Pub Date : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435255
Barokatun Hasanah, Firilia Filiana, A. I. Ismail, A. Munir, Dina Herdiana
Waveguide is capable of working at high frequencies. The addition of a resonator to the waveguide can adjust the working frequency as desired without changing the dimensions of the waveguide. In this research, circular waveguide band pass filter was made using an artificial dielectric material as the resonator. Artificial dielectric material is a material that is not available in nature, this material is made by combining small particles of conductor with dielectric material. The response of this artificial dielectric material after becoming a resonator can change the working frequency and adjust according to the propagation mode we want. In this research, a band pass filter is made with electric transfer propagation mode. Determination of this mode affects the design of the dielectric resonator that is made so that a filter with return loss and bandwidth parameters is obtained
{"title":"Implementation of Circular Waveguide Band Pass Filter using Artificial Dielectric Resonator for Transverse Electric Propagation Mode","authors":"Barokatun Hasanah, Firilia Filiana, A. I. Ismail, A. Munir, Dina Herdiana","doi":"10.1109/APWiMob51111.2021.9435255","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435255","url":null,"abstract":"Waveguide is capable of working at high frequencies. The addition of a resonator to the waveguide can adjust the working frequency as desired without changing the dimensions of the waveguide. In this research, circular waveguide band pass filter was made using an artificial dielectric material as the resonator. Artificial dielectric material is a material that is not available in nature, this material is made by combining small particles of conductor with dielectric material. The response of this artificial dielectric material after becoming a resonator can change the working frequency and adjust according to the propagation mode we want. In this research, a band pass filter is made with electric transfer propagation mode. Determination of this mode affects the design of the dielectric resonator that is made so that a filter with return loss and bandwidth parameters is obtained","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123011999","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435227
Pinasthika Aulia Fadhila, M. I. Nashiruddin
4G LTE-Advanced is the latest technology that supports faster connections. Many people in Indonesia are expecting this newest technology to facilitate activities related to an internet connection. Because of this, users are increasing and causing network congestion in Indonesia. The solution to this problem is the addition of frequencies on the 4G LTE-Advanced network. This research plans and simulates 4G LTE-Advanced network deployment in Central Jakarta with a frequency spectrum of 2100 MHz using a quantitative method with two approaches, capacity and coverage planning, and performance analysis of four parameters, namely, RSRP, SINR, radio bearer, and throughput. The results of this research are that network deployment in Central Jakarta requires at least 109 sites to cover all regions and users. The performance analysis results show that network deployment is feasible, with an RSRP value of −60,97 dBm, an average SINR of 3,37 dB, modulation using 16QAM with an efficiency of 2,4063, and throughput with an average of 22.258,37 kbps.
{"title":"Planning & Simulation Analysis of 4G LTE-Advanced Mobile Network Deployment Using 2100 MHz Frequency Spectrum in Dense Urban Area: Case Study in Central Jakarta","authors":"Pinasthika Aulia Fadhila, M. I. Nashiruddin","doi":"10.1109/APWiMob51111.2021.9435227","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435227","url":null,"abstract":"4G LTE-Advanced is the latest technology that supports faster connections. Many people in Indonesia are expecting this newest technology to facilitate activities related to an internet connection. Because of this, users are increasing and causing network congestion in Indonesia. The solution to this problem is the addition of frequencies on the 4G LTE-Advanced network. This research plans and simulates 4G LTE-Advanced network deployment in Central Jakarta with a frequency spectrum of 2100 MHz using a quantitative method with two approaches, capacity and coverage planning, and performance analysis of four parameters, namely, RSRP, SINR, radio bearer, and throughput. The results of this research are that network deployment in Central Jakarta requires at least 109 sites to cover all regions and users. The performance analysis results show that network deployment is feasible, with an RSRP value of −60,97 dBm, an average SINR of 3,37 dB, modulation using 16QAM with an efficiency of 2,4063, and throughput with an average of 22.258,37 kbps.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128362809","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435198
Hartuti Mistialustina, Chairunnisa, A. Munir
The implementation of power weighted functions in a linear antenna array is usually intended to obtain the desired antenna performance, especially the radiation pattern. This paper proposes the design of power weighted linear antenna array using Kaiser function. The challenges in the design are about choosing appropriate scheme of impedances and type of feeding network. The proposed antenna array consists of 1×8 square patches with proximity coupled feed. It is designed to operate at the X-band frequency intended for a radar application. The simulation result shows that Kaiser function utilization in linear antenna array suppresses sidelobe level (SLL) than antenna array with a uniform power distribution. The differences between obtained SLL and targeted SLL of the design is also exposed, so there must be an adjustment on Kaiser function parameter value, namely β. Based on β value of 2.0299 for 30 dB targeted SLL, the obtained SLL in the simulation is 14.93 dB.
{"title":"Design of Proximity Coupled Linear Antenna Array Using Kaiser Power Weighted Function","authors":"Hartuti Mistialustina, Chairunnisa, A. Munir","doi":"10.1109/APWiMob51111.2021.9435198","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435198","url":null,"abstract":"The implementation of power weighted functions in a linear antenna array is usually intended to obtain the desired antenna performance, especially the radiation pattern. This paper proposes the design of power weighted linear antenna array using Kaiser function. The challenges in the design are about choosing appropriate scheme of impedances and type of feeding network. The proposed antenna array consists of 1×8 square patches with proximity coupled feed. It is designed to operate at the X-band frequency intended for a radar application. The simulation result shows that Kaiser function utilization in linear antenna array suppresses sidelobe level (SLL) than antenna array with a uniform power distribution. The differences between obtained SLL and targeted SLL of the design is also exposed, so there must be an adjustment on Kaiser function parameter value, namely β. Based on β value of 2.0299 for 30 dB targeted SLL, the obtained SLL in the simulation is 14.93 dB.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127013288","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435199
H. Prasetyo, R. Sarno, R. Budiraharjo, K. R. Sungkono
One way to do business process modelling is to use the process mining. Process mining links the gap between traditional model-based process analysis such as business process management simulation and data-centric analysis techniques such as machine learning and data mining. In process modelling, bottleneck conditions are often found. Bottlenecks conditions can be found in the process models generated using Process Mining applications such as ProM and Disco based on event log data. There is another alternative to find the bottleneck condition of the event log using a statistical approach. The alternative is to view the event log as an asset that can be explored without using a normative process model. This paper proposes a statistical test of heteroscedasticity in event log data. Then the heteroscedasticity test results from the event log are compared with the results of normative process modelling with the Inductive Miner algorithm using the Process Mining application. The comparison results show that the detected event log data having heteroscedasticity problems will ensure a bottleneck condition in the process model. The approach taken can be an alternative in evaluating the process model based on its event log.
{"title":"The Effect of Duration Heteroscedasticity to the Bottleneck in Business Process Discovered by Inductive Miner Algorithm","authors":"H. Prasetyo, R. Sarno, R. Budiraharjo, K. R. Sungkono","doi":"10.1109/APWiMob51111.2021.9435199","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435199","url":null,"abstract":"One way to do business process modelling is to use the process mining. Process mining links the gap between traditional model-based process analysis such as business process management simulation and data-centric analysis techniques such as machine learning and data mining. In process modelling, bottleneck conditions are often found. Bottlenecks conditions can be found in the process models generated using Process Mining applications such as ProM and Disco based on event log data. There is another alternative to find the bottleneck condition of the event log using a statistical approach. The alternative is to view the event log as an asset that can be explored without using a normative process model. This paper proposes a statistical test of heteroscedasticity in event log data. Then the heteroscedasticity test results from the event log are compared with the results of normative process modelling with the Inductive Miner algorithm using the Process Mining application. The comparison results show that the detected event log data having heteroscedasticity problems will ensure a bottleneck condition in the process model. The approach taken can be an alternative in evaluating the process model based on its event log.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114237104","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435215
Ratri Dwi Atmaja, A. B. Suksmono, D. Danudirdjo, Taufiq Hidayat
In many applications, an incomplete measurement case aims to obtain the desired original signal. However, the limited measured signal causes the predicted signal not to be the same as the original signal. A reconstruction technique is needed to improve the predicted signal. In this paper, we apply the Yang method for signal reconstruction from incomplete measurement, i.e. image reconstruction from incomplete frequency information. Low-high resolution patches of training images are learned to produce an overcomplete dictionary. Then the overcomplete dictionary is used to predict high-resolution patches on the testing images. Each testing images are targeted to reach the smallest RMSE. To obtain the smallest RMSE, each testing images have different conditions of variables, coming from the iteration number, the number of training images, and patch factor value. 0.3512 is the greatest RMSE improvement when comparing the smallest RMSE to the RMSE of the dirty image.
{"title":"Image Reconstruction from Incomplete Frequency Information Using Yang Method","authors":"Ratri Dwi Atmaja, A. B. Suksmono, D. Danudirdjo, Taufiq Hidayat","doi":"10.1109/APWiMob51111.2021.9435215","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435215","url":null,"abstract":"In many applications, an incomplete measurement case aims to obtain the desired original signal. However, the limited measured signal causes the predicted signal not to be the same as the original signal. A reconstruction technique is needed to improve the predicted signal. In this paper, we apply the Yang method for signal reconstruction from incomplete measurement, i.e. image reconstruction from incomplete frequency information. Low-high resolution patches of training images are learned to produce an overcomplete dictionary. Then the overcomplete dictionary is used to predict high-resolution patches on the testing images. Each testing images are targeted to reach the smallest RMSE. To obtain the smallest RMSE, each testing images have different conditions of variables, coming from the iteration number, the number of training images, and patch factor value. 0.3512 is the greatest RMSE improvement when comparing the smallest RMSE to the RMSE of the dirty image.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115971772","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435273
Irzal Ahmad Sabilla, Doni Putra Purbawa, R. Sarno, A. Fauzi, D. Wijaya, Rudy Gunawan
Sweating at night can be an indication that there is a disturbance in the human metabolic system. Sweat itself is a substance that is unused in the body or the result of human excretion. The sweat glands are scattered in all parts of the body, but mostly in three locations: armpits, palms, and feet. Several kinds of research related to sweat and Electronic Nose (E-Nose) have also been studied. The study used a patch to absorb sweat and proved the presence of nicotine content from a smoker. However, the previous research has not focused on human sweat at night for potential disease. This paper aims to propose a system to distinguish men and women at night through the armpit sweat odor using Taguchi Gas Sensors (TGS) and SHT15. Researchers found four significant sensors for further investigation: TGS 822, TGS 826, TGS 833, and TGS 2620. This study obtained a total of 165 armpit sweat data, which have been processed and adjusted for this case into 25 data, 12 men (ME) and 13 women (WO). Several classification models are implemented, such as Support Vector Machine (SVM), Naïve Bayes (NB), and Decision Tree (DT) with accuracy 92.30%, 96.15%, and 84.62%, respectively. Based on the highest accuracy and the Volatile Organic Compounds (VOC) measurement, women are more likely to suffer from several diseases than men, such as leukemia.
{"title":"Men and Women Classification at Night Through the Armpit Sweat Odor using Electronic Nose","authors":"Irzal Ahmad Sabilla, Doni Putra Purbawa, R. Sarno, A. Fauzi, D. Wijaya, Rudy Gunawan","doi":"10.1109/APWiMob51111.2021.9435273","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435273","url":null,"abstract":"Sweating at night can be an indication that there is a disturbance in the human metabolic system. Sweat itself is a substance that is unused in the body or the result of human excretion. The sweat glands are scattered in all parts of the body, but mostly in three locations: armpits, palms, and feet. Several kinds of research related to sweat and Electronic Nose (E-Nose) have also been studied. The study used a patch to absorb sweat and proved the presence of nicotine content from a smoker. However, the previous research has not focused on human sweat at night for potential disease. This paper aims to propose a system to distinguish men and women at night through the armpit sweat odor using Taguchi Gas Sensors (TGS) and SHT15. Researchers found four significant sensors for further investigation: TGS 822, TGS 826, TGS 833, and TGS 2620. This study obtained a total of 165 armpit sweat data, which have been processed and adjusted for this case into 25 data, 12 men (ME) and 13 women (WO). Several classification models are implemented, such as Support Vector Machine (SVM), Naïve Bayes (NB), and Decision Tree (DT) with accuracy 92.30%, 96.15%, and 84.62%, respectively. Based on the highest accuracy and the Volatile Organic Compounds (VOC) measurement, women are more likely to suffer from several diseases than men, such as leukemia.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127355068","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435241
Md. Moklesur Rahman, H. Ryu, Md. Najmul Hossain
Wireless communication systems are operated in each different frequency band. Also, it will be much comfortable and convenient for the single device of small size to be able to cover the multiple functions. Therefore, in this paper, a compact multi-band slotted circular patch antenna is designed and presented for the next generation wireless and cellular applications whose overall dimension is $mathbf{15x12x1.6}$ [mm]. In this paper, triple band circular antenna with triangular slot patch is presented, which can operate in the Ku-band, Ka-band and mm-wave frequency bands of 5G mobile service applications. The antenna is designed to operate in the frequency ranges 16.593-18.08[GHz], 23.42-25.64[GHz] for satellite communication, radar application and 27.7-29 [GHz] for 5G mm-wave services. The first band presents in the Ku-band and the second presents in the Ka-band respectively. The maximum gain of the proposed antenna is 8.478 dB and the maximum efficiency is 89.34%.
{"title":"A Compact Slotted Patch Antenna Design for Multiband Applications","authors":"Md. Moklesur Rahman, H. Ryu, Md. Najmul Hossain","doi":"10.1109/APWiMob51111.2021.9435241","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435241","url":null,"abstract":"Wireless communication systems are operated in each different frequency band. Also, it will be much comfortable and convenient for the single device of small size to be able to cover the multiple functions. Therefore, in this paper, a compact multi-band slotted circular patch antenna is designed and presented for the next generation wireless and cellular applications whose overall dimension is $mathbf{15x12x1.6}$ [mm]. In this paper, triple band circular antenna with triangular slot patch is presented, which can operate in the Ku-band, Ka-band and mm-wave frequency bands of 5G mobile service applications. The antenna is designed to operate in the frequency ranges 16.593-18.08[GHz], 23.42-25.64[GHz] for satellite communication, radar application and 27.7-29 [GHz] for 5G mm-wave services. The first band presents in the Ku-band and the second presents in the Ka-band respectively. The maximum gain of the proposed antenna is 8.478 dB and the maximum efficiency is 89.34%.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"91 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122566455","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435217
R. Budiraharjo, H. Prasetyo, R. Sarno, K. R. Sungkono
Generating process models that reflect close behavioral resemblance to the actual process Standard Operating Procedure (SOP) in process mining can be challenging without taking the four quality criteria of process discovery into account. The four quality criteria, i.e. fitness, precision, generalization, and simplicity, should be well balanced in order to produce proper process models which are aligned to the real-life executions. This paper proposes a method to optimize process discovery quality criteria (PDQC) by implementing different thresholds and analyzing calculation results using Receiver Operating Characteristic (ROC) curve and Infrequent Inductive Miner algorithm. This paper sets up two experiments with different scenarios to measure the calculations of quality criteria and the quality of generated models. The experiments compare two SOPs to the process models discovered by Infrequent Inductive Miner algorithm; hence the SOPs serve as references to determine the generated models quality. The purpose of applying two different scenarios in the experiments is to discover how well the Infrequent Inductive Miner thresholds can produce predictive models under these two different scenarios circumstances. This paper has been successful in predicting the best-fit model in reference to the SOPs by optimizing the four quality criteria of process discovery using ROC thresholds settings and by using infrequent inductive miner algorithm for models generation, and also in improving the accuracy of models measurements. The accuracy rate of the prediction model from Experiment 1 is 83%, while Experiment 2 yields an accuracy rate of 88%. The most optimal threshold settings to generate the best model in this paper are threshold 0.4 in Experiment 1 and threshold 0.5 in Experiment 2.
{"title":"Optimizing Process Discovery Quality Criteria and Model Measurements using Receiver Operating Characteristic Analysis and Infrequent Inductive Miner","authors":"R. Budiraharjo, H. Prasetyo, R. Sarno, K. R. Sungkono","doi":"10.1109/APWiMob51111.2021.9435217","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435217","url":null,"abstract":"Generating process models that reflect close behavioral resemblance to the actual process Standard Operating Procedure (SOP) in process mining can be challenging without taking the four quality criteria of process discovery into account. The four quality criteria, i.e. fitness, precision, generalization, and simplicity, should be well balanced in order to produce proper process models which are aligned to the real-life executions. This paper proposes a method to optimize process discovery quality criteria (PDQC) by implementing different thresholds and analyzing calculation results using Receiver Operating Characteristic (ROC) curve and Infrequent Inductive Miner algorithm. This paper sets up two experiments with different scenarios to measure the calculations of quality criteria and the quality of generated models. The experiments compare two SOPs to the process models discovered by Infrequent Inductive Miner algorithm; hence the SOPs serve as references to determine the generated models quality. The purpose of applying two different scenarios in the experiments is to discover how well the Infrequent Inductive Miner thresholds can produce predictive models under these two different scenarios circumstances. This paper has been successful in predicting the best-fit model in reference to the SOPs by optimizing the four quality criteria of process discovery using ROC thresholds settings and by using infrequent inductive miner algorithm for models generation, and also in improving the accuracy of models measurements. The accuracy rate of the prediction model from Experiment 1 is 83%, while Experiment 2 yields an accuracy rate of 88%. The most optimal threshold settings to generate the best model in this paper are threshold 0.4 in Experiment 1 and threshold 0.5 in Experiment 2.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131169944","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435250
Fathania Firwan Firdaus, H. A. Nugroho, I. Soesanti
Heart disease causes the most deaths in the world with around 17.89 million people dying each year. Detecting heart disease at an early stage is needed so that further action can be done on the patient. Many researchers have conducted studies about computer-assisted diagnosis system for heart disease. This research presents a heart disease detection method using a deep neural network with hyperparameter tuning. Hyperparameter tuning is done using grid search, random search, and Bayesian optimization. In terms of tuning time, random search spends less time than Bayesian optimization and grid search. In terms of classification performance results, Bayesian optimization produces higher accuracy than grid search and random search. The classification performance of DNN with Bayesian optimization on the testing resulted in an accuracy of 91.67%, a sensitivity of 95.83%, a specificity of 88.89%, a precision of 85.19%, an F1-score of 90.20%, and an AUC value of 0.9514. It indicates that DNN with Bayesian optimization is preferable to be used in detecting heart disease.
{"title":"Deep Neural Network with Hyperparameter Tuning for Detection of Heart Disease","authors":"Fathania Firwan Firdaus, H. A. Nugroho, I. Soesanti","doi":"10.1109/APWiMob51111.2021.9435250","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435250","url":null,"abstract":"Heart disease causes the most deaths in the world with around 17.89 million people dying each year. Detecting heart disease at an early stage is needed so that further action can be done on the patient. Many researchers have conducted studies about computer-assisted diagnosis system for heart disease. This research presents a heart disease detection method using a deep neural network with hyperparameter tuning. Hyperparameter tuning is done using grid search, random search, and Bayesian optimization. In terms of tuning time, random search spends less time than Bayesian optimization and grid search. In terms of classification performance results, Bayesian optimization produces higher accuracy than grid search and random search. The classification performance of DNN with Bayesian optimization on the testing resulted in an accuracy of 91.67%, a sensitivity of 95.83%, a specificity of 88.89%, a precision of 85.19%, an F1-score of 90.20%, and an AUC value of 0.9514. It indicates that DNN with Bayesian optimization is preferable to be used in detecting heart disease.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128234106","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 : 2021-04-08DOI: 10.1109/APWiMob51111.2021.9435280
Isaac Anugerah Siahaan, Giva Andriana Mutiara, Muhammad Ikhsan Sani
Water is an important aspect that required by humans every day. The water quality is very essential on human's health. Nowadays, with the pollution that is affecting the water conditions, the quality of water consumed by humans need to be maintained. However, not every household have a dedicated system to monitor daily water quality. This paper proposed an alternative idea for utilizing several light sensors i.e. Light Dependent Resistor (LDR) and photodiode for detecting water quality especially its turbidity. This idea is proposed as an alternative solution to turbidity sensor and to have an affordable water quality monitoring system. Moreover, the sensor data is stored in a database on the Internet of Things cloud server and can be accessed by the Android- based application remotely. Based on the results, the system has successfully detected the water turbidity based on Nephelometric Turbidity Unit (NTU) scale. and the average sensor database update rate is about 16 seconds.
{"title":"A Low-Cost Water Quality Monitoring Based on Photodiode and LDR","authors":"Isaac Anugerah Siahaan, Giva Andriana Mutiara, Muhammad Ikhsan Sani","doi":"10.1109/APWiMob51111.2021.9435280","DOIUrl":"https://doi.org/10.1109/APWiMob51111.2021.9435280","url":null,"abstract":"Water is an important aspect that required by humans every day. The water quality is very essential on human's health. Nowadays, with the pollution that is affecting the water conditions, the quality of water consumed by humans need to be maintained. However, not every household have a dedicated system to monitor daily water quality. This paper proposed an alternative idea for utilizing several light sensors i.e. Light Dependent Resistor (LDR) and photodiode for detecting water quality especially its turbidity. This idea is proposed as an alternative solution to turbidity sensor and to have an affordable water quality monitoring system. Moreover, the sensor data is stored in a database on the Internet of Things cloud server and can be accessed by the Android- based application remotely. Based on the results, the system has successfully detected the water turbidity based on Nephelometric Turbidity Unit (NTU) scale. and the average sensor database update rate is about 16 seconds.","PeriodicalId":325270,"journal":{"name":"2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124229018","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：