Face recognition is a widely utilized biometric method due to its natural and non-intrusive approach. Recently, deep learning networks using Triplet Loss have become a common framework for person identification and ve...
详细信息
Face recognition is a widely utilized biometric method due to its natural and non-intrusive approach. Recently, deep learning networks using Triplet Loss have become a common framework for person identification and verification. In this paper, we present a new method on how to select appropriate hard-negatives for training using Triplet Loss. We show that, by incorporating pairs which would otherwise have been discarded yields better accuracy and performance. We also applied Adaptive Moment Estimation algorithm to mitigate the risk of early convergence due to the additional hard-negative pairs. In LFW verification benchmark, we managed to achieve an accuracy of 0.955 and AUC of 0.989 as opposed to 0.929 and 0.973 in the original OpenFace.
Students can use social media such as Twitter for online learning (E-Learning). This study aims to analyse an accuracy for the sentiments of students about E-Learning who use Indonesian on Twitter social media both po...
详细信息
Since cloud computing becoming the trend, the way servers being implemented slowly moves to the cloud. Companies did not need to buy a physical server machine to deploy an app. Having a private server on cloud infrast...
详细信息
Since cloud computing becoming the trend, the way servers being implemented slowly moves to the cloud. Companies did not need to buy a physical server machine to deploy an app. Having a private server on cloud infrastructure indeed already reduce some cost for on-premise server maintenance. However, there is still a cost for usage when the server is inactive or having low to no traffic at all. Serverless deployment offer function as a service where application is deployed as a function and cost is billed per function call. This paper proposed a solution where there are two deployment that works in turn between infrastructure as a service and function as a service deployment. This dual deployment offered the system to use the virtual private server or deployed instance on active hours, and switch to serverless functions on inactive hours. Switching to serverless on low traffic hours will cut the usage and cost of the microservice app by the least 25%, while having performance slightly comparable to microservice app deployed to instances.
Social media is a platform to share information that is very liked by everyone nowadays because some of the facilities that make it easier for us to communicate with each other, share documents, chat and even create a...
详细信息
Social media is a platform to share information that is very liked by everyone nowadays because some of the facilities that make it easier for us to communicate with each other, share documents, chat and even create a community. In addition, we can also analyze the content of social media by using several methods in data mining, so that we can get new the information to support decision making that can bring benefits to individuals and companies. The purpose of this research, to create a business intelligence dashboard to observe the performance of each Topic or channel of news posted to social media accounts such as Facebook and Twitter. Topical performance in social media is the number of Topics in articles posted to social media getting like, share, comment etc. To be able to know the Topic of a news post in social media, used some text classification techniques such as Naive Bayes, SVM and Decision Tree. The comparative results of the algorithms are taken which has the best accuracy of SVM for subsequent implementation in the data warehouse. Meanwhile, the business intelligence dashboard data source will be sourced from the data warehouses that have been made before.
In general, public or private organizations or companies have used information-based technology as a support to improve business performance to be more effective and efficient in order to achieve a company's busin...
详细信息
Information technology (IT) service management is an essential part for development of a company’s IT. This case study discusses how to convalesce IT services using the information technology infrastructure library (...
详细信息
Information technology (IT) service management is an essential part for development of a company’s IT. This case study discusses how to convalesce IT services using the information technology infrastructure library (ITIL) framework and measure service level management (SLM) using Fuzzy ITIL (FITIL) approach. This paper aims to obtain an appropriate model for the measurement of IT service management by using fuzzy approach. Besides that, this paper aims to be able to provide an improving recommendations and IT governance based on current value (as is) and expected value (to be). The research method functioned is by measuring maturity level using best practice of ITIL v3 to condition before and after of improving process based on a questionnaire that has been performed. After obtaining the value of the maturity level for each cycle within ITIL, then the value will be created as an input for FITIL. The manufacture of FITIL is done in 4 stages, namely fuzzification, knowledge base, inference, and defuzzification. The results of the conditions before and after of the improving process have been successful in increasing the level of maturity in each ITIL cycle. The case study indicates an improvement in the increased level of maturity in SLM with FITIL approach.
The number of patients that were infected by Diabetes Mellitus (DM) has reached 415 million patients in 2015 and by 2040 this number is expected to increase to approximately 642 million patients. Large amount of medic...
详细信息
The number of patients that were infected by Diabetes Mellitus (DM) has reached 415 million patients in 2015 and by 2040 this number is expected to increase to approximately 642 million patients. Large amount of medical data of DM patients is available and it provides significant advantage for researchers to fight against DM. The main objective of this research is to leverage F-Score Feature Selection and Fuzzy Support Vector Machine in classifying and detecting DM. Feature selection is used to identify the valuable features in dataset. SVM is then used to train the dataset to generate the fuzzy rules and Fuzzy inference process is finally used to classify the output. The aforementioned methodology is applied to the Pima Indian Diabetes (PID) dataset. The results show a promising accuracy of 89.02% in predicting patients with DM. Additionally, the approach taken provides an optimized count of Fuzzy rules while still maintaining sufficient accuracy.
Air pollution is hazardous to our health, especially carbon monoxide. It can cause diseases such as cough, runny nose, eye irritation, and even death. The main objective of this research is to create a device capable ...
详细信息
Air pollution is hazardous to our health, especially carbon monoxide. It can cause diseases such as cough, runny nose, eye irritation, and even death. The main objective of this research is to create a device capable of detecting carbon monoxide pollution levels by using mobile sensors and map the results into heatmaps overlayed on Google Maps. We have implemented an integrated pollution monitoring and mapping system that consists of MQ-7 sensor, GPS, GSM, display module, Arduino board, and web-server. We also evaluated two sampling methods, time-based and distance-based sampling. Based on our experiments, the distance-based sampling method produced well-distributed data and closer to the expected between-samples distances compared to the time-based method. We have also shown that our system can run in real time to monitor the carbon monoxide pollution levels.
This paper presents a systematic literature review of agile software development at decision making method for requirement engineering. Presently, agile software development method is operated to cope with requirement...
详细信息
This paper presents a systematic literature review of agile software development at decision making method for requirement engineering. Presently, agile software development method is operated to cope with requirements that changes dynamically. This study seeks to find out and discuss what types of method that have been exploited for decision making on managing feasible requirements and challenges of decision making in agile software development. Papers reviewed in this study are published from 2017 to present. Resulting 8 papers that have been identified of presenting decision making methods. Using these papers, 11 methods and 7 challenges of decision making identified. This study contributes a review of requirement management and engineering by providing decision making methods on agile software development and the challenges of decision making for requirement engineering.
Metaverse is gaining a lot of traction lately, especially after Mark Zuckerberg's Facebook changed its name to Meta as a preparation to enter another universe called metaverse. The eXtended Reality (XR) technology...
详细信息
暂无评论