number of UEs on the BLER and sum rate of the considered system. © 2023 IEEE.

Fifth-generation (5G) mobile networks have already marked their presence globally, revolutionizing entertainment, business, healthcare, and other domains. While this leap forward brings numerous advantages in speed and connectivity, it also poses new challenges for security protocols. Machine learning (ML) and deep learning (DL) have been employed to augment traditional security measures, promising to mitigate risks and vulnerabilities. This paper conducts an exhaustive study to assess ML and DL algorithms’ role and effectiveness within the 5G security landscape. Also, it offers a profound dissection of the 5G network’s security paradigm, particularly emphasizing the transformative role of ML and DL as enabling security tools. This study starts by examining the unique architecture of 5G and its inherent vulnerabilities, contrasting them with emerging threat vectors. Next, we conduct a detailed analysis of the network’s underlying segments, such as network slicing, Massive Machine-Type Communications (mMTC), and edge computing, revealing their associated security challenges. By scrutinizing current security protocols and international regulatory impositions, this paper delineates the existing 5G security landscape. Finally, we outline the capabilities of ML and DL in redefining 5G security. We detail their application in enhancing anomaly detection, fortifying predictive security measures, and strengthening intrusion prevention strategies. This research sheds light on the present-day 5G security challenges and offers a visionary perspective, highlighting the intersection of advanced computational methods and future 5G security. © 2023 by the authors.

This paper proposes a novel multi-stream clustering algorithm, MultiStream EvolveCluster (MS-EC), that can be used for continuous and distributed monitoring and analysis ofevolving time series phenomena. It can maintain evolving clustering solutions separatelyfor each stream/view and consensus clustering solutions reflecting evolving interrelationsamong the streams. Each stream behavior can be analyzed by different clustering techniques using a distance measure and data granularity that is specially selected for it. Theproperties of the MultiStream EvolveCluster algorithm are studied and evaluated withrespect to different consensus clustering techniques, distance measures, and cluster evaluation measures in synthetic and real-world smart building datasets. Our evaluation resultsshow a stable algorithm performance in synthetic data scenarios. In the case of real-worlddata, the algorithm behavior demonstrates sensitivity to the individual streams’ data quality and the used consensus clustering technique.

This paper proposes a novel multimodal deep weakly-supervised learning framework, SinkholeNet, to classify and localize sinkhole(s) in high-resolution RGB-slope aerial images. The SinkholeNet first employs a multimodal Convolutional Neural Network (CNN) architecture that simultaneously extracts features from the input RGB image and ground slope map and then fuses the extracted features. It then uses an improved ShuffleNet architecture on the fused features to classify patches as sinkholes or non-sinkholes. Finally, the last extracted feature maps, belonging to the sinkhole class, are used as input of gradient-weighted class activation mapping (Grad-CAM) to localize sinkhole(s) in a weakly-supervised setting. The proposed weakly-supervised framework intends to increase the available labeled data for training and decrease the cost of human annotation. We also introduce a novel publicly available weakly labeled sinkhole dataset comprising RGB-slope paired image patches to support reproducible research. The experimental results on the newly introduced dataset show that the SinkholeNet outperforms the other methods considered in this paper both for sinkhole classification and localization. © 2023 National Authority of Remote Sensing & Space Science

The recent advances in immersive technologies have been essential in the development of a wide range of novel standalone and networked immersive media applications. The concepts of virtual reality, augmented reality, and mixed reality relate to different compositions of real and computer-generated virtual objects. In this context, 360° video streaming has become increasingly popular offering improved immersive experiences when viewed on a head-mounted display (HMD). An important component in the development of novel immersive media systems are subjective tests in which participants assess the quality of experience of representative test stimuli. In this paper, the annotated ACR360 dataset is presented which is publicly available on GitHub. The ACR360 dataset contains a wide range of psychophysical and psychophysiological data that was collected in Subjective tests on 360° video quality. The test stimuli were shown on an HMD and rated according to the absolute category rating (ACR) and modified ACR (MACR) methods. To support an easy exploration and utilization of the ACR360 dataset by the research community, its structure on GitHub is described and a comprehensive illustration of analysis options are provided for each data category. The ACR360 dataset may be used for conducting meta-analysis in combination with other datasets to improve precision and to pursue research questions that cannot be answered by an individual study. © 2023 IEEE.

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase

Chacha20 is a widely used stream cipher known for using permutation functions to enhance resistance against cryptanalysis. Although the existing literature highlights its strengths, it is worth further exploring its potential susceptibility to differential attacks. This paper proposes an Extended Chacha20 (EChacha20) stream cipher, which offers a slight improvement of Chacha20. It incorporates enhanced Quarter Round Functions QR-F with 32-bit input words and Add , Rotate , and XOR (ARX) operations on 16, 12, 8, 7, 4, and 2 constants. Using these improved QR-Fs , we expect EChacha20 to be more secure and effective against attacks than Chacha20. The threat model leveraged in this paper considers attacker assumptions based on the Bellare-Rogaway Model (B-RM) and the Chosen Plaintext Attack (CPA) to assess the potential security weaknesses. Then, the study analyzes the EChacha20 cipher using the NIST Statistical Test Suite (NSTS) and demonstrates its effectiveness against differential cryptanalysis. A differential attack addresses this challenge, where the study comprehensively analyses the differences between original and flipped bits. The NSTS has been used to statistically analyze the outcome for uniformity and evaluate the randomness of generating sequences of tests considering 1000 tests based on a range of [{0,1}]. Uniformity is evaluated based on the p-values test against a battery of passing sequences, and 100% is achieved from Runs and Serial (2): Test 1 , respectively. The performance evaluation metrics leveraged include encryption speed, decryption speed, and memory usage. Based on the test conducted, it has been observed that with increased QR-F , EChacha20 maintains a good balance in speed although slightly higher than Chacha20; however, with also slightly high memory usage compared to Chacha20. Despite that, a comparative study has been conducted against state-of-the-art studies, and the outcome has been reported to show the significance of the current stu

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase

This paper proposes a novel multimodal deep weakly-supervised learning framework, SinkholeNet, to classify and localize sinkhole(s) in high-resolution RGB-slope aerial images. The SinkholeNet first employs a multimodal Convolutional Neural Network (CNN) architecture that simultaneously extracts features from the input RGB image and ground slope map and then fuses the extracted features. It then uses an improved ShuffleNet architecture on the fused features to classify patches as sinkholes or non-sinkholes. Finally, the last extracted feature maps, belonging to the sinkhole class, are used as input of gradient-weighted class activation mapping (Grad-CAM) to localize sinkhole(s) in a weakly-supervised setting. The proposed weakly-supervised framework intends to increase the available labeled data for training and decrease the cost of human annotation. We also introduce a novel publicly available weakly labeled sinkhole dataset comprising RGB-slope paired image patches to support reproducible research. The experimental results on the newly introduced dataset show that the SinkholeNet outperforms the other methods considered in this paper both for sinkhole classification and localization. © 2023 National Authority of Remote Sensing & Space Science

Fifth-generation (5G) mobile networks have already marked their presence globally, revolutionizing entertainment, business, healthcare, and other domains. While this leap forward brings numerous advantages in speed and connectivity, it also poses new challenges for security protocols. Machine learning (ML) and deep learning (DL) have been employed to augment traditional security measures, promising to mitigate risks and vulnerabilities. This paper conducts an exhaustive study to assess ML and DL algorithms’ role and effectiveness within the 5G security landscape. Also, it offers a profound dissection of the 5G network’s security paradigm, particularly emphasizing the transformative role of ML and DL as enabling security tools. This study starts by examining the unique architecture of 5G and its inherent vulnerabilities, contrasting them with emerging threat vectors. Next, we conduct a detailed analysis of the network’s underlying segments, such as network slicing, Massive Machine-Type Communications (mMTC), and edge computing, revealing their associated security challenges. By scrutinizing current security protocols and international regulatory impositions, this paper delineates the existing 5G security landscape. Finally, we outline the capabilities of ML and DL in redefining 5G security. We detail their application in enhancing anomaly detection, fortifying predictive security measures, and strengthening intrusion prevention strategies. This research sheds light on the present-day 5G security challenges and offers a visionary perspective, highlighting the intersection of advanced computational methods and future 5G security. © 2023 by the authors.

The recent advances in immersive technologies have been essential in the development of a wide range of novel standalone and networked immersive media applications. The concepts of virtual reality, augmented reality, and mixed reality relate to different compositions of real and computer-generated virtual objects. In this context, 360° video streaming has become increasingly popular offering improved immersive experiences when viewed on a head-mounted display (HMD). An important component in the development of novel immersive media systems are subjective tests in which participants assess the quality of experience of representative test stimuli. In this paper, the annotated ACR360 dataset is presented which is publicly available on GitHub. The ACR360 dataset contains a wide range of psychophysical and psychophysiological data that was collected in Subjective tests on 360° video quality. The test stimuli were shown on an HMD and rated according to the absolute category rating (ACR) and modified ACR (MACR) methods. To support an easy exploration and utilization of the ACR360 dataset by the research community, its structure on GitHub is described and a comprehensive illustration of analysis options are provided for each data category. The ACR360 dataset may be used for conducting meta-analysis in combination with other datasets to improve precision and to pursue research questions that cannot be answered by an individual study. © 2023 IEEE.