Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623140
Steve Chan, M. Krunz, Bob Griffin
The discernment of waveforms for the purpose of identifying the underlying wireless technologies and validating if observed transmissions are legitimate or not remains a challenge within the communications sector and beyond. Conventional techniques struggle to robustly process Signals under Test (SuTs) in real-time. A particular difficulty relates to the selection of an appropriate window size for the processed data when pertinent contextual information on SuTs is not known a priori. The disadvantage of applying a predetermined fixed window size is that of length and shape (i.e., coarse resolution). In contrast, an adaptive window size offers more optimally tuned resolution. Towards this end, we propose a novel approach that uses an Adaptive Resolution Transform (ART) to either maintain a constant (prespecified) resolution, via a Variable Window Size and Shape (VWSS), or adjust the resolution (again using the VWSS technique) to match latency requirements. Central to this approach is the utilization of Continuous Wavelet Transforms (CWTs), which do not substantively suffer from those energy leakage issues found in more commonly used transforms such as Discrete Wavelet Transforms (DWT). A robust numerical implementation of CWTs is presented via a particular class of Convolutional Neural Networks (CNNs) called Robust Convex Relaxation (RCR)-based Convolutional Long Short-Term Memory Deep Neural Networks (a.k.a., CLSTMDNNs or CLNNs). By employing small convolutional filters, this class leverages deeper cascade learning, which nicely emulates CWTs. In addition to its use for convex relaxation adversarial training, the RCR framework also improves the bound tightening for the successive convolutional layers (which contain the cascading of ever smaller “CWT-like” convolutional filters). In this paper, we explore this particular architecture for its discernment capability among the SuT time series being compared. To operationalize this architectural paradigm, non-conventional Nonnegative Matrix Factorization (NMF) and Multiresolution Matrix Factorization (MMF) is used in conjunction to facilitate the capture of the structure and content of the involved matrices so as to achieve higher resolution and enhanced discernment accuracy. The desired WT (a.k.a., Corresponding WT or CORWT) resulting from the MMF is implemented as a translation-invariant CWT PyWavelet to better illuminate the intricate structural characteristics of the SuT and facilitate the analysis/discernment of their constituent Waveforms of Interest (WoIs). A precomputed hash and lookup table is utilized to facilitate WoI classification and discernment in quasi-real-time.
{"title":"Adaptive Time-Frequency Synthesis for Waveform Discernment in Wireless Communications","authors":"Steve Chan, M. Krunz, Bob Griffin","doi":"10.1109/iemcon53756.2021.9623140","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623140","url":null,"abstract":"The discernment of waveforms for the purpose of identifying the underlying wireless technologies and validating if observed transmissions are legitimate or not remains a challenge within the communications sector and beyond. Conventional techniques struggle to robustly process Signals under Test (SuTs) in real-time. A particular difficulty relates to the selection of an appropriate window size for the processed data when pertinent contextual information on SuTs is not known a priori. The disadvantage of applying a predetermined fixed window size is that of length and shape (i.e., coarse resolution). In contrast, an adaptive window size offers more optimally tuned resolution. Towards this end, we propose a novel approach that uses an Adaptive Resolution Transform (ART) to either maintain a constant (prespecified) resolution, via a Variable Window Size and Shape (VWSS), or adjust the resolution (again using the VWSS technique) to match latency requirements. Central to this approach is the utilization of Continuous Wavelet Transforms (CWTs), which do not substantively suffer from those energy leakage issues found in more commonly used transforms such as Discrete Wavelet Transforms (DWT). A robust numerical implementation of CWTs is presented via a particular class of Convolutional Neural Networks (CNNs) called Robust Convex Relaxation (RCR)-based Convolutional Long Short-Term Memory Deep Neural Networks (a.k.a., CLSTMDNNs or CLNNs). By employing small convolutional filters, this class leverages deeper cascade learning, which nicely emulates CWTs. In addition to its use for convex relaxation adversarial training, the RCR framework also improves the bound tightening for the successive convolutional layers (which contain the cascading of ever smaller “CWT-like” convolutional filters). In this paper, we explore this particular architecture for its discernment capability among the SuT time series being compared. To operationalize this architectural paradigm, non-conventional Nonnegative Matrix Factorization (NMF) and Multiresolution Matrix Factorization (MMF) is used in conjunction to facilitate the capture of the structure and content of the involved matrices so as to achieve higher resolution and enhanced discernment accuracy. The desired WT (a.k.a., Corresponding WT or CORWT) resulting from the MMF is implemented as a translation-invariant CWT PyWavelet to better illuminate the intricate structural characteristics of the SuT and facilitate the analysis/discernment of their constituent Waveforms of Interest (WoIs). A precomputed hash and lookup table is utilized to facilitate WoI classification and discernment in quasi-real-time.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115182148","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623130
Zohreh Karimi, M. Soheili, Navid Heydarishahreza, S. Ebadollahi, Bob Gill
Indoor Positioning has been in the center of attention in trending research. To this end, various means have been applied, including WiFi, Radio Frequency Identification (RFID), Fingerprinting, and Pedestrian Dead Reckoning (PDR). Smartphones, as an efficacious remedy for PDR technique parameters, are a serviceable choice due to their vast use. This article is dedicated to identifying and classifying different smartphone carrying patterns in different motion positions. Hence, we go through two steps; First using Machine Learning (ML) and Artificial Neural Networks(ANN), we identify smartphone carrying modes during user motions with four users and one smartphone to detect the suitable algorithm with the highest accuracy. Novelty of this paper is using Weighted K-Nearest Neighbor (WKNN) and ensemble by Genetic Algorithm (GA) with optimal weight, having offered notable results in categorizing. Furthermore, we review the smartphone sensor calibration effects on accuracy obtained by categorizing using four users and two smartphones in two states, before and after calibration using ML and ANN. The outcome was, calibration with smartphone sensors helps to categorize accuracy.
{"title":"Smartphone Mode Detection for Positioning using Inertial Sensor","authors":"Zohreh Karimi, M. Soheili, Navid Heydarishahreza, S. Ebadollahi, Bob Gill","doi":"10.1109/iemcon53756.2021.9623130","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623130","url":null,"abstract":"Indoor Positioning has been in the center of attention in trending research. To this end, various means have been applied, including WiFi, Radio Frequency Identification (RFID), Fingerprinting, and Pedestrian Dead Reckoning (PDR). Smartphones, as an efficacious remedy for PDR technique parameters, are a serviceable choice due to their vast use. This article is dedicated to identifying and classifying different smartphone carrying patterns in different motion positions. Hence, we go through two steps; First using Machine Learning (ML) and Artificial Neural Networks(ANN), we identify smartphone carrying modes during user motions with four users and one smartphone to detect the suitable algorithm with the highest accuracy. Novelty of this paper is using Weighted K-Nearest Neighbor (WKNN) and ensemble by Genetic Algorithm (GA) with optimal weight, having offered notable results in categorizing. Furthermore, we review the smartphone sensor calibration effects on accuracy obtained by categorizing using four users and two smartphones in two states, before and after calibration using ML and ANN. The outcome was, calibration with smartphone sensors helps to categorize accuracy.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114447447","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623079
Hung-Chin Jang, Tsung-Yen Tsai
With the rapid development and progress of the Internet of Things and artificial intelligence, more and more businesses have combined housing with emerging technologies to create smart homes to improve residents' quality of life. Many services similar to the three major application scenarios of 5G will be applied to different smart devices in future smart homes. Therefore, the overall network traffic of smart homes will inevitably increase substantially, making network traffic management in smart homes an issue worthy of in-depth discussion. However, due to the widespread use of network encryption, it is not easy to obtain information from most network application services by decrypting the traffic. It is also difficult to classify various service flows through traditional network traffic classification methods into distinct application categories for management. This research assumes that Internet Service Providers (ISPs) have to manage tens of thousands of smart homes equipped with various kinds of IoT devices. We used software-defined networking (SDN) technology to simulate a multi-tenant smart home environment, simulate different types of smart home service traffic, and use convolutional neural networks (CNN) to classify network traffic. ISP operators can thus set the bandwidth ratio according to the classified service category to effectively improve QoS and user QoE. The experimental results show that the traffic classification accuracy of the CNN model for smart homes can reach 86.5%, which is higher than the general neural network model by 6.5%.
{"title":"Using CNN to Optimize Traffic Classification for Smart Homes in 5G Era","authors":"Hung-Chin Jang, Tsung-Yen Tsai","doi":"10.1109/iemcon53756.2021.9623079","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623079","url":null,"abstract":"With the rapid development and progress of the Internet of Things and artificial intelligence, more and more businesses have combined housing with emerging technologies to create smart homes to improve residents' quality of life. Many services similar to the three major application scenarios of 5G will be applied to different smart devices in future smart homes. Therefore, the overall network traffic of smart homes will inevitably increase substantially, making network traffic management in smart homes an issue worthy of in-depth discussion. However, due to the widespread use of network encryption, it is not easy to obtain information from most network application services by decrypting the traffic. It is also difficult to classify various service flows through traditional network traffic classification methods into distinct application categories for management. This research assumes that Internet Service Providers (ISPs) have to manage tens of thousands of smart homes equipped with various kinds of IoT devices. We used software-defined networking (SDN) technology to simulate a multi-tenant smart home environment, simulate different types of smart home service traffic, and use convolutional neural networks (CNN) to classify network traffic. ISP operators can thus set the bandwidth ratio according to the classified service category to effectively improve QoS and user QoE. The experimental results show that the traffic classification accuracy of the CNN model for smart homes can reach 86.5%, which is higher than the general neural network model by 6.5%.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128387972","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623251
Saikat Das, Ph.D., Namita Agarwal, S. Shiva
Machine learning (ML) experts have been using black-box classifiers for modeling purposes. However, the users of these systems are raising questions about the transparency of the predictions of the models. This lack of transparency results in non-acceptance of the predictions, especially in critical applications. In this paper, we propose a DDoS explainer model that provides an appropriate explanation for its detection, based on the effectiveness of the features. We used interpretable machine learning (IML) models to build the explainer model which not only provides the explanation for the DDoS detection but also justifies the explanation by adding confidence scores with it. Confidence scores are referred to as consistency scores which can be computed by the percentage of consistent explanations of similar type of data instances. Our proposed framework incorporates the best-performing explainer model chosen from the comparison of the explainer models developed by two IML models Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). We experimented with the NSL-KDD dataset and ensemble supervised ML framework for DDoS detection and validation.
{"title":"DDoS Explainer using Interpretable Machine Learning","authors":"Saikat Das, Ph.D., Namita Agarwal, S. Shiva","doi":"10.1109/iemcon53756.2021.9623251","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623251","url":null,"abstract":"Machine learning (ML) experts have been using black-box classifiers for modeling purposes. However, the users of these systems are raising questions about the transparency of the predictions of the models. This lack of transparency results in non-acceptance of the predictions, especially in critical applications. In this paper, we propose a DDoS explainer model that provides an appropriate explanation for its detection, based on the effectiveness of the features. We used interpretable machine learning (IML) models to build the explainer model which not only provides the explanation for the DDoS detection but also justifies the explanation by adding confidence scores with it. Confidence scores are referred to as consistency scores which can be computed by the percentage of consistent explanations of similar type of data instances. Our proposed framework incorporates the best-performing explainer model chosen from the comparison of the explainer models developed by two IML models Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). We experimented with the NSL-KDD dataset and ensemble supervised ML framework for DDoS detection and validation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126949366","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623122
Fu-Shiung Hsieh
Cyber-Physical Production Systems (CPPS) consists of intertwined physical components and software components that interact with each other to accommodate changes and demands in the business world. Software components in CPPS must generate the information or instructions to guide the operations of physical components based on the real-time states acquired by sensors from the shop floor. In this paper, we will focus on process optimization issue for the development of software components in CPPS. This paper aims to propose a more efficient solution algorithm to find a solution. In this paper, we will enhance the search capabilities of discrete Differential Evolution approach by a neighborhood search method. Neighborhood search explores the neighborhood of the current solution to find a potential better solution that can improve the current solution. By adopting the concept of neighborhood search, we will propose a more effective discrete Differential Evolution approach through combining the neighborhood search with existing search strategies of Differential Evolution. To verify performance and efficiency of the algorithm, we create several test cases to perform experiments to compare with previous algorithms based on experimental results. We illustrate efficiency of the proposed method by analyzing the results.
{"title":"Neighborhood Search for Process Resource Configuration in Cyber Physical Systems","authors":"Fu-Shiung Hsieh","doi":"10.1109/iemcon53756.2021.9623122","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623122","url":null,"abstract":"Cyber-Physical Production Systems (CPPS) consists of intertwined physical components and software components that interact with each other to accommodate changes and demands in the business world. Software components in CPPS must generate the information or instructions to guide the operations of physical components based on the real-time states acquired by sensors from the shop floor. In this paper, we will focus on process optimization issue for the development of software components in CPPS. This paper aims to propose a more efficient solution algorithm to find a solution. In this paper, we will enhance the search capabilities of discrete Differential Evolution approach by a neighborhood search method. Neighborhood search explores the neighborhood of the current solution to find a potential better solution that can improve the current solution. By adopting the concept of neighborhood search, we will propose a more effective discrete Differential Evolution approach through combining the neighborhood search with existing search strategies of Differential Evolution. To verify performance and efficiency of the algorithm, we create several test cases to perform experiments to compare with previous algorithms based on experimental results. We illustrate efficiency of the proposed method by analyzing the results.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"17 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123559800","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}
Edge Intelligence based collaborative learning systems have been developed to perform collaborative learning among multiple devices in a distributed environment. Majority of the collaborative learning systems have been designed using resources containing high computational power. It was identified that a system could be implemented to facilitate collaborative learning in resource constrained Internet of Things (IoT) devices. The existing collaborative learning systems were critically reviewed and analyzed to identify the ideal collaborative learning approach for resource constrained IoT edge. During the initial stages of the research, partitioned model training was identified as the most ideal approach. The research paved the way to design and implement two training architectures based on partitioned model training approach to facilitate environments with adequate and limited access to edge infrastructure. The proposed system utilized a hybrid deep learning model in partitioned model training approach for the first time. Furthermore, the research utilized a lightweight containerization mechanism to deploy the proposed collaborative learning system. The testing and evaluation phases of the research proved that the system was able to significantly reduce the resource consumption of the devices while achieving high model accuracy. The experimental setup reached up to 97% in model accuracy while consuming a significantly lower CPU consumption of 6.33%. The proposed system also proved to function efficiently by reducing energy consumption and reducing operational temperature by up to 4°C.
{"title":"Edge Intelligence Based Collaborative Learning System for IoT Edge","authors":"Lahiru Welagedara, Janani Harischandra, Nuwan Jayawardene","doi":"10.1109/iemcon53756.2021.9623215","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623215","url":null,"abstract":"Edge Intelligence based collaborative learning systems have been developed to perform collaborative learning among multiple devices in a distributed environment. Majority of the collaborative learning systems have been designed using resources containing high computational power. It was identified that a system could be implemented to facilitate collaborative learning in resource constrained Internet of Things (IoT) devices. The existing collaborative learning systems were critically reviewed and analyzed to identify the ideal collaborative learning approach for resource constrained IoT edge. During the initial stages of the research, partitioned model training was identified as the most ideal approach. The research paved the way to design and implement two training architectures based on partitioned model training approach to facilitate environments with adequate and limited access to edge infrastructure. The proposed system utilized a hybrid deep learning model in partitioned model training approach for the first time. Furthermore, the research utilized a lightweight containerization mechanism to deploy the proposed collaborative learning system. The testing and evaluation phases of the research proved that the system was able to significantly reduce the resource consumption of the devices while achieving high model accuracy. The experimental setup reached up to 97% in model accuracy while consuming a significantly lower CPU consumption of 6.33%. The proposed system also proved to function efficiently by reducing energy consumption and reducing operational temperature by up to 4°C.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124747109","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623260
Luqman Ahsan, M. Iqbal
This paper is about the design and feasibility of a grid-connected hybrid power system for an industrial unit. Due to the increase in greenhouse gases by burning fossil fuels, generating electricity from renewable resources is necessary. Solar energy is dependent on solar irradiance, which varies from site to site. A site (Shafi Texcel Limited) is selected, which is situated on Raiwind Manga Road Lahore, Pakistan. The average load demand is 2415 kW, for which a hybrid captive power plant has been designed. The sources of electricity are Grid, CATERPILLER Gas & Diesel GENSET, and the proposed solar system. For this system, optimization analysis has been carried out using HOMER and PVWatt software. Three different grid-connected cases are considered with 0% renewable energy (RE) constraints, 70% RE constraints, and with battery storage. The system parameters are different for each case, and land requisition analysis has been done using PVWatt. The NPC, cost of energy, capital cost, replacement cost for each case has been discussed in detail. The result shows that the proposed system is suitable for a selected site and can provide a significant saving. At the end, final results and possible future work has been discussed.
{"title":"Design of an Optimal Hybrid Energy System for a Captive Power Plant in Pakistan","authors":"Luqman Ahsan, M. Iqbal","doi":"10.1109/iemcon53756.2021.9623260","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623260","url":null,"abstract":"This paper is about the design and feasibility of a grid-connected hybrid power system for an industrial unit. Due to the increase in greenhouse gases by burning fossil fuels, generating electricity from renewable resources is necessary. Solar energy is dependent on solar irradiance, which varies from site to site. A site (Shafi Texcel Limited) is selected, which is situated on Raiwind Manga Road Lahore, Pakistan. The average load demand is 2415 kW, for which a hybrid captive power plant has been designed. The sources of electricity are Grid, CATERPILLER Gas & Diesel GENSET, and the proposed solar system. For this system, optimization analysis has been carried out using HOMER and PVWatt software. Three different grid-connected cases are considered with 0% renewable energy (RE) constraints, 70% RE constraints, and with battery storage. The system parameters are different for each case, and land requisition analysis has been done using PVWatt. The NPC, cost of energy, capital cost, replacement cost for each case has been discussed in detail. The result shows that the proposed system is suitable for a selected site and can provide a significant saving. At the end, final results and possible future work has been discussed.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125105059","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623182
A. Ibrahim
Tweets from social media can help in providing an early sign of market mood in the business sector. Opinion mining and machine learning can be used to discover the underlying sentiment. There's a link between Twitter sentiment and Bitcoin price changes in the future. Using the concept of Consensus clustering, this paper leverages Tweets collected during the COVID-19 timeframe to forecast early Bitcoin movements following the outbreak. Results from text datasets such as Twitter with various attributes, settings, and degrees show the superiority of the proposed consensus approach in predicting the BTC trend during and after the COVID-19 pandemic.
{"title":"Analyzing BTC's Trend During COVID-19 Using A Sentiment Consensus Clustering (SCC)","authors":"A. Ibrahim","doi":"10.1109/iemcon53756.2021.9623182","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623182","url":null,"abstract":"Tweets from social media can help in providing an early sign of market mood in the business sector. Opinion mining and machine learning can be used to discover the underlying sentiment. There's a link between Twitter sentiment and Bitcoin price changes in the future. Using the concept of Consensus clustering, this paper leverages Tweets collected during the COVID-19 timeframe to forecast early Bitcoin movements following the outbreak. Results from text datasets such as Twitter with various attributes, settings, and degrees show the superiority of the proposed consensus approach in predicting the BTC trend during and after the COVID-19 pandemic.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130102610","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623209
K. Marshall, Thomas Cantido, Jonathan Case, L. Nguyen, H. El-Razouk
Traditional authentication schemes challenge the user by something only they know, often a username and password, and become more robust with two-factor authentication. However, a new security problem arises when the system or service cannot ensure accountability for all events that occur within some user application. The vulnerability exists in authentication mechanisms that fail to provide security for events that occur after the login stage. This accountability issue leaves users susceptible to physical and cyber-attacks, such as physical compromises or Man-in-the-Middle (MITM) and replay attacks. In these cases the user is held accountable for these actions and the server is unaware that the legitimate user is no longer near the active session. Therefore, an additional authentication mechanism is needed to provide security up to the application layer when critical events are attempted. In this paper we study a practical, user-friendly approach to mediate critical events by authentication to verify the legitimate user is still near the live session. Critical events are authenticated by pairing the PC with the user's mobile smart device over a connection medium to determine if both devices are within an acceptable range. Afterwards, the PC sends a cryptographic challenge that can only be answered by the user's devices using the public key infrastructure and digital signatures. The smartphone replies back to the PC with a challenge, so that both devices can guarantee mutual authentication.
{"title":"An Event-Driven Authentication Approach for Mediation of User Actions","authors":"K. Marshall, Thomas Cantido, Jonathan Case, L. Nguyen, H. El-Razouk","doi":"10.1109/iemcon53756.2021.9623209","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623209","url":null,"abstract":"Traditional authentication schemes challenge the user by something only they know, often a username and password, and become more robust with two-factor authentication. However, a new security problem arises when the system or service cannot ensure accountability for all events that occur within some user application. The vulnerability exists in authentication mechanisms that fail to provide security for events that occur after the login stage. This accountability issue leaves users susceptible to physical and cyber-attacks, such as physical compromises or Man-in-the-Middle (MITM) and replay attacks. In these cases the user is held accountable for these actions and the server is unaware that the legitimate user is no longer near the active session. Therefore, an additional authentication mechanism is needed to provide security up to the application layer when critical events are attempted. In this paper we study a practical, user-friendly approach to mediate critical events by authentication to verify the legitimate user is still near the live session. Critical events are authenticated by pairing the PC with the user's mobile smart device over a connection medium to determine if both devices are within an acceptable range. Afterwards, the PC sends a cryptographic challenge that can only be answered by the user's devices using the public key infrastructure and digital signatures. The smartphone replies back to the PC with a challenge, so that both devices can guarantee mutual authentication.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130397093","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}
Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623240
K. K. H. Karunathilake, A. Shahan, M. N. M. Shamry, M. W. D. S. De Silva, A. Senarathne, K. Yapa
In the modern world, unique biometrics of every individual play a vital role in authentication processes. However, as convenient as it seems, biometrics come with their own set of drawbacks. For instance, if a passphrase is compromised (which is highly likely), changing it to a new passphrase would solve the issue. However, when someone's biometrics are compromised, there is no turning back. Simultaneously, biometric systems are often compromised due to the use of fake physical biometrics and trojan horse attacks that are capable of modifying the authentication process to fulfill a malicious user's intents. This research focuses on proposing a novel and secure authentication process that uses steganography. This “all-in-one” solution also focuses on mitigating the aforementioned drawbacks with the use of four modules, namely, the feature extraction module, the payload generation and authentication module, the fake physical biometrics countering module and the trojan horse countering module. This solution is implemented such that the idea behind it can be easily adopted to enhance the existing biometric authentication systems as well as improve the overall condition and user experience of the multi-factor authentication processes that are widely in use today.
{"title":"A steganography-based fingerprint authentication mechanism to counter fake physical biometrics and trojan horse attacks","authors":"K. K. H. Karunathilake, A. Shahan, M. N. M. Shamry, M. W. D. S. De Silva, A. Senarathne, K. Yapa","doi":"10.1109/iemcon53756.2021.9623240","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623240","url":null,"abstract":"In the modern world, unique biometrics of every individual play a vital role in authentication processes. However, as convenient as it seems, biometrics come with their own set of drawbacks. For instance, if a passphrase is compromised (which is highly likely), changing it to a new passphrase would solve the issue. However, when someone's biometrics are compromised, there is no turning back. Simultaneously, biometric systems are often compromised due to the use of fake physical biometrics and trojan horse attacks that are capable of modifying the authentication process to fulfill a malicious user's intents. This research focuses on proposing a novel and secure authentication process that uses steganography. This “all-in-one” solution also focuses on mitigating the aforementioned drawbacks with the use of four modules, namely, the feature extraction module, the payload generation and authentication module, the fake physical biometrics countering module and the trojan horse countering module. This solution is implemented such that the idea behind it can be easily adopted to enhance the existing biometric authentication systems as well as improve the overall condition and user experience of the multi-factor authentication processes that are widely in use today.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128808525","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：