Pub Date : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034657
A. Sari, F. Prasetya
The use of linear support vector regression on private data in cloud computing must consider data privacy. Homomorphic encryption is an approach to address the problem. However, most of the existing approaches still use inefficient fully homomorphic encryption, in which both the training data and the testing data must be encrypted using the same public key. This leads to the repetition of the training process. The problem is addressed in this paper by applying partially homomorphic encryption using Paillier cryptosystem. Operations in linear support vector regression are modified so that they can be applied to process encrypted data. The model is used to predict the motor and total UPDRS (Unified Parkinson's Disease Rating Scale) scores. To assess the performance of the model, the MRSE (Mean Root Square Error) of the prediction on encrypted data is then compared with the MRSE of the prediction on unencrypted data. The evaluation shows that the MRSE of the prediction on encrypted data is exactly the same as that on unencrypted data, which proves that the modification on the operations in linear support vector regression has been done correctly.
{"title":"Linear Support Vector Regression in Cloud Computing on Data Encrypted using Paillier Cryptosystem","authors":"A. Sari, F. Prasetya","doi":"10.1109/ISRITI48646.2019.9034657","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034657","url":null,"abstract":"The use of linear support vector regression on private data in cloud computing must consider data privacy. Homomorphic encryption is an approach to address the problem. However, most of the existing approaches still use inefficient fully homomorphic encryption, in which both the training data and the testing data must be encrypted using the same public key. This leads to the repetition of the training process. The problem is addressed in this paper by applying partially homomorphic encryption using Paillier cryptosystem. Operations in linear support vector regression are modified so that they can be applied to process encrypted data. The model is used to predict the motor and total UPDRS (Unified Parkinson's Disease Rating Scale) scores. To assess the performance of the model, the MRSE (Mean Root Square Error) of the prediction on encrypted data is then compared with the MRSE of the prediction on unencrypted data. The evaluation shows that the MRSE of the prediction on encrypted data is exactly the same as that on unencrypted data, which proves that the modification on the operations in linear support vector regression has been done correctly.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131674912","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034674
E. Purwanto, Endra Wahjono, I. Ferdiansyah, D. S. Yanaratri, Lucky Pradigta Setiya Raharja, Rachma Prilian Eviningsih, Gamar Basuki
Genetic algorithms are one method used for the optimization technique, in this paper were developed the application of GA methods to solve equations the model of induction motor (IM) by dq model (Vector Control). On this system the stator currents and rotor currents in dq axis set as the variables are determined through a process of evolution (GA) and take the price of genetic fitness of torque as objective function for each generation. On this genetic method used two kinds of encoding its chromosome, which is in binary and floating with some of the crossover, mutation and selection to obtain good results. Here will be sought after combination of each genetic operator to get the best results. The result of this method are found best result for the all.
{"title":"Implementation of Genetic Algorithm for Induction Motor Speed Control Based on Vector Control Method","authors":"E. Purwanto, Endra Wahjono, I. Ferdiansyah, D. S. Yanaratri, Lucky Pradigta Setiya Raharja, Rachma Prilian Eviningsih, Gamar Basuki","doi":"10.1109/ISRITI48646.2019.9034674","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034674","url":null,"abstract":"Genetic algorithms are one method used for the optimization technique, in this paper were developed the application of GA methods to solve equations the model of induction motor (IM) by dq model (Vector Control). On this system the stator currents and rotor currents in dq axis set as the variables are determined through a process of evolution (GA) and take the price of genetic fitness of torque as objective function for each generation. On this genetic method used two kinds of encoding its chromosome, which is in binary and floating with some of the crossover, mutation and selection to obtain good results. Here will be sought after combination of each genetic operator to get the best results. The result of this method are found best result for the all.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"418 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133158358","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034616
Puruso Muhammad Hanunggul, S. Suyanto
An attentional mechanism is very important to enhance a neural machine translation (NMT). There are two classes of attentions: global and local attentions. This paper focuses on comparing the impact of the local attention in Long Short-Term Memory (LSTM) model to generate an abstractive text summarization (ATS). Developing a model using a dataset of Amazon Fine Food Reviews and evaluating it using dataset of GloVe shows that the global attention-based model produces better ROUGE-1, where it generates more words contained in the actual summary. But, the local attention-based gives higher ROUGE-2, where it generates more pairs of words contained in the actual summary, since the mechanism of local attention considers the subset of input words instead of the whole input words.
注意机制是提高神经机器翻译能力的关键。关注有两类:全局关注和局部关注。本文比较了局部注意对长短期记忆(LSTM)模型生成抽象文本摘要(ATS)的影响。使用Amazon Fine Food Reviews的数据集开发一个模型，并使用GloVe的数据集对其进行评估，结果表明，基于全局注意力的模型产生了更好的ROUGE-1，它生成了更多包含在实际摘要中的单词。但是，基于局部注意的方法给出了更高的ROUGE-2，它生成了更多包含在实际摘要中的词对，因为局部注意的机制考虑的是输入词的子集而不是整个输入词。
{"title":"The Impact of Local Attention in LSTM for Abstractive Text Summarization","authors":"Puruso Muhammad Hanunggul, S. Suyanto","doi":"10.1109/ISRITI48646.2019.9034616","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034616","url":null,"abstract":"An attentional mechanism is very important to enhance a neural machine translation (NMT). There are two classes of attentions: global and local attentions. This paper focuses on comparing the impact of the local attention in Long Short-Term Memory (LSTM) model to generate an abstractive text summarization (ATS). Developing a model using a dataset of Amazon Fine Food Reviews and evaluating it using dataset of GloVe shows that the global attention-based model produces better ROUGE-1, where it generates more words contained in the actual summary. But, the local attention-based gives higher ROUGE-2, where it generates more pairs of words contained in the actual summary, since the mechanism of local attention considers the subset of input words instead of the whole input words.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124258124","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034568
N. N. Qomariyah, A. Fajar
Online shopping has become an important part of lifestyle nowadays. Despite their many practical advantages, the users of online shopping systems can be overwhelmed with the abundant information about the goods they want to buy. While some users start their search with a preference for certain items or manufacturers, others may find it difficult to narrow down the range of options being offered. The recommender system can assist the users to filter the information and show the most relevant items to the users. Despite being very popular in ecommerce area, research on recommender systems for education is still underexplored. Similar to the users of ecommerce system, some students may also feel overwhelmed by the available choices of material contents offered by the elearning system in which, it does not always suit to their learning style. This is important as some experts in educational psychology suggest that students need to learn by following their personal learning style. We propose an implementation design of e-learning recommender system based on a logic approach, APARELL (Active Pairwise Relation Learner), which has been implemented for used car sales domain. There is an opportunity to apply the same procedure for e-learning system to help the student to choose the best material according to their preferences. We also propose an ontology of material content based on the different learning styles. In this paper, we show that there is a big potential to implement a personalised recommender system in e-learning based on the students learning style.
{"title":"Recommender System for e-Learning based on Personal Learning Style","authors":"N. N. Qomariyah, A. Fajar","doi":"10.1109/ISRITI48646.2019.9034568","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034568","url":null,"abstract":"Online shopping has become an important part of lifestyle nowadays. Despite their many practical advantages, the users of online shopping systems can be overwhelmed with the abundant information about the goods they want to buy. While some users start their search with a preference for certain items or manufacturers, others may find it difficult to narrow down the range of options being offered. The recommender system can assist the users to filter the information and show the most relevant items to the users. Despite being very popular in ecommerce area, research on recommender systems for education is still underexplored. Similar to the users of ecommerce system, some students may also feel overwhelmed by the available choices of material contents offered by the elearning system in which, it does not always suit to their learning style. This is important as some experts in educational psychology suggest that students need to learn by following their personal learning style. We propose an implementation design of e-learning recommender system based on a logic approach, APARELL (Active Pairwise Relation Learner), which has been implemented for used car sales domain. There is an opportunity to apply the same procedure for e-learning system to help the student to choose the best material according to their preferences. We also propose an ontology of material content based on the different learning styles. In this paper, we show that there is a big potential to implement a personalised recommender system in e-learning based on the students learning style.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115957908","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034651
Qhansa Di'ayu Putri Bayu, S. Suyanto, A. Arifianto
The emotional component in a music classification is more powerful than the others. This research addresses a music emotion classification. A hierarchical classification system using a Support Vector Machine (SVM) and a k-Nearest Neighbors (kNN) is proposed. The experiments using 120 pop-rock music data with the emotional label based on the AllMusicGuide website split into four classes: "Happy", "Angry", "Sad", and "Relax" show that the proposed hierarchical model is capable of increasing the absolute performance of music emotion classification by 19.33% in the SVM (Kernel: RBF) and 13.33% in the kNN (k = 5). The best combination three-level classifier, the arrangement of the three best classifiers for each level in hierarchical music emotion classification is by using the SVM (Kernel: Linear) classifier at Level 1, then kNN (k = 3) at Level 2.1 and Level 2.2.
{"title":"Hierarchical SVM-kNN to Classify Music Emotion","authors":"Qhansa Di'ayu Putri Bayu, S. Suyanto, A. Arifianto","doi":"10.1109/ISRITI48646.2019.9034651","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034651","url":null,"abstract":"The emotional component in a music classification is more powerful than the others. This research addresses a music emotion classification. A hierarchical classification system using a Support Vector Machine (SVM) and a k-Nearest Neighbors (kNN) is proposed. The experiments using 120 pop-rock music data with the emotional label based on the AllMusicGuide website split into four classes: \"Happy\", \"Angry\", \"Sad\", and \"Relax\" show that the proposed hierarchical model is capable of increasing the absolute performance of music emotion classification by 19.33% in the SVM (Kernel: RBF) and 13.33% in the kNN (k = 5). The best combination three-level classifier, the arrangement of the three best classifiers for each level in hierarchical music emotion classification is by using the SVM (Kernel: Linear) classifier at Level 1, then kNN (k = 3) at Level 2.1 and Level 2.2.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123169031","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034663
Bemedict Wimpy, S. Suyanto
Cancer is one of the most lethal disease in the world. Therefore, early treatment of cancerous patient is proofed effective to decrease the lethal rate of this disease. For example, is cervical cancer, the precancerous step of cervical cancer is detected by looking at the cancerous transformation zone on the cervix. Furthermore, there are some different type of cervix regarding to its transformation zone. Therefore skills and experience is needed to be able to precisely determine which type of cervix making detection of cervical cancer is less efficient. This study is creating a deep learning model based on Capsule Networks to classify colposcopy images as a solution to make cervical cancer detection and treatment more effective and efficient. With a result of 100% accuracy of the test set and 94.98% accuracy of the train set. This study exceeds the result of other earlier experiments
{"title":"Classification of Cervical Type Image Using Capsule Networks","authors":"Bemedict Wimpy, S. Suyanto","doi":"10.1109/ISRITI48646.2019.9034663","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034663","url":null,"abstract":"Cancer is one of the most lethal disease in the world. Therefore, early treatment of cancerous patient is proofed effective to decrease the lethal rate of this disease. For example, is cervical cancer, the precancerous step of cervical cancer is detected by looking at the cancerous transformation zone on the cervix. Furthermore, there are some different type of cervix regarding to its transformation zone. Therefore skills and experience is needed to be able to precisely determine which type of cervix making detection of cervical cancer is less efficient. This study is creating a deep learning model based on Capsule Networks to classify colposcopy images as a solution to make cervical cancer detection and treatment more effective and efficient. With a result of 100% accuracy of the test set and 94.98% accuracy of the train set. This study exceeds the result of other earlier experiments","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124803631","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}
The application of artificial intelligence in computer games has increased in recent years. Maze chase game is a game that takes place in a maze. The aim of the game is that the player must take all the points in the maze. Inside the labyrinth there are four Non-Playable Characters (NPCs) that move to chase the player. The shortest path algorithm is applied to the NPC in order to determine the shortest path from the current position of the NPC to the player position. In this study the author will compare the optimal level of path retrieval and the length of time needed in selecting the shortest path using the A* algorithm and the Time-Bounded A* algorithm. With the implementation of the A* algorithm and the TBA* algorithm on the Maze Chase game NPCs, the authors found that the A* algorithm has a faster travel time of 0.3% when compared to the TBA* algorithm, while the TBA* algorithm expands the nodes 73.2% less compared to the A* algorithm.
{"title":"Comparison of A* Algorithm and Time Bounded A* Algorithm on Maze Chase Game NPC","authors":"Fahryandi Herlasmara Putra, Surya Michrandi Nasution, Ratna Astuti Nugrahaeni","doi":"10.1109/ISRITI48646.2019.9034566","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034566","url":null,"abstract":"The application of artificial intelligence in computer games has increased in recent years. Maze chase game is a game that takes place in a maze. The aim of the game is that the player must take all the points in the maze. Inside the labyrinth there are four Non-Playable Characters (NPCs) that move to chase the player. The shortest path algorithm is applied to the NPC in order to determine the shortest path from the current position of the NPC to the player position. In this study the author will compare the optimal level of path retrieval and the length of time needed in selecting the shortest path using the A* algorithm and the Time-Bounded A* algorithm. With the implementation of the A* algorithm and the TBA* algorithm on the Maze Chase game NPCs, the authors found that the A* algorithm has a faster travel time of 0.3% when compared to the TBA* algorithm, while the TBA* algorithm expands the nodes 73.2% less compared to the A* algorithm.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125106739","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034645
Priscilya Inri Sasia, Muhammad Ary Murti, C. Setianingsih
Smart lamp is a technology that offers convenience for users in controlling the lamp. Previously, there had been research developing this system, but the controls offered were still based on Android that can’t support a multiple platform. This system uses the Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) algorithms. Besides that, this system also does a trial by using Internet of Things System for controlling and monitoring the lamps.From this research, the results of testing show that the average time required for the system to turn on and turn off Lamp I are 3.3 seconds and 3.28 seconds respectively with a minimum sound intensity of 60.6 dB. To turn on and turn off Lamp II in succession is 3.43 second and 3.61 second with a minimum sound intensity of 60.8 dB. Meanwhile, to turn on and turn off Lamp III in a row is 3.32 seconds and 3.39 seconds with a sound intensity of at least 61.32 dB. The three lamps can be controlled with the furthest distance is 1.2 meters.
{"title":"Implementation of Lamp Control System by Reccurent Neural Network and Long-Short Term Memory","authors":"Priscilya Inri Sasia, Muhammad Ary Murti, C. Setianingsih","doi":"10.1109/ISRITI48646.2019.9034645","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034645","url":null,"abstract":"Smart lamp is a technology that offers convenience for users in controlling the lamp. Previously, there had been research developing this system, but the controls offered were still based on Android that can’t support a multiple platform. This system uses the Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) algorithms. Besides that, this system also does a trial by using Internet of Things System for controlling and monitoring the lamps.From this research, the results of testing show that the average time required for the system to turn on and turn off Lamp I are 3.3 seconds and 3.28 seconds respectively with a minimum sound intensity of 60.6 dB. To turn on and turn off Lamp II in succession is 3.43 second and 3.61 second with a minimum sound intensity of 60.8 dB. Meanwhile, to turn on and turn off Lamp III in a row is 3.32 seconds and 3.39 seconds with a sound intensity of at least 61.32 dB. The three lamps can be controlled with the furthest distance is 1.2 meters.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122316903","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034603
M. Faisal, S. Suyanto
An automatic speaker verification (ASV) is one of the challenging problem in speech processing since there are so many models of machine learnings those capable of synthesizing a fake speech from a given text. This paper discusses the impact of SpecAugment to methods such as Gaussian Mixture Models (GMM) and Deep Neural Networks (DNNs). Some experiments on a speech dataset sampled from the ASVSpoof2019, which is specially made to tackle the threat of spoofing, show that DNNs produces an Equal Error Rate (EER) of 18.1% that is better than the GMM system with EER of 19.0%. And after combining with a traditional augmentation technique, the DNNs also gives a better EER of 15.3% than GMM with EER of 15.7%.
{"title":"SpecAugment Impact on Automatic Speaker Verification System","authors":"M. Faisal, S. Suyanto","doi":"10.1109/ISRITI48646.2019.9034603","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034603","url":null,"abstract":"An automatic speaker verification (ASV) is one of the challenging problem in speech processing since there are so many models of machine learnings those capable of synthesizing a fake speech from a given text. This paper discusses the impact of SpecAugment to methods such as Gaussian Mixture Models (GMM) and Deep Neural Networks (DNNs). Some experiments on a speech dataset sampled from the ASVSpoof2019, which is specially made to tackle the threat of spoofing, show that DNNs produces an Equal Error Rate (EER) of 18.1% that is better than the GMM system with EER of 19.0%. And after combining with a traditional augmentation technique, the DNNs also gives a better EER of 15.3% than GMM with EER of 15.7%.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126724493","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034668
Febry Ghaisani, S. Suyanto
Timetabling or scheduling is a common problem in an institution of medicine, transportation, education, etc. It is a process of resource allocation by considering some predetermined constraints. In this paper, a discretization scheme is proposed to improve a meta-heuristic swarm intelligence approach called discrete firefly algorithm (DFA) in solving an undergraduate thesis defense timetabling. Some computer experiments show that the proposed discretization scheme is capable of reducing the number of constraint violations to reach an accuracy of 98.98% for a simple case of 70% occupancy. The accuracy decreases to be 82.19% for a more complex case of 95% occupancy.
{"title":"Discrete Firefly Algorithm for an Examination Timetabling","authors":"Febry Ghaisani, S. Suyanto","doi":"10.1109/ISRITI48646.2019.9034668","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034668","url":null,"abstract":"Timetabling or scheduling is a common problem in an institution of medicine, transportation, education, etc. It is a process of resource allocation by considering some predetermined constraints. In this paper, a discretization scheme is proposed to improve a meta-heuristic swarm intelligence approach called discrete firefly algorithm (DFA) in solving an undergraduate thesis defense timetabling. Some computer experiments show that the proposed discretization scheme is capable of reducing the number of constraint violations to reach an accuracy of 98.98% for a simple case of 70% occupancy. The accuracy decreases to be 82.19% for a more complex case of 95% occupancy.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125716619","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：