Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Artificial Neural Network Parameter Tuning Framework For Heart Disease Classification
Get PDFHeart Disease are among the leading cause of death worldwide. The application of artificial neural network as decision support tool for heart disease detection. However, artificial neural network required multitude of parameter setting in order to find the optimum parameter setting that produce the best performance. This paper proposed the parameter tuning framework for artificial neural network. Statlog heart disease dataset and Cleveland heart disease dataset is used to evaluate the performance of the proposed framework. The results show that the proposed framework able to produce high classification accuracy where the overall classification accuracy for Cleveland dataset is 90.9% and 90% for Statlog dataset
Personal Extreme Programming with MoSCoW Prioritization for Developing Library Information System
Get PDFSoftware development projects require experience and knowledge of the developer or clients related to the system which will be developed. Unclear clients' needs potentially emerge many changes of needs during the process of development which can not be resolved by using conventional software development methodology. The implementation on the less significant requirements either from the clients or the system cause the development of the project took a long time. In this paper, we combine personal extreme programming (PXP) methodology with Moscow technique to overcome those problems. PXP is suitable to use in small to medium-sized projects if the clients do not know in detail about the needs in the development of application, application needed in relatively quick time, and the development phase is adjusted to use by a single programmer. Moscow technique was used for prioritizing requirements elicited in PXP methodology. Moscow is a method to determine priority needs based on cost, risk, and business value. This technique was applied during the planning phase of PXP to develop library application, thereby it reduced the time of project completion. The result was a library application suited the needs of clients to support business processes at Batu State Attorney's library
Partial Discharge and Breakdown Strength of Plasma Treated Nanosilica/LDPE Nanocomposites
Get PDFNanocomposites have been actively studied in recent years as an insulating material due to their excellent in electrical, mechanical and thermal properties. Even though, the addition of nanoparticles into polymer matrices showed better performance in relation to partial discharge (PD) and AC breakdown strength tests. However, the introduction of nanoparticles could lead to the formation of agglomeration of the fillers which may nullify the true capabilities of the composites. Therefore, silane coupling agent was introduced for surface functionalization treatment of the nano filler but among the issues associated are toxicity and complexity. In the present study, atmospheric pressure plasma is proposed to enhance the surface functionalization of the nano filler. This proposed method was used to treat the nanosilica (SiO 2 ) surfaces to enhance the interfacial interaction between the host (LDPE) and nano filler. SiO 2 nano filler was added into the LDPE at weight percentages of 1, 3 and 5%. The phase-resolved PD behaviour and Weibull analysis of AC breakdown strength of untreated and plasma-treated LDPE nanocomposites were measured to evaluate the performance of the samples. As results, the plasma treated LDPE nanocomposites experience apparent increments of the PD resistance and AC breakdown strength as compared to the untreated nanocomposites. It is implied that the plasma treatment of nanosilica has contributed to the enhancement of the filler dispersion and eventually reducing the agglomeration
Client Side Channel State Information Estimation for MIMO Communication
Get PDFMultiple-input multiple-output (MIMO) system relies on a feedback signal which holds channel state information (CSI) from receiver to the transmitter to do pre-coding for achieving better performance. However, sending CSI feedback at each time stamp for long duration is an overhead in the communication system. We introduce a deep reinforcement learning based channel estimation at receiver end for single user MIMO communication without CSI feedback. In this paper we propose to train the receiver with known pilot signals to analyse the stochastic behaviour of the wireless channel. The simulation on MIMO channel with additive white Gaussian noise (AWGN) shows that our proposed method can learn the different characteristics affecting the channel with limited number of pilot signals. Extensive experiments show that the proposed method was able to outperform the existing state-of-the-art end to end reinforcement learning method. The results demonstrate that the proposed method learns and predicts the stochastic time varying channel characteristic accurately at receiver’s end
Early Detection Application of Bipolar Disorders Using Backpropagation Algorithm
Get PDFMental health is an important aspect in realizing overall health and important to be considered as physical health. Mental disorders are classified as difficult to diagnose due to the similarity of symptoms that can occur. In addition, information about mental disorders is inadequate so that it can be difficult for experts to provide a diagnosis of the disorders experienced by patients. The difficulty of experts in diagnosing is usually caused by the similarity of symptoms in mental disorders, such as in schizophrenia and bipolar disorder. Based on these problems, this research would like to conduct an early detection study of bipolar disorder by using screening questionnaire data from 300 respondents and serve as a knowledge base to be processed using the backpropagation algorithm. Based on all the results of testing the backpropagation algorithm that has been done to find out the results obtained accuracy and the highest results of training, the highest results obtained with the total test data correct or suitable is 249 and the wrong data is 1 of 250 test data. If it is calculated by a formula, the resulting accuracy rate is 99.6%. And it can be concluded broadly that the greatest influence of the accuracy of the backpropagation algorithm is based on momentum. Because in testing momentum the highest accuracy can be produced compared to the results of other analyzes
Emotion and Attention of Neuromarketing Using Wavelet and Recurrent Neural Networks
Get PDFOne method concerning evaluating video ads is neuromarketing. This information comes from the viewer's mind, thus minimizing subjectivity. Besides, neuromarketing can overcome the difficulties of respondents who sometimes do not know the response to the video ads they watch. Neuromarketing is based on neuropsychology, which is sourced from the human brain through electrical activity signals recorded by Electroencephalogram. Usually, Neuropsychology consists of emotions, attention, and concentration. This research proposed the Wavelet method and Recurrent Neural Networks to measure the emotional and attention variable of neuropsychology in real-time every two seconds while watching video ads. The results showed that Wavelet and Recurrent Neural Networks could provide training data accuracy of 100% and 89.73% for new data. The experiment also gave that the RMSprop optimization model for the weight correction contributed to higher correctness of 1.34% than the Adam model. Meanwhile, using Wavelet for extraction can increase accuracy by 4%
OTEC Potential Studies For Energy Sustainability In Riau Islands
Get PDFInterest in the use of alternative renewable energy resources has been developed recently due to increased energy consumption and depletion of fossil fuel reserves. A major concern the world to reduce is dependence impact from fossil fuel consumption with renewable energy. Renewableenergy sources have enormous economic, environmental benefits and provide energy security. The most potential renewable energy sources of ocean energy include Ocean Thermal Energy Conversion (OTEC). OTEC is a technology to generate electricity using a heat source thermal energy stored in the sea and is becoming increasingly attractive option to supply additional energy for many tropical countries and islands such as Riau Islands. Two monitoring stations were collected in Bintan Island using CTD. CTD profiler allows to the determination of derived and relevant quantities in situ measurement ocean temperature per depth. The relationship between ocean temperature and ocean depth represented with Regression Model Fit Analysis (RMFA). RMFA models to estimates ocean temperature profiles from CTD measurements. To predict ocean depths up to 2000 meters using Equation of State Model (EoSM) of ocean water. The OTEC efficiency value can be calculated using the equation of Carnot efficiency (η). Carnot efficiency maximum in Riau Island is η <0.7
Fish Eggs Calculation Models Using Morphological Operation
Get PDFCalculations on group objects are the concern of current researchers, to find optimal detection and calculation solutions. One of them is fish eggs in a group. Fish cultivators need precision in calculations, because currently conventional methods often make errors in calculations. If the calculation is wrong, it will have an impact on production and sales that are not balanced (loss). Small and easily broken fish eggs are grouped and it isdifficult to do manual calculations. The purpose of this study is to test which segmentation method is the most optimal in calculating these grouped fish egg objects and produce precise and fast calculations. The test model was developed from algorithm of morphological operations,watershed and statistical approaches with the same number of samples. The result shows morphological operation is better than the others with 96.67%, watershed 81.28% and the count statistic is 95.62% with an average calculation process speed of 54.5 seconds for morphological operations, watershed 1 minute 55 seconds and statistical approach 58.9 seconds. As a result. morphology gets the most optimal and fast calculation results
Implementation of L3 Function on Virtualization Environment using Virtual Machine Approach
Get PDFThere are 2 approaches to implement layer 3 network function on virtualization platforms, the first approach uses the conventional physical devices; while the second is software-based. Several previous studies have been carried out to test the performance of L3 function on virtualization using software-based and obtained positive result for the performance over the physical-based. While the previous studies were limited only within the scope of testing environment, this paper tries to extend the study not only limited to the performance test based-on RFC 2544 standard, but also implementation in the production environment using virtual machine (VM) approach. Mikrotik CHR (Cloud Hosted Router) designed specifically for virtualization environment will be used as the L3 platform on the VM. Implementation in the production environment was conducted at University computer laboratory that has 207 desktops (190 in the form of virtual desktops, 17 in the form of PCs) not including user' devices that connected via WiFi networks. VM-based approach for routing functions (Layer 3) using Mikrotik CHR has proven to be stable and sufficient for use in the computer laboratory after 6 months of usage. Performance test also shown that VM-based L3 function had higher transfer rates; physical-based router was about 23,4% slower for 1 routing load and 4,25% slower for 2 routings load. The characteristic of VM itself also add some benefits like VM snapshot and migration for recovery. The test also revealed that VM-based L3 function prone to performance penalties when more than one routing load performed compared with physical-based
Spatial Coordinate Trial : Converting Non-Spatial Data Dimension for DBSCAN
Get PDFIn big data, noise in data mining is a necessity. Its existence depends on data and algorithm, but it does not mean the algorithm caused noise. Although the advantages of the Density Based Spatial Clustering Application with Noise, DBSCAN algorithm, in executing spatial data (two-dimensional data) have been widely discussed, but it has not been convincing in executing non-spatial data. As an algorithm should perform well on any data for optimizing data mining, this research proposes a trial to convert dimensions of non-spatial data into 2 dimensions for executing with DBSCAN algorithm, and a different input value for epsilon to know about its minimum which begins arising noise in the execution. Method of analysis in trial is with considering the attributes of non-spatial data as variables that represent coordinate points, rather than cardinality. Technically, it is assumed that 2-dimensional coordinate axes as a spot point for coordinate with more than or equal 3 dimensions according to development of Cartesian coordinate system, by first paying attention to relationship of variables (attributes). This way is then called Spatial Coordinate. The different input values are with paying attention to numbers from non-zero minimum distance to the forth of epsilon where the epsilon is in integer. The results of trial and testing on clusters formed, with Silhouette Coefficient, point out that the clusters are well, strong, and quality enough. Therefore, this research gives a new way on how preprocessing non-spatial data for DBSCAN algorithm performance