EMITTER International Journal of Engineering Technology
Not a member yet
160 research outputs found
Sort by
Comparison of The Data-Mining Methods in Predicting The Risk Level of Diabetes
No full textMellitus Diabetes is an illness that happened in consequence of the too high glucose level in blood because the body could not release or use insulin normally. The purpose of this research is to compare the two methods in The data-mining, those are a Regression Logistic method and a Bayesian method, to predict the risk level of diabetes by web-based application and nine attributes of patients data. The data which is used in this research are 1450 patients that are taken from RSD BALUNG JEMBER, by collecting data from 26 September 2014 until 30 April 2015. This research uses performance measuring from two methods by using discrimination score with ROC curve (Receiver Operating Characteristic). On the experiment result, it showed that two methods, Regression Logistic method and Bayesian method, have different performance excess score and are good at both. From the highest accuracy measurement and ROC using the same dataset, where the excess of Bayesian has the highest accuracy with 0,91 in the score while Regression Logistic method has the highest ROC score with 0.988, meanwhile on Bayesian, the ROC is 0.964. In this research, the plus of using Bayesian is not only can use categorical but also numerical
Performance of Implementation IBR-DTN and Batman-Adv Routing Protocol in Wireless Mesh Networks
No full textWireless mesh networks is a network which has high mobility and flexibility network. In Wireless mesh networks nodes are free to move and able to automatically build a network connection with other nodes. High mobility, heterogeneous condition and intermittent network connectivity cause data packets drop during wireless communication and it becomes a problem in the wireless mesh networks. This condition can happen because wireless mesh networks use connectionless networking type such as IP protocol which it is not tolerant to delay. To solve this condition it is needed a technology to keep data packets when the network is disconnect. Delay tolerant technology is a technology that provides store and forward mechanism and it can prevent packet data dropping during communication. In our research, we proposed a test bed wireless mesh networks implementation by using proactive routing protocol and combining with delay tolerant technology. We used Batman-adv routing protocol and IBR-DTN on our research. We measured some particular performance aspect of networking such as packet loss, delay, and throughput of the network. We identified that delay tolerant could keep packet data from dropping better than current wireless mesh networks in the intermittent network condition. We also proved that IBR-DTN and Batman-adv could run together on the wireless mesh networks. In The experiment throughput test result of IBR-DTN was higher than Current TCP on the LoS (Line of Side) and on environment with obstacle.Keywords: Delay Tolerant, IBR-DTN, Wireless Mesh, Batman-adv, Performanc
Cluster Oriented Spatio Temporal Multidimensional Data Visualization of Earthquakes in Indonesia
No full textSpatio temporal data clustering is challenge task. The result of clustering data are utilized to investigate the seismic parameters. Seismic parameters are used to describe the characteristics of earthquake behavior. One of the effective technique to study multidimensional spatio temporal data is visualization. But, visualization of multidimensional data is complicated problem. Because, this analysis consists of observed data cluster and seismic parameters. In this paper, we propose a visualization system, called as IES (Indonesia Earthquake System), for cluster analysis, spatio temporal analysis, and visualize the multidimensional data of seismic parameters. We analyze the cluster analysis by using automatic clustering, that consists of get optimal number of cluster and Hierarchical K-means clustering. We explore the visual cluster and multidimensional data in low dimensional space visualization. We made experiment with observed data, that consists of seismic data around Indonesian archipelago during 2004 to 2014.Keywords: Clustering, visualization, multidimensional data, seismic parameters
Performance Analysis of Scheduling Schemes for Femto to Macro Interference Coordination in LTE-Femtocell Deployment Scenario
No full textDeploying femtocells that have low power level in LTE with small coverage area is an alternative solution for mobile operators to improve indoors network coverage area as well as system capacity. However deploying femtocells (HeNB) that were used co-channel frequency, can be brought about interference problem to the Macro BTS (eNB). Close Subscriber Group (CSG) of HeNB allows only User equipment (UE) to access HeNB. HeNB is the source of interference for UE who cannot access it. Therefore it is necessary for interference coordination methods among the HeNB and eNB. The methods are ICIC (Intercell Interference Coordination) and eICIC (enhanced Intercell Interference Coordination). Â This paper proposed performance analysis of scheduling schemes for Femto to macro interference coordination that allocated resource in the frequency and time domain using LTE-Femtocell suburban and urban deployment scenario. Simulation result using ICIC methods can improve SINR performance 15.77 % in urban and 28.66 % in suburban, throughput performance 10.11 % in urban and 21.05 % in suburban. eICIC methods can improve SINR performance 17.44 % in urban and 31.14 % in suburban, throughput performance 19.83% in urban and 44.39 % in suburban.The result prove using eICIC method in time domain resource have better performance than using ICIC method in frequency resource. However using eICIC method in suburban deployment scenariocan increase the performance of SINR and throughput more effective than using eICIC method in urban deployment scenario
Performance Analysis of Cell Zooming Based Centralized Algorithm for Energy Efficient in Surabaya
No full textThe cellular subscribers’s growth over the years increases the traffic volume at Base Stations (BSs) significantly. Typically, in central business district (CBD) area, the traffic load in cellular network in the daytime is relatively heavy, and light in the daynight. But, Base Station still consumes energy normally. It can cause the energy consumption is wasted. On the other hand, energy consumption being an important issue in the world. Because, higher energy consumption contributes on increasing of emission. Thus, it requires for efficiency energy methods by switching BS dynamically. The methods are Lower-to-Higher (LH) and Higher-to-Lower (HL) scheme on centralized algorithm. In this paper propose cell zooming technique which can adjusts the cell size dynamic based on traffic condition. The simulation result by using Lower-to-Higher (LH) scheme can save the network energy consumption up to 70.7917% when the number of mobile user is 37 users and 0% when the number of mobile user is more than or equal to 291 users. While, Higher-to-Lower (HL) scheme can save the network energy consumption up to 32.3303% when the number of mobile user is 37 users and 0% when the number of mobile user is more than or equal to 292 users. From both of these schemes, we can analyze that by using Lower-to-Higher (LH) scheme reduces energy consumption greater than using Higher-to-Lower (HL) scheme. Nevertheless, both of them can be implemented for energy-efficient method in CBD area. Eventually, the cell zooming technique by using two schemes on centralized algorithm which leads to green cellular network in Surabaya is investigated
Feature Selection of Network Intrusion Data using Genetic Algorithm and Particle Swarm Optimization
No full textThis paper describes the advantages of using Evolutionary Algorithms (EA) for feature selection on network intrusion dataset. Most current Network Intrusion Detection Systems (NIDS) are unable to detect intrusions in real time because of high dimensional data produced during daily operation. Extracting knowledge from huge data such as intrusion data requires new approach. The more complex the datasets, the higher computation time and the harder they are to be interpreted and analyzed. This paper investigates the performance of feature selection algoritms in network intrusiona data. We used Genetic Algorithms (GA) and Particle Swarm Optimizations (PSO) as feature selection algorithms. When applied to network intrusion datasets, both GA and PSO have significantly reduces the number of features. Our experiments show that GA successfully reduces the number of attributes from 41 to 15 while PSO reduces the number of attributes from 41 to 9. Using k Nearest Neighbour (k-NN) as a classifier,the GA-reduced dataset which consists of 37% of original attributes, has accuracy improvement from 99.28% to 99.70% and its execution time is also 4.8 faster than the execution time of original dataset. Using the same classifier, PSO-reduced dataset which consists of 22% of original attributes, has the fastest execution time (7.2 times faster than the execution time of original datasets). However, its accuracy is slightly reduced 0.02% from 99.28% to 99.26%. Overall, both GA and PSO are good solution as feature selection techniques because theyhave shown very good performance in reducing the number of features significantly while still maintaining and sometimes improving the classification accuracy as well as reducing the computation time
Semantic Songket Image Search with Cultural Computing of Symbolic Meaning Extraction and Analytical Aggregation of Color and Shape Features
No full textThe term "Songket" comes from the Malay word "Sungkit", which means "to hook" or "to gouge". Every motifs names and variations was derived from plants and animals as source of inspiration to create many patterns of songket. Each of songket patterns have a philosophy in form of rhyme that refers to the nature of the sources of songket patterns and that philosophy reflects to the beliefs and values of Malay culture. In this research, we propose a system to facilitate an understanding of songket and the philosophy as a way to conserve Songket culture. We propose a system which is able to collect information in image songket motif variations based on feature extraction methods. On each image songket motif variations, we extracted philosophy of rhyme into impressions, and extracting color features of songket images using a histogram 3D-Color Vector quantization (3D-CVQ), shape feature extraction songket image using HU Moment invariants. Then, we created an image search based on impressions, and impressions search based on image. We use techniques of search based on color, shape and aggregation (combination of colors and shapes). The experiment using impression as query : 1) Result based on color, the average value of true 7.3, total score 41.9, 2) Result based on shape, the average value of true 3, total score 16.4, 3) Result based on aggregation, the average value of true 3, total score 17.4. While based using Image Query : 1) Result based on color, the average precision 95%, 2) Result based on shape, average precision 43.3%, 3) Based aggregation, the average precision 73.3%. From our experiments, it can be concluded that the best search system using query impression and query image is based on the color.Keyword : Image Search, Philosophy, impression, Songket, cultural computing, Feature Extraction, Analytical aggregation
Fast Response Three Phase Induction Motor Using Indirect Field Oriented Control (IFOC) Based On Fuzzy-Backstepping
No full textInduction Motor in Electrical drive system at a accelleration speed for example in electric cars have a hard speed setting is set on a wide range, causing an inconvenience for motorists and a fast response is required any change of speed. It is necessary for good system performance in control motor speed and torque at low speed or fast speed response, which is operated by Indirect Field Oriented Control (IFOC). Speed control on IFOC methods should be better to improving the performance of rapid response in the induction motor. In this paper presented a method of incorporation of Fuzzy Logic Controller and Backstepping (Fuzzy-Backstepping) to improve the dynamically response speed and torque in Induction Motor on electric car, so we get smoothness at any speed change and braking as well as maximum torque of induction motor. Test results showed that Fuzzy-Backstepping can increase the response to changes speed in electric car. System testing is done with variations of the reference point setting speed control system, the simulation results of the research showed that the IFOC method is not perfect in terms of induction motor speed regulation if it’s not use speed control. Fuzzy-Backstepping control is needed which can improve the response of output, so that the induction motor has a good performance, small oscillations when start working up to speed reference.Keywords: Fuzzy-Backstepping, IFOC, induction moto
Modified GTS Allocation Scheme for IEEE 802.15.4
No full textIEEE 802.15.4 standard is widely used in wireless personal area networks (WPANs). The devices transmit data during two periods: contention access period (CAP) by accessing the channel using CSMA/CA and contention free period (CFP), which consists of guaranteed time slots (GTS) allocated to individual devices by the personal area network (PAN). However, the use of GTS slot size may lead to severe bandwidth wastage if the traffic pattern is not fit or only a small portion of GTS slot is used by allocated device. The proposed scheme devides the GTS slot and then optimizes the GTS slot size by exploiting the value of superframe order (SO) information. The proposed scheme was tested through simulations and the results show that the new GTS allocation scheme perform better than the original IEEE 802.15.4 standard in terms of average transmitted packets, throughput, latency and probability of successful packets
An Adaptive Connectivity-based Centroid Algorithm for Node Positioning in Wireless Sensor Networks
No full textIn wireless sensor network applications, the position of nodes is randomly distributed following the contour of the observation area. A simple solution without any measurement tools is provided by range-free method. However, this method yields the coarse estimating position of the nodes. In this paper, we propose Adaptive Connectivity-based (ACC) algorithm. This algorithm is a combination of Centroid as range-free based algorithm, and hop-based connectivity algorithm. Nodes have a possibility to estimate their own position based on the connectivity level between them and their reference nodes. Each node divides its communication range into several regions where each of them has a certain weight depends on the received signal strength. The weighted value is used to obtain the estimated position of nodes. Simulation result shows that the proposed algorithm has up to 3 meter error of estimated position on 100x100 square meter observation area, and up to 3 hop counts for 80 meters' communication range. The proposed algorithm performs an average error positioning up to 10 meters better than Weighted Centroid algorithm.Keywords: adaptive, connectivity, centroid, range-free