2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)最新文献

{"title":"Indonesian Parsing using Probabilistic Context-Free Grammar (PCFG) and Viterbi-Cocke Younger Kasami (Viterbi-CYK)","authors":"D. E. Cahyani, L. Gumilar, Ajie Pangestu","doi":"10.1109/ISRITI51436.2020.9315395","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315395","url":null,"abstract":"Parsing is a tool for understanding natural grammar patterns. The problem of structural ambiguity in identifying sentence patterns often occurs in parsing. Syntactic parsing is one approach to solving structural ambiguity problems using the Probabilistic Context-Free Grammar (PCFG) and Viterbi-Cocke Younger Kasami (Viterbi-CYK) methods. Meanwhile, a large number of Indonesian language resources are needed as machine knowledge to parse. This research build a parsing of Indonesian sentence patterns with Indonesian Tagged corpus resource then solve the ambiguity problem of Indonesian sentence pattern parsing using PCFG and Viterbi-CYK algorithms. The corpus data is processed to obtain grammar rules using the PCFG algorithm. Then, the sentence on the corpus is processed by the PCFG rule that generated and uses the Viterbi-CYK algorithm to get the parse tree taken based on the highest probability value. The results of the research produced an average value of similarity production rules which the highest values is 92.95%. This shows that the Indonesian parsing successfully parses Indonesian sentence and can solve the problem of structural ambiguity in the parsing of Indonesian sentence patterns.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121959983","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}

{"title":"The Best Parameter Tuning on RNN Layers for Indonesian Text Classification","authors":"Awaliyatul Hikmah, Sumarni Adi, Mulia Sulistiyono","doi":"10.1109/ISRITI51436.2020.9315425","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315425","url":null,"abstract":"Recurrent Neural Network (RNN) is a deep learning architecture commonly used to process time series and sequence data. Various architectures have been developed to improve the performance of the algorithm in terms of both accuracy and computation time. Besides, the use of appropriate parameter values when building a neural network model also plays an important role in the quality and the outcome of the learning model. In this study, the model trained using RNN-Vanilla, LSTM, and GRU each with 4 different combinations of parameter settings, namely bidirectional mode (True, False), the number of neuron units on each layer (64, 128, 256), the number of RNN layers on the neural network (1, 2, 3), and the batch size when training the model (32, 64, 128). By combining all the parameter values, 162 trials were carried out to perform the task of classifying Indonesian language customer support tickets with four category classes. This study gives the result that the same network architecture but with different parameter combinations results in significant differences in the level of accuracy. The lowest accuracy of all experiments was 32.874% and the highest accuracy resulted was 84.369%. Overall, by calculating the average accuracy of each parameter value, the results obtained are: GRU has the best performance, accuracy tends to increase by activating bidirectional mode, increasing the number of neuron units in the hidden layer, and reducing the batch size. Meanwhile, the addition of the number of RNN layers on the neural network has no impact on increasing the level of accuracy.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125898804","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}

{"title":"Design and Prototype Development of Internet of Things for Greenhouse Monitoring System","authors":"D. Widyawati, A. Ambarwari, Anung Wahyudi","doi":"10.1109/ISRITI51436.2020.9315487","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315487","url":null,"abstract":"Greenhouse technology is a solution to optimize food crop production. However, the controlled climate conditions in the greenhouse make extra work in monitoring and controlling environmental conditions in the greenhouse. This paper introduces a monitoring system for environmental conditions in a greenhouse using the internet of things (IoT) technology. Sensors are designed to collect information about environmental conditions in the greenhouse such as temperature, humidity, soil temperature, soil moisture, and light intensity. The data from the sensor is then sent to the gateway once every minute through an access point installed in the greenhouse area. Then the data received by the gateway is stored in the SQLite database. Besides, the data received by the gateway is also displayed in real-time through the Node-RED dashboard installed on the gateway as user interfaces for monitoring greenhouse conditions. The gateway installed in the greenhouse area is also connected to the local network server so that the monitoring of the greenhouse can be carried out over a larger area. The test results for seven days showed that the IoT prototype for the greenhouse monitoring system was able to run well. This is indicated by the average percentage of data that is successfully storing at 99.76% and the average percentage of data loss or duplication is 0.24%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124967352","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}

{"title":"A Modified Deep Convolutional Network for COVID-19 detection based on chest X-ray images","authors":"Fian Yulio Santoso, H. Purnomo","doi":"10.1109/ISRITI51436.2020.9315479","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315479","url":null,"abstract":"COVID-19 pandemic caused vast impact worldwide. Many efforts have been made to tackle the pandemic, including in the deep learning community. In this research, a modification of deep neural network based on Xception model is proposed. The model is used for COVID-19 detection based on the chest X-ray images. The proposed model implements two stacks of two dense layers and batch normalization. The layers addition is used to avoid overfitting of the proposed model. The performance of the proposed model is compared to Resnet50, InceptionV3 and Xception. The experiment result shows that the proposed model has better performance than the other models used in the research. However, its computational time is higher than the other models used in the research.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123171780","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}

{"title":"Students Academic Performance Prediction with k-Nearest Neighbor and C4.5 on SMOTE-balanced data","authors":"U. Pujianto, Wisnu Agung Prasetyo, Agusta Rakhmat Taufani","doi":"10.1109/ISRITI51436.2020.9315439","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315439","url":null,"abstract":"Success in predicting student academic performance from an early age will make it easier for teachers to provide assistance to students who have academic abilities below the class average or who have difficulty following the learning process in the classroom. This study uses a public dataset to predict student academic performance based on a number of attributes that students have, both static and dynamic. This study compares the performance of two classifiers, namely C4.5 and k-Nearest Neighbor (KNN) and applies the SMOTE preprocessing method in the classification of student academic performance. Experiments carried out using the Rapid Miner application resulted in the fact that the C4.5 Decision Tree method resulted in better prediction performance in terms of accuracy, recall, and precision values, respectively 71.09%, 71.63%, 71.54% compared to the K-Nearest Neighbor algorithm.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121534038","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}

{"title":"Stemming Javanese: Another Adaptation of the Nazief-Adriani Algorithm","authors":"Mohammad Arifin Nq, L. Manik, Dany Widiyatmoko","doi":"10.1109/ISRITI51436.2020.9315420","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315420","url":null,"abstract":"Javanese is the regional language with the most speakers in Indonesia. Not only in the Java island, but the Javanese is also spoken by people outside Indonesia, such as in Malaysia and Suriname. Besides Bahasa Indonesia, which is the national language that must be learned by Indonesian society, the regional languages, like Javanese, also must be preserved. One of the preservation methods is by using an information retrieval system. One of the popular preprocessing methods in information retrieval is called stemming. It is used to reduce differences in word forms so that the information retrieval process becomes effective. Since Javanese has its uniqueness, the language morphology is different from Bahasa Indonesia. Thus, the stemming process of Javanese words also differs from Bahasa Indonesia. The stemming algorithm in this paper is developed by adapting the Nazief-Adriani algorithm, a well-known Bahasa Indonesia stemmer method. The algorithm in this paper is made based on the rules of Javanese language morphology. It removes ater-ater (prefixes), seselan (infixes), penambang (suffixes), bebarengan (confixes), and tembung rangkep (repeated word).","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126490371","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}

{"title":"Multilayer Secure Hardware Network Stack using FPGA","authors":"Shreyus Yadaveerappa Kouty","doi":"10.1109/ISRITI51436.2020.9315502","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315502","url":null,"abstract":"This paper presents an implementation of a User Datagram Protocol (UDP)/Internet Protocol (IP) Hardware network Stack using Field Programmable Gate Array (FPGA) [1] and technology to secure and protect data integrity and authenticity at three layers: Transport Layer, Network Layer and Data Link layer using True Random Number Generator (TRNG) digital signal processor (DSP) intellectual property (IP) Core [4]. UDP/IP stack is preferred proposal over Transport Control Protocol (TCP)/Internet Protocol (IP) stack as it is connectionless oriented, and widely used in Internet of Things (IoT), Industrial IoT (IIoT), Virtual Protocol Network (VPN), Video Conference, Voice over Internet Protocol (VoIP), Avionics and defense communication systems. Due to its technology independent, digital entropy source, easy to integrate and port to FPGA, TRNG is preferred over other reported cost-effective security methods like Static Random Access Memory (SRAM) based Physical Un-clonable Functions (PUF) generates random number based on start up behavior due to nano variations in circuit elements in addressing cloning, impersonation and data integrity loss, and also TRNG is not effected by environmental fluctuations such as voltage, temperature, and noise. However, cross inverters in SRAM PUF can be used as source of entropy in TRNG. FPGA based Hardware network stack is preferred over software network stack as it reduces the execution overhead in the Operating System (OS), Hardware network stack node is independent of Microprocessors as it consists of its own Digital Clock Manager (DCM), Memory Blocks, Dedicated Hardware Interfaces, and System on Chip (SoC) IP Cores which are configurable and extendable based on requirements. Hardware based network stack is susceptible to loss of data integrity and authenticity due to 1. Unstable digital circuits, 2. Noise diode and register, small AC voltage, polarity semiconductor, 3. instability of oscillator (jitter in circuits), 4. Meta-stability of flip-flops, 5. Cross inverters in SRAM circuits (SRAM PUF) and 6. Block RAM write conflict [7]. Multilayer secure Hardware network node is important as the data integrity and authenticity is responsible for good communication network with the high performance and throughput. This paper discusses about, how TRNG DSP IP Core is used in securing the three layers of the FPGA based UDP/IP Hardware Network Stack to secure data.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122170609","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}

{"title":"Personality Dimensions Classification with EEG Analysis using Support Vector Machine","authors":"Fadhilah Qalbi Annisa, E. Supriyanto, Sahar Taheri","doi":"10.1109/ISRITI51436.2020.9315507","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315507","url":null,"abstract":"Personality is the fundamental thing that forms the behavioral tendencies of each individuality in a situation. A common model used to describe personality is the big five personality that divides personality traits into five dimensions of neuroticism, extraversion, openness, agreeableness, and conscientiousness. Personality assessment through physiological signals offers objectivity and reliability of the test results due to the minimal role of test takers in the examination process. One widely recommended approach is signal-based analysis of electroencephalography (EEG). The EEG signal feature of the ASCERTAIN public database was extracted using discrete wavelet transform (DWT) and was classified using support vector machine (SVM) to determine personality dimensions. The results showed better performance compared to the application of other techniques on the same dataset with 69% and 75.9% accuracy to determine extraversion and neuroticism level, respectively. However, this accuracy still needs to be improved to generate reliable model. Increased data variability can be useful for understanding brain dynamic activity per individual.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124981469","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}

{"title":"Measuring Instagram Activity and Engagement Rate of Hospital: A Comparison Before and During COVID-19 Pandemic","authors":"Badra Al Aufa, W. Sulistiadi, Faizah Abdullah Djawas","doi":"10.1109/ISRITI51436.2020.9315490","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315490","url":null,"abstract":"Social media operated by hospitals plays a significant role during the COVID-19 pandemic. However, the hospitals' effort to engage their followers during the pandemic is understudied. The study aimed to identify the hospitals' frequency post in their Instagram account and the engagement rate before and during the COVID-19 pandemic. The study observed the activities through the Instagram posts of each hospital. The observation was conducted using a cross-sectional review of the hospital-related activities of 19 Instagram accounts owned by the hospitals across Depok City, Indonesia. Further, to measure the engagement rate, the period of the posts was limited from January to June 2020. The rate was calculated by dividing the total number of likes by the total number of followers' times the number of posts times the probability of followers viewing the posts; then multiplied by 100%. The Mann Whitney U test was employed to determine the significant difference in the daily Instagram posts and the engagement rate before and during the pandemic. The study showed that 15 hospitals increase Instagram activities during the pandemic, and eight hospitals (42.11%) showed a significant increase compared to the pre-pandemic period. Besides, the results revealed that nine hospitals (47.37%) increased the engagement rate. Meanwhile, about 40% of the samples increased the frequency of post and engagement rates. However, few hospitals, primarily publicly owned hospitals, need to improve the posts and the engagement rate.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131578138","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}

{"title":"Performance Analysis FSR and DSR Routing Protocol in VANET with V2V and V2I Models","authors":"Renal Zikriyan Akbar, Istikmal, Sussi","doi":"10.1109/ISRITI51436.2020.9315367","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315367","url":null,"abstract":"Vehicular Ad-hoc Network (VANET) is a technology concept that makes it possible for vehicles to communicate with other vehicles as Vehicle to Vehicle (V2V) communication or network infrastructure along the road as Vehicle to Infrastructure (V2I) communication type. VANET has characteristics where each node can communicate even if the nodes move at high speeds. Therefore, the right type of routing protocol is needed. This research aims to analyze the performance of two types of topology-based routing protocols namely the proactive Fisheye State Routing (FSR) routing protocol and the reactive Dynamic Source Routing (DSR) routing protocol with the V2V and V2I communication models. The contribution of this paper is investigated the performance of FSR and DSR using the scenario of changes number of nodes, the scenario of speed changes, and the scenario of packet size variations with V2V and V2I model. The simulation results show that DSR outperforms FSR in V2V and V2I communication in terms of throughput and end-to-end delay.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134152048","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}