Ana Ibáñez-Hernández, Natalia Papí-Gálvez, Carmen Carretón-Ballester
This paper addresses the scientific production of pharmaceutical communication in Spain around the COVID-19 crisis, in which information overload, amplified by the digital media, evidenced the relevance of communication in the digital society. The research observes the evolution and characteristics of such studies, identifying scientific fields and disciplines related to communication, thematic lines, agents and publics. To this end, it proposes an exploratory review study adjusted to the PRISMA protocol with a search strategy including three databases (Scopus, WOS and Dialnet) and whose filtration produced a final population of 56 publications on Spanish pharmaceutical communication between 2018 and 2022. The results point to a greater production of scientific papers around the year of the pandemic. These papers were published by university institutions in health sciences journals, although differences in authorship by gender were detected. Most of them are empirical papers, with a predominance of mixed content analyses. The field of public relations stands out, but terminological confusion was also detected. This leads to a reflection on its causes and solutions in favour of the transparency and accountability in pharmaceutical communication.
{"title":"Pharmaceutical Communication in Spain around the COVID-19 Crisis: A Scoping Review","authors":"Ana Ibáñez-Hernández, Natalia Papí-Gálvez, Carmen Carretón-Ballester","doi":"10.3390/systems11060309","DOIUrl":"https://doi.org/10.3390/systems11060309","url":null,"abstract":"This paper addresses the scientific production of pharmaceutical communication in Spain around the COVID-19 crisis, in which information overload, amplified by the digital media, evidenced the relevance of communication in the digital society. The research observes the evolution and characteristics of such studies, identifying scientific fields and disciplines related to communication, thematic lines, agents and publics. To this end, it proposes an exploratory review study adjusted to the PRISMA protocol with a search strategy including three databases (Scopus, WOS and Dialnet) and whose filtration produced a final population of 56 publications on Spanish pharmaceutical communication between 2018 and 2022. The results point to a greater production of scientific papers around the year of the pandemic. These papers were published by university institutions in health sciences journals, although differences in authorship by gender were detected. Most of them are empirical papers, with a predominance of mixed content analyses. The field of public relations stands out, but terminological confusion was also detected. This leads to a reflection on its causes and solutions in favour of the transparency and accountability in pharmaceutical communication.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73980922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ubiquitous mobile edge computing (MEC) using the internet of things (IoT) is a promising technology for providing low-latency and high-throughput services to end-users. Resource allocation and quality of service (QoS) optimization are critical challenges in MEC systems due to the large number of devices and applications involved. This results in poor latency with minimum throughput and energy consumption as well as a high delay rate. Therefore, this paper proposes a novel approach for resource allocation and QoS optimization in MEC using IoT by combining the hybrid kernel random Forest (HKRF) and ensemble support vector machine (ESVM) algorithms with crossover-based hunter–prey optimization (CHPO). The HKRF algorithm uses decision trees and kernel functions to capture the complex relationships between input features and output labels. The ESVM algorithm combines multiple SVM classifiers to improve the classification accuracy and robustness. The CHPO algorithm is a metaheuristic optimization algorithm that mimics the hunting behavior of predators and prey in nature. The proposed approach aims to optimize the parameters of the HKRF and ESVM algorithms and allocate resources to different applications running on the MEC network to improve the QoS metrics such as latency, throughput, and energy efficiency. The experimental results show that the proposed approach outperforms other algorithms in terms of QoS metrics and resource allocation efficiency. The throughput and the energy consumption attained by our proposed approach are 595 mbit/s and 9.4 mJ, respectively.
{"title":"Machine Learning-Driven Ubiquitous Mobile Edge Computing as a Solution to Network Challenges in Next-Generation IoT","authors":"M. A. Moteri, S. B. Khan, M. Alojail","doi":"10.3390/systems11060308","DOIUrl":"https://doi.org/10.3390/systems11060308","url":null,"abstract":"Ubiquitous mobile edge computing (MEC) using the internet of things (IoT) is a promising technology for providing low-latency and high-throughput services to end-users. Resource allocation and quality of service (QoS) optimization are critical challenges in MEC systems due to the large number of devices and applications involved. This results in poor latency with minimum throughput and energy consumption as well as a high delay rate. Therefore, this paper proposes a novel approach for resource allocation and QoS optimization in MEC using IoT by combining the hybrid kernel random Forest (HKRF) and ensemble support vector machine (ESVM) algorithms with crossover-based hunter–prey optimization (CHPO). The HKRF algorithm uses decision trees and kernel functions to capture the complex relationships between input features and output labels. The ESVM algorithm combines multiple SVM classifiers to improve the classification accuracy and robustness. The CHPO algorithm is a metaheuristic optimization algorithm that mimics the hunting behavior of predators and prey in nature. The proposed approach aims to optimize the parameters of the HKRF and ESVM algorithms and allocate resources to different applications running on the MEC network to improve the QoS metrics such as latency, throughput, and energy efficiency. The experimental results show that the proposed approach outperforms other algorithms in terms of QoS metrics and resource allocation efficiency. The throughput and the energy consumption attained by our proposed approach are 595 mbit/s and 9.4 mJ, respectively.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86445193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abdullah Sultan Al Shammre, Adel Benhamed, O. Ben-Salha, Zied Jaidi
The latest decades have been marked by rapid climate change and global warming due to the release of greenhouse gas emissions into the atmosphere. Environmental taxes have emerged as a cost-effective way to tackle environmental degradation. However, the effectiveness of environmental taxes in reducing pollution remains a topic of ongoing debate. The purpose of this paper is to examine empirically the effects of various environmental tax categories (energy, pollution, resource and transport) on CO2 emissions in 34 OECD countries between 1995 and 2019. The dynamic panel threshold regression developed by Seo and Shin (2016) is implemented to assess whether the impact of environmental taxes on CO2 emissions depends on a given threshold level. The locally weighted scatterplot smoothing analysis provides evidence for a nonlinear association between environmental taxes and CO2 emissions. The analysis indicates the existence of one significant threshold and two regimes (lower and upper) for all environmental tax categories. The dynamic panel threshold regression reveals that the total environmental tax, energy tax and pollution tax reduce CO2 emissions in the upper regime, i.e., once a given threshold level is reached. The threshold levels are 3.002% of GDP for the total environmental tax, 1.991% for the energy tax and 0.377% for the pollution tax. Furthermore, implementing taxes on resource utilization may be effective but with limited environmental effects. Based on the research results, it is recommended that countries in the OECD implement specific environmental taxes to reduce greenhouse gas emissions.
{"title":"Do Environmental Taxes Affect Carbon Dioxide Emissions in OECD Countries? Evidence from the Dynamic Panel Threshold Model","authors":"Abdullah Sultan Al Shammre, Adel Benhamed, O. Ben-Salha, Zied Jaidi","doi":"10.3390/systems11060307","DOIUrl":"https://doi.org/10.3390/systems11060307","url":null,"abstract":"The latest decades have been marked by rapid climate change and global warming due to the release of greenhouse gas emissions into the atmosphere. Environmental taxes have emerged as a cost-effective way to tackle environmental degradation. However, the effectiveness of environmental taxes in reducing pollution remains a topic of ongoing debate. The purpose of this paper is to examine empirically the effects of various environmental tax categories (energy, pollution, resource and transport) on CO2 emissions in 34 OECD countries between 1995 and 2019. The dynamic panel threshold regression developed by Seo and Shin (2016) is implemented to assess whether the impact of environmental taxes on CO2 emissions depends on a given threshold level. The locally weighted scatterplot smoothing analysis provides evidence for a nonlinear association between environmental taxes and CO2 emissions. The analysis indicates the existence of one significant threshold and two regimes (lower and upper) for all environmental tax categories. The dynamic panel threshold regression reveals that the total environmental tax, energy tax and pollution tax reduce CO2 emissions in the upper regime, i.e., once a given threshold level is reached. The threshold levels are 3.002% of GDP for the total environmental tax, 1.991% for the energy tax and 0.377% for the pollution tax. Furthermore, implementing taxes on resource utilization may be effective but with limited environmental effects. Based on the research results, it is recommended that countries in the OECD implement specific environmental taxes to reduce greenhouse gas emissions.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86081905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The higher education (HE) system is witnessing immense transformations to keep pace with the rapid advancements in digital technologies and due to the recent COVID-19 pandemic compelling educational institutions to completely switch to online teaching and assessments. Assessments are considered to play an important and powerful role in students’ educational experience and evaluation of their academic abilities. However, there are many stigmas associated with both “traditional” and alternative assessment methods. Rethinking assessments is increasingly happening worldwide to keep up with the shift in current teaching and learning paradigms due to new possibilities of using digital technologies and a continuous improvement of student engagement. Many educational decisions such as a change in assessment from traditional summative exams to alternate methods require appropriate rationale and justification. In this paper, we adopt data-driven decision-making (DDDM) as a process for rethinking assessment methods and implementing assessment transformations innovatively in an HE environment. We make use of student performance data to make an informed decision for moving from exam-based assessments to nonexam assessment methods. We demonstrate the application of the DDDM approach for an educational institute by analyzing the impact of transforming the assessments of 13 out of 27 subjects offered in a Bachelor of Information Technology (BIT) program as a case study. A comparison of data analysis performed before, during, and after the COVID-19 pandemic using different student learning measures such as failure rates and mean marks provides meaningful insights into the impact of assessment transformations. Our implementation of the DDDM model along with examining the influencing factors of student learning through assessment transformations in an HE environment is the first of its kind. With many HE providers facing several challenges due to the adoption of blended learning, this pilot study based on a DDDM approach encourages innovation in classroom teaching and assessment redesign. In addition, it opens further research in implementing such evidence-based practices for future classroom innovations and assessment transformations towards achieving higher levels of educational quality.
{"title":"Data-Driven Decision-Making (DDDM) for Higher Education Assessments: A Case Study","authors":"S. Kaspi, S. Venkatraman","doi":"10.3390/systems11060306","DOIUrl":"https://doi.org/10.3390/systems11060306","url":null,"abstract":"The higher education (HE) system is witnessing immense transformations to keep pace with the rapid advancements in digital technologies and due to the recent COVID-19 pandemic compelling educational institutions to completely switch to online teaching and assessments. Assessments are considered to play an important and powerful role in students’ educational experience and evaluation of their academic abilities. However, there are many stigmas associated with both “traditional” and alternative assessment methods. Rethinking assessments is increasingly happening worldwide to keep up with the shift in current teaching and learning paradigms due to new possibilities of using digital technologies and a continuous improvement of student engagement. Many educational decisions such as a change in assessment from traditional summative exams to alternate methods require appropriate rationale and justification. In this paper, we adopt data-driven decision-making (DDDM) as a process for rethinking assessment methods and implementing assessment transformations innovatively in an HE environment. We make use of student performance data to make an informed decision for moving from exam-based assessments to nonexam assessment methods. We demonstrate the application of the DDDM approach for an educational institute by analyzing the impact of transforming the assessments of 13 out of 27 subjects offered in a Bachelor of Information Technology (BIT) program as a case study. A comparison of data analysis performed before, during, and after the COVID-19 pandemic using different student learning measures such as failure rates and mean marks provides meaningful insights into the impact of assessment transformations. Our implementation of the DDDM model along with examining the influencing factors of student learning through assessment transformations in an HE environment is the first of its kind. With many HE providers facing several challenges due to the adoption of blended learning, this pilot study based on a DDDM approach encourages innovation in classroom teaching and assessment redesign. In addition, it opens further research in implementing such evidence-based practices for future classroom innovations and assessment transformations towards achieving higher levels of educational quality.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72641697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Venture capital plays a vital role in boosting economic growth by providing an inexhaustible impetus for economic innovation and development. We use all the joint venture capital events of Chinese listed companies in the past 10 years to describe the characteristics of the joint venture capital network structure, identify the dynamic evolution characteristics of the community, and introduce random attacks and deliberate attacks to explore the resilience of joint venture capital cooperation. The study finds that the joint venture capital network in China has expanded in scale, with an increasing number of participants and a diversified investment industry. However, the connection between members within the network remains relatively loose, indicating fragmentation and a need to improve network quality. The community structure of core members is significant, with evident differences in scale. The network exhibits weak robustness, relying heavily on key enterprises and demonstrating a poor ability to resist external interference. The study proposes countermeasures and suggestions for optimizing the network structure of joint venture capital, aiming to enhance the environment and performance of joint venture capital and promote the high-quality development of China’s joint venture capital market.
{"title":"Venture Capital Syndication Network Structure of Public Companies: Robustness and Dynamic Evolution, China","authors":"Xin Luo, Jianling Yin, Hongtao Jiang, DanQi Wei, Ru-Yi Xia, Yi Ding","doi":"10.3390/systems11060302","DOIUrl":"https://doi.org/10.3390/systems11060302","url":null,"abstract":"Venture capital plays a vital role in boosting economic growth by providing an inexhaustible impetus for economic innovation and development. We use all the joint venture capital events of Chinese listed companies in the past 10 years to describe the characteristics of the joint venture capital network structure, identify the dynamic evolution characteristics of the community, and introduce random attacks and deliberate attacks to explore the resilience of joint venture capital cooperation. The study finds that the joint venture capital network in China has expanded in scale, with an increasing number of participants and a diversified investment industry. However, the connection between members within the network remains relatively loose, indicating fragmentation and a need to improve network quality. The community structure of core members is significant, with evident differences in scale. The network exhibits weak robustness, relying heavily on key enterprises and demonstrating a poor ability to resist external interference. The study proposes countermeasures and suggestions for optimizing the network structure of joint venture capital, aiming to enhance the environment and performance of joint venture capital and promote the high-quality development of China’s joint venture capital market.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75680514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jianjun Zhang, Jin-ping Huang, Tianhao Wang, Jin Zhao
In recent years, epidemic disasters broke through frequently around the world, posing a huge threat to economic and social development, as well as human health. A fair and accurate distribution of emergency supplies during an epidemic is vital for improving emergency rescue efficiency and reducing economic losses. However, traditional emergency material allocation models often focus on meeting the amount of materials requested, and ignore the differences in the importance of different emergency materials and the subjective urgency demand of the disaster victims. As a result, it is difficult for the system to fairly and reasonably match different scarce materials to the corresponding areas of greatest need. Consequently, this paper proposes a material shortage adjustment coefficient based on the entropy weight method, which includes indicators such as material consumption rate, material reproduction rate, durability, degree of danger to life, and degree of irreplaceability, to enlarge and narrow the actual shortage of material supply according to the demand urgency. Due to the fact that emergency materials are not dispatched in one go during epidemic periods, a multi-period integer programming model was established to minimize the adjusted total material shortage based on the above function. Taking the cases of Wuhan and Shanghai during the lockdown and static management period, the quantitative analysis based on material distribution reflected that the model established in this paper was effective in different scenarios where there were significant differences in the quantity and structure of material demand. At the same time, the model could significantly adjust the shortage of emergency materials with higher importance and improve the satisfaction rate.
{"title":"Dynamic Optimization of Emergency Logistics for Major Epidemic Considering Demand Urgency","authors":"Jianjun Zhang, Jin-ping Huang, Tianhao Wang, Jin Zhao","doi":"10.3390/systems11060303","DOIUrl":"https://doi.org/10.3390/systems11060303","url":null,"abstract":"In recent years, epidemic disasters broke through frequently around the world, posing a huge threat to economic and social development, as well as human health. A fair and accurate distribution of emergency supplies during an epidemic is vital for improving emergency rescue efficiency and reducing economic losses. However, traditional emergency material allocation models often focus on meeting the amount of materials requested, and ignore the differences in the importance of different emergency materials and the subjective urgency demand of the disaster victims. As a result, it is difficult for the system to fairly and reasonably match different scarce materials to the corresponding areas of greatest need. Consequently, this paper proposes a material shortage adjustment coefficient based on the entropy weight method, which includes indicators such as material consumption rate, material reproduction rate, durability, degree of danger to life, and degree of irreplaceability, to enlarge and narrow the actual shortage of material supply according to the demand urgency. Due to the fact that emergency materials are not dispatched in one go during epidemic periods, a multi-period integer programming model was established to minimize the adjusted total material shortage based on the above function. Taking the cases of Wuhan and Shanghai during the lockdown and static management period, the quantitative analysis based on material distribution reflected that the model established in this paper was effective in different scenarios where there were significant differences in the quantity and structure of material demand. At the same time, the model could significantly adjust the shortage of emergency materials with higher importance and improve the satisfaction rate.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76488207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, with the rapid development of Internet technology, the number of credit card users has increased significantly. Subsequently, credit card fraud has caused a large amount of economic losses to individual users and related financial enterprises. At present, traditional machine learning methods (such as SVM, random forest, Markov model, etc.) have been widely studied in credit card fraud detection, but these methods are often have difficulty in demonstrating their effectiveness when faced with unknown attack patterns. In this paper, a new Unsupervised Attentional Anomaly Detection Network-based Credit Card Fraud Detection framework (UAAD-FDNet) is proposed. Among them, fraudulent transactions are regarded as abnormal samples, and autoencoders with Feature Attention and GANs are used to effectively separate them from massive transaction data. Extensive experimental results on Kaggle Credit Card Fraud Detection Dataset and IEEE-CIS Fraud Detection Dataset demonstrate that the proposed method outperforms existing fraud detection methods.
{"title":"Credit Card Fraud Detection Based on Unsupervised Attentional Anomaly Detection Network","authors":"Shan Jiang, Ruiting Dong, Jie Wang, Min Xia","doi":"10.3390/systems11060305","DOIUrl":"https://doi.org/10.3390/systems11060305","url":null,"abstract":"In recent years, with the rapid development of Internet technology, the number of credit card users has increased significantly. Subsequently, credit card fraud has caused a large amount of economic losses to individual users and related financial enterprises. At present, traditional machine learning methods (such as SVM, random forest, Markov model, etc.) have been widely studied in credit card fraud detection, but these methods are often have difficulty in demonstrating their effectiveness when faced with unknown attack patterns. In this paper, a new Unsupervised Attentional Anomaly Detection Network-based Credit Card Fraud Detection framework (UAAD-FDNet) is proposed. Among them, fraudulent transactions are regarded as abnormal samples, and autoencoders with Feature Attention and GANs are used to effectively separate them from massive transaction data. Extensive experimental results on Kaggle Credit Card Fraud Detection Dataset and IEEE-CIS Fraud Detection Dataset demonstrate that the proposed method outperforms existing fraud detection methods.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83660241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Internet of Things (IoT) technology has been incorporated into the majority of people’s everyday lives and places of employment due to the quick development in information technology. Modern agricultural techniques increasingly use the well-known and superior approach of managing a farm known as “smart farming”. Utilizing a variety of information and agricultural technologies, crops are observed for their general health and productivity. This requires monitoring the condition of field crops and looking at many other indicators. The goal of smart agriculture is to reduce the amount of money spent on agricultural inputs while keeping the quality of the final product constant. The Internet of Things (IoT) has made smart agriculture possible through data collection and storage techniques. For example, modern irrigation systems use effective sensor networks to collect field data for the best plant irrigation. Smart agriculture will become more susceptible to cyber-attacks as its reliance on the IoT ecosystem grows, because IoT networks have a large number of nodes but limited resources, which makes security a difficult issue. Hence, it is crucial to have an intrusion detection system (IDS) that can address such challenges. In this manuscript, an IoT-based privacy-preserving anomaly detection model for smart agriculture has been proposed. The motivation behind this work is twofold. Firstly, ensuring data privacy in IoT-based agriculture is of the utmost importance due to the large volumes of sensitive information collected by IoT devices, including on environmental conditions, crop health, and resource utilization data. Secondly, the timely detection of anomalies in smart agriculture systems is critical to enable proactive interventions, such as preventing crop damage, optimizing resource allocation, and ensuring sustainable farming practices. In this paper, we propose a privacy-encoding-based enhanced deep learning framework for the difficulty of data encryption and intrusion detection. In terms of data encoding, a novel method of a sparse capsule-auto encoder (SCAE) is proposed along with feature selection, feature mapping, and feature normalization. An SCAE is used to convert information into a new encrypted format in order to prevent deduction attacks. An attention-based gated recurrent unit neural network model is proposed to detect the intrusion. An AGRU is an advanced version of a GRU which is enhanced by an attention mechanism. In the results section, the proposed model is compared with existing deep learning models using two public datasets. Parameters such as recall, precision, accuracy, and F1-score are considered. The proposed model has accuracy, recall, precision, and F1-score of 99.9%, 99.7%, 99.9%, and 99.8%, respectively. The proposed method is compared using a variety of machine learning techniques such as the deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM
{"title":"Iot-Based Privacy-Preserving Anomaly Detection Model for Smart Agriculture","authors":"Keerthi Kethineni, Pradeepini Gera","doi":"10.3390/systems11060304","DOIUrl":"https://doi.org/10.3390/systems11060304","url":null,"abstract":"Internet of Things (IoT) technology has been incorporated into the majority of people’s everyday lives and places of employment due to the quick development in information technology. Modern agricultural techniques increasingly use the well-known and superior approach of managing a farm known as “smart farming”. Utilizing a variety of information and agricultural technologies, crops are observed for their general health and productivity. This requires monitoring the condition of field crops and looking at many other indicators. The goal of smart agriculture is to reduce the amount of money spent on agricultural inputs while keeping the quality of the final product constant. The Internet of Things (IoT) has made smart agriculture possible through data collection and storage techniques. For example, modern irrigation systems use effective sensor networks to collect field data for the best plant irrigation. Smart agriculture will become more susceptible to cyber-attacks as its reliance on the IoT ecosystem grows, because IoT networks have a large number of nodes but limited resources, which makes security a difficult issue. Hence, it is crucial to have an intrusion detection system (IDS) that can address such challenges. In this manuscript, an IoT-based privacy-preserving anomaly detection model for smart agriculture has been proposed. The motivation behind this work is twofold. Firstly, ensuring data privacy in IoT-based agriculture is of the utmost importance due to the large volumes of sensitive information collected by IoT devices, including on environmental conditions, crop health, and resource utilization data. Secondly, the timely detection of anomalies in smart agriculture systems is critical to enable proactive interventions, such as preventing crop damage, optimizing resource allocation, and ensuring sustainable farming practices. In this paper, we propose a privacy-encoding-based enhanced deep learning framework for the difficulty of data encryption and intrusion detection. In terms of data encoding, a novel method of a sparse capsule-auto encoder (SCAE) is proposed along with feature selection, feature mapping, and feature normalization. An SCAE is used to convert information into a new encrypted format in order to prevent deduction attacks. An attention-based gated recurrent unit neural network model is proposed to detect the intrusion. An AGRU is an advanced version of a GRU which is enhanced by an attention mechanism. In the results section, the proposed model is compared with existing deep learning models using two public datasets. Parameters such as recall, precision, accuracy, and F1-score are considered. The proposed model has accuracy, recall, precision, and F1-score of 99.9%, 99.7%, 99.9%, and 99.8%, respectively. The proposed method is compared using a variety of machine learning techniques such as the deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81084618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The outbreak of COVID-19 posed a significant challenge to the emergency management system for public health emergencies, especially in China, where the epidemic began. As intelligent technology has injected new vitality into emergency management, applying intelligent technology to optimize emergency resource allocation (ERA) has become a focus of research in the post-epidemic era. Based on China’s experience in preventing and controlling COVID-19, this paper first analyzes the characteristics and process of ERA in public health emergencies, and then synthesizes the relevant Chinese studies in recent years to identify the intelligent technologies affecting ERA in China using word frequency analysis technology. We also construct an intelligent emergency resource allocation mechanism in four areas: medical intelligence, management intelligence, decision-making intelligence, and supervision intelligence. Finally, we use the entropy-TOPSIS method to evaluate the impact of intelligent technologies on ERA, and we rank the criticality of intelligent technologies. The experimental results show that (i.) medical intelligence and management intelligence are the keys to developing intelligent ERA, and (ii.) among the identified essential intelligent technologies, artificial intelligence (AI), and big data technology have a more significant and critical role in emergency resource intelligence allocation.
{"title":"Research on Intelligent Emergency Resource Allocation Mechanism for Public Health Emergencies: A Case Study on the Prevention and Control of COVID-19 in China","authors":"Ruhao Ma, Fansheng Meng, Haiwen Du","doi":"10.3390/systems11060300","DOIUrl":"https://doi.org/10.3390/systems11060300","url":null,"abstract":"The outbreak of COVID-19 posed a significant challenge to the emergency management system for public health emergencies, especially in China, where the epidemic began. As intelligent technology has injected new vitality into emergency management, applying intelligent technology to optimize emergency resource allocation (ERA) has become a focus of research in the post-epidemic era. Based on China’s experience in preventing and controlling COVID-19, this paper first analyzes the characteristics and process of ERA in public health emergencies, and then synthesizes the relevant Chinese studies in recent years to identify the intelligent technologies affecting ERA in China using word frequency analysis technology. We also construct an intelligent emergency resource allocation mechanism in four areas: medical intelligence, management intelligence, decision-making intelligence, and supervision intelligence. Finally, we use the entropy-TOPSIS method to evaluate the impact of intelligent technologies on ERA, and we rank the criticality of intelligent technologies. The experimental results show that (i.) medical intelligence and management intelligence are the keys to developing intelligent ERA, and (ii.) among the identified essential intelligent technologies, artificial intelligence (AI), and big data technology have a more significant and critical role in emergency resource intelligence allocation.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83726228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Semi-formal software techniques have been very successful in industry, government institutions and other areas such as academia. Arguably, they owe a large part of their success to their graphical notation, which is more human-oriented than their counterpart text-based and formal notation techniques. However, ensuring the consistency between two or more models is one of the known challenges of these techniques. This work looks closely at the specific case of the User Requirements Notation (URN) technique. Although the abstract model of URN provides for link elements to ensure the consistency between its two main components, namely, Goal-Oriented Requirement Language (GRL) and Use Case Maps (UCM), the effective implementation of such links is yet to be fully addressed. This paper performs a detailed analysis of the existing URN models construction process and proposes an improved process with some guidelines to ensure, by construction, the correctness and consistency of the GRL and UCM models. A case study is used throughout the paper to illustrate the suggested solution.
{"title":"An Improved User Requirements Notation (URN) Models' Construction Approach","authors":"Cyrille Dongmo, J. A. V. D. Poll","doi":"10.3390/systems11060301","DOIUrl":"https://doi.org/10.3390/systems11060301","url":null,"abstract":"Semi-formal software techniques have been very successful in industry, government institutions and other areas such as academia. Arguably, they owe a large part of their success to their graphical notation, which is more human-oriented than their counterpart text-based and formal notation techniques. However, ensuring the consistency between two or more models is one of the known challenges of these techniques. This work looks closely at the specific case of the User Requirements Notation (URN) technique. Although the abstract model of URN provides for link elements to ensure the consistency between its two main components, namely, Goal-Oriented Requirement Language (GRL) and Use Case Maps (UCM), the effective implementation of such links is yet to be fully addressed. This paper performs a detailed analysis of the existing URN models construction process and proposes an improved process with some guidelines to ensure, by construction, the correctness and consistency of the GRL and UCM models. A case study is used throughout the paper to illustrate the suggested solution.","PeriodicalId":52858,"journal":{"name":"syst mt`lyh","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90797951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：