Pub Date : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466039
Akbar Serdano, M. Zarlis, E. Nababan
In data security, a technique is needed to secure data from experiments and attacks by cryptanalysts. The technique of securing data is also known as cryptography. In this research, it has been done to improve data security by combining the Hill Cipher Algorithm with the Caesar Cipher Algorithm. This process can be seen from the tests that have been carried out in this study. The result is in a different and sufficiently improved processing time both in terms of decryption and encryption. By combining the two cryptographic algorithms, it is known that message security is much better. It occurs because the encryption and decryption process of the message is carried out using 2 different keys. Based on the tests, it shows that the time of the encryption process with the decryption process on the $5times 5$ matrix key is very different from using the $3times 3$ matrix key, the difference is slightly different in time. It shows that the use of a larger matrix key affects the decryption process is very long and also influenced by other cryptographic algorithm processes. In this study, another cryptographic algorithm is the Caesar Cipher Algorithm.
{"title":"Performance of Combining Hill Cipher Algorithm and Caesar Cipher Algorithm in Text Security","authors":"Akbar Serdano, M. Zarlis, E. Nababan","doi":"10.1109/AIMS52415.2021.9466039","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466039","url":null,"abstract":"In data security, a technique is needed to secure data from experiments and attacks by cryptanalysts. The technique of securing data is also known as cryptography. In this research, it has been done to improve data security by combining the Hill Cipher Algorithm with the Caesar Cipher Algorithm. This process can be seen from the tests that have been carried out in this study. The result is in a different and sufficiently improved processing time both in terms of decryption and encryption. By combining the two cryptographic algorithms, it is known that message security is much better. It occurs because the encryption and decryption process of the message is carried out using 2 different keys. Based on the tests, it shows that the time of the encryption process with the decryption process on the $5times 5$ matrix key is very different from using the $3times 3$ matrix key, the difference is slightly different in time. It shows that the use of a larger matrix key affects the decryption process is very long and also influenced by other cryptographic algorithm processes. In this study, another cryptographic algorithm is the Caesar Cipher Algorithm.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115730673","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466029
Nanang Cahyadi, B. Rahardjo
People counting systems can provide statistical trend information used for human behavior analysis. Intuitively people counting system works based on sequence detection, tracking, and counting. However, with active research activities in Artificial Intelligence in Computer Vision, there are many alternatives available for implementing a people counting system. A systematic literature review is used to obtain the latest research information that accurately following the requirements of the system being designed as well as the gap areas that arise in implementation. The gap areas found are in the design of an implementation that suits your needs and increases the accuracy of the counters who enter or leave the frame. Several strategies can be done to achieve this goal by conducting head detection and training with a pretrained model in the object detection and tracking framework. This strategy is expected to increase accuracy through stabilizing object detection and tracking.
{"title":"Literature Review of People Counting","authors":"Nanang Cahyadi, B. Rahardjo","doi":"10.1109/AIMS52415.2021.9466029","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466029","url":null,"abstract":"People counting systems can provide statistical trend information used for human behavior analysis. Intuitively people counting system works based on sequence detection, tracking, and counting. However, with active research activities in Artificial Intelligence in Computer Vision, there are many alternatives available for implementing a people counting system. A systematic literature review is used to obtain the latest research information that accurately following the requirements of the system being designed as well as the gap areas that arise in implementation. The gap areas found are in the design of an implementation that suits your needs and increases the accuracy of the counters who enter or leave the frame. Several strategies can be done to achieve this goal by conducting head detection and training with a pretrained model in the object detection and tracking framework. This strategy is expected to increase accuracy through stabilizing object detection and tracking.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116174531","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466017
Dwieka Septian Arif Prasetya, D. Arseno, Brian Pamukti, H. Vidyaningtyas
In the era of technology 4.0, the automobile industry began to develop with the increasing comfort, safety and apply new technologies such as artificial intelligence. We propose a Light Detection and Ranging (LIDAR) sensor as a medium for detection and data transmission for safety between cars. Our proposal has been tested on prototype vehicles that can be used indoors, such as in a company that requires automation of the vehicle. This study uses a $2times 2$ array Light Emitting Diode (LED) simultaneously to the LIDAR sensor. Prototype vehicles has been observed and analyzed for the impact of changes in distance and angle. With intensive experiments, the results show that using the LIDAR sensor in the prototype vehicle obtains accurate distance detection. We also proved that the prototype yields the optimal distance in transmitting data to be 20 cm to 120 cm at 0 degrees, 20 to 60 cm at 10 degrees, and 20 to 40 cm at 15 degrees. In addition, the maximum distance that this prototype vehicle can transmit is 260 cm at 0 degrees, 100 cm at 10 degrees, 40 cm at 15 degrees, which is still relatively safe for vehicle distance tolerance.
{"title":"Experimental Analysis of Vehicle-to-Vehicle Communication using Light Detection and Ranging (LIDAR) for Detection and Data Transmission","authors":"Dwieka Septian Arif Prasetya, D. Arseno, Brian Pamukti, H. Vidyaningtyas","doi":"10.1109/AIMS52415.2021.9466017","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466017","url":null,"abstract":"In the era of technology 4.0, the automobile industry began to develop with the increasing comfort, safety and apply new technologies such as artificial intelligence. We propose a Light Detection and Ranging (LIDAR) sensor as a medium for detection and data transmission for safety between cars. Our proposal has been tested on prototype vehicles that can be used indoors, such as in a company that requires automation of the vehicle. This study uses a $2times 2$ array Light Emitting Diode (LED) simultaneously to the LIDAR sensor. Prototype vehicles has been observed and analyzed for the impact of changes in distance and angle. With intensive experiments, the results show that using the LIDAR sensor in the prototype vehicle obtains accurate distance detection. We also proved that the prototype yields the optimal distance in transmitting data to be 20 cm to 120 cm at 0 degrees, 20 to 60 cm at 10 degrees, and 20 to 40 cm at 15 degrees. In addition, the maximum distance that this prototype vehicle can transmit is 260 cm at 0 degrees, 100 cm at 10 degrees, 40 cm at 15 degrees, which is still relatively safe for vehicle distance tolerance.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124844743","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466013
M. N. A. Khan, U. Ghafoor, K. Hong
To date, several studies have utilized brain stimulation to evoke particular brain activity. One of the most critical questions that remain unaddressed is how long the stimulation should last. To address this issue, this paper investigates two different stimulation durations for braincomputer interface (BCI) with functional near-infrared spectroscopy (fNIRS). To do so, this paper investigates the influence of the stimulation duration on the hemodynamic response (HR) signal in the sensorimotor cortex of the human brain. fNIRS is used for the measurement of HRs. For brain stimulation, right-hand index finger tapping and poking tasks are utilized, and the HR signals are acquired. Two different stimulation durations, i.e., 10 and 15 secs, were utilized in this study, and a total of 5 subjects participated in the experiment. After acquiring the signals, signals are filtered, leading to classification. From the study results, it is concluded that the classification accuracy does not increase with the increase in the stimulation duration among the tested stimulation durations. So, the use of longer stimulation durations, i.e., 15 secs, can't serve the purpose well and make the subjects tired. In contrast, 10-sec stimulation yielded a higher classification accuracy in a comparatively shorter time, which is the BCI's core objective.
{"title":"Classification of sensorimotor cortex signals based on the task durations: an fNIRS-BCI study","authors":"M. N. A. Khan, U. Ghafoor, K. Hong","doi":"10.1109/AIMS52415.2021.9466013","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466013","url":null,"abstract":"To date, several studies have utilized brain stimulation to evoke particular brain activity. One of the most critical questions that remain unaddressed is how long the stimulation should last. To address this issue, this paper investigates two different stimulation durations for braincomputer interface (BCI) with functional near-infrared spectroscopy (fNIRS). To do so, this paper investigates the influence of the stimulation duration on the hemodynamic response (HR) signal in the sensorimotor cortex of the human brain. fNIRS is used for the measurement of HRs. For brain stimulation, right-hand index finger tapping and poking tasks are utilized, and the HR signals are acquired. Two different stimulation durations, i.e., 10 and 15 secs, were utilized in this study, and a total of 5 subjects participated in the experiment. After acquiring the signals, signals are filtered, leading to classification. From the study results, it is concluded that the classification accuracy does not increase with the increase in the stimulation duration among the tested stimulation durations. So, the use of longer stimulation durations, i.e., 15 secs, can't serve the purpose well and make the subjects tired. In contrast, 10-sec stimulation yielded a higher classification accuracy in a comparatively shorter time, which is the BCI's core objective.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114428946","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466062
I. G. S. M. Diyasa, A. Prayogi, I. Purbasari, A. Setiawan, Sugiarto, Prismahardi Aji Riantoko
For a company engaged in the service and health sector, it is essential to read consumers' characteristics to develop the company and produce the right products. It is still challenging to determine patients' nutritional treatment, with many patients' healthy treatment remained appropriate and accurate for each patient. Patient data collection and patient interviews are needed to obtain suitable treatment data for the patient. However, to get appropriate further treatment, a system must process past patient data, resulting in more accurate follow-up treatments. The method used in this study is to calculate the value of the training data and K point with the K-Nearest Neighbors (K-NN) Algorithm. The goal is to determine the treatment package menu recommendations for consumers. The K-Nearest Neighbors algorithm is one of the algorithms used for the implementation of this system development. The patient characteristics and data distance calculation using the euclidean distance function can produce a category used to determine a more accurate and good nutritional treatment for each patient. The scenario in the test with a comparison of training data and test data 3: 1 has the highest program accuracy reaching 88%, precision reaching 91%, and recall going 95% among all the results of the test scenario
{"title":"Data Classification of Patient Characteristics Based on Nutritional Treatment Using the K-Nearest Neighbors Algorithm","authors":"I. G. S. M. Diyasa, A. Prayogi, I. Purbasari, A. Setiawan, Sugiarto, Prismahardi Aji Riantoko","doi":"10.1109/AIMS52415.2021.9466062","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466062","url":null,"abstract":"For a company engaged in the service and health sector, it is essential to read consumers' characteristics to develop the company and produce the right products. It is still challenging to determine patients' nutritional treatment, with many patients' healthy treatment remained appropriate and accurate for each patient. Patient data collection and patient interviews are needed to obtain suitable treatment data for the patient. However, to get appropriate further treatment, a system must process past patient data, resulting in more accurate follow-up treatments. The method used in this study is to calculate the value of the training data and K point with the K-Nearest Neighbors (K-NN) Algorithm. The goal is to determine the treatment package menu recommendations for consumers. The K-Nearest Neighbors algorithm is one of the algorithms used for the implementation of this system development. The patient characteristics and data distance calculation using the euclidean distance function can produce a category used to determine a more accurate and good nutritional treatment for each patient. The scenario in the test with a comparison of training data and test data 3: 1 has the highest program accuracy reaching 88%, precision reaching 91%, and recall going 95% among all the results of the test scenario","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123709235","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466026
H. Khan, Hammad Nazeer, Håvard Engell, Noman Naseer, O. Korostynska, P. Mirtaheri
Human gait uses complex coordination between muscles, joints, and brain, which involves a high cognition level. Planning of this complex cognitive behaviour involves the prefrontal cortex (PFC) of the brain cerebrum. Due to mobility and comfortability, functional near-infrared spectroscopy (fNIRS) is widely used to monitor brain activation in the PFC. This case study reports on a novel approach towards investigating the effect of different walking patterns, footwear, and ground conditions on prefrontal activation. An activation map of oxygenated haemoglobin (HbO) based on the t-values method was generated for comparative analysis of cognitive levels in different conditions. High activation in the PFC was found while performing barefooted simple and catwalks on the Kybun® mat. Compared to all other walking conditions, low channel activation was observed while performing a barefooted walk on a hard surface. The difference in activation level between two different footwear types (shoes with different heelbone angle construction) was not significant. Similarly, the activation in pre- and post-exercise was almost similar. Improvements such as increasing the number of subjects, experimental length, and the number of optodes are considered for further experiments. The experimental setup and paradigm need further improvement to understand better the effect of footwear, walking patterns, and ground conditions on the prefrontal activation during walking.
{"title":"Prefrontal Cortex Activation Measured during Different Footwear and Ground Conditions Using fNIRS — A Case Study","authors":"H. Khan, Hammad Nazeer, Håvard Engell, Noman Naseer, O. Korostynska, P. Mirtaheri","doi":"10.1109/AIMS52415.2021.9466026","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466026","url":null,"abstract":"Human gait uses complex coordination between muscles, joints, and brain, which involves a high cognition level. Planning of this complex cognitive behaviour involves the prefrontal cortex (PFC) of the brain cerebrum. Due to mobility and comfortability, functional near-infrared spectroscopy (fNIRS) is widely used to monitor brain activation in the PFC. This case study reports on a novel approach towards investigating the effect of different walking patterns, footwear, and ground conditions on prefrontal activation. An activation map of oxygenated haemoglobin (HbO) based on the t-values method was generated for comparative analysis of cognitive levels in different conditions. High activation in the PFC was found while performing barefooted simple and catwalks on the Kybun® mat. Compared to all other walking conditions, low channel activation was observed while performing a barefooted walk on a hard surface. The difference in activation level between two different footwear types (shoes with different heelbone angle construction) was not significant. Similarly, the activation in pre- and post-exercise was almost similar. Improvements such as increasing the number of subjects, experimental length, and the number of optodes are considered for further experiments. The experimental setup and paradigm need further improvement to understand better the effect of footwear, walking patterns, and ground conditions on the prefrontal activation during walking.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121044924","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466057
Fateh Seghir
The nonfunctional (QoS-aware) web Service Composition (QSC) problem, which is a strong NP-hard optimization one, is widely addressed by considering the advertised Quality of Service (QoS) values of web services as non-ambiguous. However, in real world environments, and due to some of their unconditional factors like network architectures changes, communications congestion and economic policies, the QoS values ambiguity should be undertaken in formulating the QSC problem. In this paper, we present a genetic algorithm that integrates an elitism replacement method for solving the QoS problem under fuzzy QoS parameters, which have been expressed as generalized trapezoidal fuzzy numbers. The addressed QSC problem is formulated as a fuzzy nonlinear integer constrained single-objective optimization model through adapting the well-known simple additive weighting method. To illustrate the performance and the efficiency of the proposed algorithm, we present the experimental comparisons to a fuzzy approach of an existing Particle Swarm Optimization (PSO)-based web service selection algorithm over a fuzzy extended version of the real-world QWS dataset.
{"title":"A genetic algorithm with an elitism replacement method for solving the nonfunctional web service composition under fuzzy QoS parameters","authors":"Fateh Seghir","doi":"10.1109/AIMS52415.2021.9466057","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466057","url":null,"abstract":"The nonfunctional (QoS-aware) web Service Composition (QSC) problem, which is a strong NP-hard optimization one, is widely addressed by considering the advertised Quality of Service (QoS) values of web services as non-ambiguous. However, in real world environments, and due to some of their unconditional factors like network architectures changes, communications congestion and economic policies, the QoS values ambiguity should be undertaken in formulating the QSC problem. In this paper, we present a genetic algorithm that integrates an elitism replacement method for solving the QoS problem under fuzzy QoS parameters, which have been expressed as generalized trapezoidal fuzzy numbers. The addressed QSC problem is formulated as a fuzzy nonlinear integer constrained single-objective optimization model through adapting the well-known simple additive weighting method. To illustrate the performance and the efficiency of the proposed algorithm, we present the experimental comparisons to a fuzzy approach of an existing Particle Swarm Optimization (PSO)-based web service selection algorithm over a fuzzy extended version of the real-world QWS dataset.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114612926","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466071
Firdaus Aulian Cahyanto, Gutama Indra Gandha, M. A. Heryanto
The Sharp GP2Y0A02YK0F is an infrared-based nonlinear distance measuring sensor unit. This sensor categorized as low-cost sensor. Since this sensor has nonlinear characteristic in output voltage made this sensor is not easy to compute the measured distance. The modelling process is one of the solutions to complete this challenge. The Newton polynomial is a robust polynomial method that used in computational purpose. However, the polynomial-based modelling methods are suffered with Runge's phenomenon especially for nonlinear model. The partial modelling method with piecewise Newton polynomials algorithm has been used to minimize the occurrence of Runge's phenomenon. The piecewise Newton polynomials method has been succeeded to generate a nonlinear model and minimize the occurrence of Runge's phenomenon. The low MSE (Mean Squared Error) level by 0.001 and error percentage by 2.38% has been achieved for the generated model. The accuracy level of the final model is 97.62%.
{"title":"The Partial Modelling of Non-Linear Analog Distance Sensor using Piecewise Newton Polynomials Algorithm to Minimize the Occurrence of Runge's Phenomenon","authors":"Firdaus Aulian Cahyanto, Gutama Indra Gandha, M. A. Heryanto","doi":"10.1109/AIMS52415.2021.9466071","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466071","url":null,"abstract":"The Sharp GP2Y0A02YK0F is an infrared-based nonlinear distance measuring sensor unit. This sensor categorized as low-cost sensor. Since this sensor has nonlinear characteristic in output voltage made this sensor is not easy to compute the measured distance. The modelling process is one of the solutions to complete this challenge. The Newton polynomial is a robust polynomial method that used in computational purpose. However, the polynomial-based modelling methods are suffered with Runge's phenomenon especially for nonlinear model. The partial modelling method with piecewise Newton polynomials algorithm has been used to minimize the occurrence of Runge's phenomenon. The piecewise Newton polynomials method has been succeeded to generate a nonlinear model and minimize the occurrence of Runge's phenomenon. The low MSE (Mean Squared Error) level by 0.001 and error percentage by 2.38% has been achieved for the generated model. The accuracy level of the final model is 97.62%.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682070","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466083
Adawiyah Ulfa, A. Bustamam, Arry Yanuar, R. Amalia, P. Anki
In recent years, various focusing on Dipeptidyl Peptidase-4 inhibitors drugs discovery to achieve better treatments for type II Diabetes Mellitus. As such, new medical research on new DPP-4 inhibitors with minimal effects is still crucial. One of the drug designs based on in silico is a virtual screening-based ligand (LBVS). The LBVS method used in this research is Quantitative structure-activity relation (QSAR). The QSAR model is a fast and cost-effective alternative for experimental measurement in drug discovery. Deep learning has also been successful and is now widely used in drug discovery. In this study, we propose a combination of two deep learning approaches, namely the Conv1D-LSTM model as a renewable method for predicting the classification of Dipeptidyl Peptidase-4 inhibitors. This model includes the Conv1D model as a data encoding stage and LSTM as a model for the classification of compounds in Dipeptidyl Peptidase-4 inhibitors. We use 2604 molecular structures of DPP-4 inhibitors with 1443 active compounds and 1161 inactive compounds. The result in our proposed model has great accuracy for the classification of compounds in the Dipeptidyl Peptidase-4 inhibitors with an accuracy of 86.18%. Furthermore, the values for sensitivity, specificity, and MCC were obtained are 91.05%, 79.45%, and 71.50% respectively.
{"title":"Model QSAR Classification Using Conv1D-LSTM of Dipeptidyl Peptidase-4 Inhibitors","authors":"Adawiyah Ulfa, A. Bustamam, Arry Yanuar, R. Amalia, P. Anki","doi":"10.1109/AIMS52415.2021.9466083","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466083","url":null,"abstract":"In recent years, various focusing on Dipeptidyl Peptidase-4 inhibitors drugs discovery to achieve better treatments for type II Diabetes Mellitus. As such, new medical research on new DPP-4 inhibitors with minimal effects is still crucial. One of the drug designs based on in silico is a virtual screening-based ligand (LBVS). The LBVS method used in this research is Quantitative structure-activity relation (QSAR). The QSAR model is a fast and cost-effective alternative for experimental measurement in drug discovery. Deep learning has also been successful and is now widely used in drug discovery. In this study, we propose a combination of two deep learning approaches, namely the Conv1D-LSTM model as a renewable method for predicting the classification of Dipeptidyl Peptidase-4 inhibitors. This model includes the Conv1D model as a data encoding stage and LSTM as a model for the classification of compounds in Dipeptidyl Peptidase-4 inhibitors. We use 2604 molecular structures of DPP-4 inhibitors with 1443 active compounds and 1161 inactive compounds. The result in our proposed model has great accuracy for the classification of compounds in the Dipeptidyl Peptidase-4 inhibitors with an accuracy of 86.18%. Furthermore, the values for sensitivity, specificity, and MCC were obtained are 91.05%, 79.45%, and 71.50% respectively.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134163996","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466088
Fajar Arasy Isman, Anggunmeka Luhur Prasasti, Ratna Astuti Nugrahaeni
In testing an application such as a video game, user response or user experience in playing a video game was very important for the developer itself. The utilization of the convolutional neural network (CNN) machine learning classification for facial expression feedback in terms of gameplay satisfaction would greatly help developers in finalizing their products. In this researched, the expressions that could've have been classified were angry, fear, sad, happy, neutral, disgusted, and surprised. This researched was done using cnn and the facial expression recognition 2013 (fer2013) dataset. In the proposed system, cnn was applied in the extraction of characteristics, classification of images, and recommendations. Before classifying expressions, the training model needed to have been processed first. Testing was carried throughout the following stages, namely the process of determining the dataset used, training the model, testing process, and performance test. The test results with a data ratio of 90% data training and 10% data test resulted in a training model with a final accuracy value of 64.26%, while the real time performance testing with the best result was obtained from a test scheme with distance of 60 cm with a moderate light intensity of 14 lux that gets 100% accuracy. Compared to the other researched in this area, the system implemented facial expression classification in real time and give a recap of expressions classified during the real time classification in the form of graph and pie chart.
{"title":"Expression Classification For User Experience Testing Using Convolutional Neural Network","authors":"Fajar Arasy Isman, Anggunmeka Luhur Prasasti, Ratna Astuti Nugrahaeni","doi":"10.1109/AIMS52415.2021.9466088","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466088","url":null,"abstract":"In testing an application such as a video game, user response or user experience in playing a video game was very important for the developer itself. The utilization of the convolutional neural network (CNN) machine learning classification for facial expression feedback in terms of gameplay satisfaction would greatly help developers in finalizing their products. In this researched, the expressions that could've have been classified were angry, fear, sad, happy, neutral, disgusted, and surprised. This researched was done using cnn and the facial expression recognition 2013 (fer2013) dataset. In the proposed system, cnn was applied in the extraction of characteristics, classification of images, and recommendations. Before classifying expressions, the training model needed to have been processed first. Testing was carried throughout the following stages, namely the process of determining the dataset used, training the model, testing process, and performance test. The test results with a data ratio of 90% data training and 10% data test resulted in a training model with a final accuracy value of 64.26%, while the real time performance testing with the best result was obtained from a test scheme with distance of 60 cm with a moderate light intensity of 14 lux that gets 100% accuracy. Compared to the other researched in this area, the system implemented facial expression classification in real time and give a recap of expressions classified during the real time classification in the form of graph and pie chart.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133096137","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：