Nowadays, multimedia data has been spreading throughout the world in a network, and the Internet of Things (IoT) also plays a role in it. The current technology can provide multimedia data sensing in an embedded device. The communication resource limitation is still going to be encountered, and it leads to choosing the proper protocol. Constrained Application Protocol (CoAP) is a suitable protocol for the embedded device since it works on top of User Datagram Protocol (UDP), which has a lower overhead compared to Transmission Control Protocol (TCP). CoAP protocol can communicate reliably with a large data payload through a confirmable block-wise approach. The evaluation has been conducted to the CoAP protocol in some research, but it is not yet evaluated in a wireless multimedia sensor network (WMSN) in multiple devices. This paper presents the evaluation of the CoAP protocol performance in multiple multimedia sensor devices connected to the edge server. Several different numbers of nodes are sending the multimedia data through resource-limited access point. The performance is measured by comparing the throughput value and the retransmission event number. The experiment result shows that the device addition affects the average throughput reduction in a linear pattern.
The development of the Internet that moves quickly makes the trend of online shopping in e-commerce and social commerce emerge. Currently, both e-commerce and social commerce come with a live streaming shopping feature that allows interaction between sellers and buyers even from a distance. However, the effectiveness of this strategy needs further validation. This study aims to find out the impact of live streaming shopping on customers' purchase intentions. The study was conducted using causal research and SmartPLS as a tool for data analysis. Data for this study was obtained by distributing questionnaires via Google Form with 300 respondents from all over Indonesia. This study reveals that immersion has an influence on purchase intention through customer trust (indicated by p-values of less than 0.05), while social presence and telepresence have no influence on purchase intention (indicated by p-values of greater than 0.05). It is hoped that this study could contribute to the advancement of social commerce and e-commerce research and practice, where it is advised that sellers across platforms make the best of live streaming shopping to increase their sales performance.
ISO 9001 is a standard for an organization that focuses on quality management. In ISO 9001, the organization must implement seven main clauses in achieving the certification or audit if the company has obtained ISO 9001 certification. One of the clauses is clause 6.2, which is related to quality objectives and focuses on process. The organization can achieve this clause if all SOPs in the organization are appropriately implemented. Therefore, if the SOP is well implemented, the process inside also runs well, and the quality objectives will be in line with the expectations. Manufacturing industry will be the case of the organization for this study. This study proposed a tracing system for the procedure in the SOP that used to achieve clause 6.2, quality objectives in ISO 9001. The database has an important role in system development because the system will store all information in it. Databases with conventional method have various weaknesses in data handling, such as centralized data storage and lack of security. Centralized data will make it difficult for each staff in the organization to access data if the main server is down. This study will focus on blockchain applied to traceability system as database technology because it can minimize the shortcomings of the database with conventional method. The results show that the data traceability system can trace procedures well and the data running well according to its function in storing data with blockchain. Based on these results, the traceability system in this study can trace procedures in achieving quality objectives in ISO 9001.
Some research uses the random forest model and sentiment analysis to detect COVID-19 fake news. However, there is still a research opportunity to apply the method to Indonesian Tweets and reevaluate the feature's performance. Our research aims to reevaluate synthesizing the sentiment analysis feature on detecting COVID-19 fake news on Indonesian Tweets by using the Spark Dataframe. We divide the stages of machine learning development into several steps, including collecting data using Tweepy and then applying sentiment polarity scores using Apache Spark. We apply random forest to classify fake news using the Spark MLlib. Further, we use model evaluation calculation through the level of Accuracy, Recall, Precision, and F1. The results show that applying the sentiment polarity calculation to our Tweet dataset labels 148 Tweets with positive sentiments, 118 Tweets with negative sentiments, and 99 Tweets with neutral sentiments. The Pearson correlation coefficient (PCC) feature score of Sentiment equals 0.056 and ranks fifth in the top feature correlation scores list. According to the experimental findings, the random forest model produces Accuracy = 0.787 for both models with sentiment analysis and without sentiment analysis. Which indicates that sentiment analysis provides no significance in the prediction model.
Land transportation is still the main focus of transportation in Indonesia. With a total length of roads reaching hundreds of thousands of kilometers, it is necessary to monitor the health of the roads to ensure the roads can be traversed properly and immediately follow up if there are roads that are not suitable for passage. Currently, Dinas Bina Marga dan Penataan Ruang Provinsi Jawa Barat (unit that carries out government affairs in the field of public works and spatial planning including road sub-affairs, construction services sub-affairs, and spatial planning sub-affairsis) working with the Bandung Institute of Technology to develop the Survei Kondisi Perkerasan Jalan application to support the efficiency of Road Condition Survey activities. However, this application is still running semi-automatically with human intervention, one of which is the detection process. For that we need a solution in the form of detecting road damage automatically. This research aims to detect road damage automatically using the Canny Edge Detection algorithm. In operation, the system is capable of detecting road damage and selecting the damaged road area. The benefit of this research is to simplify the road damage classification process and time efficiency of road condition survey activities. The results of the tests carried out on video recordings of roads with a camera angle of 0 degrees using the Canny Edge Detection algorithm are 54.5% accuracy, 24.2% precision, 78.9% recall, and 37% F-score.
Digital business transformation is the use of technology that creates new business models, processes, software, and systems to generate increased revenue, competitive advantage, and efficiency of an Organisation. The emergence of digital business transformation is triggered by dynamic market changes and changes in consumer behavior in the use of technology and is triggered by the Coronavirus Disease 19 (Covid-19) pandemic. The impact of factors mentioned above affects medium-sized enterprises, in this case, the creative agency that is the research object. To assist creative agencies in maintaining their business, a guideline in the form of a digital business transformation framework is needed because there has not been a framework that can provide measurable guidance for digital business transformation in the sector. Researchers developed this framework using Design Science Research Methodology (DSRM). Evaluation of the proposed framework using a questionnaire with internal company respondents resulted that the aspect of people stating that 92% helped the digital business transformation in the scope of people's involvement in it. However, there was a percentage of 8% stated that they had not measurably minimized the impact of the change. While the results of the technology aspect stated that 100% had been able to help form a technology change team. Finally, the results of the process aspect stated that 100% had been able to explain and achieve the company's KPIs. The conclusion is that all of these aspects have digital business transformations, and the proposed framework can be used as a guide to influence in a structured and measurable way.
The development of the banking business in Indonesia is currently showing very rapid progress, along with the increasingly rapid progress of the banking business, it is also necessary to support the use of information technology. How Information Technology Innovation can help facilitate various services/facilities in the financial sector, especially in the credit sector, starting from evaluating the feasibility of credit applications, maintaining the course of a loan, creating credit product with an Information Technology approach that can adjust situation dynamically, and creating a unique credit products for customers is the main research problem. This study also provide an understanding to researchers in the field of loan analysis and also the banking sector to be able to provide an understanding of what loan analysis is and what methods based on IT approach that have been developed to perform loan analysis. This paper will also contribute to research on how to create a loan product model in information technology approach with the focus on loan analysis framework. This paper aims to review the definition of loan, the definition of loan analysis, and loan analysis methods.
Regional Development Plan Forum (Musrenbang) is an activity to support the development planning and budgeting process of local government in Indonesia. Medan City has developed an information system to manage that activity and manage the data of development planning. The information system is referred to as DevPlan and is built in monolithic approach. In the utilization of DevPlan problems arises. Complicated when it is repaired an error occurs or when it is updated due to modifications in Regional Development Planning Body (Bappeda) business process or regulations. Also, the repetitive activities in the same data management on the development planning system built by the Ministry of Home Affairs. These problems could be solved by migrating the system into service platform based on microservice to increase the efficiency and effectiveness in the Musrenbang process, with the service platform the two systems or others can be integrated and use the resources together. Service computing system engineering (SCSE) combined with migration strategy is used as a methodology to help the migration and produce the design and prototype of IT Services.
The Emerge of Digital Twin (DT) makes many changes to the life quality improvement, one of it is in how to manage the transportation systems. With DT, the current transportation systems have a great probability to become smarter. This research has a purpose to describe a variation of DT usage in transportation system. To achieve the targeted result, this research is using qualitative approach with code and network methods. Based on the analysis, there are three functions of DT in this domain. First, DT can be used to model the transportation system and find the best formula for optimizing it. Second, DT also can be used for conducting several policy scenarios (changing in the parameters). Lastly, DT can be used to monitor the quality of transport data that in to the model's algorithm.
In recent years, FinTech has developed very rapidly, especially in Indonesia. One of them is E-Wallet. The rapid development of E-Wallet makes understanding the related technologies even more important, such as Artificial Intelligence and Big Data. In this paper, we do a literature review and discuss how the use of Artificial Intelligence and Machine Learning help a lot in decision making, analysis security, and creating innovations that are useful in the FinTech industry, especially E-Wallet. The use of data mining and text mining in Big Data is also being discussed here. The technologies in E-Wallet are certainly very helpful, but the question is how secure the E-Wallet application is itself. There are a lot of cybercrimes including scamming, phishing, theft of personal data, and privacy losses that happened in the past few years. Therefore, we discuss the regulations in Indonesia regarding the E-Wallet and why it is not strong enough to protect the data or privacy of E-Wallet users. The readers will get the insight about the security of using E-Wallet and how the government, BI (Bank Indonesia), and OJK (Otoritas Jasa Keuangan) need to cooperate. That is because even though the regulations about data protection have been regulated here, there is no broader explanation about how the consumers should be informed about the processing of their data provided in the regulations. In this this paper, we use a Systematic Literature Review along with the research questions.
Advances in information technology and computer science have brought significant changes to various sectors of human life. In education, computers have helped ease a variety of human tasks, especially for large-scale and repetitive tasks such as essay grading. Current's computer capabilities make it possible to do essay scoring automatically. Research related to automatic essay scoring continues to develop by trying certain techniques and methods to improve the accuracy of automatic scoring close to that of human scoring. This systematic review aims to explore the 21st century applications of automated essay grading used in education. We carried out a bibliometric analysis of the meta data obtained from the SCOPUS database using the Bibliometrix and VOSviewer software reporting the main themes of implementing automated essay scoring applications in educational studies, providing an overview of the current state of the art and future directions of research and applications. Based on bibliometric analysis, we found that research related to automatic essay assessment in education has a fluctuating development trend and the current direction of AES research has used deep learning techniques such as long short-term memory, transfer learning and bert to build a better AES.
Advancement of human computer interactions have led to the development of automated systems for the study of facial emotions. Currently, human intervention is required to identify the emotional state of an individual, thus our study proposes an automated process using a novel mobile application named Chezer which aims to identify the emotion expression and recognition abilities of children. The main objective of this study is to provide an affordable application to low income families by eliminating the need to visit clinics for child emotion related concerns. Chezer uses a multi-sensory gaming approach in developing games to identify the emotion expression and recognition ability of a child, where a level and a scenario based gaming methods are implemented respectively. The games include various methods such as visual and audio stimulation and quiz based assessments to aid a parent in analyzing the ability of their children. To evaluate the games, an emotion prediction model based on Convolution Neural Network which yields an accuracy of 90% is incorporated along with other models to detect valence, arousal and emotion levels which makes the study unique in the context of children. Valence and arousal detection models yield Root Mean Square Error scores of 0.23 and 0.05 respectively. LIRIS and EmoReact children video datasets were used for the model training and testing purposes. Further, the application was tested among the children at Sri Lanka which yielded promising results. Overall, combination of all these features in a single application makes the study novel.
Indonesia is still considered a developing country, with an HDI score of. 718. A study needs to be conducted to increase its performance through Smart Government. This study aims to find out variables that can increase the performance of the Village called Nagari in West Sumatera to implement a Smart Government. The study used Village Development Index (VDI) as dependent variables and Information Technology Adoption, Human Resource Competence, Fund Availability, Organizational Culture, Environmental Factors, and Education of the Village Head as Independent Variables. Data were collected using a questionnaire distributed to all Nagari in West Sumatra. The research questionnaire can only be distributed to 720 Nagari from 928 Nagari throughout West Sumatra because 208 Nagari do not have an internet network (blank spot). There were 166 Nagari who responded to the questionnaires, equal to 23% of the population. Data were analyzed by using SEM-PLS. The study results found that Information Technology Adoption, Human Resource Competence, and Education of Nagari Heads have a significant and positive effect on the VDI of Nagari. Meanwhile, Fund Availability, Culture, and External Factors do not influence the VDI. The study results show that Nagari should have suitable IT adoption, Competent Human Recourses, and high-level education of Nagari Head to increase its performance through Smart Government. Other Villages, Districts, Municipalities/regencies, and provinces can use the research results to improve their VDI and performance to actualize the Smart Government.
Access to electricity at the southern coast of the Special Region of Yogyakarta (DIY), located in the Gunung Kidul district, has not been evenly covered. There are still many areas where the public electricity grid has not reached from Perusahaan Listrik Negara (PLN). This could be due to the geographical conditions of the area consisting of mountains and coral hills. However, the coastal area here is a popular tourist area and is quite promising for income for local governments. So, giving access to electricity will make tourism facilities in the area more advanced. This article will discuss the reliable design of a mini solar home system used in civilian buildings in coastal areas, such as; houses, shops, places of worship, or public facilities. The design method used is a quantitative approach, starting with calculating the potential of solar power in location, the electricity requirements for a city building, and the number of solar power systems. The results of the mini solar home system (SHS) design based on quantitative calculations the system operating voltage is 12V with a stand-alone off-grid topology. The power plant uses two solar photo voltaic (PV) panels with a capacity of 100Wp each and a 12V 20A solar charge controller. The solar panel used is monocrystalline. At the same time, the storage section uses 1 unit of 12V 50Ah deep cycle batteries. Then the power conversion section uses a modified sine wave inverter 50 Watt. The design of this system will make a stable supply of electricity for 1 unit of civil buildings with a load of 5 lamps 5 Watt.
COMMONKADS is a method for developing knowledge-based system. This method describes foundation, technique, modeling language and document structure for develop the knowledge-based system. COMMONKADS is people-oriented system development methodology, and this methodology is often used for developing organizational knowledge management system. COMMONKADS approach is divided based on context (organizational model, task model, agent model), concept (knowledge model) and artifact (design model). COMMONKADS have been used widely for knowledge-based system in several fields, such as COMMONKADS that integrated in tourism knowledge-based system, COMMONKADS for irrigation expert system, expertise model using COMMONKADS in manufactured company, COMMONKADS in energy management system and many more. Generally, there are eight strengths of COMMONKADS methodology for develop knowledge-based system. Its strength is flexible to use in any scope, represent knowledge (organizational, domain, task and inference knowledge), complete (representation, model, and form), powerful, accurate, comprehensive, represent KM process, systematic and effective. While the weakness of COMMONKADS methodology only three, there are don't have validation process and difficult to acquisition knowledge and use semi formal language, large data storage. Nevertheless, COMMONKADS is recommended methodology for develop knowledge-based system.
The financial industry has been disrupted by digital transformation. Nowadays, most banks have provided digital banking services to their customers. However, the current issue shows that not all groups of the society in Indonesia can easily access banking services, such as people with disabilities, especially visually impaired people as the largest percentage of people with disabilities in Indonesia. They often face difficulties and discrimination when registering bank accounts. Moreover, existing digital banking has low accessibility for visually impaired people. This study aimed to improve the interaction design of digital banking with inclusive design so it could be used as inclusive as possible. User research was conducted to understand users' needs and problems through questionnaires and interviews. Then, a prototype that is equipped with a voice user interface (VUI) was developed and evaluated with three visually impaired and two sighted people. The evaluation was measured through the System Usability Scale (SUS), Single Ease Question (SEQ), and an additional five-point scale questionnaire. The empirical result showed that the prototype has achieved usability and user experience goals: effective to use with 100% completion rate, easy to learn with 96.3% score, helpful with 96% score, and satisfying with 88% SUS score, both for visually impaired and sighted users.
Road extraction, one of the processes in map-making, is widely used by various services such as intelligent transportation systems, disaster navigation and urban planning. So far, road extraction is done manually, which takes a long time, costs a lot, and needs to be carried out by a team of experts. Automated semantic segmentation can speed up the road extraction process. The author proposes the application of Deeplab V3+ model for road extraction from very high resolution orthophoto with the Indonesian study area. From the study, the model achieved mean Intersection Ratio Union value 88% and Mean Dice loss 6.8%.
Getting success in Profesional career for every worker is dependent on skill. A great motivation give energy in learning process, academic and career life. A school Counselling teacher only able to guide students based on Student's major at High school. It is not adequate to select College major based on ability and talent only. The selection in College major have not decided by Academic capability only but also influenced by talent. Nowadays, College student candidates difficult in selecting College majors in National Selection of State Polytechnic Entrance or Seleksi Nasional Masuk Politeknik Negeri (SNMPN) because there is not Interest and Ability testing in the beginning process of the Selection. This research using Fuzzy Simple Additive Weighting (SAW) methode to select some Polytechnic majors using talent and ability by using some criterias as follows: High school accreditation, Report score and Extra curricular achievement to select College Students more appropriate based on Interest and Ability so the percentage of college students to finish their study in College is high. Preference score for every alternative with Fuzzy Simple Additive Weighting Methode matched on 45 data from 70 data tested. Candidate students are able to select more appropriate major for them by using Fuzzy Simple Additive Weighting by getting the highest score on their most appropriate major by using following scores: School accreditation score, Subjects score on School Report and Student's Extra Curricular Achievement.
COVID-19 pandemic has made an enormous change in various aspects of society. One of it, is limitation to number of people in public place and physical contact called social distancing. Supermarket is one of the places affected by social distancing to minimize the spread of the virus. Trolley is one of the tools that mainly available to ease shopping process in supermarket but also the one that mainly get direct physical contact during shopping process. Therefore, as the world adapts with this condition, it is needed to develop a smart trolley that can help minimizing the spread of COVID-19 by reducing direct physical contact without abandoning customer satisfaction while shopping in supermarket. This smart trolley will automatically follow a specific customer using position localization method based on QR code mapping. The localization was implemented using computer vision while customer-following movement command distribution was implemented using IoT. By using unique and specific QR code, it will prevent wrong customer detection and wrong position mapping thus making this a reliable tracking mechanism and a reliable autonomous customer following system.
