Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
The Improved Artificial Neural Network Based on Cosine Similarity in Facial Emotion Recognition
Get PDFIn this study, we present the improved artificial neural network based on cosine similarity in facial emotion recognition. We apply a shifting window that employs neural network for two concurrent processes consisting of face detection and emotional recognition. In order to prevent the slow and futile computations, non-face areas need to be filtered from neurons on each network layer, thus we propose the improved artificial neural network based on cosine similarity. Cosine similarity is employed to bypass the process of non-face areas in neural network. The accuracy of the proposed method reaches 0.84, while the accuracy of the original neural network method reaches 0.74. It can be concluded that our methods work accurately.proposed method is superior to the state-of-the-art algorithms
Flatbuffers Implementation on MQTT Publish/Subscribe Communication as Data Delivery Format
Get PDFCommunication between devices can be done in various ways, one of them is the Publish / Subscribe model that uses the MQTT protocol From the shortcomings that exist in JSON, such as long processing time, Google recently introduced a new data format called Flatbuffers. Flatbuffers has a better data format serialization process than other data formats. This paper will discuss the implementation and testing of the Flatbuffers data format performance compared to other data formats through the MQTT Publish / Subscribe communication model. Testing is done by measuring the value of payload, latency, and throughput obtained from each data format. The test results show that the Flatbuffers data format is very well used as a data extraction format based on data processing latency of 0.5002 ms and throughput 518.4649 bytes/ms with payload 0.996108949 character/byte
Intelligent System for Recommending Study Level in English Language Course using CBR Method
Get PDFIn the admission process, an English Course uses a level placement test. The implementation of the test encountered some problems such as slow determination of student learning levels based on the results of paper based test that are still conventional. The purpose of this research provides the recommendations for an intelligent knowledgebased system in recommending student learning levels using the Case-Based Reasoning (CBR) method. CBR is one of the method that uses the Artificial Intelligence approach and focuses on solving problems based on knowledge from the previous cases, by calculating numerical local similarity and global similarity using the nearest neighbor algorithm as the basic for the technical development of this intelligent system. The result of the study was tested for the data accuracy with the confusion matrix method by the result 100% for the accuracy. For evaluating the system systematically was using the User Acceptance Test (UAT) method with the results of the evaluation is 88% of the system meets user needs and expectation
Testing Big Data Applications
Get PDFToday big data has become the basis of discussion for the organizations. The big task associated with big data stream is coping with its various challenges and performing the appropriate testing for the optimal analysis of the data which may benefit the processing of various activities, especially from a business perspective. Big data term follows the massive volume of data, (might be in units of petabytes or exabytes) exceeding the processing and analytical capacity of the conventional systems and thereby raising the need for analyzing and testing the big data before applications can be put into use. Testing such huge data coming from the various number of sources like the internet, smartphones, audios, videos, media, etc. is a challenge itself. The most favourable solution to test big data follows the automated/programmed approach. This paper outlines the big data characteristics, and various challenges associated with it followed by the approach, strategy, and proposed framework for testing big data applications
Fractals Study and Its Application
Get PDFThe overall of this paper is a review of fractal in many areas of application. The review exposes fractal definition, analysis, and its application. Most applications discussed are based on analysis from geometric and image processing studies. Patterns of some fractals will be discussed. Some simulation results are supplied to illustrate the discussion. Simulation resulted are from various software and tools. Some principles of fractals with informative patterns have been simulated. Whereas the simulations could support some recommendations for prospective purposes and applications. The prospective application may help in predictive pattern of many fields. The predictive pattern will lead to pattern control and pattern disruptions
Design and Implementation of Web-based Church Information Systems (Case Study : HKBP Kebon Jeruk)
Get PDFHKBP Kebon Jeruk Church has a lot of data consisting of church data, Pastor data, Church server data, family data, marital data, baptismal data, and also about church agenda such as the schedule of activities Church, schedule of church service. The problem in HKBP Kebon Jeruk is that the Data is provided and managed manually, as well as difficulties in finding the necessary information. Therefore, the system needs to be built by the HKBP Kebon Jeruk Church to request church management data.The method used in the HKBP Kebon Jeruk system is the Extreme Programming method, and the analysis used is the PIECES analysis. The result of this research is to build the HKBP Kebon Jeruk system according to the needs of the user
Enhancing IPsec Performance in Mobile IPv6 Using Elliptic Curve Cryptography
Get PDFInternet has become indispensable to the modern society nowadays. Due to the dynamic nature of human activities, the evolving mobile technology has played a significant role and it is reflected in the exponential growth of the number of mobile users globally. However, the characteristic of the Internet as an open network made it vulnerable to various malicious activities. To secure communication at network layer, IETF recommended IPsec as a security feature. Mobile IPv6 as the successor of the current mobile technology, Mobile IPv4, also mandated the use of IPsec. However, since IPsec is a set of security algorithm, it has several well-known weaknesses such as bootstrapping issue when generating a security association as well as complex key exchange mechanism. It is a well-known fact that IPsec has a high overhead especially when implemented on Mobile IPv6 and used on limited energy devices such as mobile devices. This paper aims to enhance the IPsec performance by substituting the existing key exchange algorithm with a lightweight elliptic curve algorithm. The experiments managed to reduce the delay of IPsec in Mobile IPv6 by 67% less than the standard implementation
Applying MAC Address-Based Access Control for Securing Admin’s Login Page
Get PDFAuthentication is a very important process for securing web applications. Username and password are two parameters commonly used for user authentication on the administrator’s login page. However, such the two authentication parameters can be easily breached so that they can become a vulnerability that adversary parties can use to conduct malicious activities. For example, the attackers can commit a crime such as data modification or theft or even more dangerous take over administrator services of a system. Therefore, it is necessary to improve the security mechanism by adding additional factor of authentication other than username and password. In this study, an improvement in authentication mechanisms was carried out by applying MAC Address-based access control as an additional authentication factor. In this method, Address Resolution Protocol (ARP) is used in mapping the users Internet Protocol (IP) address to their MAC address during validation process. The experimental results showed that the addition of the MAC address made the authentication process resistant to Dictionary Attack and Shoulder Surfing Attack
SeizeIT: SEIZURE victims are no longer leashed
Get PDFSeizure considered to be one of the severe and most common type of neurological disorders. Despite the availability of numerous anti-seizure drugs, it is often difficult to control the disease completely and effectively. Lack of close supervision and failure in providing urgent medical care during and after seizure episodes, leads to serious injuries or even death. On the other hand, Use of wireless sensor networks in everyday applications have rapidly increased due to decreased technology costs and improved product reliability. Therefore developing a wearable device to monitor seizure may complete the anamnesis, help medical staff in diagnosing and acute treatment while preventing seizure related accidents. There are number of seizure detection systems available in the market. Still their performance is far from perfect. This paper explores an application of biomedical wireless sensor networks, which attempts to monitor patients in a completely non-invasive and non-intrusive manner. It describes a wearable device together with seizure prediction and alerting system, which is designed to address some issues with seizure detection systems in the market. Its functional block diagram and operating modes are detailed. Possible application areas of the device are also discusse
Keystroke-Level Model to Evaluate Chatbot Interface for Reservation System
Get PDFThe tour package reservation system is an important part of improving tourism services. Reservations must be able to meet the information needs of prospective customers and can serve the desired tour package bookings. A reservation system is usually a form that must be filled in sequence by prospective visitors. This paper discusses the evaluation of the application of the chatbot interface on the reservation system with the keystroke-level model. Changing the interaction design that previously did the task fills out the form into a conversation interaction. The aim is to increase the speed of the ordering process through the system. Prospective visitors do not need to fill in the form, they only need to have a conversation with the system while entering the order data. The evaluation results using the keystroke-level model show that the chatbot interface can increase the speed of the process by shortening steps