Pub Date : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887404
Lidya Nabila, W. Priharti, Istiqomah
Home security system with good accuracy and efficiency in controlling access to the door system is needed in order to identify people who enter the house accurately. Home security conventionally uses a key to open the door, making security low due to several factors. Various face recognition methods has been studied to determine the most accurate method in identifying people who has access to the house. In this study, Haar Cascade and CNN (Convolutional Neural Network) method were applied to face detection and classify 5 class of family member that can access the house. Based on the results of the analysis, the CNN model in this study uses an 64x64 sizes of input, 0.001 learning rate value, 3x3 filter size, 10 number of epochs, 1200 training data with 240 data for each class, and 150 testing data with 30 data for each class. The classification process yields the accuracy of 99% in identifying the family member of the house, hence giving access to open the door.
{"title":"Design of Home Security System Using Face Recognition with Convolutional Neural Network Method","authors":"Lidya Nabila, W. Priharti, Istiqomah","doi":"10.1109/IAICT55358.2022.9887404","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887404","url":null,"abstract":"Home security system with good accuracy and efficiency in controlling access to the door system is needed in order to identify people who enter the house accurately. Home security conventionally uses a key to open the door, making security low due to several factors. Various face recognition methods has been studied to determine the most accurate method in identifying people who has access to the house. In this study, Haar Cascade and CNN (Convolutional Neural Network) method were applied to face detection and classify 5 class of family member that can access the house. Based on the results of the analysis, the CNN model in this study uses an 64x64 sizes of input, 0.001 learning rate value, 3x3 filter size, 10 number of epochs, 1200 training data with 240 data for each class, and 150 testing data with 30 data for each class. The classification process yields the accuracy of 99% in identifying the family member of the house, hence giving access to open the door.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126029900","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887452
Marc Schroth, Andreas Ilg, L. Kohout, Wilhelm Stork
Human activity recognition enables technical systems to analyse human behaviour in various settings. For example, it can be directly used to support the user in elder care, healthcare or training environments. Nevertheless, human activities are often times highly variable and therefore pose a challenge for any technical system to correctly classify and, even more importantly, generate a feedback that is valuable to the user. In this paper the process for designing a system that uses machine learning on the sensor node itself is presented in order to improve human activity recognition within a sensor network. Each sensor node of the network consists of a Bluetooth capable system on module and an accelerometer. The acceleration data is used to distinguish between several slicing techniques of different vegetables with the aim to help the network to distinguish the different dishes cooked with those vegetables. Various steps were taken to find the best possible machine learning model and sensor configuration to infer the cut vegetable on the sensor hardware, which is based on a standard microcontroller and therefore poses a challenge with its limited memory. Overall, the system is able to correctly infer the correct class most of the times while enabling a sufficient battery run time. Within this paper these steps and tests for the design and implementation of the embedded machine learning algorithm is described and its capability for activity recognition evaluated
{"title":"A Method for Designing an Embedded Human Activity Recognition System for a Kitchen Use Case Based on Machine Learning","authors":"Marc Schroth, Andreas Ilg, L. Kohout, Wilhelm Stork","doi":"10.1109/IAICT55358.2022.9887452","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887452","url":null,"abstract":"Human activity recognition enables technical systems to analyse human behaviour in various settings. For example, it can be directly used to support the user in elder care, healthcare or training environments. Nevertheless, human activities are often times highly variable and therefore pose a challenge for any technical system to correctly classify and, even more importantly, generate a feedback that is valuable to the user. In this paper the process for designing a system that uses machine learning on the sensor node itself is presented in order to improve human activity recognition within a sensor network. Each sensor node of the network consists of a Bluetooth capable system on module and an accelerometer. The acceleration data is used to distinguish between several slicing techniques of different vegetables with the aim to help the network to distinguish the different dishes cooked with those vegetables. Various steps were taken to find the best possible machine learning model and sensor configuration to infer the cut vegetable on the sensor hardware, which is based on a standard microcontroller and therefore poses a challenge with its limited memory. Overall, the system is able to correctly infer the correct class most of the times while enabling a sufficient battery run time. Within this paper these steps and tests for the design and implementation of the embedded machine learning algorithm is described and its capability for activity recognition evaluated","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"397 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192801","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887382
Subhanjan Konwer, Maria Sojan, P. Adeeb Kenz, Sooraj K Santhosh, Tresa Joseph, T. Bindiya
Artificial neural networks have gradually become omnipresent to the extent that they are recognised as the explicit solution to innumerable practical applications across various domains. This work aims to propose a novel hardware architecture for implementing the activation functions recurrently employed in artificial neural networks. The approach involves the development of a new hardware for the sigmoid and hyperbolic tangent activation functions based on the optimised polynomial approximations, which comprises of the critical half of realising neural Networks in general and recurrent neural networks in particular.
{"title":"Hardware Realization of Sigmoid and Hyperbolic Tangent Activation Functions","authors":"Subhanjan Konwer, Maria Sojan, P. Adeeb Kenz, Sooraj K Santhosh, Tresa Joseph, T. Bindiya","doi":"10.1109/IAICT55358.2022.9887382","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887382","url":null,"abstract":"Artificial neural networks have gradually become omnipresent to the extent that they are recognised as the explicit solution to innumerable practical applications across various domains. This work aims to propose a novel hardware architecture for implementing the activation functions recurrently employed in artificial neural networks. The approach involves the development of a new hardware for the sigmoid and hyperbolic tangent activation functions based on the optimised polynomial approximations, which comprises of the critical half of realising neural Networks in general and recurrent neural networks in particular.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114875867","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887431
M. Fauzan, Achmad Rizal, S. Hadiyoso
Electrocardiogram (ECG), as a biometric that has been widely studied, has advantages that are difficult to fake compared to biometrics using physical characteristics. This study simulated an ECG based biometric system with 15 subjects. It used the Butterworth low pass filter (LPF), ensemble empirical mode decomposition (EEMD) or variational mode decomposition (VMD), and statistical features as feature extraction method. The filtered signal will be segmented, and the subsequent five level decomposition using EEMD and VMD. Then, the signal analysis used the statistical feature approach for each intrinsic mode function (IMF) as result of decomposition process. These values become a feature set entered of K-Nearest Neighbor (KNN) as classifier; the highest result of 93% was achieved using VMD and KNN with Manhattan distance.
{"title":"ECG Biometric using Statistical Feature of EEMD and VMD","authors":"M. Fauzan, Achmad Rizal, S. Hadiyoso","doi":"10.1109/IAICT55358.2022.9887431","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887431","url":null,"abstract":"Electrocardiogram (ECG), as a biometric that has been widely studied, has advantages that are difficult to fake compared to biometrics using physical characteristics. This study simulated an ECG based biometric system with 15 subjects. It used the Butterworth low pass filter (LPF), ensemble empirical mode decomposition (EEMD) or variational mode decomposition (VMD), and statistical features as feature extraction method. The filtered signal will be segmented, and the subsequent five level decomposition using EEMD and VMD. Then, the signal analysis used the statistical feature approach for each intrinsic mode function (IMF) as result of decomposition process. These values become a feature set entered of K-Nearest Neighbor (KNN) as classifier; the highest result of 93% was achieved using VMD and KNN with Manhattan distance.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132202410","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887417
Srinath Srinivasan, S. G. Shivanirudh, Sujay Sathya, T. T. Mirnalinee
In this paper, we aim to model the Bayesian uncertainty of a model designed to solve the task of book genre classification. Model prediction confidence can judge the predictive quality and usability of predictions made from a machine learning model. This work explores two methods to ascertain model uncertainty using Monte Carlo dropouts and deep ensembling. We apply uncertainty modeling to a bidirectional LSTM model trained on the CMU book summary dataset to perform book genre classification from book summaries. We show how these techniques improve results by 14% from the best baseline model and discuss their feasibility in real-world scenarios.
{"title":"Exploring Bayesian Uncertainty Modeling for Book Genre Classification","authors":"Srinath Srinivasan, S. G. Shivanirudh, Sujay Sathya, T. T. Mirnalinee","doi":"10.1109/IAICT55358.2022.9887417","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887417","url":null,"abstract":"In this paper, we aim to model the Bayesian uncertainty of a model designed to solve the task of book genre classification. Model prediction confidence can judge the predictive quality and usability of predictions made from a machine learning model. This work explores two methods to ascertain model uncertainty using Monte Carlo dropouts and deep ensembling. We apply uncertainty modeling to a bidirectional LSTM model trained on the CMU book summary dataset to perform book genre classification from book summaries. We show how these techniques improve results by 14% from the best baseline model and discuss their feasibility in real-world scenarios.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132301669","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887522
C. Stefanovic, Mohammad Alibakhshikenari, D. Stefanovic, F. Arpanaei, Stefan R. Panic
This paper considers single-input single-output (SISO) multi-hop wireless communication system (M-WCS) that consists of two dual-hop re-configurable intelligent surface (RIS)-enabled links that are connected by a unmanned aerial vehicle (UAV)-amplify-and-forward relay (AFR) in order to extend coverage. In particular, probability density function (PDF) $p_{R_{2}^{2}}(gamma_{tr,2})$ and cumulative distribution function (CDF) $F_{R_{2}^{2}}(gamma_{tr,2})$ of end-to-end SNR for the hybrid double RIS-enabled communications (RIS-ECs) with a UAV-AFR over dissimilar Rayleigh-Nakagami-m fading channels are derived. Capitalizing on the obtained mathematical expressions the system performance analysis in terms of outage probability (OP) $P_{R_{2}^{2}}(gamma_{tr,2})$ is further performed, graphically presented and analysed for different number of RIS modules and under various severity conditions. Moreover, we provide comparison between double RIS-ECs link with UAV-AFR and RIS-ECs link without UAVAFR in terms of outage statistics. It is further analysed that the RIS-ECs with UAV-AFR can not only extend the coverage but also can be deployed with sufficiently large number of RIS elements to improve the system performances.
{"title":"Outage Statistics of Hybrid Double-RIS System Assisted by Aerial AF-Relay for Multi-hop Communications","authors":"C. Stefanovic, Mohammad Alibakhshikenari, D. Stefanovic, F. Arpanaei, Stefan R. Panic","doi":"10.1109/IAICT55358.2022.9887522","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887522","url":null,"abstract":"This paper considers single-input single-output (SISO) multi-hop wireless communication system (M-WCS) that consists of two dual-hop re-configurable intelligent surface (RIS)-enabled links that are connected by a unmanned aerial vehicle (UAV)-amplify-and-forward relay (AFR) in order to extend coverage. In particular, probability density function (PDF) $p_{R_{2}^{2}}(gamma_{tr,2})$ and cumulative distribution function (CDF) $F_{R_{2}^{2}}(gamma_{tr,2})$ of end-to-end SNR for the hybrid double RIS-enabled communications (RIS-ECs) with a UAV-AFR over dissimilar Rayleigh-Nakagami-m fading channels are derived. Capitalizing on the obtained mathematical expressions the system performance analysis in terms of outage probability (OP) $P_{R_{2}^{2}}(gamma_{tr,2})$ is further performed, graphically presented and analysed for different number of RIS modules and under various severity conditions. Moreover, we provide comparison between double RIS-ECs link with UAV-AFR and RIS-ECs link without UAVAFR in terms of outage statistics. It is further analysed that the RIS-ECs with UAV-AFR can not only extend the coverage but also can be deployed with sufficiently large number of RIS elements to improve the system performances.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126525168","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887461
Carla Silva, A. Rodrigues, A. Jorge, I. Dutra
This research aims to extract knowledge of sensors behavior resorting to Bayesian networks (BNs) and dynamic Bayesian networks (DBNs), a time-based BN version. These two types of models belong to the group of probabilistic graphical models (PGMs). These graphical models can be very useful to get insights from data in order to improve sensor capabilities in the industry of fire detection systems, since it can provide the conditional dependence structure among various sensor variables. Relevant sensors with fire alerts were selected and studied at device level. We conduct a data fusion analysis since we deal with heterogeneous data sources, Remote Alert (RA) with sensor states and Condition Monitoring (CM) with numerical data. To achieve an accurate fusion of the data, a pipeline was designed to align both sources of data in a regular time interval. Furthermore, a change point detection (CPD) method was used to discretize the numerical variables. In addition, one-hot encoding was used to create binarized datasets and combine all data (RA+CM). Our modeling helps understanding the dependencies among the sensor variables, highlighting that individual devices of the same type can have a very different probabilistic behavior along the time, probably due to be installed in distinct regions. Moreover, the models helped capturing strange probabilistic sensor behavior such as a low probability of a NORMAL state happening given that states FIRE, WARNING and TROUBLE did not happen.
{"title":"Sensor data modeling with Bayesian networks","authors":"Carla Silva, A. Rodrigues, A. Jorge, I. Dutra","doi":"10.1109/IAICT55358.2022.9887461","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887461","url":null,"abstract":"This research aims to extract knowledge of sensors behavior resorting to Bayesian networks (BNs) and dynamic Bayesian networks (DBNs), a time-based BN version. These two types of models belong to the group of probabilistic graphical models (PGMs). These graphical models can be very useful to get insights from data in order to improve sensor capabilities in the industry of fire detection systems, since it can provide the conditional dependence structure among various sensor variables. Relevant sensors with fire alerts were selected and studied at device level. We conduct a data fusion analysis since we deal with heterogeneous data sources, Remote Alert (RA) with sensor states and Condition Monitoring (CM) with numerical data. To achieve an accurate fusion of the data, a pipeline was designed to align both sources of data in a regular time interval. Furthermore, a change point detection (CPD) method was used to discretize the numerical variables. In addition, one-hot encoding was used to create binarized datasets and combine all data (RA+CM). Our modeling helps understanding the dependencies among the sensor variables, highlighting that individual devices of the same type can have a very different probabilistic behavior along the time, probably due to be installed in distinct regions. Moreover, the models helped capturing strange probabilistic sensor behavior such as a low probability of a NORMAL state happening given that states FIRE, WARNING and TROUBLE did not happen.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127700402","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887423
Lyla B. Das, E. P. Jayakumar, G. Jagadanand, O. Meghana, P. Satheesh, R. Sriharsha, V. L. Prasanna, Vundavalli Aswini
This paper intends to address the problems of people who are visually challenged. One of the most vital parts of the human body is the eyes, unarguably. A visually challenged person is unable to appreciate many good things in life and has to spend his entire lifetime in darkness whereas a person without hands or legs can still do his daily chores on his own. Also, in the knowledge driven world, quality education is an absolute necessity in order to succeed and advance. All the available books and documents are not in the digital format. For a visually challenged person, to access these, a portable text reader is required. People with impaired vision face difficulty in their locomotion. They need to remember all the objects around when they are moving around in familiar places (home environment). This work proposes a hand-held device for visually handicapped people that integrates a Text Read-out system and a navigation assistant, which will help them to handle such challenging situations. This paper describes the implementation of a system that acts as a personal device for people with vision impairment. The implementation is done using ‘off the shelf hardware and software’ components.
{"title":"Design of a Personal Digital Assistant for the Visually Challenged","authors":"Lyla B. Das, E. P. Jayakumar, G. Jagadanand, O. Meghana, P. Satheesh, R. Sriharsha, V. L. Prasanna, Vundavalli Aswini","doi":"10.1109/IAICT55358.2022.9887423","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887423","url":null,"abstract":"This paper intends to address the problems of people who are visually challenged. One of the most vital parts of the human body is the eyes, unarguably. A visually challenged person is unable to appreciate many good things in life and has to spend his entire lifetime in darkness whereas a person without hands or legs can still do his daily chores on his own. Also, in the knowledge driven world, quality education is an absolute necessity in order to succeed and advance. All the available books and documents are not in the digital format. For a visually challenged person, to access these, a portable text reader is required. People with impaired vision face difficulty in their locomotion. They need to remember all the objects around when they are moving around in familiar places (home environment). This work proposes a hand-held device for visually handicapped people that integrates a Text Read-out system and a navigation assistant, which will help them to handle such challenging situations. This paper describes the implementation of a system that acts as a personal device for people with vision impairment. The implementation is done using ‘off the shelf hardware and software’ components.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114424928","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887482
Nabila Syadzwina Effendi, Y. Natali, C. Apriono
In 5G Network, Cloud Radio Access Network (C-RAN) plays a substantial role in escalating network performance efficiency. Nevertheless, this C-RAN concept’s main challenge lies in the need for a fronthaul network to handle high capacity and low delay. The Radio over Fiber (RoF) has been a solution to satisfy the high capacity and high-speed transmission required by the 5G fronthaul network. Keeping the attenuation effect low to achieve the minimum BER by using the optical amplifier is necessary. This paper investigates RoF by considering amplifier placement and different bitrate with 16-QAM modulation for Indonesia’s 5G Fronthaul Network Implementation. Optical amplifier placement scenarios are pre-amplifier and booster amplifier. The results show that the booster amplifier scheme can cover a maximum fronthaul transmission distance of 20 km. As a comparison, the pre-amplifier scheme can reach a transmission distance of up to 15 km. Moreover, increasing the bitrate from 1 Gbps to 2.5 Gbps causes the BER value to increase. This result shows that different optical amplifiers and the increase in bit rate will affect the obtained BER values and limit the transmission distance that the fronthaul network can achieve.
{"title":"Design of Radio over Fiber System with 16-QAM Modulation for 5G Fronthaul Network Implementation in Indonesia","authors":"Nabila Syadzwina Effendi, Y. Natali, C. Apriono","doi":"10.1109/IAICT55358.2022.9887482","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887482","url":null,"abstract":"In 5G Network, Cloud Radio Access Network (C-RAN) plays a substantial role in escalating network performance efficiency. Nevertheless, this C-RAN concept’s main challenge lies in the need for a fronthaul network to handle high capacity and low delay. The Radio over Fiber (RoF) has been a solution to satisfy the high capacity and high-speed transmission required by the 5G fronthaul network. Keeping the attenuation effect low to achieve the minimum BER by using the optical amplifier is necessary. This paper investigates RoF by considering amplifier placement and different bitrate with 16-QAM modulation for Indonesia’s 5G Fronthaul Network Implementation. Optical amplifier placement scenarios are pre-amplifier and booster amplifier. The results show that the booster amplifier scheme can cover a maximum fronthaul transmission distance of 20 km. As a comparison, the pre-amplifier scheme can reach a transmission distance of up to 15 km. Moreover, increasing the bitrate from 1 Gbps to 2.5 Gbps causes the BER value to increase. This result shows that different optical amplifiers and the increase in bit rate will affect the obtained BER values and limit the transmission distance that the fronthaul network can achieve.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131127172","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 : 2022-07-28DOI: 10.1109/IAICT55358.2022.9887476
N. Dudija, Lezia Natalia, A. Alamsyah, A. Romadhony
Human resources are essential for the business organization to adapt to change. Identifying the personality dimensions of new talent could help recruiters conduct the selection process of matching skilled talent to the organization’s needs. The objective of this study is to identify the personality dimensions corresponding to the job need, which correlates with extraversion and neuroticism. The legacy methodology to determine personality dimensions is through interviews or questionnaire surveys, but this process is costly and takes longer time to complete. This paper proposes a work on a person personality identification based on social media text as a complementary methodology. We utilize the textual data to support identifying new talent personality dimensions. In this study, we use IndoBERT model to capture person personality dimension based on their post on Twitter social media. As a result, our model achieves 96% accuracy in identifying extraversion and neuroticism personality dimensions. We also compare our result with the previous work based on the ontology model.
{"title":"Identification of Extraversion and Neuroticism Personality Dimensions Using IndoBERT’s Deep Learning Model","authors":"N. Dudija, Lezia Natalia, A. Alamsyah, A. Romadhony","doi":"10.1109/IAICT55358.2022.9887476","DOIUrl":"https://doi.org/10.1109/IAICT55358.2022.9887476","url":null,"abstract":"Human resources are essential for the business organization to adapt to change. Identifying the personality dimensions of new talent could help recruiters conduct the selection process of matching skilled talent to the organization’s needs. The objective of this study is to identify the personality dimensions corresponding to the job need, which correlates with extraversion and neuroticism. The legacy methodology to determine personality dimensions is through interviews or questionnaire surveys, but this process is costly and takes longer time to complete. This paper proposes a work on a person personality identification based on social media text as a complementary methodology. We utilize the textual data to support identifying new talent personality dimensions. In this study, we use IndoBERT model to capture person personality dimension based on their post on Twitter social media. As a result, our model achieves 96% accuracy in identifying extraversion and neuroticism personality dimensions. We also compare our result with the previous work based on the ontology model.","PeriodicalId":154027,"journal":{"name":"2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115947639","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：