Search

Abstract Traditional Food Knowledge (TFK) is needed to define the acculturation of culture, society, and health in the context of food. TFK is essential for a human’s cultural, economic, and health aspects. Variations of ethnicity, culture, and lifestyle affect the diversity of traditional Indonesian food. Recognition of food is needed to maintain the sustainability of traditional food. Nowadays, there are many food dataset collections, but there needs to be a dataset that specifically collects standard food datasets. Our main contributions to the TFK research field are professional food image data acquisition, innovative development of an automatic, scalable food recognition system, and multi-process inference service. There are 34 variations of traditional foods from all regions in Indonesia that were acquired in this dataset. The dataset comprises 1644 high-quality images captured by professional cameras and 1020 by a smartphone. Several deep learning models are implemented in food recognition systems. This system can accommodate the addition and reduction of food variations in the knowledge recognition system and is capable of multiple concurrent requests at a time. The current prototype incorporates traditional types of food from Indonesia. However, the food model can also be expanded to other countries traditional foods. The automatic recognition systems are evaluated using several deep-learning network models. The experiment results have shown that the AUROC score is 0.99, and the request success rate can be improved by 70% with a multiprocess inference service.

Smart cities are faced with the challenges of systematically initiating the strategies needed to implement predetermined goals according to their plan. Therefore, this study aims to identify smart cities components and build an initial model that can be used for smart cities initiatives in Indonesia. The systematic review methods were used to overview research trends, architecture, components, and challenges to build an initial model for Indonesia. The systematic review results show popular topics, such as the standardization of a smart city and the strategies used to determine relevant models in each city's uniqueness and context. The results also identified thirteen smart city components and their challenges. Furthermore, this study's novelty is proposed the smart city's initial models with the smart government as a key component and to be a centre of other smart city components. The triangulation method determined the research validation using systematic review finding, expert judgment, and a questionnaire for collecting random data from 66 respondents from various cities in Indonesia. The collected survey data and initial models were validated by expert judgment, which showed that the proposed smart city's initial model component's agreement is 90%. In future, these results may be used to develop an assessment in smart cities implementation.

Abstract Real-time information mining of a big dataset consisting of time series data is a very challenging task. For this purpose, we propose using the mean distance and the standard deviation to enhance the accuracy of the existing fast incremental model tree with the drift detection (FIMT-DD) algorithm. The standard FIMT-DD algorithm uses the Hoeffding bound as its splitting criterion. We propose the further use of the mean distance and standard deviation, which are used to split a tree more accurately than the standard method. We verify our proposed method using the large Traffic Demand Dataset, which consists of 4,000,000 instances; Tennet’s big wind power plant dataset, which consists of 435,268 instances; and a road weather dataset, which consists of 30,000,000 instances. The results show that our proposed FIMT-DD algorithm improves the accuracy compared to the standard method and Chernoff bound approach. The measured errors demonstrate that our approach results in a lower Mean Absolute Percentage Error (MAPE) in every stage of learning by approximately 2.49% compared with the Chernoff Bound method and 19.65% compared with the standard method.

Abstract Traditional food knowledge (TFK) is an essential aspect of human life. In terms of sociocultural aspects, TFK is necessary to protect ancestral culture. In terms of health, traditional foods contain better and more natural ingredients compared to the ingredients of processed foods. Considering this background, in this study, data acquisition and automatic food recognition were performed for traditional food in Indonesia. The food images were captured in a professional mini studio. The food image data were captured under the same light intensity, camera settings, and shooting distance from the camera. The parameters were precisely measured and configured with a light intensity meter, adjustable lighting, and a laser distance measurement device. The data of 1644 traditional food images were successfully obtained in the data acquisition process. These images corresponded to 34 types of traditional foods, and 30–50 images were obtained for each type of food. The size of the raw food image data was 53 GB. The data were divided into sets for training, testing, and validation. An automatic recognition system was developed to classify the traditional food of Indonesia. Training was performed using several types of convolutional neural network (CNN) models such as Densenet121, Resnet50, InceptionV3, and Nasnetmobile. The evaluation results indicated that when using a high quality dataset, the automatic recognition system could realize satisfactory area under the receiver operating characteristics (AUROC) and high accuracy, precision, and recall values of more than 0.95.

Abstract Prediction of bone age from an x-ray is one of the methods in the medical field to support predicting endocrine gland disease, growth abnormalities, and genetic disorders. A decision support system to predict the bone age from the x-ray image has been implemented. It utilizes traditional machine learning methods and deep learning. We propose the Region-Based Feature Connected Layer (RB-FCL) from the essential segmented region of hand x-ray. We treat the deep learning models as the feature extraction for each region of the hand x-ray bone. The Feature Connected Layers are the output from the trained important region, such as 1-radius-ulna, 2-carpal, 3-metacarpal, 4-phalanges, and 5-ephypisis. DenseNet121, InceptionV3, and InceptionResNetV2 are the deep learning models that we used to train the critical region. From the evaluation results, the Mean Absolute Error (MAE) results produced is 6.97. This result is better compared to standard deep learning models, which are 9.41.

Abstract We propose a Chernoff-bound approach and examine standard deviation value to enhance the accuracy of the existing fast incremental model tree with the drift detection (FIMT-DD) algorithm. It is a data stream mining algorithm that can observe and form a model tree from a large dataset. The standard FIMT-DD algorithm uses the Hoeffding bound for its splitting criterion. The use of the simplified Chernoff bound is proposed for splitting a tree more accurately than the Hoeffding bound. We verify our proposed Chernoff bound and standard deviation value examination by evaluating several large real-world datasets that consists of 100,000,000 instances. The result shows that our proposed method has an improvement in term of accuracy compared to the Hoeffding bound in the FIMT-DD algorithm. Error value measurements demonstrate that the Chernoff bound approach contributes to smaller error value compared to the standard method. In term of overall simulation time, the Chernoff bound approach increases the duration of simulation time and utilizes more memory compared to Hoeffding bound. However, Chernoff bound is much faster to get a smaller error compared to the standard algorithm.

Intelligent transport systems (ITS) are a promising area of studies. One implementation of ITS are advanced driver assistance systems (ADAS), involving the problem of obstacle detection in traffic. This study evaluated the YOLOv4 model as a state-of-the-art CNN-based one-stage detector to recognize traffic obstacles. A new dataset is proposed containing traffic obstacles on Indonesian roads for ADAS to detect traffic obstacles that are unique to Indonesia, such as pedicabs, street vendors, and bus shelters, and are not included in existing datasets. This study established a traffic obstacle dataset containing eleven object classes: cars, buses, trucks, bicycles, motorcycles, pedestrians, pedicabs, trees, bus shelters, traffic signs, and street vendors, with 26,016 labeled instances in 7,789 images. A performance analysis of traffic obstacle detection on Indonesian roads using the dataset created in this study was conducted using the YOLOv4 method.

One of the challenges in machine learning is a classification in multi-modal data. The problem needs a customized method as the data has a feature that spreads in several areas. This study proposed a multi-codebook fuzzy neural network classifiers using clustering and incremental learning approaches to deal with multi-modal data classification. The clustering methods used are K-Means and GMM clustering. Experiment result, on a synthetic dataset, the proposed method achieved the highest performance with 84.76% accuracy. Whereas on the benchmark dataset, the proposed method has the highest performance with 79.94% accuracy. The proposed method has 24.9% and 4.7% improvements in synthetic and benchmark datasets respectively compared to the original version. The proposed classifier has better accuracy compared to a popular neural network with 10% and 4.7% margin in synthetic and benchmark dataset respectively.

A series of experiments has been conducted to show that FPGA synthesis of Galois-Field (GF) based arithmetic operators can be optimized automatically to improve Rijndael Cipher throughput. Moreover, it has been demonstrated that efficiency improvement in GF operators does not directly correspond to the system performance at application level. The experiments were motivated by so many research works that focused on improving performance of GF operators. Each of the variants has the most efficient form in either time (fastest) or space (smallest occupied area) when implemented in FPGA chips. In fact, GF operators are not utilized individually, but rather integrated one to the others to implement algorithms. Contribution of this paper is to raise issue on GF-based application performance and suggest alternative aspects that potentially affect it. Instead of focusing on GF operator efficiency, system characteristics are worth considered in optimizing application performance.

Abstract Intrauterine growth restriction (IUGR) is one of many fetal abnormalities, which has high contribution on maternal mortality rate and perinatal mortality rate in Indonesia. Apparently, IUGR impact can be reduced if only the symptoms are detected earlier and the correct treatment is applied. However, fetal growth detection and monitoring process in Indonesia is obstructed because the number of physicians is very limited and ultrasonography (USG) devices are expensive. Moreover, both the physicians and USG devices are only available in big cities. To answer those problems, this research proposed an intelligent system that can provide fetal growth telemonitoring in rural areas. This system consists of three components: portable USG device, mobile application which is developed using Android operating system, and server application which is developed using Django. The main feature of this system is automatic fetal head parameter detection and its ability to operate in the limited internet access environment. In this system, automatic fetal head parameter detection uses RHT method to approximate fetal head’s ellipse shape. Experiment result shows that RHT detection ability with ∆ellipse average of 79.564 and running time average of 0.373 second.

Basis Data Berorientasi Objek (BDBO) menggunakan model berorientasi objek untuk penyimpanan data. Selama ini penggunaan BDBO tidak populer disebabkan oleh beberapa standar yang berbeda dalam pemodelan dan perancangan skema data, serta kinerja yang dianggap kurang baik. Padahal dengan pengembangan aplikasi berorientasi objek seyogyanya penggunaan BDBO dapat menurunkan kerumitan dan meningkatkan kualitas kode aplikasi. Penelitian ini bertujuan mengkaji standar penerapan model objek data dan metode perancangan skema data pada BDBO melalui pengukuran kinerja dan kualitas kode dari aplikasi. Penelitian ini mengkaji penerapan model data ODMG 3.0 dan notasi UML pada aplikasi JPetStore dengan menggunakan transformasi Muller untuk perancangan skema data. Aplikasi JPetStore versi MySQL (BDR) dibandingkan kinerjanya dengan versi DB4O (BDBO). Hasil kajian adalah beberapa tambahan pada model ODMG 3.0 dan tambahan notasi UML untuk pemodelan data pada BDBO serta penyesuaian proses transformasi Muller. Kinerja aplikasi versi DB4O secara umum lebih cepat dibandingkan versi MySQL, kecuali dalam membaca data sederhana secara berurut. Kualitas kode aplikasi versi DB4O lebih baik dibandingkan versi MySQL.

Reed Solomon (RS) codes is a mechanism to detect and correct burst of errors in data transmission and storage systems. It provides a solid introduction to foundation mathematical concept of Galois Field algebra and its application. With the development of digital hardware technology, the RS concepts were brought into reality, i.e. the implementation of RS codec chips. This paper presents the development steps of a generic RS encoder using VHDL. The encoder is able to handle generic width of data, variable length of information, number of error as well as variable form of primitive polynomial and generator polynomial used in the system. The design has been implemented for FPGA chip Xilinx XC3S200-5FT256 and has a better performance than commercially available equivalent encoder.

Abstract Congestion is one of the severe problems that occurs in big cities like Jakarta, the center of the Indonesian government. One alternative solution to solve this problem is with a Traffic Information System which is easily accessible by the public. Twitter as a social media can be used as one of information source to develop the Traffic Information System. The most common problem in the processing of information on Twitter, especially in Indonesia, is the use of abbreviations and typographical error (typo). We propose an application of Web Place Name Dictionary in addressing abbreviations and typos in the name of the location contained on Twitter to develop a Traffic Information System. Three cases in find coordinate point in the street that derived from location name in Twitter can be handled through the proposed system. This system produces 90% accuration rate on 100 data set that obtained via @TMCPoldaMetro. This study only focus on the implementation of Web Place Name Dictionary method so we do not compare our system with the other methods.

Kajian terhadap beberapa pendekatan virtualisasi telah dilakukan dan dilaporkan dalam paper ini. Pendekatan virtualisasi yang dikaji adalah full virtualization, hardware-assisted virtualization, paravirtualization, dan operating system-level virtualization. Evaluasi dilakukan melalui pengukuran kinerja masing-masing pendekatan dengan beban kerja tertentu saat dijalankan menggunakan virtualisasi dan saat virtualisasi tidak digunakan. Hasil eksperimen menunjukkan bahwa operating system-level virtualization lebih efisien dalam hal penggunaan sumber daya komputer dibanding pendekatan lainnya. Hasil evaluasi menunjukkan bahwa pendekatan virtualisasi seharusnya ikut menjadi pertimbangan dalam memilih solusi virtualisasi. Study of some of the virtualization approach has been carried out and reported in this paper. Virtualization approaches that were examined are full virtualization, hardware-assisted virtualization, paravirtualization, and operating system-level virtualization. Evaluation is done by measuring the performance of each approach with a particular work load when run using virtualization and virtualization when not in use. The experimental results show that the operating system-level virtualization is more efficient in the use of computer resources than other approaches. Evaluation results show that the virtualization approach should help to be a consideration in choosing a virtualization solution.

Penerapan Dominance-based Rough Set Approach (DRSA) untuk menentukan peringkat kualitas sejumlah aplikasi berbasis objek telah dipelajari. DRSA diterapkan untuk memformulasikan satu set klasifikasi dimana kualitas software aplikasi digolongkan. Klasifikasi dibentuk berdasarkan hasil pengukuran Metrics of Object Oriented Design (MOOD) terhadap properti software berbasis Java. Pemanfaatan DRSA merupakan metode alternatif untuk menginterpretasikan nilai-nilai metrics dan menentukan sebuah nilai kuantitatif yang merepresentasikan kualitasnya relatif terhadap software yang lain. Studi eksperimental menunjukkan bahwa akurasi hasil DRSA bergantung pada jumlah sample aplikasi yang dijadikan referensi dalam menurunkan satu set definisi aturan untuk mengklasifikasikan properti software. Sample aplikasi dalam eksperimen diambil dari library Java yang telah teruji modularity, usability dan maintainability-nya. Secara umum, hasil eksperimen menyimpulkan bahwa DRSA dapat diterapkan untuk menentukan peringkat kualitas relatif dari sejumlah aplikasi dalam populasi sample. Application of Dominance-based Rough Set Approach (DRSA) to rank the quality of a number of object-based applications have been studied. DRSA applied to formulate a set of software quality classification in which the application is classified. Classification established by the results of measurements Metrics of Object Oriented Design (MOOD) against the property of Java-based software. Utilization of DRSA is an alternative method for interpreting the values of metrics and determine a quantitative value that represents the quality relative to other software. Experimental studies indicate that the accuracy of the DRSA depends on the number of sample applications that are used as reference in the definition set down one rule for classifying software properties. Sample applications in the experiment was taken from a proven library Java modularity, usability and maintainability of his. In general, the experimental results concluded that the DRSA can be applied to rank the relative quality of a number of applications in the sample population.

Situs web sangat kompleks dengan beragam isi dan dinamis karena selalu menampilkan informasi terbaru. Kompleksitas situs web akan bertambah saat situs web tersebut harus dimodifikasi untuk menambahkan halaman-halaman baru dan fitur-fitur baru sesuai permintaan pengunjung. Untuk menghindari kompleksitas tersebut, perlu diciptakan sebuah aplikasi berbasis web yang dapat digunakan untuk mengelola seluruh sumber daya situs web. Aplikasi ini dikenal dengan sistem manajemen isi (content management system). Makalah ini membagikan pengalaman penulis dalam mengembangkan sistem manajemen isi pada PT X yang dinamai dengan xCMS. Metode pengembangan perangkat lunak yang digunakan adalah ICONIX Process. Metode ICONIX Process menggunakan Unified Modeling Language (UML) sebagai notasi utama untuk mengambarkan dan mendokumentasikan sistem yang dibangun. Makalah ini menguraikan secara garis besar aktifitas-aktifitas dan artefak-artefak yang dihasilkan pada setiap fase pengembangan. Hasil akhir adalah sebuah prototipe aplikasi manajemen isi aplikasi web yang diberi nama xCMS.

Sebuah metode untuk mengukur kualitas desain berdasarkan hasil implementasinya dalam Java source codes diusulkan dalam penelitian ini. Metode yang diusulkan menggabungkan Metrics for Object-Oriented Software Engineering (MOOSE), properti kualitas desain software dan konsep Analytic Hierarchy Process (AHP). Sebagai studi kasus, metode ini diterapkan pada sejumlah aplikasi ERP yang bersifat open source yaitu Adempiere, OpenBravo, Plazma, FreedomERP, dan JAllInOne. Pengukuran MOOSE dilakukan dengan bantuan tool CKJM 1.8. Hasil ukur MOOSE dikelompokkan dalam properti kualitas yaitu efficiency, understandability, reusability, testability dan maintainability. Kombinasi MOOSE dan AHP yang dihasilkan dapat menjadi alat bantu dalam menentukan peringkat kualitas software dari aspek orientasi objek. A method for measuring the quality of the design is based on the results of its implementation in the Java source codes proposed in this study. The proposed method combines Metrics for Object-Oriented Software Engineering (MOOSE), property and the concept of software design quality Analytic Hierarchy Process (AHP). As a case study, this method is applied to a number of applications that are open source ERP is Adempiere, Openbravo, Plazma, FreedomERP, and JAllInOne. MOOSE measurements done with the aid tool CKJM 1.8. MOOSE measuring results are grouped in quality properties that are efficiency, understandability, reusability, testability and maintainability. MOOSE and AHP combination that have been produced can be a useful tool in determining the quality ratings of aspects of object oriented software.