Articles
14 Documents
Search results for
, issue
"Vol 7, No 1 (2022)"
:
14 Documents
clear
<![CDATA[Metode Algoritma Convolutional Neural Network pada Klasifikasi Penyakit Tanaman Cabai ]]>
<![CDATA[Dwi Suci Anggraeni]]>;
<![CDATA[Arif Widayana]]>;
<![CDATA[Putri Dwi Rahayu]]>;
<![CDATA[Chaerur Rozikin]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13304
<![CDATA[In Indonesia, chili is a very important vegetable, which is consumed for domestic trade as well as for export. In addition to containing nutrients, chili also has a high economic value. Due to the increasing quality of chili as a commodity that often experiences the highest price fluctuations, it is necessary to classify chili plants to maintain the quality of chili harvests so that chili production can increase. This research is a classification of chili plant diseases using the convolutional neural network method, with several design and implementation processes. The purpose of this research is to assist in classifying the quality of chili plants in the hope of maintaining the quality of chili in the market and preventing the price spikes. Classification of chili plant diseases using a convolutional neural network based on train data and test data. To form a model in the classification, training data needs to be carried out and there are 3 categories used for the classification model, namely yellowish, leaf curl, and healthy. Training data compatible with computers in single GPU mode and validation data are not included in the training process as well as interpreter review materials to determine the type of chili plant object that is difficult to distinguish significantly, namely the results of the classification label that appears on the network.]]>
<![CDATA[Sistem Rekomendasi Musik dengan Metode Collaborative Filtering Berbasis Android ]]>
<![CDATA[Muhamad Veri Anggoro]]>;
<![CDATA[Millati Izzatillah]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.10300
<![CDATA[The recommendation system is a system that can suggest information based on the results of observation of users’ desires to users. In this study, the recommendation system can be implemented into an online music player application by displaying song recommendations so that the application looks more personal to its users. The research method used to design this music recommendation system is a collaborative filtering by which the music recommendations for users are determined. The system produces a pretty good prediction when viewed from the MAE (Mean Absolute Error) score of 0.09639423292263861 and RMSE (Root Mean Squared Error) of 0.024737713540837314, meaning that the smaller the evaluation result is or close to 0, the more accurate it will be. The results of the MAE and RMSE calculations show that the prediction error rate is very small, so that they can be used as a parameter for determining music recommendations according to users’ needs.]]>
<![CDATA[Klasifikasi Tutupan Lahan pada Citra Sentinel-2 Kabupaten Kuningan dengan NDVI dan Algoritme Random Forest ]]>
<![CDATA[Dwi Marlina]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.12948
<![CDATA[The current remote sensing technology has produced various advantages, one of which is land cover classification. This technique is effective in land cover monitoring because of its ability to provide spatial information on the surface of the earth quickly, broadly, precisely and easily. The vegetation index obtained based on remote sensing is a fairly simple and effective method for quantitative and qualitative evaluation of cover, strength, and vegetation growth dynamics. The vegetation index using reflections from vegetation that is commonly used to evaluate vegetation quality is the normalized difference vegetation index (NDVI). Land cover classification analysis is performed with NDVI and random forest algorithms. The random forest algorithm is one of the supervised machine learning algorithms which can be used in classifying pixels in land cover classification classes. This research is aimed at classifying land cover of Sentinel-2 satellite images using NDVI and random forest algorithms. The result of this research is that the NDVI value -0.3 – 0.91 and the random forest algorithm accuracy is 91.39%, and Kappa 0.88. In conclusion, it can be said that random forest algorithms is effective to perform land cover classification by using Sentinel-2 satellite images]]>
<![CDATA[Klasifikasi Down Syndrome Menggunakan Tekstur LBP dengan Tiga Variasi Distance Classifiers ]]>
<![CDATA[Agung Tjahjo Nugroho]]>;
<![CDATA[Yustisi Wulandari]]>;
<![CDATA[Bowo Eko Cahyono]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13532
<![CDATA[Down syndrome is the most easily identified and most common genetic disorder. Down syndrome variation of trisomy 21 has characteristics that are common to people with Down syndrome. But, children with this Down syndrome variation have slight differences in the mouth and appearance because they tend to have similar oral features with their parents and siblings so that distinguishing them is quite complex. Therefore, it is important to know in more details the special characteristics of children with Down syndrome. This study aims to create an innovative image processing-based system so that it is more practical to classify people with down syndrome and normal people. The method that can be used is the Local Binary Pattern (LBP) method. This study used 2400 mouth frames of children with Down syndrome and normal children for data training. Then, it also uses 3600 mouth frames for children with Down syndrome and normal children for testing data. The results obtained are the threshold value which gives a good classification of 0.1-0.2 for the three variations of the distance calculation method. The Euclidean and Chebychev methods have an accuracy quality of 100% while the City block method at the threshold of 0.1-0.2 has an accuracy of 91.6. So, it can be said that the most accurate method in this research is the Chebychev, Euclidean, then City Block method.]]>
<![CDATA[Aplikasi Multi Platform Penerapan Algoritma Naive Bayes untuk Klasifikasi Keterlambatan Pembayaran Premi Asuransi ]]>
<![CDATA[Jorgi Antonius Karlia]]>;
<![CDATA[Wawan Nurmansyah]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.11932
<![CDATA[Human carelessness can be one of the main factors in accidents. Knowing this situation, the insurance company takes the role as well as the opportunity from the consumers, to be the one who will bear the loss known as risk. The problem that often arises in insurance companies is the number of customers who are in arrears in paying premiums. In the procedures applicable to insurance, there is a grace period for payment of 30 days during which the customer/insured must pay a predetermined amount of premium and if the customer/insured does not pay the premium, the insurance policy will be canceled so that the insurance profit will be reduced and if it happens, it will be detrimental to the insurance. This research is conducted by applying the Naive Bayes algorithm using insurance customer data. The result of this study is a classification system for late payment of insurance premiums that can classify the status of premium payments for insurance customers. The system test results show that the system can classify the premium payment status of insurance customers with an accuracy rate of 82.5%, then the resulting precision level is 94.83% and the resulting recall is 86.39%.]]>
<![CDATA[DC MOTOR SPEED CONTROL USING PID CONTROL WITH ENCODER AS FEEDBACK ]]>
<![CDATA[Muhammad Reza Aditya Nurkholis Putera]]>;
<![CDATA[Rahmat Hidayat]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13026
<![CDATA[PID controllers are widely used to improve system response , as they offer clear, simple functionality and ease of deployment and use. One of the important roles of the PID controller can be seen in its application to control and stabilize the angular velocity in the reference value of a direct current (DC) motor. The purpose of this task is to implement a PID controller as a DC motor speed controller so that it can understand the characteristics of each PID controller parameter on the system response curve. The test results show that each PID value parameter (Proportional, Integral, Derivative) has different characteristics to the system response. For example, adding the Kp parameter can reduce the steady-state error, reduce the rise time, but can increase the overshot value. Meanwhile, adding the Ki parameter can affect the increase in overshot, reduce the rise time, and reduce or even almost eliminate the steady state error value. Then, adding the Kd parameter can reduce the overshot, reduce the rise time, and increase the undershot]]>
<![CDATA[Implementasi Metode Dempster Shafer Berbasis Web untuk Mendiagnosa Kerusakan Jaringan LAN ]]>
<![CDATA[Sukmawati Sukmawati]]>;
<![CDATA[Rifky Maulana]]>;
<![CDATA[Ranti Holiyanti]]>;
<![CDATA[Betha Nurina Sari]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13548
<![CDATA[Local Area Network (LAN) is a type of computer network that covers a local area and is widely used in various aspects.In places that provide LAN connections there are those using Wi-Fi technology which are usually called hotspots. Damage to the LAN, especially Wi-fi itself, is often experienced by the community.It is also inconvenient for internet network users due to lack of knowledge about the damage. Therefore, it is necessary to create a system that can be used to collect knowledge data from network experts and store it. The result of this research is an expert system that diagnoses LAN network damage. The system automatically provides diagnostic results by displaying the type of glitch and its solution based on the symptoms of the glitches experienced. The conclusion of this study is that an expert system by using the Dempster Shafer method to handle data uncertainty when diagnosing LAN service disruptions is very helpful in overcoming the problem of declining service quality.]]>
<![CDATA[Pengaturan Torsi Motor Induksi 3 Phasa Menggunakan Direct Torque Control ]]>
<![CDATA[Alvin Tri Nugroho]]>;
<![CDATA[Yuliyanto Agung Prabowo]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.11993
<![CDATA[The three-phase induction motor is the most widely used drive in the industry due to its sturdy construction and relatively affordable price. However, there is a disadvantage that it is difficult to control torque and speed dynamically and separately. The torque and speed characteristics of the three-phase induction motor are a couple and are nonlinear. So it is difficult to be able to control torque and speed separately. To overcome these problems, there is a decoupling control method that will separate the control between torque and speed using DTC (Direct Torque Control) by setting the value of the stator flux as a sector selector switching. DCT is a form of vector control. The least square estimation method is used for speed forecasting on induction motors through measurement data of stator flux and rotor flux which are regressed into non-linear form to monitor motor speed. Based on tests using simulations, the results show that when an induction motor is given a torque load, the torque response changes (tracking) the torque response of the induction motor can follow these changes. Where the characteristic value of the response transient, time constant (?) is 0.082 seconds, the rise time (TR) is 0.242 seconds and the settling time (TS) is 0.246 seconds.]]>
<![CDATA[Implementasi Metode Rapid Application Development pada Pengembangan Aplikasi Inventory Barang ]]>
<![CDATA[Siti Anisah]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13064
<![CDATA[The Faculty of Medicine and Health, Universitas Muhammadiyah Jakarta, still manually manages inventory, especially the consumables, using paper media such as in processing incoming and outgoing goods and in reporting the goods that are recorded and stored on spreadsheet tools. making it difficult to manage data. The purpose of this study is to design and build an inventory information system to facilitate the effective inventory data management process. The system development method uses Rapid Application Development (RAD). Tools in system design use UML, while system programming uses PHP and mysql database and system testing uses blackbox method. The results of this study produce an inventory of goods information system by providing convenience in managing inventory data, making the finding of goods inventory easier or faster because the system can show the goods data section, making the inventory can be accurately and easily controlled.]]>
<![CDATA[Sistem Internet of Things dan Transmisi Data Menggunakan Aplikasi Telegram pada Sistem Keamanan Sepeda Motor ]]>
<![CDATA[Abdul Kholik]]>;
<![CDATA[Ibrahim Ibrahim]]>;
<![CDATA[Reni Rahmadewi]]>
<![CDATA[ STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 7, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Indraprasta PGRI Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30998/string.v7i1.13877
<![CDATA[A motorcycle is a two-wheeled vehicle that is driven by an engine. With a motorcycle, it will be faster and easier to reach our destination. This makes motorcycle users on the road more visible than other vehicles. As a result of a large number of motorcycle vehicles, the crime of motorcycle theft has increased. The main factor underlying the theft of motorcycles is economic factors. Therefore, an IoT-based motorcycle security system was created with the Telegram application. Where the security system uses the Quectel L80 GPS, and fingerprint and can also control the motorbike with the telegram application. The results of testing the command on the motorcycle security system using the telegram application obtained a stable delay time in each experiment. Where the average value of delay in testing the Engine ON and Engine OFF commands is 5.01. While the average value of delay in the fingerprint ADD test is 4.4 seconds and the average delay value in the fingerprint Delete test is 2.3 seconds. In the Quality of Service assessment from the test results using Wireshark, it can be seen that the average results on the network are good because they meet the standardization requirements with an index value of 3.3. Where the average delay value is 170,168865 ms, the average throughput value is 17573,68780-kilo bytes/17k, and the packet loss value is 0%..]]>
