Articles
<![CDATA[Identifikasi Tanda Tangan dengan Ekstraksi Ciri GLCM dan LBP ]]>
<![CDATA[yuliana diah pristanti]]>;
<![CDATA[Panca Mudjirahardjo]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal EECCIS Vol 13, No 1 (2019) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Signature identification with extraction features of GLCM (The Gray Level Co-occurrence Matrix) and LBP (The Local Binary Pattern) compare the results of both accuracy. By using signatures from 15 people, each of which has 10 signatures. For the training data, 7 signatures from each person were taken so that the training data amounted to 105 signatures. While the testing data was taken 3 signatures from each person so that the test data amounted to 45 signatures. From the results of image processing obtained the percentage using GLCM feature extraction is greater than the percentage using LBP feature extraction, namely GLCM reaches 86.67% and LBP 80.00%. But both remain at a high level of success. So it can be concluded that both GLCM and LBP feature extraction can be recommended to recognize signature textures. Index Terms—GLCM, LBP, Signature.]]>
<![CDATA[IDENTIFICATION OF PATCHOULI PLANTS USING LANDSAT-8 SATELLITE IMAGERY AND IMPROVED K-MEANS METHOD ]]>
<![CDATA[Candra Dewi]]>;
<![CDATA[Muhammad Syaifuddin Zuhri]]>;
<![CDATA[Achmad Basuki]]>;
<![CDATA[Budi Darma Setiawan]]>
<![CDATA[ Journal of Environmental Engineering and Sustainable Technology Vol 3, No 2 (2016) ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (517.806 KB)
|
DOI: 10.21776/ub.jeest.2016.003.02.1
<![CDATA[To maintain the availability of the patchouli plants required monitoring the spread of patchouli plantation. This study performed the identification of patchouli plant through Landsat-8 satellite imagery and Improved K-Means method. Improved was done on this study include the process of determining the initial cluster by specifying the closeness between the data and the determination of the number of cluster (K) by using the histogram equalization technique. The result of internal criteria testing shows that determining the number of clusters using the histogram is less effective because it produces the lower value of the silhouette. On almost all image data test found the best value of the silhouette's coefficient is 75.089% at K=2 and data in February. Furthermore, based on the results of testing the external criteria known the highest purity value in February data with a number of cluster 5 is 0.6829268. The test results also show that the use of the Improved K-Means on the Landsat-8 image has not been able to recognize the difference patchouli plants with other crops due to the limited resolution of imagery data and also the minimum number and variation of test data. But, visually the patchouli plant cluster is found for February data while the age of the rice crop surrounding the patchouli is still in the early phase of planting.]]>
<![CDATA[Optimasi Nilai K pada Algoritma KNN untuk Klasifikasi Spam dan Ham Email ]]>
<![CDATA[Eko Laksono]]>;
<![CDATA[Achmad Basuki]]>;
<![CDATA[Fitra Bachtiar]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 2 (2020): April 2020 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (464.316 KB)
|
DOI: 10.29207/resti.v4i2.1845
<![CDATA[There are many cases of email abuse that have the potential to harm others. This email abuse is commonly known as spam, which contains advertisements, phishing scams, and even malware. This study purpose to know the classification of email spam with ham using the KNN method as an effort to reduce the amount of spam. KNN can classify spam or ham in an email by checking it using a different K value approach. The results of the classification evaluation using confusion matrix resulted in the KNN method with a value of K = 1 having the highest accuracy value of 91.4%. From the results of the study, it is known that the optimization of the K value in KNN using frequency distribution clustering can produce high accuracy of 100%, while k-means clustering produces an accuracy of 99%. So based on the results of the existing accuracy values, the frequency distribution clustering and k-means clustering can be used to optimize the K-optimal value of the KNN in the classification of existing spam emails.]]>
<![CDATA[Pemerataan Utilisasi Jaringan Multipath dengan Mode Controller Proactive-Reactive pada Software Defined Networking ]]>
<![CDATA[Akhmad Mukhtarom]]>;
<![CDATA[Achmad Basuki]]>;
<![CDATA[Muhammad Aswin]]>
<![CDATA[ Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 11 No. 2 (2017) ]]>
Publisher : <![CDATA[Fakultas Teknik, Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (661.184 KB)
|
DOI: 10.21776/jeeccis.v11i2.467
<![CDATA[Distributing traffic flows on fat-tree network topology used in data center networks is essential. Multipath routing is the common technique used to balance the traffic flows. In Software Defined Networking (SDN), the routing path is fully controlled by a controller to select the optimal path or the multiple paths in order to optimize flows throughput. This paper presents an implementation of a Hydrid proactive and reactive controller mode in SDN to load-balance traffic flows. The controller monitors the path utilization and will reactively install flow-tables to the appropriate switches whenever there are significant traffic spikes for a certain period. For the case of frequently high-utilized paths, the controller will proactively apply flow-tables to the appropriate switches. The evaluation results in a fat-tree topology show that the proposed Hydrid method outperforms LABERIO by 2.38 Mbps higher throughput and 18 seconds lower latency.]]>
<![CDATA[Rancang Bangun IOT Cloud Platform Berbasis Protokol Komunikasi MQTT ]]>
<![CDATA[Moh Wildan Habibi]]>;
<![CDATA[Adhitya Bhawiyuga]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 2 (2018): Februari 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (912.136 KB)
<![CDATA[Internet of Things (IoT) referring to a network that linking various device in the physical world with a variety of different protocols. However, there are limitations in terms of computing and storage because IoT device only use minimum computational and storage components. While cloud is a virtual environment that generally has a big capacity of computing and storage. By integrating cloud and IoT, it is necessary to divert IoT device's computational process and storage towards cloud, so that cloud can resolve the limitations on the IoT device. There are two main issues in the integration, heterogeneity and security. Heterogeneity refers to number range of devices that can communicate with the cloud, so it is necessary to use specific communication protocol so that all devices can be connected to the cloud. Security refers to the validity of the IoT devices that can transmit data to the cloud. From the previous explanation, then this research makes an architecture of IoT cloud platform that use MQTT communication protocol to resolve the problem of heterogeneity. Whereas to ensure the validity of IoT devices that can transmit data, constructed a mechanism to manage IoT device, authentication, and authorization. The performance test results showed, built systems capable of handling the publisher up to 250 publishers in each second.]]>
<![CDATA[Analisis Perbandingan Metode Routing Spray and Wait dengan Prophet untuk Daerah Terpencil ]]>
<![CDATA[Imron Sazali]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 4 (2018): April 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1355.993 KB)
<![CDATA[Indonesia's geographical conditions, some of which are inland, in which there is no reliable internet connection. Routing model selection is highly dependent on the geographical conditions of the area. Routing is a process for determining the route from source to destination in a communication scheme. It takes a Routing scheme that has tolerance for delay, mobility, and requires minimal resources. Delay Tolerant Network (DTN) technology is a data delivery mechanism that resists latency, and can carry large data packets with minimal system resources. With the DTN (Delay Tolerant Network) technology the problem is likely to be resolved. Two DTN protocols in this final project are Prophets that use knowledge and Spray and Wait with replica strategies. Both protocols are simulated in a predetermined environment using One Simulator and then analyzed based on performance measurement parameters of delivery probability, average delay and overhead ratio. From the results of research conducted, obtained data that Routing Spray and Wait has a tendency better performance in terms of Delivery Probability and Average Delay. Whereas in the case of Overhead Ratio, Routing Prophet shows a smaller value. For the environment that has characteristics as in this study Spray and Wait is better than Prophet.]]>
<![CDATA[Analisis Perbandingan Kinerja Protokol Websocket dengan Protokol SSE pada Teknologi Push Notification ]]>
<![CDATA[Panser Brigade Muhammad]]>;
<![CDATA[Widhi Yahya]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 6 (2018): Juni 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1096.66 KB)
<![CDATA[Push notification technology allows users (clients) to get information periodically. Information submitted by push notification in the form of notifications such as on social network or news sites. There are many technologies that can be applied to notification delivery. One of them is notification delivery using Websocket protocol and Server-Sent Events (SSE). The Websocket protocol implements full-duplex communication so that either the server or client can send and receive data simultaneously. While the SSE protocol implements half-duplex communication so that the client can only receive data sent server periodically. This study was conducted to compare the performance of Websocket protocol with SSE related to method of delivery of both protocols on push notification technology. Both protocols will be implemented and tested based on predetermined scenarios. The results obtained are the average delay and CPU usage in SSE protocol is smaller than Websocket protocol.]]>
<![CDATA[High Availability Controller Software Defined Network Menggunakan Heartbeat dan DRBD ]]>
<![CDATA[Maskur Purwiadi]]>;
<![CDATA[Widhi Yahya]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1099.118 KB)
<![CDATA[Network model architecture that used nowadays are difficult to apply a new protocol because it depends upon vendor, so it appeared a concept that manage network systemperformance through software named Software Defined Network. SDN separating data-plane and control-plane in network devices such as router and switch, so that programming network devices may be done centrally through a controller.A controller manage forwarding table switch which forwarding the flow of communication package.If a controller goes offlinea switch not be able to forwarding the flow of communication package from a device to other devices. So it needs high availabillity controller mechanism to be able to maintain the availability of a controller so the communication package can be arrive. High availability controller can be done by mechanism failover use Heartbeat and DRBD.Testing in this research done with planned downtime methods. The test results that obtained from the average downtime of POX controller when failover process is 23 seconds, and 59,6 seconds when failback process, while Opendaylight controller took time 195 seconds for failover process and 219 seconds for faillback. This method is a good enough, where the more features run in a controller the longer time downtime will produced.]]>
<![CDATA[Perbandingan Performansi Protokol Routing Epidemic dan Maxprop Berdasarkan Mobilitas Node pada Delay Tolerant Network ]]>
<![CDATA[Andi Yudiko Leonardo Solin]]>;
<![CDATA[Rakhmadhany Primananda]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (609.526 KB)
<![CDATA[The DTN architecture provides a solution for communication with long delay and intermittent connectivity. The moving node results in the large number of waiting time required by data packets to receive information from source to destination through many nodes. The movement of nodes that occur will produce such a patterned pattern movement and random movement. In sending messages DTN apply some routing protocols used in a different location and situation. DTN protocol in this research is routing Epidemic and Maxprop by doing DTN network simulation on The ONE Simulator to compare the performance of DTN protocol based on node mobility with the addition of node and message size. The results show that in the case of Delivery Probability routing Maxprop has better performance tendency than Epidemic routing with the highest Delivery Probability value on patterned movement 89% compared to 88% in Epidemic. On the random movement the best value of Delivery Probability produced is 41% compared to 35% in routing Epidemic. The Best value of Overhead Ratio routing Maxprop on patterned movement is 6,1379 compared to 7,9173 in Epidemic. On random movement the best of Overhead Ratio value is 4,0769 versus 3,7143 on Epidemic routing. The best Average Latency of routing Maxprop on patterned movement is 513,1642s compared to 574,1728s in Epidemic. In the random movement, routing Epidemic and Maxprop have the same Latency Average value is 1389.3500s]]>
<![CDATA[Implementasi Sistem Pencarian Perangkat USB berbasis Protokol USB/IP dalam Jaringan IP Multicast ]]>
<![CDATA[La Ode Muh. Fadlun Akbar]]>;
<![CDATA[Dahnial Syauqy]]>;
<![CDATA[Achmad Basuki]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (868.166 KB)
<![CDATA[USB/IP is a technology that proposes a USB device sharing mechanism has some problems related to their access mechanisms. The problem is there are no service discovery system that makes USB device sharing mechanism is inefficient. This causes the user has to know exactly the IP address of USB/IP provider and through a highly technical configuration process. The problem can be solved by implementing a service discovery system to USB/IP protocol by utilizing group management system in the IP multicast network. Not only resolved IP address problems, we also provide limits on the scope of USB/IP services when it operates. In this research, there are 4 important components to realize the discovery system, there are limitation of scope, communication method, system observation method, and method of selecting and requesting access of USB device. Based on implementation, updating the list of USB devices (based on system observation method) takes the longest time among other mechanisms, which is 569,033±6,036 milliseconds. This is due to sequence of processes that need to be run, both on the USB/IP provider as well as on the user application. Moreover, the service discovery system can be implemented without changing the original specifications of USB/IP.]]>
