Vicente García Díaz, Jerry Chun‐wei Lin, Juan Antonio Morente Molinera
Most countries around the world are trying to make the idea of “smart cities” a reality by building the basic infrastructure needed to use the technology. In this case, edge computing (EC) is very important for faster data processing and faster responses at the edges of the network. In recent years, smart cities have started using EC to improve building security, home automation, urban parking systems, and traffic and city management. Traditional IoT networks collect data and send it to a central cloud for further processing. EC devices, in contrast, can process and analyze the data themselves, as well as reduce the load on the network. In addition, mobile crowdsensing (MCS) and mobile edge computing (MEC) provide the crowdsensing services needed for a smart city in a densely populated area. These techniques provide a specific service at a specific location and for a specific period of time. However, they are better suited to support technical communication services with static edges than the human side. This leads to a dynamic extension of MEC called human-enabled edge computing (HEC), which combines people, devices, the Internet, and information with the architecture of MEC and the ability to sense MCS. In general, a traditional sensor network does not take context into account as well as HEC because it uses smart devices such as smartphones and wearables that people carry with them. It also uses data from mobile devices to obtain crowd intelligence and provide services based on what people want. Edge computing involves both people and things and therefore requires intelligent methods for classification and decision making, such as machine learning, data mining, and cognitive intelligence. Edge intelligence is used in the smart city to leverage data from different parts of the smart city. This is done by running analytics algorithms at the edge of the city. This speeds up the time it takes networked devices to make decisions and improves the quality of the data. Smart cities are taking advantage of HEC and next-generation wireless technology to connect things to people and the Internet of Things (IoT), resulting in powerful services and automation in the creation of dense and changing data sets. A successful edge computing infrastructure requires a local server, AI, and connections to computing systems in mobile devices, cars, and the Internet of Things (IoT). The research community has responded with enthusiasm. Only research articles that meet the journal’s requirements are accepted for publication after peer review. In this special issue, we have received 34 articles, and we finally include only one article, which has been fairly peerreviewed and accepted for publication. The following points highlight the remarkable scientific achievements of the accepted article.
{"title":"Introduction to the Special Section on Edge Computing AI-IoT Integrated Energy Efficient Intelligent Transportation System for Smart Cities","authors":"Vicente García Díaz, Jerry Chun‐wei Lin, Juan Antonio Morente Molinera","doi":"10.1145/3584745","DOIUrl":"https://doi.org/10.1145/3584745","url":null,"abstract":"Most countries around the world are trying to make the idea of “smart cities” a reality by building the basic infrastructure needed to use the technology. In this case, edge computing (EC) is very important for faster data processing and faster responses at the edges of the network. In recent years, smart cities have started using EC to improve building security, home automation, urban parking systems, and traffic and city management. Traditional IoT networks collect data and send it to a central cloud for further processing. EC devices, in contrast, can process and analyze the data themselves, as well as reduce the load on the network. In addition, mobile crowdsensing (MCS) and mobile edge computing (MEC) provide the crowdsensing services needed for a smart city in a densely populated area. These techniques provide a specific service at a specific location and for a specific period of time. However, they are better suited to support technical communication services with static edges than the human side. This leads to a dynamic extension of MEC called human-enabled edge computing (HEC), which combines people, devices, the Internet, and information with the architecture of MEC and the ability to sense MCS. In general, a traditional sensor network does not take context into account as well as HEC because it uses smart devices such as smartphones and wearables that people carry with them. It also uses data from mobile devices to obtain crowd intelligence and provide services based on what people want. Edge computing involves both people and things and therefore requires intelligent methods for classification and decision making, such as machine learning, data mining, and cognitive intelligence. Edge intelligence is used in the smart city to leverage data from different parts of the smart city. This is done by running analytics algorithms at the edge of the city. This speeds up the time it takes networked devices to make decisions and improves the quality of the data. Smart cities are taking advantage of HEC and next-generation wireless technology to connect things to people and the Internet of Things (IoT), resulting in powerful services and automation in the creation of dense and changing data sets. A successful edge computing infrastructure requires a local server, AI, and connections to computing systems in mobile devices, cars, and the Internet of Things (IoT). The research community has responded with enthusiasm. Only research articles that meet the journal’s requirements are accepted for publication after peer review. In this special issue, we have received 34 articles, and we finally include only one article, which has been fairly peerreviewed and accepted for publication. The following points highlight the remarkable scientific achievements of the accepted article.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"22 1","pages":"1 - 2"},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43272319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introduction to the Special Section on Cyber Security in Internet of Vehicles","authors":"Ching-Hsien Hsu, Amir H. Alavi, M. Dong","doi":"10.1145/3584746","DOIUrl":"https://doi.org/10.1145/3584746","url":null,"abstract":"a","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"22 1","pages":"1 - 6"},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47228162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Ciortea, Xiao-Wan Zhu, C. Pu, Munindar P. Singh
Over the past two decades, the Internet of Things (IoT) has evolved from silos built around custom protocol stacks into a system of systems built around standards—and the recent standardization of the Web of Things (WoT) at the IETF and the W3C further facilitates application-layer interoperability in the IoT. Constrained Web servers now target devices with as little as 10 KiB of RAM and 100 KiB of ROM, which means sensors and actuators can be abstracted behind embedded Web services. Going further, the WoT aims to provide uniform access to IoT devices through the Web—by hiding the protocols and interfaces used to access the devices behind abstract interaction patterns and hypermedia controls. From the edge of the network to the cloud, the Web is now emerging as a uniform hypermedia fabric that interconnects IoT devices and digital services. Still, many research questions remain open. IoT systems are not only inherently complex and heterogeneous, but also highly dynamic as the availability of devices (and their services) changes continually. Moreover, the IoT is inherently decentralized because it is not under the control of a single entity. In such settings, traditional engineering paradigms become impractical. Researchers and practitioners in the IoT community therefore require means to build sophisticated software agents that can achieve their design objectives through flexible interaction with other entities in their system. Many of the underlying research questions the IoT community is now confronted with—such as how to balance goal-directed and reactive behavior in software agents, or how to design and govern interactions in a decentralized IoT—have been investigated in the scientific literature on multiagent systems. At the same time, the IoT unlocks new practical use cases for multiagent systems.
{"title":"Introduction to the Special Issue on Multiagent Systems and Services in the Internet of Things","authors":"A. Ciortea, Xiao-Wan Zhu, C. Pu, Munindar P. Singh","doi":"10.1145/3584744","DOIUrl":"https://doi.org/10.1145/3584744","url":null,"abstract":"Over the past two decades, the Internet of Things (IoT) has evolved from silos built around custom protocol stacks into a system of systems built around standards—and the recent standardization of the Web of Things (WoT) at the IETF and the W3C further facilitates application-layer interoperability in the IoT. Constrained Web servers now target devices with as little as 10 KiB of RAM and 100 KiB of ROM, which means sensors and actuators can be abstracted behind embedded Web services. Going further, the WoT aims to provide uniform access to IoT devices through the Web—by hiding the protocols and interfaces used to access the devices behind abstract interaction patterns and hypermedia controls. From the edge of the network to the cloud, the Web is now emerging as a uniform hypermedia fabric that interconnects IoT devices and digital services. Still, many research questions remain open. IoT systems are not only inherently complex and heterogeneous, but also highly dynamic as the availability of devices (and their services) changes continually. Moreover, the IoT is inherently decentralized because it is not under the control of a single entity. In such settings, traditional engineering paradigms become impractical. Researchers and practitioners in the IoT community therefore require means to build sophisticated software agents that can achieve their design objectives through flexible interaction with other entities in their system. Many of the underlying research questions the IoT community is now confronted with—such as how to balance goal-directed and reactive behavior in software agents, or how to design and govern interactions in a decentralized IoT—have been investigated in the scientific literature on multiagent systems. At the same time, the IoT unlocks new practical use cases for multiagent systems.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":" ","pages":"1 - 3"},"PeriodicalIF":5.3,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42518489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ramesh Sekaran, Fadi M. Al-Turjman, Rizwan Patan, V. Ramasamy
Mobile network is a collection of devices with dynamic behavior where devices keep moving, which may lead to the network track to be connected or disconnected. This type of network is called Intermittently Connected Mobile Network (ICMN). The ICMN network is designed by splitting the region into `n' regions, ensuring it is a disconnected network. This network holds the same topological structure with mobile devices in it. This type of network routing is a challenging task. Though research keeps deriving techniques to achieve efficient routing in ICMN such as Epidemic, Flooding, Spray, copy case, Probabilistic, and Wait, these derived techniques for routing in ICMN are wise with higher packet delivery ratio, minimum latency, lesser overhead, and so on. A new routing schedule has been enacted comprising three optimization techniques such as Privacy-Preserving Ant Routing Protocol (PPARP), Privacy-Preserving Routing Protocol (PPRP), and Privacy-Preserving Bee Routing Protocol (PPBRP). In this paper, the enacted technique gives an optimal result following various network characteristics. Algorithms embedded with productive routing provide maximum security. Results are pointed out by analysis taken from spreading false devices into the network and its effectiveness at worst case. This paper also aids with the comparative results of enacted algorithms for secure routing in ICMN.
{"title":"Tripartite Transmitting Methodology for Intermittently Connected Mobile Network (ICMN)","authors":"Ramesh Sekaran, Fadi M. Al-Turjman, Rizwan Patan, V. Ramasamy","doi":"10.1145/3433545","DOIUrl":"https://doi.org/10.1145/3433545","url":null,"abstract":"Mobile network is a collection of devices with dynamic behavior where devices keep moving, which may lead to the network track to be connected or disconnected. This type of network is called Intermittently Connected Mobile Network (ICMN). The ICMN network is designed by splitting the region into `n' regions, ensuring it is a disconnected network. This network holds the same topological structure with mobile devices in it. This type of network routing is a challenging task. Though research keeps deriving techniques to achieve efficient routing in ICMN such as Epidemic, Flooding, Spray, copy case, Probabilistic, and Wait, these derived techniques for routing in ICMN are wise with higher packet delivery ratio, minimum latency, lesser overhead, and so on. A new routing schedule has been enacted comprising three optimization techniques such as Privacy-Preserving Ant Routing Protocol (PPARP), Privacy-Preserving Routing Protocol (PPRP), and Privacy-Preserving Bee Routing Protocol (PPBRP). In this paper, the enacted technique gives an optimal result following various network characteristics. Algorithms embedded with productive routing provide maximum security. Results are pointed out by analysis taken from spreading false devices into the network and its effectiveness at worst case. This paper also aids with the comparative results of enacted algorithms for secure routing in ICMN.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":" ","pages":"1 - 18"},"PeriodicalIF":5.3,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46702566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yirui Wu, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan
With the remarkable technological development in cyber-physical systems, industry 4.0 has evolved by a significant concept named as digital twin (DT). However, it’s still difficult to construct relationship between twin simulation and real scenario considering dynamic variations, especially when dealing with small surface defect detection tasks with high performance and computation resource requirement. In this paper, we aim to construct cyber-manufacturing systems to achieve a DT solution for small surface defect detection task. Focusing on DT based solution, the proposed system consists of an Edge-Cloud architecture and a surface defect detection algorithm. Considering dynamic characteristics and real-time response requirement, Edge-Cloud architecture is built to achieve smart manufacturing by efficiently collecting, processing, analyzing, and storing data produced by factory. A deep learning based algorithm is then constructed to detect surface defeats based on multi-modal data, i.e., imaging and depth data. Experiments show the proposed algorithm could achieve high accuracy and recall in small defeat detection task, thus constructing DT in cyber-manufacturing.
{"title":"Digital Twin of Intelligent Small Surface Defect Detection with Cyber-Manufacturing Systems","authors":"Yirui Wu, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan","doi":"10.1145/3571734","DOIUrl":"https://doi.org/10.1145/3571734","url":null,"abstract":"With the remarkable technological development in cyber-physical systems, industry 4.0 has evolved by a significant concept named as digital twin (DT). However, it’s still difficult to construct relationship between twin simulation and real scenario considering dynamic variations, especially when dealing with small surface defect detection tasks with high performance and computation resource requirement. In this paper, we aim to construct cyber-manufacturing systems to achieve a DT solution for small surface defect detection task. Focusing on DT based solution, the proposed system consists of an Edge-Cloud architecture and a surface defect detection algorithm. Considering dynamic characteristics and real-time response requirement, Edge-Cloud architecture is built to achieve smart manufacturing by efficiently collecting, processing, analyzing, and storing data produced by factory. A deep learning based algorithm is then constructed to detect surface defeats based on multi-modal data, i.e., imaging and depth data. Experiments show the proposed algorithm could achieve high accuracy and recall in small defeat detection task, thus constructing DT in cyber-manufacturing.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"1 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44237622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Desktop as a Service (DaaS) has become widely used by enterprises. In 2020, the use of DaaS increased dramatically due to the demand to work remotely from home during the COVID-19 pandemic. The DaaS market is expected to continue growing rapidly [1]. The quality of experience (QoE) of a DaaS service has been one of the main factors to enhance DaaS user satisfaction. To ensure user QoE, the amount of cloud computation resources for a DaaS service must be appropriately designed. We propose an Intent-driven DaaS Management (IDM) framework to autonomously determine the cloud-resource-amount configurations for a given DaaS QoE requirement. IDM enables autonomous resource design by abstracting the knowledge about the dependency between DaaS workload, resource configuration, and performance from previous DaaS performance log data. To ensure the IDM framework's applicability to actual DaaS services, we analyzed five main challenges in applying the IDM framework to actual DaaS services: identifying the resource-design objective, quantifying DaaS QoE, addressing low log data availability, designing performance-inference models, and addressing low resource variations in the log data. We addressed these challenges through detailed designing of IDM modules. The effectiveness of the IDM framework was assessed from the aspects of DaaS performance-inference precision, DaaS resource design, and time and human-resource cost reduction.
{"title":"An Intent-driven DaaS Management Framework to Enhance User Quality of Experience","authors":"Chaofeng Wu, Shingo Horiuchi, Kenji Murase, Hiroaki Kikushima, Kenichi Tayama","doi":"10.1145/3488586","DOIUrl":"https://doi.org/10.1145/3488586","url":null,"abstract":"Desktop as a Service (DaaS) has become widely used by enterprises. In 2020, the use of DaaS increased dramatically due to the demand to work remotely from home during the COVID-19 pandemic. The DaaS market is expected to continue growing rapidly [1]. The quality of experience (QoE) of a DaaS service has been one of the main factors to enhance DaaS user satisfaction. To ensure user QoE, the amount of cloud computation resources for a DaaS service must be appropriately designed. We propose an Intent-driven DaaS Management (IDM) framework to autonomously determine the cloud-resource-amount configurations for a given DaaS QoE requirement. IDM enables autonomous resource design by abstracting the knowledge about the dependency between DaaS workload, resource configuration, and performance from previous DaaS performance log data. To ensure the IDM framework's applicability to actual DaaS services, we analyzed five main challenges in applying the IDM framework to actual DaaS services: identifying the resource-design objective, quantifying DaaS QoE, addressing low log data availability, designing performance-inference models, and addressing low resource variations in the log data. We addressed these challenges through detailed designing of IDM modules. The effectiveness of the IDM framework was assessed from the aspects of DaaS performance-inference precision, DaaS resource design, and time and human-resource cost reduction.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":" ","pages":"1 - 25"},"PeriodicalIF":5.3,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44911688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Geographically distributed (geo-distributed) datacenters for stream data processing typically comprise multiple edges and core datacenters connected through Wide-Area Network (WAN) with a master node responsible for allocating tasks to worker nodes. Since WAN links significantly impact the performance of distributed task execution, the existing task assignment approach is unsuitable for distributed stream data processing with low latency and high throughput demand. In this paper, we propose SAFA, a resource provisioning framework using the Software-Defined Networking (SDN) concept with an SDN controller responsible for monitoring the WAN, selecting an appropriate subset of worker nodes, and assigning tasks to the designated worker nodes. We implemented the data plane of the framework in P4 and the control plane components in Python. We tested the performance of the proposed system on Apache Spark, Apache Storm, and Apache Flink using the Yahoo! streaming benchmark on a set of custom topologies. The results of the experiments validate that the proposed approach is viable for distributed stream processing and confirm that it can improve at least 1.64× the processing time of incoming events of the current stream processing systems.
{"title":"SDN-enabled Resource Provisioning Framework for Geo-Distributed Streaming Analytics","authors":"H. Mostafaei, Shafi Afridi","doi":"10.1145/3571158","DOIUrl":"https://doi.org/10.1145/3571158","url":null,"abstract":"Geographically distributed (geo-distributed) datacenters for stream data processing typically comprise multiple edges and core datacenters connected through Wide-Area Network (WAN) with a master node responsible for allocating tasks to worker nodes. Since WAN links significantly impact the performance of distributed task execution, the existing task assignment approach is unsuitable for distributed stream data processing with low latency and high throughput demand. In this paper, we propose SAFA, a resource provisioning framework using the Software-Defined Networking (SDN) concept with an SDN controller responsible for monitoring the WAN, selecting an appropriate subset of worker nodes, and assigning tasks to the designated worker nodes. We implemented the data plane of the framework in P4 and the control plane components in Python. We tested the performance of the proposed system on Apache Spark, Apache Storm, and Apache Flink using the Yahoo! streaming benchmark on a set of custom topologies. The results of the experiments validate that the proposed approach is viable for distributed stream processing and confirm that it can improve at least 1.64× the processing time of incoming events of the current stream processing systems.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":" ","pages":"1 - 21"},"PeriodicalIF":5.3,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41533278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martino Trevisan, Francesca Soro, M. Mellia, I. Drago, R. Morla
Privacy on the Internet has become a priority, and several efforts have been devoted to limit the leakage of personal information. Domain names, both in the TLS Client Hello and DNS traffic, are among the last pieces of information still visible to an observer in the network. The Encrypted Client Hello extension for TLS, DNS over HTTPS or over QUIC protocols aim to further increase network confidentiality by encrypting the domain names of the visited servers. In this article, we check whether an attacker able to passively observe the traffic of users could still recover the domain name of websites they visit even if names are encrypted. By relying on large-scale network traces, we show that simplistic features and off-the-shelf machine learning models are sufficient to achieve surprisingly high precision and recall when recovering encrypted domain names. We consider three attack scenarios, i.e., recovering the per-flow name, rebuilding the set of visited websites by a user, and checking which users visit a given target website. We next evaluate the efficacy of padding-based mitigation, finding that all three attacks are still effective, despite resources wasted with padding. We conclude that current proposals for domain encryption may produce a false sense of privacy, and more robust techniques should be envisioned to offer protection to end users.
{"title":"Attacking DoH and ECH: Does Server Name Encryption Protect Users’ Privacy?","authors":"Martino Trevisan, Francesca Soro, M. Mellia, I. Drago, R. Morla","doi":"10.1145/3570726","DOIUrl":"https://doi.org/10.1145/3570726","url":null,"abstract":"Privacy on the Internet has become a priority, and several efforts have been devoted to limit the leakage of personal information. Domain names, both in the TLS Client Hello and DNS traffic, are among the last pieces of information still visible to an observer in the network. The Encrypted Client Hello extension for TLS, DNS over HTTPS or over QUIC protocols aim to further increase network confidentiality by encrypting the domain names of the visited servers. In this article, we check whether an attacker able to passively observe the traffic of users could still recover the domain name of websites they visit even if names are encrypted. By relying on large-scale network traces, we show that simplistic features and off-the-shelf machine learning models are sufficient to achieve surprisingly high precision and recall when recovering encrypted domain names. We consider three attack scenarios, i.e., recovering the per-flow name, rebuilding the set of visited websites by a user, and checking which users visit a given target website. We next evaluate the efficacy of padding-based mitigation, finding that all three attacks are still effective, despite resources wasted with padding. We conclude that current proposals for domain encryption may produce a false sense of privacy, and more robust techniques should be envisioned to offer protection to end users.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":" ","pages":"1 - 22"},"PeriodicalIF":5.3,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46905161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luigi Asprino, E. Daga, Aldo Gangemi, P. Mulholland
Data integration is the dominant use case for RDF Knowledge Graphs. However, Web resources come in formats with weak semantics (for example, CSV and JSON), or formats specific to a given application (for example, BibTex, HTML, and Markdown). To solve this problem, Knowledge Graph Construction (KGC) is gaining momentum due to its focus on supporting users in transforming data into RDF. However, using existing KGC frameworks result in complex data processing pipelines, which mix structural and semantic mappings, whose development and maintenance constitute a significant bottleneck for KG engineers. Such frameworks force users to rely on different tools, sometimes based on heterogeneous languages, for inspecting sources, designing mappings, and generating triples, thus making the process unnecessarily complicated. We argue that it is possible and desirable to equip KG engineers with the ability of interacting with Web data formats by relying on their expertise in RDF and the well-established SPARQL query language [2]. In this article, we study a unified method for data access to heterogeneous data sources with Facade-X, a meta-model implemented in a new data integration system called SPARQL Anything. We demonstrate that our approach is theoretically sound, since it allows a single meta-model, based on RDF, to represent data from (a) any file format expressible in BNF syntax, as well as (b) any relational database. We compare our method to state-of-the-art approaches in terms of usability (cognitive complexity of the mappings) and general performance. Finally, we discuss the benefits and challenges of this novel approach by engaging with the reference user community.
{"title":"Knowledge Graph Construction with a Façade: A Unified Method to Access Heterogeneous Data Sources on the Web","authors":"Luigi Asprino, E. Daga, Aldo Gangemi, P. Mulholland","doi":"10.1145/3555312","DOIUrl":"https://doi.org/10.1145/3555312","url":null,"abstract":"Data integration is the dominant use case for RDF Knowledge Graphs. However, Web resources come in formats with weak semantics (for example, CSV and JSON), or formats specific to a given application (for example, BibTex, HTML, and Markdown). To solve this problem, Knowledge Graph Construction (KGC) is gaining momentum due to its focus on supporting users in transforming data into RDF. However, using existing KGC frameworks result in complex data processing pipelines, which mix structural and semantic mappings, whose development and maintenance constitute a significant bottleneck for KG engineers. Such frameworks force users to rely on different tools, sometimes based on heterogeneous languages, for inspecting sources, designing mappings, and generating triples, thus making the process unnecessarily complicated. We argue that it is possible and desirable to equip KG engineers with the ability of interacting with Web data formats by relying on their expertise in RDF and the well-established SPARQL query language [2]. In this article, we study a unified method for data access to heterogeneous data sources with Facade-X, a meta-model implemented in a new data integration system called SPARQL Anything. We demonstrate that our approach is theoretically sound, since it allows a single meta-model, based on RDF, to represent data from (a) any file format expressible in BNF syntax, as well as (b) any relational database. We compare our method to state-of-the-art approaches in terms of usability (cognitive complexity of the mappings) and general performance. Finally, we discuss the benefits and challenges of this novel approach by engaging with the reference user community.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"23 1","pages":"1 - 31"},"PeriodicalIF":5.3,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46818022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The financial impact of online reviews has prompted some fraudulent sellers to generate fake consumer reviews for either promoting their products or discrediting competing products. In this study, we propose a novel ensemble model—the Multi-type Classifier Ensemble (MtCE)—combined with a textual-based featuring method, which is relatively independent of the system, to detect fake online consumer reviews. Unlike other ensemble models that utilise only the same type of single classifier, our proposed ensemble utilises several customised machine learning classifiers (including deep learning models) as its base classifiers. The results of our experiments show that the MtCE can adequately detect fake reviews, and that it outperforms other single and ensemble methods in terms of accuracy and other measurements for all the relevant public datasets used in this study. Moreover, if set correctly, the parameters of MtCE, such as base-classifier types, the total number of base classifiers, bootstrap, and the method to vote on output (e.g., majority or priority), can further improve the performance of the proposed ensemble.
{"title":"A Multi-type Classifier Ensemble for Detecting Fake Reviews Through Textual-based Feature Extraction","authors":"G. S. Budhi, R. Chiong","doi":"10.1145/3568676","DOIUrl":"https://doi.org/10.1145/3568676","url":null,"abstract":"The financial impact of online reviews has prompted some fraudulent sellers to generate fake consumer reviews for either promoting their products or discrediting competing products. In this study, we propose a novel ensemble model—the Multi-type Classifier Ensemble (MtCE)—combined with a textual-based featuring method, which is relatively independent of the system, to detect fake online consumer reviews. Unlike other ensemble models that utilise only the same type of single classifier, our proposed ensemble utilises several customised machine learning classifiers (including deep learning models) as its base classifiers. The results of our experiments show that the MtCE can adequately detect fake reviews, and that it outperforms other single and ensemble methods in terms of accuracy and other measurements for all the relevant public datasets used in this study. Moreover, if set correctly, the parameters of MtCE, such as base-classifier types, the total number of base classifiers, bootstrap, and the method to vote on output (e.g., majority or priority), can further improve the performance of the proposed ensemble.","PeriodicalId":50911,"journal":{"name":"ACM Transactions on Internet Technology","volume":"23 1","pages":"1 - 24"},"PeriodicalIF":5.3,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43432553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：