Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623160
J. Ozogbuda, M. Iqbal
In the remote part of Nigeria, most households suffer from lack of electricity due to inaccessibility to the utility grid. This paper presents the simulation of a Photovoltaic (PV) hybrid system with battery and generator backup of an off-grid Stand-alone PV system for a house located in remote Benin City, Edo State in Nigeria. House peak load is 1.26kW and daily energy consumption is 3.4kWh, with no access to the electricity grid for fulfilment of load requirement to meet the basic electrical needs. The system is designed in Homer Pro and simulated using the Matlab Simulink software, it comprises of a 1.23kW PV made up of 4 modules (325W each with 2 in series and 2 in parallel), A MPPT (maximum power point tracking), a DC -DC buck converter, 4 backup battery of 12V, 350Ahr connected in series and a 4.8kW emergency generator system with a 1.6kW inverter which converts the output DC voltage of 48V from the converter to an alternating AC. The inverter is connected directly to a step-up transformer which boosts the voltage from to 220V AC for supply to the load. Result shows different scenarios and configuration. With a 50% State of Charge (SOC) of the battery and full electrical load, the PV charges the battery and supply power to the load. However, when the volatage of the battery is below 49V the emergency generator turns ON to charge up the battery. Whereas, in the scenario of 98% SOC of the battery, regardless of the load, the generator is not operational because the control of the generator automatically turns off when the battery is above 49V. The system dynamic simulation results and response to changing inputs are presented in this paper.
{"title":"Dynamic Simulation of a Standalone Photovoltaic Hybrid System of a Remote house in Nigeria","authors":"J. Ozogbuda, M. Iqbal","doi":"10.1109/iemcon53756.2021.9623160","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623160","url":null,"abstract":"In the remote part of Nigeria, most households suffer from lack of electricity due to inaccessibility to the utility grid. This paper presents the simulation of a Photovoltaic (PV) hybrid system with battery and generator backup of an off-grid Stand-alone PV system for a house located in remote Benin City, Edo State in Nigeria. House peak load is 1.26kW and daily energy consumption is 3.4kWh, with no access to the electricity grid for fulfilment of load requirement to meet the basic electrical needs. The system is designed in Homer Pro and simulated using the Matlab Simulink software, it comprises of a 1.23kW PV made up of 4 modules (325W each with 2 in series and 2 in parallel), A MPPT (maximum power point tracking), a DC -DC buck converter, 4 backup battery of 12V, 350Ahr connected in series and a 4.8kW emergency generator system with a 1.6kW inverter which converts the output DC voltage of 48V from the converter to an alternating AC. The inverter is connected directly to a step-up transformer which boosts the voltage from to 220V AC for supply to the load. Result shows different scenarios and configuration. With a 50% State of Charge (SOC) of the battery and full electrical load, the PV charges the battery and supply power to the load. However, when the volatage of the battery is below 49V the emergency generator turns ON to charge up the battery. Whereas, in the scenario of 98% SOC of the battery, regardless of the load, the generator is not operational because the control of the generator automatically turns off when the battery is above 49V. The system dynamic simulation results and response to changing inputs are presented in this paper.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"26 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":"115370213","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/iemcon53756.2021.9623216
Robin Teotia, Shannon Freeman, Piper J. Jackson
This research is a comparative analysis of applying different machine-learning methods to health care data. The data used is from the interRAI home care assessment instrument, collected in central British Columbia, Canada. The primary dataset used contains more than 100,000 records each with 423 attributes. We built models for predicting home care usage in the three weeks following an assessment by applying different regression and classification machine learning algorithms. The main regression algorithms used in the process were multiple linear regression, lasso, ridge, decision tree and ensemble methods, with the last being the most promising. In the area of classification, KNN, logistic regression, decision tree and ensemble methods were used. Apart from the technical machine learning algorithms, both patient partners and health systems experts participated and provided feedback regarding home care practices and issues. These formed essential element in designing the research question, selecting variables, and improving the models. The highest accuracy achieved was 84.3% which was achieved through a random forest classifier and evaluated using K-fold cross validation.
{"title":"Predicting Home Care Use After Assessment Using Multiple Machine Learning Methods","authors":"Robin Teotia, Shannon Freeman, Piper J. Jackson","doi":"10.1109/iemcon53756.2021.9623216","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623216","url":null,"abstract":"This research is a comparative analysis of applying different machine-learning methods to health care data. The data used is from the interRAI home care assessment instrument, collected in central British Columbia, Canada. The primary dataset used contains more than 100,000 records each with 423 attributes. We built models for predicting home care usage in the three weeks following an assessment by applying different regression and classification machine learning algorithms. The main regression algorithms used in the process were multiple linear regression, lasso, ridge, decision tree and ensemble methods, with the last being the most promising. In the area of classification, KNN, logistic regression, decision tree and ensemble methods were used. Apart from the technical machine learning algorithms, both patient partners and health systems experts participated and provided feedback regarding home care practices and issues. These formed essential element in designing the research question, selecting variables, and improving the models. The highest accuracy achieved was 84.3% which was achieved through a random forest classifier and evaluated using K-fold cross validation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"91 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":"123174475","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/iemcon53756.2021.9623244
M. Hassan, Nikkhah Babaei, S. Ebadollahi, Bob Gill
Indoor positioning systems are becoming more and more popular nowadays. There are many challenges in designing such systems. An effective method of designing these systems is to employ Wi-Fi technology along with the fingerprinting algorithm. This algorithm consists of an offline or setup phase and an online or exploitation phase. A challenge that these systems face is the offline phase, in which a database is collected from the signal intensities of modems existing at different points in an environment. In this case, the large volume of the database demands high rates of temporal costs and human labor, which increases the setup costs of these systems. At the same time, decreasing the number of sampling points will reduce the positioning accuracy. The genetic algorithm was used in this paper to select and arrange the number of database points in order to decrease the database volume and keep accuracy within an acceptable range.
{"title":"Database Optimization of Fingerprint-Based Indoor Positioning System Using Genetic Algorithm","authors":"M. Hassan, Nikkhah Babaei, S. Ebadollahi, Bob Gill","doi":"10.1109/iemcon53756.2021.9623244","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623244","url":null,"abstract":"Indoor positioning systems are becoming more and more popular nowadays. There are many challenges in designing such systems. An effective method of designing these systems is to employ Wi-Fi technology along with the fingerprinting algorithm. This algorithm consists of an offline or setup phase and an online or exploitation phase. A challenge that these systems face is the offline phase, in which a database is collected from the signal intensities of modems existing at different points in an environment. In this case, the large volume of the database demands high rates of temporal costs and human labor, which increases the setup costs of these systems. At the same time, decreasing the number of sampling points will reduce the positioning accuracy. The genetic algorithm was used in this paper to select and arrange the number of database points in order to decrease the database volume and keep accuracy within an acceptable range.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"12 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":"125386370","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/iemcon53756.2021.9623218
John Barker, Amal O. Hamada, M. Azab
Internet of Things (IoT) revolutionizes cutting-edge technologies by enabling smart sensing, and actuation of the physical world. IoT enables cooperation between numerous heterogeneous smart devices to exchange and aggregate data from the surrounding environment through the internet. Recently, the range of IoT technology could be utilized in the real world by the rapid spread of sensor devices. These capabilities open the door for vital challenges. Security is the major challenge that faces the IoT networks. Traditional solutions cannot tackle smart and powerful attackers. Moving Target Defense (MTD) deploys mechanisms and strategies that increase attackers' uncertainty and frustrate their attempt to eavesdrop the target to be protected. In addition, Steganography is the practice of concealing a message within another message. For security proposes, Steganography is used to hide significant data within any transmitted messages, such as images, videos, and text files. This paper presents Stegano-MTD framework that enables combination between MTD mechanisms with steganography. This combination offers a lightweight solution that can be implemented on the IoT network. Stegano-MTD slices the message into small labeled chunks and sends them randomly through the network's nodes. Steganography is used for hide the key file that used to reconstruct the original data. Simulation results show the effectiveness of the presented solution.
{"title":"Lightweight Proactive Moving-target Defense for Secure Data Exchange in IoT Networks","authors":"John Barker, Amal O. Hamada, M. Azab","doi":"10.1109/iemcon53756.2021.9623218","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623218","url":null,"abstract":"Internet of Things (IoT) revolutionizes cutting-edge technologies by enabling smart sensing, and actuation of the physical world. IoT enables cooperation between numerous heterogeneous smart devices to exchange and aggregate data from the surrounding environment through the internet. Recently, the range of IoT technology could be utilized in the real world by the rapid spread of sensor devices. These capabilities open the door for vital challenges. Security is the major challenge that faces the IoT networks. Traditional solutions cannot tackle smart and powerful attackers. Moving Target Defense (MTD) deploys mechanisms and strategies that increase attackers' uncertainty and frustrate their attempt to eavesdrop the target to be protected. In addition, Steganography is the practice of concealing a message within another message. For security proposes, Steganography is used to hide significant data within any transmitted messages, such as images, videos, and text files. This paper presents Stegano-MTD framework that enables combination between MTD mechanisms with steganography. This combination offers a lightweight solution that can be implemented on the IoT network. Stegano-MTD slices the message into small labeled chunks and sends them randomly through the network's nodes. Steganography is used for hide the key file that used to reconstruct the original data. Simulation results show the effectiveness of the presented solution.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"348 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":"116462180","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/iemcon53756.2021.9623070
Maurine C. Panergo, F. Cruz, R. R. Maaliw
Hypertension is one of the leading causes of mortality worldwide, increasing the likelihood of developing heart, renal, brain, and other illnesses. Reliable blood pressure measurement is critical because even minor errors can have severe effects on individuals. In this study, we developed a telehealth system that integrates an instrumentation amplifier and band-pass filter circuit to resolve dissipation losses and monitor such conditions, thus improving accurate health parameter measurements. Our prototype was tested on 30 subjects of varying ages for ten cross-validated trials. Quantitative results show that our amplified system was able to outperform high-end digital commercially available instruments with a mean precision of 96.67% (mean arterial pressure), 96.79% (pulse rate), and 99.13% (temperature).
{"title":"A Circuit Design of a Sensor Amplifier for Improving Blood Pressure Measurement in Telehealth System","authors":"Maurine C. Panergo, F. Cruz, R. R. Maaliw","doi":"10.1109/iemcon53756.2021.9623070","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623070","url":null,"abstract":"Hypertension is one of the leading causes of mortality worldwide, increasing the likelihood of developing heart, renal, brain, and other illnesses. Reliable blood pressure measurement is critical because even minor errors can have severe effects on individuals. In this study, we developed a telehealth system that integrates an instrumentation amplifier and band-pass filter circuit to resolve dissipation losses and monitor such conditions, thus improving accurate health parameter measurements. Our prototype was tested on 30 subjects of varying ages for ten cross-validated trials. Quantitative results show that our amplified system was able to outperform high-end digital commercially available instruments with a mean precision of 96.67% (mean arterial pressure), 96.79% (pulse rate), and 99.13% (temperature).","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"14 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":"122200658","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/iemcon53756.2021.9623123
Azadeh Etedali, Chung-Horng Lung, S. Ajila
The use of Software-as-a-Service (SaaS) cloud model is increasing rapidly. Among different SaaS deployment models, Single Instance Multi-Tenant (SIMT) has multiple advantages, e.g., high scalability and lower cost, but it also has practical concerns for management, as tenants may have distinct requirements or even conflicting preferences, and the number of features and tenants may be large. Offering the best user satisfaction, dealing with tenants' preferences and operational environment changes is crucial but challenging for effective SaaS management. Genetic algorithms (GAs) have been applied to the optimization problem in many fields. Further a GA-based approach, GAFES, specifically adapted to constraint-based feature selection optimization in Software Product Line (SPL) for multi-tenant SaaS has been reported. On the other hand, an XML filter technique, Yfilter, has been applied to various problem domains and recently to SIMT for SaaS. The aim of this paper is to experimentally evaluate the performance of GAFES and Yfilter for SaaS configuration with recourse constraints. We have conducted experiments to evaluate the two very different multi-tenant SaaS configuration techniques. The results show that both approaches can meet the user satisfaction, but Yfilter has much higher performance compared to GAFES.
{"title":"Comparative Analysis of Genetic Algorithm and XML Filtering Technique for Multi-Tenant SaaS Configuration Management","authors":"Azadeh Etedali, Chung-Horng Lung, S. Ajila","doi":"10.1109/iemcon53756.2021.9623123","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623123","url":null,"abstract":"The use of Software-as-a-Service (SaaS) cloud model is increasing rapidly. Among different SaaS deployment models, Single Instance Multi-Tenant (SIMT) has multiple advantages, e.g., high scalability and lower cost, but it also has practical concerns for management, as tenants may have distinct requirements or even conflicting preferences, and the number of features and tenants may be large. Offering the best user satisfaction, dealing with tenants' preferences and operational environment changes is crucial but challenging for effective SaaS management. Genetic algorithms (GAs) have been applied to the optimization problem in many fields. Further a GA-based approach, GAFES, specifically adapted to constraint-based feature selection optimization in Software Product Line (SPL) for multi-tenant SaaS has been reported. On the other hand, an XML filter technique, Yfilter, has been applied to various problem domains and recently to SIMT for SaaS. The aim of this paper is to experimentally evaluate the performance of GAFES and Yfilter for SaaS configuration with recourse constraints. We have conducted experiments to evaluate the two very different multi-tenant SaaS configuration techniques. The results show that both approaches can meet the user satisfaction, but Yfilter has much higher performance compared to GAFES.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"177 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":"129573398","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/iemcon53756.2021.9623142
Ruth Ogubuike, Ashfaq Adib, Rita Orji
Mobile applications have made significant positive contributions to our daily lives in recent years. They have greatly improved practices in critical sectors such as healthcare, education, and agriculture etc. The agricultural sector is under pressure to meet the ever-increasing food demand while needing to deal with lack of agricultural resources (such as water and soil) and climate change issues. There is also a need to figure out how to attract and involve young people in agriculture in order to replace aging farmers. These issues necessitate the development of new, sustainable agricultural solutions. This is the demand that Masa app is attempting to meet. This paper presents the design and implementation of an AI-adaptive mobile app for sustainable agriculture. The app is divided into two sections: the market section which creates a platform where buyers are able to connect with the farmers directly and the resource center section where the power of AI is used to give guidance to the farmers. It also has learning resources where new entrants into the Agric sector can have first-hand walk-through guides in the Agric field containing all the information they need to venture into farming any product of choice. This will help mitigate some of the challenges faced by people who are new or venturing into the agricultural sector thereby encouraging more people to enter agriculture hence its sustainability. Initial feedback on the application from researchers of human-computer interaction domain show the application's promise in closing the gap in farming knowledge among general people while highlighting some limitations and suggestion that can be considered for improving the application.
{"title":"Masa: AI-Adaptive Mobile App for Sustainable Agriculture","authors":"Ruth Ogubuike, Ashfaq Adib, Rita Orji","doi":"10.1109/iemcon53756.2021.9623142","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623142","url":null,"abstract":"Mobile applications have made significant positive contributions to our daily lives in recent years. They have greatly improved practices in critical sectors such as healthcare, education, and agriculture etc. The agricultural sector is under pressure to meet the ever-increasing food demand while needing to deal with lack of agricultural resources (such as water and soil) and climate change issues. There is also a need to figure out how to attract and involve young people in agriculture in order to replace aging farmers. These issues necessitate the development of new, sustainable agricultural solutions. This is the demand that Masa app is attempting to meet. This paper presents the design and implementation of an AI-adaptive mobile app for sustainable agriculture. The app is divided into two sections: the market section which creates a platform where buyers are able to connect with the farmers directly and the resource center section where the power of AI is used to give guidance to the farmers. It also has learning resources where new entrants into the Agric sector can have first-hand walk-through guides in the Agric field containing all the information they need to venture into farming any product of choice. This will help mitigate some of the challenges faced by people who are new or venturing into the agricultural sector thereby encouraging more people to enter agriculture hence its sustainability. Initial feedback on the application from researchers of human-computer interaction domain show the application's promise in closing the gap in farming knowledge among general people while highlighting some limitations and suggestion that can be considered for improving the application.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"13 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":"129901632","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/iemcon53756.2021.9623143
Fengyang Long, Chengfang Gao, Yanfeng Dong
Using the Total Electron Content (TEC) data of four grid nodes at different latitudes in western China provided by the Crustal Movement Observation Network of China (CMONOC), the empirical models were established by using BP neural network (BPNN) and random forest (RF) respectively, in which the data from 2004, 2016 and 2018 were used as test sets, and the training sets included the data from 2006 to 2019 except for those test sets. In order to improve the stability of predictions of BPNN model, an integrated neural network model based on bootstrap sampling was proposed. The TEC values from CODE's 1-day predicted global ionospheric maps (C1PG) and International Reference Ionosphere (IRI) model were used for comparison in model evaluation. The results show that the machine learning methods proposed in this paper can simulate the training set well, but the RF model performs poorly in high solar activity years, and even worse than C1PG product and IRI model. BPNN model performs well at mid-latitudes, but it is not as well as C1PG product at low-latitudes. The Inte-BP model is superior to other models in all aspects. Compared with the BPNN model that only gets weights and bias parameters after one certain training session, the Inte-BP model that integrates multiple base learners can output more stable and accurate predictions.
{"title":"Modeling and Predicting the Ionospheric Total Electron Content Over Western China With Machine Learning","authors":"Fengyang Long, Chengfang Gao, Yanfeng Dong","doi":"10.1109/iemcon53756.2021.9623143","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623143","url":null,"abstract":"Using the Total Electron Content (TEC) data of four grid nodes at different latitudes in western China provided by the Crustal Movement Observation Network of China (CMONOC), the empirical models were established by using BP neural network (BPNN) and random forest (RF) respectively, in which the data from 2004, 2016 and 2018 were used as test sets, and the training sets included the data from 2006 to 2019 except for those test sets. In order to improve the stability of predictions of BPNN model, an integrated neural network model based on bootstrap sampling was proposed. The TEC values from CODE's 1-day predicted global ionospheric maps (C1PG) and International Reference Ionosphere (IRI) model were used for comparison in model evaluation. The results show that the machine learning methods proposed in this paper can simulate the training set well, but the RF model performs poorly in high solar activity years, and even worse than C1PG product and IRI model. BPNN model performs well at mid-latitudes, but it is not as well as C1PG product at low-latitudes. The Inte-BP model is superior to other models in all aspects. Compared with the BPNN model that only gets weights and bias parameters after one certain training session, the Inte-BP model that integrates multiple base learners can output more stable and accurate predictions.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"10 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":"126879856","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/iemcon53756.2021.9623238
P. Hajibabaee, Masoud Malekzadeh, Maryam Heidari, Samira Zad, Ozlem Uzuner, James H. Jones
A fundamental task in machine learning involves node classification. However, when considering the context of large graph data, this problem becomes much more challenging. In this paper, we use the Wikipedia hyperlink dataset to evaluate our semi-supervised node classification model. Given a small set of labeled nodes, we develop a multiclass classifier that utilizes the network structure as well as textual descriptions of nodes to predict the most probable category(label) for each test node in a semi-supervised setting. Our experiment shows promising results for graph multiclass classification using directed graphSAGE and word2vec algorithms together. We also visualize the node embeddings in 2D using the t-SNE method.
{"title":"An Empirical Study of the GraphSAGE and Word2vec Algorithms for Graph Multiclass Classification","authors":"P. Hajibabaee, Masoud Malekzadeh, Maryam Heidari, Samira Zad, Ozlem Uzuner, James H. Jones","doi":"10.1109/iemcon53756.2021.9623238","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623238","url":null,"abstract":"A fundamental task in machine learning involves node classification. However, when considering the context of large graph data, this problem becomes much more challenging. In this paper, we use the Wikipedia hyperlink dataset to evaluate our semi-supervised node classification model. Given a small set of labeled nodes, we develop a multiclass classifier that utilizes the network structure as well as textual descriptions of nodes to predict the most probable category(label) for each test node in a semi-supervised setting. Our experiment shows promising results for graph multiclass classification using directed graphSAGE and word2vec algorithms together. We also visualize the node embeddings in 2D using the t-SNE method.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"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":"114870829","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/iemcon53756.2021.9623233
Md Maruf Abir Bappy, Md. Rubel Sarkar, Saad Ibn Hasan, Md Minhajul Azmir, Dewan Mohammed Rashid
The paper represents the full design process of a two-stage differential operational amplifier (op-amp) as well as a brief behavior analysis of the design. This work also demonstrates the performance variation of the op-amp by changing the potential level of the body biasing terminal in Fully Depleted Silicon on Insulator (FD-SOI) technology. If the FD-SOI technology is used, the performance of the circuit can be varied without changing the parameter of the CMOS (Complementary Metal Oxide Semiconductor) devices related to the physical dimensions (length and width). This paper showed the result of performance variation depending on different back bias connection and explains how FD-SOI technology provides the advantages to the designer in case of limited option of parameter variations. The supply voltage of the designed op-amp was 0.8V and the circuit simulations were done under room temperature, 27° Celsius using Cadence Spectre Analog Design Environment (ADE). The result was varied without any manipulation of device parameter while only change was in bias potential. Due to the variation of bias potential the design performance is varied, the variation of gain is obtained from 34.15dB to 45.76dB, the bandwidth was varied from 3MHz to 7.18MHz at −3dB and leakage was also improved from 30.14μA to 26.02 µA. The phase margin was achieved up to 65.4° from 60.01°. To have a clear view of the performance a table is appended in this paper to demonstrate the advantage of FD-SOI technology in case of op-amp design.
本文介绍了一种两级差分运算放大器的完整设计过程，并对该设计进行了简要的性能分析。这项工作还展示了在完全耗尽绝缘体上硅(FD-SOI)技术中，通过改变体偏置终端的电位水平来改变运算放大器的性能变化。如果使用FD-SOI技术，可以在不改变CMOS(互补金属氧化物半导体)器件的物理尺寸(长度和宽度)相关参数的情况下改变电路的性能。本文展示了不同背偏置连接的性能变化结果，并解释了FD-SOI技术如何在参数变化选择有限的情况下为设计人员提供优势。所设计的运放的电源电压为0.8V，电路仿真在室温27℃下使用Cadence Spectre Analog Design Environment (ADE)进行。结果在不改变器件参数的情况下发生变化，只改变偏置电位。由于偏置电位的变化，设计性能发生了变化，增益从34.15dB变化到45.76dB，带宽从3MHz变化到7.18MHz，泄漏从30.14μA提高到26.02 μA。相位裕度从60.01°提高到65.4°。为了对性能有一个清晰的认识，本文附加了一个表格来展示FD-SOI技术在运算放大器设计中的优势。
{"title":"Design Process and Performance Analysis of Two Stage Differential Op-amp by Varying The Body Biasing in Fully Depleted Silicon On Insulator Technology","authors":"Md Maruf Abir Bappy, Md. Rubel Sarkar, Saad Ibn Hasan, Md Minhajul Azmir, Dewan Mohammed Rashid","doi":"10.1109/iemcon53756.2021.9623233","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623233","url":null,"abstract":"The paper represents the full design process of a two-stage differential operational amplifier (op-amp) as well as a brief behavior analysis of the design. This work also demonstrates the performance variation of the op-amp by changing the potential level of the body biasing terminal in Fully Depleted Silicon on Insulator (FD-SOI) technology. If the FD-SOI technology is used, the performance of the circuit can be varied without changing the parameter of the CMOS (Complementary Metal Oxide Semiconductor) devices related to the physical dimensions (length and width). This paper showed the result of performance variation depending on different back bias connection and explains how FD-SOI technology provides the advantages to the designer in case of limited option of parameter variations. The supply voltage of the designed op-amp was 0.8V and the circuit simulations were done under room temperature, 27° Celsius using Cadence Spectre Analog Design Environment (ADE). The result was varied without any manipulation of device parameter while only change was in bias potential. Due to the variation of bias potential the design performance is varied, the variation of gain is obtained from 34.15dB to 45.76dB, the bandwidth was varied from 3MHz to 7.18MHz at −3dB and leakage was also improved from 30.14μA to 26.02 µA. The phase margin was achieved up to 65.4° from 60.01°. To have a clear view of the performance a table is appended in this paper to demonstrate the advantage of FD-SOI technology in case of op-amp design.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"63 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":"115823591","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：