Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Data Reduction Approach Based on Fog Computing in IoT Environment
Get PDFThis paper investigates a data processing model for a real experimental environment in which data is collected from several IoT devices on an edge server where a clustering-based data reduction model is implemented. Then, only representative data is transmitted to a cloud-hosted service instead of raw data. In our model, the subtractive clustering algorithm is employed for the first time for streamed IoT data with high efficiency. Developed services show the real impact of data reduction technique at the fog node on enhancing overall system performance. High accuracy and reduction rate have been obtained through visualizing data before and after reduction
Features Extraction on IoT Intrusion Detection System Using Principal Components Analysis (PCA)
Get PDFThere are several ways to increase detection accuracy result on the intrusion detection systems (IDS), one way is feature extraction. The existing original features are filtered and then converted into features with lower dimension. This paper uses the Principal Components Analysis (PCA) for features extraction on intrusion detection system with the aim to improve the accuracy and precision of the detection. The impact of features extraction to attack detection was examined. Experiments on a network traffic dataset created from an Internet of Thing (IoT) testbed network topology were conducted and the results show that the accuracy of the detection reaches 100 percent
Hand Movement Identification Using Single-Stream Spatial Convolutional Neural Networks
Get PDFHuman-robot interaction can be through several ways, such as through device control, sounds, brain, and body, or hand gesture. There are two main issues: the ability to adapt to extreme settings and the number of frames processed concerning memory capabilities. Although it is necessary to be careful with the selection of the number of frames so as not to burden the memory, this paper proposed identifying hand gesture of video using Spatial Convolutional Neural Networks (CNN). The sequential image's spatial arrangement is extracted from the frames contained in the video so that each frame can be identified as part of one of the hand movements. The research used VGG16, as CNN architecture is concerned with the depth of learning where there are 13 layers of convolution and three layers of identification. Hand gestures can only be identified into four movements, namely 'right', 'left', 'grab', and 'phone'. Hand gesture identification on the video using Spatial CNN with an initial accuracy of 87.97%, then the second training increased to 98.05%. Accuracy was obtained after training using 5600 training data and 1120 test data, and the improvement occurred after manual noise reduction was performed
Smart Navigation Equipment Monitoring System
Get PDFDigital image processing is a processing of digital frames using digital computation. Image processing has been used in many sectors such as military, biomedics, and in this paper, the authors will implement it in the civil aviation sector by introducing a new method to monitor an aviation navigation equipment. It can be used on all LED-based Built-in Monitor navigation equipment, despite it is a low-cost system. The image processing of this research is done by doing perspective correction and then continue with BLOB detection in a segmentation stage. The final result will be displayed on a web page. Compared to its predecessor, this method gives better flexibility which does not need to be electrically connected with monitored equipment and not limited to certain brands
Memory Prediction on Real-Time User Behavior Traffic Detection
Get PDFHuman brain is a learning system. Human have to learn by getting exposed to something. This capability of learning system to recognize new patterns is called generalization. The abilities of human brain to perform generalization are yet to be matched by neural network or even by any of artificial intelligence algorithm in general. Thus, the need for new machine intelligence approach is imperative. Neural network is designed to take advantages of the speed of computers to solve engineering and computational complex problems intelligently. On the other hand, human brain is somewhat not computationally powerful. Human brain is not even able to calculate quadratic problems within milliseconds. Instead, it uses its vast amounts of memory to store everything human know and have learned. According to a modern neuroscience theory named memory-prediction framework, introduced by Hawkins and Blakeslee in 2005, human brain uses this memory-based model to make continuous predictions of future events. Therefore, a hybrid approach that possesses the ability to compute like neural network and at the same time think like human brain will shed some light in the advancement of machine learning research as well as the development of a truly intelligent machine. This talk discusses the memory-prediction framework and proposes simplified single cell assembled sequential hierarchical memory (s-SCASHM) model instead of hierarchical temporal memory (HTM) in order to speed up the learning convergence. s-SCASHM consists of single neuronal cell (SNC) model and simplified sequential hierarchical superset (SHS) platform. The SHS platform is designed by simplifying to have a region with four rows columnar architecture instead of having six rows per region as in human neocortex. Then, the s-SCASHM is implemented as the prediction engine of user behavior analysis tool to detect insider attacks/anomalies. As nearly half of incidents in enterprise security triggered by the Insider, it is important to deploy more intelligent defense system to assist the enterprise be able to pinpoint and resolve any incidents caused by the Insider or malicious software (malware). The attacks evolve; however, current detection systems that use the deep learning techniques cannot perform online (on-the-fly) learning. Thus, an intelligent detection system with on-the-fly learning capability is required. Experimental results show that the proposed memory model is able to predict user behavior traffic with significant level of accuracy and performs on-the-fly learning
Intelligent Wheelchair Control System based on Finger Pose Recognition
Get PDFIn the old day, wheelchairs are moved manually by using hand or with the assistance of someone else. Users of this wheelchair get tired quickly if they have to walk long distances. The electric wheelchair emerged as a form of innovation and development for the manual wheelchair. This paper presented the control system of the electric wheelchair based on finger poses using the Convolutional Neural Network (CNN). The camera is used to take pictures of five-finger poses. Images are selected only in certain sections using Region of Interest (ROI). The five-finger poses represent the movement of the electric wheelchair to stop, right, left, forward, and backward. The experimental results indicated that the accuracy of the finger pose detection is about 93.6%. Therefore, the control system using CNN can be a potential solution for an electric wheelchair
Development of Formalin Tester Device for Food Using Microcontroller AT89S51
Get PDFThis article discusses the manufacture of formaldehyde content test kit device. The device made can find out whether formalin or samples that are dropped are reagents, its characteristics can be processed electronically to determine the levels of formalin detected in the reagent/test kit. The design is made using AT89S51 microcontroller. Detection of formaldehyde levels using a color measurement method for reagent fluids consisting of R, G, and B values. Measurement of these color parameters using the TCS230 sensor. With this device, it is expected to facilitate health workers, especially health analysts, to automatically test the level of formaldehyde in food with a display on the LCD. The result of device test, this device is feasible to use by the percent error value of less than 10%
Estimated Profits of Rengginang Lorjuk Madura by Used Comparison of Holt-Winter and Moving Average
Get PDFRengginang Lorjuk is a typical Madura food that is ordered more by SMEs and is found in Sumenep Regency and several other areas in Madura. This product is made for supplies and orders, where demand will surge at certain times. Therefore, SMEs of Rengginang Lorjuk is required to have good planning in determining the selling price in accordance with the revenue target obtained. Considering that the main raw materials used are sticky rice and ensis leei (lorjuk) are raw materials that have fluctuating prices, this studio compares forecasting methods namely Holt Winter (HW) and Moving Average (MA), supported by MSE and MAPE, in order to obtain accurate forecasting results. These forecasting results show that HW has better accuracy than the MA, which is then used to calculate the cost of production with an Activity-Based Costing system, which requires charging costs for all activities carried out in production, namely the cost of raw materials, direct labor costs, and overhead factory fee. Using MAPE values, this study yields 4 estimates of production costs in accordance with changes in raw material costs
Classification of Post-Stroke EEG Signal Using Genetic Algorithm and Recurrent Neural Networks
Get PDFStroke is caused by a sudden burst of blood vessels in the brain, causing speech difficulties, memory loss, and also paralysis. The identification of electrical activity in the brain of post-stroke patients from EEG signals is an attempt to evaluate rehabilitation. EEG signal recording involves multiple channels with overlapping information. Therefore the importance of channel optimization is to reduce processing time and reduce the computational burden. Besides, that channel optimization can have an overfitting effect due to excessive utilization of EEG channels. This paper proposed the optimization of EEG channels for the identification of post-stroke patients using Genetic Algorithms and Recurrent Neural Networks. Data was taken from 75 subjects with a recording duration of 180 seconds in a seated state. The data was segmented and extracted using Wavelet to get the frequency of the Alpha, Theta, Mu, Delta, and Amplitude changes. The next step is the channel optimization process using Genetic Algorithms. The method applied to get a combination of channels that qualifies. Then, the EEG signal identification proceeds of the optimization of the channels used Recurrent Neural Network. The result showed that applying the Genetic Algorithm afforded 12 channels configuration with 90.00% of accuracy; meanwhile, used all channels gave a 72.22% result. Therefore, channel optimization is essential to reduce redundancy and increase recognition
IoT-Enabled Community Care for Ageing-in-Place: The Singapore Experience
Get PDFThe paradigm of ageing-in-place - where the elderly live and age in their own homes, independently and safely, with care provided by the community - is compelling, especially in societies that face both shortages in institutionalized eldercare resources, and rapidly ageing populations. When the number of elderly who live alone rises rapidly, support and care from their communities become increasing crucial. Internet of Things (IoT) technologies. They can become the fundamental enabler for smart community eldercare. In this presentation, I would like to share our experiences and learnings gathered from large-scale deployments of IoT systems in in-home and community spaces that elderly living alone interact with, focusing on the key insights as well as operational and usability aspects of such systems