JUTI: Jurnal Ilmiah Teknologi Informasi
Not a member yet
407 research outputs found
Sort by
INCREASING THE ROBUSTNESS OF CLASSIFICATION ALGORITHMS TO QUANTIFY LEAKS THROUGH OPTIMIZATION
Full text linkLeaks in water pipeline networks have cost billions of dollars each year. Robust leak quantification (to detect and to localize) methods are needed to minimize the lost. We quantify leaks by classifying their locations using machine learning algorithms, namely Support Vector Machine and C4.5. The algorithms are chosen due to their high performance in classification. We simulate leaks at different positions at different sizes and use the data to train the algorithms. We tune the algorithm by optimizing the algorithms\u27 parameters in the training process. Then, we tested the algorithms\u27 models against real observation data. We also experimented with noisy data, due to sensor inaccuracies, that often happen in real situations. Lastly, we compared the two algorithms to investigate how accurate and robust they localize leaks with noisy data. We found that C4.5 is more robust against noisy data than SVM
FACIAL INPAINTING IN UNALIGNED FACE IMAGES USING GENERATIVE ADVERSARIAL NETWORK WITH FEATURE RECONSTRUCTION LOSS
Full text linkFacial inpainting or face restoration is a process to reconstruct some missing region on face images such that the inpainting results still can be seen as a realistic and original image without any missing region, in such a way that the observer could not realize whether the inpainting result is a generated or original image. Some of previous researches have done inpainting using generative network, such as Generative Adversarial Network. However, some problems may arise when inpainting algorithm have been done on unaligned face. The inpainting result show spatial inconsistency between the reconstructed region and its adjacent pixel, and the algorithm fail to reconstruct some area of face. Therefore, an improvement method in facial inpainting based on deep-learning is proposed to reduce the effect of the stated problem before, using GAN with additional loss from feature reconstruction and two discriminators. Feature reconstruction loss is a loss obtained by using pretrained network VGG-Net, Evaluation of the result shows that additional loss from feature reconstruction loss and two type of discriminators may help to increase visual quality of inpainting result, with higher PSNR and SSIM than previous result
IMPLEMENTATION OF BLUETOOTH LOW ENERGY TECHNOLOGY AND TRILATERATION METHOD FOR INDOOR ROUTE SEARCH
Full text linkCurrently, route search is made easier by the presence of a Global Positioning System (GPS) technology that can be used by using the Maps application on a smartphone. By using the Maps application, people can find out their current location and can find a route to their desired destination. But the level of GPS accuracy will decrease if the user is in a building or in a closed room. This is caused by the satellite signals being sent that are not able to penetrate thick walls or concrete so that the search for routes using GPS is limited to the search for routes outside the building or outdoors. In this research, Bluetooth Low Energy and trilateration are used to determine the location in a room or building and Dijkstra\u27s algorithm for finding the shortest route to the destination location. The proposed method has a location determination error of 0.728 meters with a distance between the user and the beacon less than 10 meters to get a stable signal
GCRFP - PAGE REPLACEMENT FOR SOLID STATE DRIVE USING GHOST-CACHE
Full text linkState Drive (SSD) is an alternative to data storage that is popular today, widely used as a media cache to speed up data access to the hard disk (HDD). This paper proposes page replacement technique on SSD cache that used frequency and recency parameter, alternately. The algorithm is selected adaptively based on trace input. This method helps to overcome changes in access patterns while minimizing the number of write processes to SSD. The proposed algorithm can choose a replacement technique that suits the user access pattern so that it can bring a better hit rate. The proposed algorithm is also integrated with the ghost-cache mechanism so that the reduction in the number of writing processes to SSD is significant. The experiment runs using a real dataset, describing trace of data read, and data write taken from real usage. The trial shows that the proposed algorithm can give good results compared to other similar algorithms
PREDICT URBAN AIR POLLUTION IN SURABAYA USING RECURRENT NEURAL NETWORK – LONG SHORT TERM MEMORY
Full text linkAir is one of the primary needs of living things. If the condition of air is polluted, then the lives of humans and other living things will be disrupted. So it is needed to perform special handling to maintain air quality. One way to facilitate the prevention of air pollution is to make air pollutionforecasting by utilizing past data. Through the Environmental Office, the Surabaya City Government has monitored air quality in Surabaya every 30 minutes for various air quality parameters including CO, NO, NO2, NOx, PM10, SO2 and meteorological data such as wind direction, wind direction, wind speed, wind speed, global radiation, humidity, and air temperature. These data are very useful to build a prediction model for the forecast of air pollution in the future. With the large amount and variance of data generated from monitoring air quality in Surabaya city, a qualified algorithm is needed to process it. One algorithm that can be used is Recurrent Neural Network - Long Short Term Memory (RNN-LSTM). RNN-LSTM is built for sequential data processing such as time-series data. In this study, several analyses are performed. There are trend analysis, correlation analysis of pollutant values to meteorological data, and predictions of carbon monoxide pollutants using the Recurrent Neural Network - LSTM in the city of Surabaya correlated with meteorological data. The results of this study indicate that the best prediction model using RNN-LSTM with RMSE calculation gets an error of 1,880 with the number of hidden layer 2 and epoch 50 scenarios. The predicted results built can be used as a reference in determining the policy of the city government to deal with air pollution going forward
FACE RECOGNITION USING DEEP NEURAL NETWORKS WITH THE COMBINATION OF DISCRETE WAVELET TRANSFORM, STATIONARY WAVELET TRANSFORM, AND DISCRETE COSINE TRANSFORM METHODS
Full text linkPersonal identification can be done by using face, fingerprint, palm prints, eye’s retina, or voice recognition which commonly called as biometric methods. Face recognition is the most popular and widely used among those biometric methods. However, there are some issues in the implementation of this method: lighting factor, facial expression, and attributes (chin, mustache, or wearing some accessories). In this study, we propose a combination method of Discrete Wavelet Transform and Stationary Wavelet Transform that able to improve the image quality, especially in the small-sized image. Moreover, we also use Histogram Equalization in order to correct noises such as over or under exposure, Discrete Cosine Transform in order to transform the image into frequency domain, and Deep Neural Networks in order to perform the feature extraction and classify the image. A 10-fold cross-validation method was used in this study. As the result, the proposed method showed the highest accuracy up to 92.73% compared to Histogram Equalization up to 80.73%, Discrete Wavelet Transform up to 85.85%, Stationary Wavelet Transform up to 64.27%, Discrete Cosine Transform up to 89.50%, the combination of Histogram Equalization, Discrete Wavelet Transform, and Stationary Wavelet Transform up to 69.77%, and the combination of Stationary Wavelet Transform, Discrete Wavelet Transform, and Histogram Equalization up to 77.39%
DEVELOPMENT OF LOAD BALANCING MECHANISMS IN SDN DATA PLANE FAT TREE USING MODIFIED DIJKSTRA’S ALGORITHM
Full text linkSDN is a computer network approach that allows network administrators to manage network services through the abstraction of functionality at a higher level, by separating systems that make decisions about where traffic is sent (control plane), then forwarding traffic to the chosen destination (data plane). SDN can have problems with network congestion, high latency, and decreased throughput due to unbalanced traffic allocation on available links, so a load-balancing load method is needed. This technique divides the entire load evenly on each component of the network on the path or path that connects the data plane and S-D (Source Destination) host. The Least Loaded Path (LLP) of our proposed concept, which is a Dijkstra development, selects the best path by finding the shortest path and the smallest traffic load, the smallest traffic load (minimum cost) obtained from the sum of tx and rx data in the switchport data plane involved in the test, this result which will then be determined as the best path in the load balancing process
KLASIFIKASI KEBUTUHAN NON-FUNGSIONAL MENGGUNAKAN FSKNN BERBASIS ISO/IEC 25010
Full text linkAspek kualitas kebutuhan non-fungsional merupakan salah satu faktor penting yang berperan dalam kesuksesan pengembangan perangkat lunak. Namun, mengidentifikasi aspek kualitas kebutuhan non-fungsional merupakan hal yang sulit untuk dilakukan. Karena aspek kualitas kebutuhan non-fungsional sering ditemukan tercampur dengan kebutuhan fungsional. Oleh karena itu dibutuhkan suatu cara untuk dapat mengidentifikasi aspek kualitas kebutuhan non-fungsional. Penelitian yang ada mampu mengidentifikasi aspek kebutuhan non-fungsional dengan melakukan klasifikasi. Akan tetapi, standar kualitas yang digunakan sebagai rujukan untuk melabeli kalimat kebutuhan masih menggunakan standar ISO/IEC 9126. ISO/IEC 9126 merupakan standar lama yang dirilis pada tahun 2001. Peneliti sebelumnya mengungkapkan ambiguitas dalam enam sub-atribut pada struktur hirarkis ISO/IEC 9126. Oleh karena itu, standar kualitas yang digunakan untuk melabeli kalimat kebutuhan pada penelitian ini adalah ISO/IEC 25010. Sedangkan metode klasifikasi yang digunakan adalah FSKNN. Metode klasifikasi yang digunakan diuji dengan menggunakan nilai tetangga terdekat 10, 20 dan 30. Pada penelitian ini metode FSKNN berhasil memeroleh nilai tertinggi berdasarkan ground truth pakar yaitu precision sebesar 22.55 dan recall 27.64
KLASIFIKASI KUALITAS PERANGKAT LUNAK BERDASARKAN ISO/IEC 25010 MENGGUNAKAN AHP DAN FUZZY MAMDANI UNTUK SITUS WEB E-COMMERCE
Full text linkEvaluasi kualitas fungsional dan antar muka situs web e-commerce dari perspektif pengguna sangat penting untuk membangun atau mengembangkan situs web e-commerce yang memenuhi standar kualitas. Namun, untuk menilai kualitas fungsional dan antar muka dari situs web e-commerce sulit untuk didefinisikan sehingga membutuhkan model evaluasi perangkat lunak. Pentingnya evaluasi kualitas situs web e-commerce berdasarkan karakteristik perangkat lunak utnuk dapat dikembangkan dan menyesuaikan standar kualitas perangkat lunak.Penelitian ini mengusulkan sebuah model evaluasi kualitas situs web e-commerce berdasarkan karakteristik pada functional suitability, performance efficiency, reliability dan usability pada ISO/IEC 25010. Pada penelitian ini menggunakan metode Fuzzy Mamdani untuk menilai kualitas dari situs web e-commerce berdasarkan karakteristik dan pembobotan kepentingan karakteristik menggunakan metode Analytical Hierarchy Process. Model yang diusulkan diterapkan ke beberapa situs web e-commerce di Indonesia sebagai studi kasus untuk mengevaluasi tingkat kualitas perangkat lunak. Hasil yang didapat dari model evaluasi dapat membantu pengembang untuk merancang dan menggembangkan situs web e-commerce yang kualitas dengan tingkat accurasy 0,684%
The Alignment of Business Process In Event Organizer And Enterprise Architecture Using TOGAF
Full text linkEvent organizer is a company which engaged in event organizing, PR, and advertising. A suitable information systems that fit company\u27s business needs are required so the company can adapt themselves in this globalization era. Information systems had an important role in order to support the company’s business process and its performance. An example of applied information systems that have been widely used by companies is enterprise architecture. Currently, enterprise architecture has been used by many enterprises to be able connect between the planning and the technology implementation to the current business in the company. Enterprise Architecture Planning (EAP) is a method in enterprise architecture which can provides alignment between business and information technology by defining company’s needs. Main components of EAP are data architecture, applications, and technology. The framework that will be used to develop EAP on this research is TOGAF ADM with phases starting from preliminary phase, requirements management, architecture vision, business architecture, information systems architectures, technology architecture, opportunities & solutions, and migration planning. A result on this research will be a blueprint of enterprise architecture model that an event organizer can use in supporting its business. The blueprint contains the current used information systems and the ideal information systems planned by the authors