Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Semantic Classification of Scientific Sentence Pair Using Recurrent Neural Network
Get PDFOne development of Natural Language Processing is the semantic classification of sentences and documents. The challenge is finding relationships between words and between documents through a computational model. The development of machine learning makes it possible to try out various possibilities that provide classification capabilities. This paper proposes the semantic classification of sentence pairs using Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM). Each couple of sentences is turned into vectors using Word2Vec. Experiments carried out using CBOW and Skip-Gram to get the best combination. The results are obtained that word embedding using CBOW produces better than Skip-Gram, although it is still around 5%. However, CBOW slows slightly at the beginning of iteration but is stable towards convergence. Classification of all six classes, namely Equivalent, Similar, Specific, No Alignment, Related, and Opposite. As a result of the unbalanced data set, the retraining was conducted by eliminating a few classes member from the data set, thus providing an accuracy of 73% for non-training data. The results showed that the Adam model gave a faster convergence at the start of training compared to the SGD model, and AdaDelta, which was built, gave 75% better accuracy with an F1-Score of 67%
Ball and Beam Control using Adaptive PID based on Q-Learning
Get PDFThe ball and beam system is one of the most used systems for benchmarking the controller response because it has nonlinear and unstable characteristics. Furthermore, in line with the increasing of computation power availability and artificial intelligence research intensity, especially the reinforcement learning field, nowadays plenty of researchers are working on a learning control approach for controlling systems. Due to that, in this paper, the adaptive PID controller based on Q-Learning (Q-PID) was used to control the ball position on the ball and beam system. From the simulation result, Q-PID outperforms the conventional PID and heuristic PID controller technique with the swifter settling time and lower overshoot percentage
Experimental Investigation of Algorithms for Simultaneous Localization and Mapping
Get PDFThis paper describes a mobile robot system designed for simultaneous localization and mapping. The architecture of a robotic mobile system based on the mini-tractor chassis is considered. The existing and modern methods and approaches to solving the SLAM problem are described, as well as the results of experimental studies of the work of methods on a mobile robot. A description of the developed robotic system for solving the navigation problem and constructing a route map is given. The issues addressed in this paper include the design, development and experimental testing of the mobile robot. The advantages, disadvantages of the algorithm, as well as the direction of further research are described in this work
Quality in Use of Digital Wallet based on ISO/IEC 25022
Get PDFThe growth of financial technology (fintech) has led to an increase in cashless transactions. One of the technology that is developing and widely used is digital wallets. Because of the frequent use of digital wallet services, an assessment to measure quality in use needs to be done. Quality in use relates to user interaction with software when the product is used. The assessment standard used to measure quality in use is ISO/IEC 25022. The criteria assessed are effectiveness, efficiency, satisfaction, and freedom from risk. To strengthen the results obtained, a correlation between the existing criteria and the quality in use of digital wallets is sought. From these results, it will be known which criteria have the highest correlation to the quality in use of digital wallets. This study does not focus on assessing the quality in use of each digital wallet, but on digital wallets globally (in this study the digital wallets used are OVO, Gopay, and Dana) because after the results of the questionnaire, almost all respondents use more than one digital wallet, even besides the mentioned digital wallets. The conclusion obtained in this study is that digital wallet product users are satisfied with the use of digital wallets although there are still some risks that may arise
IoT Botnet Malware Classification Using Weka Tool and Scikit-learn Machine Learning
Get PDFBotnet is one of the threats to internet network security-Botmaster in carrying out attacks on the network by relying on communication on network traffic. Internet of Things (IoT) network infrastructure consists of devices that are inexpensive, low-power, always-on, always connected to the network, and are inconspicuous and have ubiquity and inconspicuousness characteristics so that these characteristics make IoT devices an attractive target for botnet malware attacks. In identifying whether packet traffic is a malware attack or not, one can use machine learning classification methods. By using Weka and Scikit-learn analysis tools machine learning, this paper implements four machine learning algorithms, i.e.: AdaBoost, Decision Tree, Random Forest, and Naïve Bayes. Then experiments are conducted to measure the performance of the four algorithms in terms of accuracy, execution time, and false positive rate (FPR). Experiment results show that the Weka tool provides more accurate and efficient classification methods. However, in false positive rate, the use of Scikit-learn provides better results
Steering System of Electric Vehicle using Extreme Learning Machine
Get PDFThe development of electric vehicle technology is currently increasing and growing very fast. Some efforts have been conducted, one of which is using BLDC (brushless direct current) motors to improve efficiency. This study utilized extreme learning machine (ELM) embedded on the microcontroller as well as the differential method for controlling the rotational speed of the BLDC motor. The experimental results on the acceleration testing by traveling a distance of 200 meters achieved the average current of 1.09 amperes. The average power efficiency test is 104 watts. Furthermore, the results of the efficiency experiment with a track length of 3.3 km (kilometers) in 10 minutes obtained the energy efficiency of 177.34 km/kWh (kilowatt for one hour
Combination of Genetic Algorithm and Brill Tagger Algorithm for Part of Speech Tagging Bahasa Madura
Get PDFPart of speech (POS) is commonly known as word types in a sentence such as verbs, adjectives, nouns, and so on. Part of Speech (POS) Tagging is a process of marking the word class or part of speech in every word in a sentence. Part of Speech Tagging has an important role to be used as a basis for research in Natural Language Processing. That is why research on Part of Speech Tagging for Bahasa Madura as an effort to preserve and develop the use of regional languages. In this research, POS Tagging is done using the Brill Tagger Algorithm which is combined with the Genetic Algorithm. Brill Tagger is a POS Tagging Algorithm that has the best level of accuracy when implemented in other languages. Genetic Algorithms used in the contextual learner process with consideration in previous studies can increase the speed of the training process so that it is more efficient. The results of this study are then compared with the results of the previous study so that we can find out suitable algorithms used for the development of text processing in Bahasa Madura. From a series of experiments, the average accuracy obtained by using Brill Tagger is 86.4% with the highest accuracy of 86.7%, while using GA Brill Tagger shows an average accuracy of 86.5% with the highest accuracy of 86.6%. Testing by observing OOV (Out of Vocabulary) achieves an average accuracy of 67.7% for Brill Taggers and 64.6% for GA Brill Taggers. Testing by considering multiple POS with Brill Tagger produces an average accuracy of 73.3% while testing using GA Brill Tagger produces an average accuracy of 90.9%. This shows that the accuracy with GA Brill Tagger is better than Brill Tagger, especially if considering multiple POS. This is because GA Brill Tagger can generate rules for handling the existence of multiple POS more than pure Brill Tagger.Part of speech (POS) is commonly known as word types in a sentence such as verbs, adjectives, nouns, and so on. Part of Speech (POS) Tagging is a process of marking the word class or part of speech in every word in a sentence. Part of Speech Tagging has an important role to be used as a basis for research in Natural Language Processing. That is why research on Part of Speech Tagging for Bahasa Madura as an effort to preserve and develop the use of regional languages. In this research, POS Tagging is done using the Brill Tagger Algorithm which is combined with the Genetic Algorithm. Brill Tagger is a POS Tagging Algorithm that has the best level of accuracy when implemented in other languages. Genetic Algorithms used in the contextual learner process with consideration in previous studies can increase the speed of the training process so that it is more efficient. The results of this study are then compared with the results of the previous study so that we can find out suitable algorithms used for the development of text processing in Bahasa Madura. From a series of experiments, the average accuracy obtained by using Brill Tagger is 86.4% with the highest accuracy of 86.7%, while using GA Brill Tagger shows an average accuracy of 86.5% with the highest accuracy of 86.6%. Testing by observing OOV (Out of Vocabulary) achieves an average accuracy of 67.7% for Brill Taggers and 64.6% for GA Brill Taggers. Testing by considering multiple POS with Brill Tagger produces an average accuracy of 73.3% while testing using GA Brill Tagger produces an average accuracy of 90.9%. This shows that the accuracy with GA Brill Tagger is better than Brill Tagger, especially if considering multiple POS. This is because GA Brill Tagger can generate rules for handling the existence of multiple POS more than pure Brill Tagge
UFMC and f-OFDM: Contender Waveforms of 5G Wireless Communication System
Get PDFBecause of the increased demand for high data rates, looking for using new technologies that meet these requirements are considered a necessary. Hence, Fifth Generation (5G) is expected to be impressive in offering these requirements and implement around 2020. Orthogonal Frequency Division Multiplexing (OFDM) is considered a main technology of LTE wireless communication standards. Due to its suffering from high Bit Error Rate (BER) and Peak Average Power Ratio (PAPR), OFDM doesn't consider as charming solution for future wireless communications and several emerging applications of 5G. Moreover, high Out of Band Emission (OOBE) and inability of supporting the flexible numerology are other demerits of OFDM systems. Thus, looking for alternative waveforms which have the ability of solving OFDM disadvantages are necessary to introduce it as contender candidate for 5G wireless communication systems. In this paper, both of Filtered-OFDM (f-OFDM) and Universal Filtered Multi carrier (UFMC) systems have been discussed for 5G wireless communication systems and compared to OFDM system. The results showed that f-OFDM system is better than both OFDM and UFMC systems and could be introducing as competitive candidate for 5G wireless communication systems because of its ability of reducing OOBE and enhancing BER performance
Implementation of Linear and Lagrange Interpolation on Compression of Fibrous Peat Soil Prediction
Get PDFPrevious studies have predicted the compression of fibrous peat soils using the Gibson & Lo method. But the prediction process is still done manually so it requires quite a long time. Therefore this research implements linear and Lagrange interpolation methods using Matlab software to speed up the prediction process. This study also carried out a comparison of the results of the implementation of the two methods to determine its effectiveness in making predictions. Based on the results of trials and analysis, it can be seen that the prediction of compression of fibrous peat soil using linear interpolation is more effective than using Lagrange interpolation, this can be proven by the smaller average RMSE prediction results using linear interpolation, with a difference in the average value of RMSE 7.7. Besides, prediction testing using Lagrange interpolation requires longer time, because it still does the iteration process as much as laboratory test data
The Improvement Impact Performance of Face Detection Using YOLO Algorithm
Get PDFImage data augmentation is a way that makes it possible to increase the diversity of available data without actually collecting new data. In this study, researchers have evaluated the application of image manipulation with the Thatcher effect, double illusion, and inversion on the performance of face detection for data augmentation needs where the data obtained has a weakness that is the limited amount of data to create a training model. The purpose of this research is to increase the diversity of the data so that it can make predictions correctly if given other similar datasets. To perform face detection on images, it is done using YOLOv3 then comparing the accuracy results from the dataset after and before adding data augmentation