Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Ant Colony Optimization Modelling for Task Allocation in Multi-Agent System for Multi-Target
Get PDFTask allocation in multi-agent system can be defined as a problem of allocating a number of agents to the task. One of the problems in task allocation is to optimize the allocation of heterogeneous agents when there are multiple tasks which require several capabilities. To solve that problem, this research aims to modify the Ant Colony Optimization (ACO) algorithm so that the algorithm can be employed for solving task allocation problems with multiple tasks. In this research, we optimize the performance of the algorithm by minimizing the task completion cost as well as the number of overlapping agents. We also maximize the overall system capabilities in order to increase efficiency. Simulation results show that the modified ACO algorithm has significantly decreased overall task completion cost as well as the overlapping agents factor compared to the benchmark algorithm.
Task allocation in multi-agent system can be defined as a problem of allocating a number of agents to the task. One of the problems in task allocation is to optimize the allocation of heterogeneous agents when there are multiple tasks which require several capabilities. To solve that problem, this research aims to modify the Ant Colony Optimization (ACO) algorithm so that the algorithm can be employed for solving task allocation problems with multiple tasks. In this research, we optimize the performance of the algorithm by minimizing the task completion cost as well as the number of overlapping agents. We also maximize the overall system capabilities in order to increase efficiency. Simulation results show that the modified ACO algorithm has significantly decreased overall task completion cost as well as the overlapping agents factor compared to the benchmark algorithm
Faux Insider Hazard Investigation on Non-Public Cloud Computing by Using ADAM’s Technique
Get PDFCloud computing is a service system mechanism that businesses and organizations use to perform computerized and integrated transactions over computer networks. The service system must, of course, be”matched”with a”certain amount”of security. It is applied to” forecast the probability of cybercrime. A Cloud Service Provider (CSP) often offers cloud-based services with a basic level of security. Typically, CSPs are set up to offer their services on the open internet. Data security-focused organizations strive to shield their systems from a wide range of attackers. One of the alternatives is to construct a private cloud computing system. The issue is the potential for Man in the Cloud (MITC) assaults, which compromise and modify identities and are identified in cloud systems as phony insider threats. Based on the ISO 27032 standard research, the goal of this work is to undertake a threat analysis of MITC attack methodologies against private cloud computing services. With regards to risks to cloud services in a private cloud computing environment, it is intended that reporting and documenting the study' findings would lead to suggestions for more research and cybersecurity management procedures.
Cloud computing is a service system mechanism that businesses and organizations use to perform computerized and integrated transactions over computer networks. The service system must, of course, be”matched”with a”certain amount”of security. It is applied to” forecast the probability of cybercrime. A Cloud Service Provider (CSP) often offers cloud-based services with a basic level of security. Typically, CSPs are set up to offer their services on the open internet. Data security-focused organizations strive to shield their systems from a wide range of attackers. One of the alternatives is to construct a private cloud computing system. The issue is the potential for Man in the Cloud (MITC) assaults, which compromise and modify identities and are identified in cloud systems as phony insider threats. Based on the ISO 27032 standard research, the goal of this work is to undertake a threat analysis of MITC attack methodologies against private cloud computing services. With regards to risks to cloud services in a private cloud computing environment, it is intended that reporting and documenting the study' findings would lead to suggestions for more research and cybersecurity management procedures
E-commerce Recommender System Using PCA and K-Means Clustering
Get PDFRecently, recommender system has an important role in e-commerce to market products for users. One of recommender system approach that used in e-commerce is Collaborative Filtering. This system works by providing product recommendations based on products liked by other users who have similar preferences. However, sparse conditions in user data will cause sparsity problems, namely the system is difficult to provide recommendations because of the lack of important information needed. Therefore, we propose an e-commerce product recommendation system based on Collaborative Filtering using Principal Component Analysis (PCA) and K-Means Clustering. K-Means is used to overcome sparsity problems and to form user clusters to reduce the amount of data that needs to be processed. While PCA is used to reduce data dimensions and improve clustering performance of K-Means. The test results using the sports product dataset on the Olist e-commerce show that the proposed system has a lower RMSE value compared to other methods. For the number of neighbors of 10, 20, 30, and 40, our system obtains values of 0.771806, 0.75747, 0.75304, 0.75304, and 0.75270.
Recently, recommender system has an important role in e-commerce to market products for users. One of recommender system approach that used in e-commerce is Collaborative Filtering. This system works by providing product recommendations based on products liked by other users who have similar preferences. However, sparse conditions in user data will cause sparsity problems, namely the system is difficult to provide recommendations because of the lack of important information needed. Therefore, we propose an e-commerce product recommendation system based on Collaborative Filtering using Principal Component Analysis (PCA) and K-Means Clustering. K-Means is used to overcome sparsity problems and to form user clusters to reduce the amount of data that needs to be processed. While PCA is used to reduce data dimensions and improve clustering performance of K-Means. The test results using the sports product dataset on the Olist e-commerce show that the proposed system has a lower RMSE value compared to other methods. For the number of neighbors of 10, 20, 30, and 40, our system obtains values of 0.771806, 0.75747, 0.75304, 0.75304, and 0.75270
Implementation of the Conversational Hybrid Design Model to Improve Usability in the FAQ
Get PDFFAQ is an important part of a system because it is used to make it easier for users to solve problems faced by users. Some FAQ systems have even started using Chatbot technology to make it easier for users. Chatbots have been widely used as a medium for services in almost all fields. Starting from marketing, service systems, education, health, culture and entertainment. Various types of chatbots have sprung up, ranging from text-based like short messaging applications to voice-based ones. However, not all forms of chatbot designs have been successfully implemented in the FAQ system. Adjustments need to be made, especially considering the persona of the user. This research provides a solution by implementing a hybrid conversational design. Hybrid conversation design is accomplished by incorporating text, voice, and buttons into the chatbot interface. Conversation activities with this hybrid interface provide keywords that users may search for in the form of buttons. The hybrid design of the FAQ Chatbot is proven to be able to improve user usability compared to full text chatbots and full text FAQs. The increase in user usability is measured using UEQ, the results of which show an increase in usability from all existing aspects. However, the implementation of this hybrid design also has the consequence that the conversation management system must have structured initial information.
FAQ is an important part of a system because it is used to make it easier for users to solve problems faced by users. Some FAQ systems have even started using Chatbot technology to make it easier for users. Chatbots have been widely used as a medium for services in almost all fields. Starting from marketing, service systems, education, health, culture and entertainment. Various types of chatbots have sprung up, ranging from text-based like short messaging applications to voice-based ones. However, not all forms of chatbot designs have been successfully implemented in the FAQ system. Adjustments need to be made, especially considering the persona of the user. This research provides a solution by implementing a hybrid conversational design. Hybrid conversation design is accomplished by incorporating text, voice, and buttons into the chatbot interface. Conversation activities with this hybrid interface provide keywords that users may search for in the form of buttons. The hybrid design of the FAQ Chatbot is proven to be able to improve user usability compared to full text chatbots and full text FAQs. The increase in user usability is measured using UEQ, the results of which show an increase in usability from all existing aspects. However, the implementation of this hybrid design also has the consequence that the conversation management system must have structured initial information
Content Based VGG16 Image Extraction Recommendation
No full textData transfer across numerous platforms has increased dramatically due to the enormous number of visitors or users of the present e-commerce platform. With the rise of increasingly massive data, consumers are finding it challenging to obtain the right data. The recommendation engine may be used to make it simpler to find information that is relevant to the user's needs. Clothing, gadgets, autos, furniture, and other e-commerce items rely on product visualization to entice shoppers. There are millions of images in these items. Displaying the information sought by clients based on visual data is a difficult challenge to address. One strategy that is simple to use in a recommendation system is content-based filtering. This approach will eventually make suggestions to consumers based on previously accessible goods or product descriptions. Content-based filtering works by searching for similarities based on the properties of a product item. User interactions with a product will be recorded and analyzed in order to recommend certain similarities to users. Text-based datasets are used in the majority of content-based filtering studies. In this study, however, we attempt to leverage a dataset received from Kaggle in the form of images of futsal shoes. Then, VGG16 architecture is used to extract the image dataset. The top 5 most relevant item rankings are generated by this recommendation method using cosine similarity. In addition, the NDCG (Normalized Discounted Cumulative Gain) approach is used to assess the results of the suggestions. The NDCG was evaluated in ten test scenarios, with an average NDCG value of 0.855, indicating that the system delivers a reasonable performance suggestion.Data transfer across numerous platforms has increased dramatically due to the enormous number of visitors or users of the present e-commerce platform. With the rise of increasingly massive data, consumers are finding it challenging to obtain the right data. The recommendation engine may be used to make it simpler to find information that is relevant to the user's needs. Clothing, gadgets, autos, furniture, and other e-commerce items rely on product visualization to entice shoppers. There are millions of images in these items. Displaying the information sought by clients based on visual data is a difficult challenge to address. One strategy that is simple to use in a recommendation system is content-based filtering. This approach will eventually make suggestions to consumers based on previously accessible goods or product descriptions. Content-based filtering works by searching for similarities based on the properties of a product item. User interactions with a product will be recorded and analyzed in order to recommend certain similarities to users. Text-based datasets are used in the majority of content-based filtering studies. In this study, however, we attempt to leverage a dataset received from Kaggle in the form of images of futsal shoes. Then, VGG16 architecture is used to extract the image dataset. The top 5 most relevant item rankings are generated by this recommendation method using cosine similarity. In addition, the NDCG (Normalized Discounted Cumulative Gain) approach is used to assess the results of the suggestions. The NDCG was evaluated in ten test scenarios, with an average NDCG value of 0.855, indicating that the system delivers a reasonable performance suggestion
Prediction of Water Levels on Peatland using Deep Learning
No full textThe water level on peatlands is one of the causes of peatland fires, so water levels must be maintained at a safe standard value. Government Regulation No. 71/2014 stipulates water level standard value is 0.4 meters. The forest and land fires in 2015 caused huge losses of 220 trillion Rupiah. However, fires still occur frequently. BRGM (Peatland and Mangrove Restoration Agency) installed sensors measuring peatland water levels to obtain real-time data. These data can be used to predict water levels. Several previous studies used drought indices, regression models, and artificial neural networks to predict water levels. In this study, it is proposed to use deep learning Long Short-Term Memory (LSTM), and apply the CRISP-DM methodology. The dataset in this study contains water level data from 15 measurement stations in Central Kalimantan from 2018 through 2021. It was concluded that the LSTM model could predict water level well, as indicated by the average RMSE of 0.07 m, the average R2 of 0.85, and the average MAE of 0.04 m. The optimal LSTM model parameters are 50 epochs, a 70%:30% ratio of training data to testing data, and two hidden layers.
 
Prediction of Retweets Based on User, Content, and Time Features Using EUSBoost
Get PDFTwitter is one of the popular microblogs that allow users to write posts. Retweeting is one of the mechanisms for the diffusion of information on Twitter. One way to understand the spread of information is to learn about retweet predictions. This study focuses on predicting retweets using Evolutionary Undersampling Boosting (EUSBoost) based on user, content, and time-based features. We also consider the vector of text as a predictive feature. Models with EUSBoost are able to outperform models using the AdaBoost method. The evaluation results show that the best model can achieve an AUC performance score of 77.21% and a GM score of 77.18%. While the Adaboost-based models achieved AUC scores ranging from 68% to 69% and GM scores ranging from 62% to 63%. In addition, we found that there was no significant difference between using numeric features only and combining numeric and text features.
Twitter is one of the popular microblogs that allow users to write posts. Retweeting is one of the mechanisms for the diffusion of information on Twitter. One way to understand the spread of information is to learn about retweet predictions. This study focuses on predicting retweets using Evolutionary Undersampling Boosting (EUSBoost) based on user, content, and time-based features. We also consider the vector of text as a predictive feature. Models with EUSBoost are able to outperform models using the AdaBoost method. The evaluation results show that the best model can achieve an AUC performance score of 77.21% and a GM score of 77.18%. While the Adaboost-based models achieved AUC scores ranging from 68% to 69% and GM scores ranging from 62% to 63%. In addition, we found that there was no significant difference between using numeric features only and combining numeric and text features
Identifikasi Citra Pap Smear RepoMedUNM dengan Menggunakan K-Means Clustering dan GLCM
No full textCervical cancer’s a gynecological malignancy in women that’s very dangerous, even causes death. Prevention through early detection of Pap smear test. It was carried out by pathologists with the help of a microscope still have obstacles in observations. There’re many studies on Pap smear image processing for helping pathologists in cell identification. Availability of Pap smear image dataset is needed in cervical cancer early detection research. The purpose of this study was to segment, feature extraction and classify 180 Pap smear images of RepoMedUNM. The method used to identify Pap smear images begins with preprocessing, namely changing the color in the image to L*a*b color, segmentation using the K-means method, extraction of 6 features, namely metric, eccentricity, contrast, correlation, energy, and homogeneity, and then identified by calculating the closest distance between the training data features and the test data features with the Euclidean distance. The result of identification ThinPrep Pap smear images in 3 classes achieve average accuracy of 93.33%, Non-ThinPrep Pap smear images in 2 classes achieve 90% average accuracy and the average accuracy of the overall in the 4 classes reached 92%. These results indicate that the proposed method can identify Pap smear images well.Kanker serviks merupakan keganasan ginekologi pada wanita yang sangat membahayakan bahkan menimbulkan kematian. Pencegahan melalui deteksi dini tes Pap smear. Pap smear dilakukan oleh ahli patologi dengan bantuan mikroskop dan masih memiliki kendala dalam pengamatannya. Banyak penelitian mengenai pengolahan citra Pap smear dengan tujuan membantu para ahli patologi dalam identifikasi sel. Ketersediaan dataset citra Pap smear sangat dibutuhkan pada penelitian deteksi dini kanker serviks. Tujuan penelitian ini adalah melakukan segmentasi, ekstraksi fitur dan klasifikasi pada180 citra Pap smear RepoMedUNM. Metode yang digunakan untuk melakukan identifikasi citra Pap smear diawali dengan preprocessing, yaitu mengubah warna pada citra menjadi warna L*a*b, segmentasi menggunakan metode K-means, ekstraksi 6 fitur yaitu metric, eccentricity, contras, correlation, energy, dan homogeneity, dan selanjutnya diidentifikasi dengan menghitung jarak terdekat antara fitur data latih dengan fitur data uji dengan persamaan euclidean distance. Hasil identifikasi citra Pap smear ThinPrep pada 3 kelas mencapai rata-rata akurasi 93,33%, sedangkan citra Pap smear Non-ThinPrep pada 2 kelas mencapai rata-rata akurasi 90% dan rata-rata akurasi keseluruhan citra pada 4 kelas mencapai 92%. Hasil ini menunjukkan bahwa metode usulan dapat mengidentifikasi citra Pap smear dengan baik
Prediksi Harga Saham Menggunakan BiLSTM dengan Faktor Sentimen Publik
No full textStock market is one economic driver. It has roles in growth and development of a country. Stock is an attractive investment due to the huge profit. Many people buy and sell their stock. Stock investors try to choose the good investment company to get profits with small risk. Therefore, stock investors need to be careful and must evaluate a company. With machine learning technology, stock prediction problems can be solved. Deep learning is a subset of machine learning with own network. Deep learning has good performance in managing large amounts of data. This study used stock price history data and public sentiment data on a company. The method used in this research is Bidirectional Long-Short Term Memory (BiLSTM). The features used were closing price and compound score value of the public sentiment. Four scenarios were used in finding the best predictive model. The four scenarios use the same test data with different lengths of training data window. From the modelling, predictions with the model built using BiLSTM resulted in the smallest MSE value of 0.094 and the smallest RMSE value of 0.306.
Pasar saham adalah salah satu penggerak ekonomi, pertumbuhan dan perkembangan suatu negara. Saham adalah investasi yang menarik karena mampu memberikan tingkat keuntungan yang besar. Investor saham berusaha memilih perusahaan investasi yang baik untuk mendapatkan keuntungan dengan resiko relatif kecil. Oleh sebab itu, para investor saham perlu memiliki ketelitian dan melakukan penilaian terhadap suatu perusahaan. Dengan teknologi pembelajaran mesin, permasalahan prediksi saham dapat diselesaikan. Deep learning adalah bagian dari pembelajaran mesin yang memiliki performa baik dalam mengelola data dengan jumlah banyak. Penelitian ini membangun model prediksi memakai data histori harga saham dan data sentimen publik pada suatu perusahaan. Metode yang digunakan pada penelitian ini adalah Bidirectional Long-Short Term Memory (BiLSTM). Fitur yang digunakan adalah harga penutup dan nilai compound score dari sentimen publik yang ada. Dalam mencari model prediksi terbaik, empat skenario digunakan dalam penelitian ini. Keempat skenario tersebut menggunakan data uji yang sama dengan panjang data latih yang berbeda dari sisi panjang jendela datanya. Pada pemodelan yang dilakukan, prediksi dengan model yang dibangun menggunakan BiLSTM menghasilkan nilai MSE terkecil 0.094 dan nilai RMSE terkecil 0.306
Pengembangan Aplikasi Tiga-Tingkat Menggunakan Metode Scrum pada Aplikasi Presensi Karyawan Glints Academy
Get PDFThe rapid development of technology requires a software development management system that can be adaptive in rapidly changing circumstances. Scrum is an agile method that has the advantage of being agile and adaptive. Glints Academy holds an Industry Project Exploration as the program to prepare students for the rapid development of technology and reduce the gap between the education field and industrial field by MBKM program from the Ministry of Education and Culture. This study aims to apply the Scrum method in a heterogeneous developer team and divergent ability backgrounds to build an application with three-level architecture. The developer team is college students who come from different regions spread across Indonesia with full online implementation. Scrum is used because it is advantageous to other methods in a relatively fast-changing environment and also provides good quality control. The sprints were carried out in two sprints with two weeks of development in each sprint. The application built is an employee attendance application with a three-tier architecture: client, server, and data. The client-tier application is a front-end server built using the React.js framework while the server-tier and data-tier are built-in back-end servers with the Node.js and Express.js frameworks. JWT (JSON Web Token) authentication determines access role to functions and resources available on the back-end server. The result is a web application that fulfills the entire product backlog determined by the product owner. The results of this research are this method can used to develop features enhancement in the middle of the application development process without affecting the main feature development and this method is effectively used for different team developer backgrounds and during its online developmentPesatnya perkembangan teknologi memerlukan sistem manajemen pengembangan perangkat lunak yang juga dapat beradaptasi dengan keadaan yang silih berganti. Scrum sebagai metode agile memiliki keunggulan sebagai metode yang selain tangkas juga dapat adaptif. Glints Academy yang mengadakan program Industry Project Exploration untuk mempersiapkan mahasiswa menghadapi pesatnya perkembangan teknologi dan mengurangi jurang antara dunia pendidikan tinggi dengan dunia kerja di industri sesuai dengan visi program MBKM dari Kemendikbud. Penelitian ini bertujuan untuk menerapkan metode scrum dalam lingkungan developer team yang heterogen dan latar belakang kemampuan divergen untuk membangun sebuah aplikasi dengan arsitektur tiga-tingkat. Developer team adalah mahasiswa yang berasal dari wilayah berbeda dan tersebar di Indonesia dengan pelaksanaan yang sepenuhnya berlangsung secara daring. Scrum digunakan karena lebih unggul dari metode lainnya dalam lingkungan industri yang relatif cepat berubah dan juga memberikan kontrol kualitas yang baik. Sprint dilaksanakan dalam dua kali sprint dengan tiap sprint dilaksanakan selama dua minggu. Aplikasi yang dibangun berupa aplikasi presensi karyawan dengan arsitektur tiga-tingkat yaitu sisi client, server, dan data. Sisi client aplikasi dalam bentuk front-end server dibangun menggunakan framework React.js sedangkan sisi server dan sisi data berada dalam back-end server dengan framework Node.js dan Express.js. Autentikasi dengan JWT (JSON Web Token) menentukan hak akses terhadap fungsi dan sumber daya yang tersedia dalam back-end server. Hasil yang diperoleh adalah sebuah aplikasi berbasis web yang telah memenuhi seluruh product backlog yang ditentukan oleh product owner. Hasil dari penelitian ini adalah metode yang diterapkan mampu mengembangkan fitur di tengah proses pengembangan aplikasi tanpa mempengaruhi pengembangan fitur utama dan metode ini efektif digunakan bagi lingkungan pengembang aplikasi yang berbeda yang pengembangannya berlangsung secara daring