Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Faktor-faktor Utama untuk Meningkatkan Kualitas Kerja Tim di Startup Indonesia menggunakan Kerangka aTWQ
No full textDue to the ever-changing needs of IT in today's businesses, agile software development has become popular due to its adaptive capabilities. Startups are among those who continuously strive to meet changing needs. Despite the potential benefits of the Agile methodology, teamwork quality remains a challenge. Furthermore, the global recession has made it increasingly important for startups to have effective teamwork, given the high level of uncertainty that leads to challenges in surviving, especially with cost-cutting and downsizing efforts. Therefore, this study aims to evaluate teamwork quality in Indonesian startups using the Agile Teamwork Quality (aTWQ) approach. TWQ is a comprehensive set of criteria designed to assess teamwork quality in agile environments. The primary objective of this study is to identify the factors that most strongly increase the quality of teamwork of Indonesian startups. To achieve this objective, data will be collected from Indonesian companies using an online survey based on the aTWQ framework. The challenges were identified most on the dimensions of cohesion, balance of contribution, and effort. The findings of this study are consistent with previous research, which may hopefully help start-ups in Indonesia improve their teamwork quality and achieve greater success in their respective industries.Dalam bisnis saat ini, kebutuhan IT selalu berubah dan pengembangan perangkat lunak agile menjadi populer karena kemampuan adaptifnya. Kerjasama tim adalah hal penting dalam penerapan metode agile yang akan mempengaruhi keberhasilan proyek dan tujuan organisasi. Selain itu, resesi global membuat kerja tim yang efektif semakin penting bagi startup, terutama ketika ada upaya pengurangan jumlah anggota tim karena tingkat ketidakpastian yang tinggi. Penelitian ini bertujuan untuk mengetahui faktor-faktor penting yang dapat meningkatkan kualitas kerja tim pada startup di Indonesia. Penelitian ini akan menggunakan pendekatan Agile Teamwork Quality (aTWQ) sebagai alat evaluasi kualitas kerja tim. aTWQ adalah seperangkat kriteria yang dirancang untuk menilai kualitas kerja tim di lingkungan agile. Untuk mencapai tujuan ini, data akan dikumpulkan dari startup-startup Indonesia melalui survei online berdasarkan kerangka aTWQ. Faktor-faktor utama untuk meningkatkan kualitas kerja tim diidentifikasi berada pada dimensi kohesi, keseimbangan kontribusi, dan effort. Temuan dari penelitian ini diharapkan dapat membantu memberikan pemahaman tentang seberapa besar pengaruh kualitas kerjasama tim pada kesuksesan proyek dan juga dapat membantu startup di Indonesia meningkatkan kualitas kerja tim mereka dan mencapai kesuksesan yang lebih besar di industri masing-masing
Studi Perbandingan Investigasi Cloud Forensik Menggunakan Metode ADAM Dan NIST 800-86 Pada Layanan Private Cloud Computing
No full textAs information technology advances, associated risks also increase, particularly in the field of private cloud computing services. These services are subject to potential internal abuse risks, either due to system vulnerabilities or other factors. However, the investigation of these incidents in private cloud computing varies greatly due to the different frameworks and unique characteristics of each cloud service. The lack of a standardized approach to analyzing and assessing investigative processes in cloud computing services has been a persistent problem. This lack of consensus affects the accuracy, efficiency, and data acquisition process when dealing with digital evidence in each method, causing concern among researchers. To overcome this, a comparative study was carried out with a focus on the ADAM (The Advanced Data Acquisition Model) method and the NIST (National Institute of Standards and Technology) method. The goal is to identify the most effective investigative process to deal with cyber attack incidents on both the server and client side of cloud computing services. By testing these methods in a network that is built on private cloud computing services, then the results from this research include the weaknesses and strengths of the ADAM and NIST methods are found when applied to cloud computing case studies and these have not been identified in previous research, then produce recommendations for investigators when conducting investigations on case studies on cloud computing, and in this study managed to find a bug in the ownCloud application version 10.9.1. Then this study also aims to provide researchers with valuable references to carry out analysis and assessment in the investigative process, where standardization is still an unresolved issue.Seiring kemajuan teknologi informasi, risiko yang terkait juga meningkat, khususnya di ranah layanan private cloud computing. Layanan tersebut menghadapi potensi risiko penyalahgunaan internal, baik karena kerentanan sistem atau faktor lainnya. Namun, menyelidiki insiden ini dalam private cloud computing sangat bervariasi karena perbedaan kerangka kerja dan karakteristik unik dari setiap layanan cloud. Kurangnya pendekatan standar untuk menganalisis dan menilai proses investigasi pada layanan cloud computing telah menjadi masalah yang terus-menerus. Kurangnya konsensus berdampak pada akurasi, efisiensi, dan proses akuisisi data saat menangani bukti digital di setiap metode menimbulkan kekhawatiran di kalangan peneliti. Untuk mengatasi hal tersebut, dilakukan studi banding dengan fokus pada metode ADAM (The Advanced Data Acquisition Model) dan metode NIST (National Institute of Standards and Technology). Tujuannya adalah untuk mengidentifikasi proses investigasi yang paling efektif untuk menangani insiden serangan dunia maya pada sisi server dan klien dari layanan cloud computing. Dengan menguji metode-metode ini dalam jaringan yang dibangun di atas layanan private cloud computing, penelitian ini bertujuan untuk memberikan para penyelidik referensi berharga untuk melakukan analisis dan penilaian dalam proses investigasi, di mana standardisasi tetap menjadi masalah yang belum terselesaikan
Meningkatkan Antarmuka Pengguna Melalui Analisis Sentimen: Mengungkap Pengalaman Pengguna di Aplikasi Bukalapak
No full textIn this research, we use sentiment analysis to refine the user interface (UI) and user experience (UX) of the Bukalapak application, a leading online trading platform in Indonesia. We focus our scrutiny on 4,462 reviews related to the UI within a larger dataset of 246,947. Almost a third of these critiques express dissatisfaction, predominantly pointing out issues related to the UI design and its functionality. The critiques underscore the potential of sentiment analysis as a tool to uncover areas of user-centric design that need improvement. To address these issues, it is necessary to incorporate user feedback and sentiment analysis into the design workflow, allowing a more in-depth understanding of user needs and facilitating more effective service enhancements. Embracing a user-centered methodology allows for UI fine-tuning, leading to better functionality and increased user contentment. Our investigation reveals a positive link between design refinements and usability ratings, indicating improved user experience satisfaction. To summarize, this research highlights the essential contribution of user feedback and sentiment analysis to detect and correct UI shortfalls, thus augmenting UX and contributing to the triumph of platforms like Bukalapak within Indonesia's dynamically changing e-commerce environment.
Dalam penelitian ini, kami memanfaatkan analisis sentimen untuk menyempurnakan User Interface (UI) dan User Experience (UX) aplikasi Bukalapak, platform jual beli online terkemuka di Indonesia. Kami memfokuskan pengawasan kami pada 4.462 ulasan terkait UI dari 246.947 data. Hampir sepertiga dari kritik yang disampaikan mengungkapkan ketidakpuasan, terutama menunjukkan masalah yang berkaitan dengan desain UI dan fungsinya. Ini memperlihatkan potensi analisis sentimen sebagai alat untuk mengungkap area dalam desain yang berpusat pada pengguna yang perlu ditingkatkan. Untuk mengatasi masalah ini, umpan balik pengguna dan analisis sentimen perlu dimasukkan ke dalam alur kerja desain, sehingga memungkinkan pemahaman yang lebih mendalam tentang kebutuhan pengguna dan memfasilitasi peningkatan layanan yang lebih efektif. Menggunakan metodologi yang berpusat pada pengguna, memungkinkan penyempurnaan UI, yang mengarah kepada fungsionalitas yang lebih baik dan meningkatkan kepuasan pengguna. Hasil penelitian kami mengungkapkan hubungan positif antara penyempurnaan desain dan peringkat kegunaan, yang menunjukkan peningkatan kepuasan pengalaman pengguna. Sebagai rangkuman, penelitian ini menyoroti kontribusi penting dari umpan balik pengguna dan analisis sentimen dalam menemukan dan mengoreksi kekurangan UI, sehingga menambah UX dan berkontribusi pada kemenangan platform seperti Bukalapak dalam lingkungan e-commerce Indonesia yang selalu berubah secara dinamis
 
Perbandingan Metode Peningkatan Gambar untuk Skrining Retinopati Diabetik
No full textThe most common factor contributing to visual abnormalities that result in blindness is known as diabetic retinopathy (DR). Retinal fundus scanning, a non-invasive method that is integral to the picture pre-processing phase, can be used to identify and monitor DR. Low intensity, irregular lighting, and inhomogeneous color are some of the main issues with DR fundus photographs. Analysis of aberrant characteristics on retinal fundus images to identify diabetic retinopathy is one of the key responsibilities of image enhancement. However, a variety of approaches have been created and it is unknown whether one is best suited for use with images of the retinal fundus. This study investigated various image enhancement methods in order to see aberrant abnormalities on retinal fundus pictures more clearly. This study investigated various image enhancement methods in order to see aberrant abnormalities on retinal fundus pictures more clearly. The contrast-limited adaptive histogram equalization (CLAHE) method, the gray-level slicing method, the median filtering method, and the low light method are image improvement methods used to enhance images of the retinal fundus. The parameters Natural Image Quality Evaluator (NIQE), Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and entropy will be used to assess each image enhancement technique's performance. An ophthalmologist from Sains University Hospital (HUSM) provided the image data. The findings indicate that while each technique has its own benefits, the CLAHE technique, with a standard deviation MSE of 0.0004, is the best. Diabetic retinopathy (DR) diketahui sebagai penyebab utama gangguan penglihatan yang berujung pada kebutaan. Deteksi dan pemantauan DR dapat dilakukan dengan menggunakan teknik non-intrusif yang disebut pemindaian fundus retina yang tidak dapat dipisahkan dari tahap pra-pemrosesan citra. Beberapa masalah mendasar dari citra DR fundus adalah memiliki intensitas yang rendah, pencahayaan yang tidak merata dan warna yang tidak homogen. Salah satu tugas utama peningkatan citra adalah menganalisis fitur abnormal pada citra fundus retina untuk mendeteksi retinopati diabetik. Namun, banyak teknik telah dikembangkan dan tidak ada bukti teknik mana yang paling cocok untuk gambar fundus retina. Studi ini membandingkan teknik peningkatan gambar yang berbeda untuk mendapatkan penglihatan yang lebih jelas dari fitur abnormal pada gambar fundus retina. Teknik peningkatan citra meliputi Low Light, Gray Level Slicing, Median Filtering, dan Contras Limited Adaptive Histogram Equalization (CLAHE) untuk memperbaiki citra fundus retina. Performansi dari masing-masing metode peningkatan citra akan dievaluasi berdasarkan parameter Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), entropy dan Natural Image Quality Evaluator (NIQE). Data citra diperoleh dari dokter spesialis mata di HUSM Kubang Kerian, Kelantan. Hasil penelitian menunjukkan bahwa semua teknik memiliki keunggulan masing-masing dan yang terbaik adalah teknik CLAHE dengan standar deviasi MSE = 0,000
The Integrated Information System Implementation Strategy in Korlantas Polri Based on the Zachman Framework Approach
Get PDFTraffic Police Corps (Korlantas Polri) is the executor of the main duties of the Indonesian National Police in the areas of security, safety, order and smooth traffic. Korlantas has some information that can be accessed by the public, namely information on congestion, accidents, traffic flow status, vital objects, road conditions, data and visual images from CCTV, public service conditions, and traffic infrastructure. However, these data are stand alone and not integrated with their respective applications and systems. The purpose of this study is to analyze the strategy for implementing an integrated information system at Korlantas Polri and what steps can be taken to integrate the existing system. This study uses the Zachman Framework which is adapted to Enterprise Architecture Planning (EAP) and qualitative data collection methods by interviewing stakeholders who are involved in managing information systems at Korlantas Polri. The results obtained are the need for a data warehouse by implementing an AI based integrated database system, Geospatial Information System, Business Intelligence and DSS, as well as Smart Visualization to visualize existing data. Then standardize the need for equipment and support for improving the ability of personnel in the IT field.
Traffic Police Corps (Korlantas Polri) is the executor of the main duties of the Indonesian National Police in the areas of security, safety, order and smooth traffic. Korlantas has some information that can be accessed by the public, namely information on congestion, accidents, traffic flow status, vital objects, road conditions, data and visual images from CCTV, public service conditions, and traffic infrastructure. However, these data are stand alone and not integrated with their respective applications and systems. The purpose of this study is to analyze the strategy for implementing an integrated information system at Korlantas Polri and what steps can be taken to integrate the existing system. This study uses the Zachman Framework which is adapted to Enterprise Architecture Planning (EAP) and qualitative data collection methods by interviewing stakeholders who are involved in managing information systems at Korlantas Polri. The results obtained are the need for a data warehouse by implementing an AI based integrated database system, Geospatial Information System, Business Intelligence and DSS, as well as Smart Visualization to visualize existing data. Then standardize the need for equipment and support for improving the ability of personnel in the IT field
Comparison of Segmentation Analysis in Nucleus Detection with GLCM Features using Otsu and Polynomial Methods
Get PDFPap smear is a digital image generated from the recording of cervical cancer cell preparation. Images generated are susceptible to errors due to the relatively small cell sizes and overlapping cell nuclei. Therefore, accurate Pap smear image analysis is essential to obtain the right information. This research compares nucleus segmentation and detection using Grey Level Co-occurrence Matrix (GLCM) features in two methods: Otsu and Polynomial. The tested data consisted of 400 images sourced from RepoMedUNM, a publicly accessible repository containing 2,346 images. Both methods were compared and evaluated to obtain the most accurate features. The research results showed that the average distance of the Otsu method was 6.6457, which was superior to the Polynomial method with a value of 6.6215. Distance refers to the distance between the nucleus detected by the Otsu and the Polynomial method. Distance is an important measure to assess how closely the detection results align with the actual nucleus positions. It indicates that the Polynomial method produces nucleus detections that are on average closer to the actual nucleus positions compared to the Otsu method. Consequently, this research can serve as a reference for further studies in developing new methods to enhance the accuracy of identification
Forecasting Photovoltaic Output Power Based on Environmental Parameters Using Artificial Neural Network Methods
No full textPhotovoltaics are systems that can convert sunlight into electrical energy. However, photovoltaic efficiency tends to be low, and its performance is affected by several environmental parameters such as dust, wind speed, humidity, temperature, and other external factors. Because there are many factors that can affect the power generated, we need a power output prediction system that can help in planning and managing as well as increasing the efficiency of photovoltaic systems. In this research, a system is designed that can predict the photovoltaic output power in the short term using the artificial neural network method or what is often called an artificial neural network. Predictions are made based on the effects of several environmental parameters such as wind speed, dust, humidity, and temperature on a 10 Wp photovoltaic system. Performance data for 7 days is used as a dataset and then processed using ANN with 1 input layer, 3 hidden layers, and 1 output layer, and 3 sample epochs (10, 100, and 1000). The results of the study can predict the output of photovoltaic power for the next 4 days with an error value of Mean Square Error (MSE) of 0.0010, Mean Absolute Error (MAE) of 0.0155, Root Mean Square Error (RMSE) of 0.0229 with an increase in power reaching 0.5 to 1 watt
Comparative Analysis of Various Ensemble Algorithms for Computer Malware Prediction
Get PDFBy 2022 it is estimated that 29 billion devices have been connected to the internet so that cybercrime will become a major threat. One of the most common forms of cybercrime is infection with malicious software (malware) designed to harm end users. Microsoft has the highest number of vulnerabilities among software companies, with the Microsoft operating system (Windows) contributing to the largest vulnerabilities at 68.85%. Malware infection research is mostly done when malware has infected a user's device. This study uses the opposite approach, which is to predict the potential for malware infection on the user's device before the infection occurs. Similar studies still use single algorithms, while this study uses ensemble algorithms that are more resistant to bias-variance trade-off. This study builds models from data on computer features that affect the possibility of malware infection on computer devices with Microsoft Windows operating system using ensemble algoritms, such as Bagging Classifier, Random Forest, Light Gradient Boosting Machine, Extreme Gradient Boosting Machine, Category Boosting, and Stacking Classifier. The best model is Stacking Classifier, which is a combination of Light Gradient Boosting Machine and Category Boosting Classifier, with training and test results of 0.70665 and 0.64694. Important features have also been identified as a reference for taking policies to protect user devices from malware infections.By 2022 it is estimated that 29 billion devices have been connected to the internet so that cybercrime will become a major threat. One of the most common forms of cybercrime is infection with malicious software (malware) designed to harm end users. Microsoft has the highest number of vulnerabilities among software companies, with the Microsoft operating system (Windows) contributing to the largest vulnerabilities at 68.85%. Malware infection research is mostly done when malware has infected a user's device. This study uses the opposite approach, which is to predict the potential for malware infection on the user's device before the infection occurs. Similar studies still use single algorithms, while this study uses ensemble algorithms that are more resistant to bias-variance trade-off. This study builds models from data on computer features that affect the possibility of malware infection on computer devices with Microsoft Windows operating system using ensemble algoritms, such as Bagging Classifier, Random Forest, Light Gradient Boosting Machine, Extreme Gradient Boosting Machine, Category Boosting, and Stacking Classifier. The best model is Stacking Classifier, which is a combination of Light Gradient Boosting Machine and Category Boosting Classifier, with training and test results of 0.70665 and 0.64694. Important features have also been identified as a reference for taking policies to protect user devices from malware infections.
 
Implementation of Self Driving Car System with HSV Filter Method Based on Raspberry and Arduino Serial Communication
Get PDFThe development of technology in the transportation sector at this time is increasingly crucial. So the company innovates to create a car that can run itself with a high level of security. In this study, we designed an autonomous drive system for a 1:10 scale RC car using the main components in the form of a Raspberry Pi 4 and a Raspberry Pi camera as image processing for automatic control of an self driving car. Then the Arduino Nano, BTS7960, and Driver L298N components are used to regulate the movement of the DC motor. In this article, the control strategy of this self-driving car will be shown which will be implemented to detect lanes as a guide to walk autonomously. This study uses the HSV color filer method with morphology techniques to detect the path to be passed. This study resulted in a path detection that was very accurate and operated in real-time when compared to the CNN method using sampling paths to be passed that had previously been researched. After the path is detected, the interconnection between the mini computer and the microcontroller will work to synchronize the path detection and motor movement. In trials and hardware implementations carried out in the self-driving car laboratory with artificial intelligence, it can work according to the algorithm created with a success rate of 90%.
The development of technology in the transportation sector at this time is increasingly crucial. So the company innovates to create a car that can run itself with a high level of security. In this study, we designed an autonomous drive system for a 1:10 scale RC car using the main components in the form of a Raspberry Pi 4 and a Raspberry Pi camera as image processing for automatic control of an self driving car. Then the Arduino Nano, BTS7960, and Driver L298N components are used to regulate the movement of the DC motor. In this article, the control strategy of this self-driving car will be shown which will be implemented to detect lanes as a guide to walk autonomously. This study uses the HSV color filer method with morphology techniques to detect the path to be passed. This study resulted in a path detection that was very accurate and operated in real-time when compared to the CNN method using sampling paths to be passed that had previously been researched. After the path is detected, the interconnection between the mini computer and the microcontroller will work to synchronize the path detection and motor movement. In trials and hardware implementations carried out in the self-driving car laboratory with artificial intelligence, it can work according to the algorithm created with a success rate of 90%
Analysis of Supermarket Product Purchase Transactions With the Association Data Mining Method
No full textThe development of business world is entering the era of big data. In meeting supermarkets' sales and purchase targets, the management needs to improve themselves in managing the goods available in the store. The research aims to determine the pattern of purchases that occur in a transaction, find out related and related products in supermarkets, and improve supermarket services to customers. The method applied uses the association rules approach to data mining. Several purchasing data from customers have been able to be analyzed by displaying a diagram as a visualization of the number of specified association rules. The processing results show a relationship above 90%: sugar and coffee with a confidence of 94.4%, shirts and trousers with a confidence of 93.4%, and sugar, milk, and coffee with a confidence of 92.0%. Decisions that can be taken by supermarket management in providing places and goods need to consider and follow product relationships and proximity based on the highest confidence value to provide services to customers effectively and efficiently