Articles
176 Documents
<![CDATA[Komparasi Algoritma Klasifikasi Genre Musik pada Spotify Menggunakan CRISP-DM: Indonesia ]]>
<![CDATA[Salma Navisa]]>;
<![CDATA[Luqman Hakim]]>;
<![CDATA[Aulia Nabilah]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 2 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i2.162
<![CDATA[Sebelum era modernisasi di Indonesia, jika seseorang ingin mendengarkan musik harus berada di suatu tempat atau dapat mendengarkan dan melihat dari perangkat yang tidak bisa dibawa kemana-mana, misalnya radio. Membuat seseorang tidak dapat memilih genre musik yang diinginkan. Dengan munculnya internet di Indonesia dan perkembangan zaman, masyarakat dapat mendengarkan musik secara online sesuai selera atau genre musik yang disukai atau mendengarkan musik dengan genre musik yang dimainkan secara acak. Proses data mining memiliki berbagai algoritma klasifikasi yang selalu berkembang. Teknik klasifikasi pada fungsionalitas data mining merupakan data yang dapat dikategorikan berdasarkan label kelas yang telah diketahui sebelumnya. Teknik klasifikasi telah digunakan di berbagai bidang termasuk penelitian di industri musik. Penelitian ini bertujuan untuk membandingkan algoritma klasifikasi mana yang menghasilkan kinerja terbaik berdasarkan proses data mining menggunakan CRISP-DM. Algoritma klasifikasi yang digunakan untuk pengujian adalah Naive Bayes, K-NN, dan Random Forest. Dari penelitian yang dilakukan diperoleh hasil akurasi terbaik dengan algoritma Naive Bayes dengan nilai 58.91%. Algoritma dengan kinerja terbaik adalah K-NN dan Random Forest dengan nilai 0,528.]]>
<![CDATA[Sistem Deteksi Senjata Otomatis Menggunakan Deep Learning Berbasis CCTV Cerdas ]]>
<![CDATA[Iqbal Ahmad Dahlan]]>;
<![CDATA[Dananjaya Ariateja]]>;
<![CDATA[Muhammad Abditya Arghanie]]>;
<![CDATA[Muhammad Azka Versantariqh]]>;
<![CDATA[Muhammad David]]>;
<![CDATA[Uvi Desi Fatmawati]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 2 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i2.172
<![CDATA[Nowadays, security and safety are big concerns in this modern and cyberwar era. Many countries invest some safety infrastructure to ensure their inhabitants for keeping their lives safely. Indonesia is the country with many problems because of urbanization and other challenges. This problem should be solved with smart city solution and it must be able to face the challenge of ensuring the safety and improving the quality of life regarding network centric warfare era. This problem also should be tackled with CCTV analytics with the ability to implement an automatic weapon detection system. It also can provide the early detection of potentially violent situations that is of paramount importance for citizens security. This paper is using deep Learning techniques based on Convolutional Neural Networks (CNN) can be trained to detect this type of object with YOLOv4 model and it proposes to implement CCTV analytics as a platform to process real-time data for monitoring weapon detection into knowledge displayed in a dashboard with accuracy 0.89, precision 0.82, recall 0.96 dan F1 Score 0.90 result on weapon detection with a real time speed of processing with NVIDIA 2080 Ti around of 35 FPS. It will send an early warning notification if the system detects the weapon detection such as a knife, gun etc.]]>
<![CDATA[Smart Crowdsensing Berbasis Smart Service untuk Pemulihan Sektor Kesehatan dan Ekonomi di Masa Pandemi ]]>
<![CDATA[Amanda Putri Septiani]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 3 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i3.96
<![CDATA[The use of intelligent systems and technology is very much needed during this Covid-19 pandemic. The reason is that there are many sectors that must be rescued immediately, such as health and the economy. On the one hand, the community must be saved from the ongoing epidemic, but on the other hand, economic activity must continue to be pursued even though it is not in ideal conditions. One solution to these problems is the design of Smart Crowdsensing based on smart services that can be used to support physical distancing but still stimulate economic activity to keep moving. In general, smart crowdsensing functions to (i) detect crowds using location data from the user's mobile device GPS, (ii) self-quarantine surveillance and contact tracing using position history in real time, and (iii) collect and process information from citizen interactions. on social media to find out citizen reports related to the pandemic. Smart crowdsensing is designed using a smart service engineering method that allows it to communicate with other services using a REST API.]]>
<![CDATA[Tinjauan Teknologi Cerdas Pendukung Pemulihan Ekonomi UMKM Terdampak Covid-19 ]]>
<![CDATA[Dian Margahayu]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 3 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i3.151
<![CDATA[The implementation of Large-Scale Social Restrictions (PSBB) in various provinces in Indonesia has an impact on the Indonesian economy. The publication of the Analysis of the Covid-19 Impact Survey Results by BPS stated that 82.29% UMB and 84.20% MSE experienced a decrease in income. The government through the Covid-19 Handling Committee and National Economic Recovery launched the National Economic Recovery program, one of which was to provide a stimulus for business capital assistance to MSMEs. Apart from stimulus assistance, technology is also needed to accelerate economic recovery. Smart technologies that can be tried to be applied in the recovery of the national economy, including blockchain, smart contracts, e-commerce, IoT and cloud computing.]]>
<![CDATA[Analisis Klasifikasi SMS Spam Menggunakan Logistic Regression ]]>
<![CDATA[Ferin Reviantika Suprihati]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 3 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i3.166
<![CDATA[SMS or Short Message Service is usually found on cell phones. SMS is divided into two categories, namely SMS spam and SMS non-spam (ham). Spam SMS is an SMS that is annoying to phone users because it tends to contain messages that are not important such as promos and scams. Meanwhile, non-spam SMS (ham) tend to contain important SMS, such as messages from previous users. In this study, the classification of spam SMS and non-spam SMS (ham) was carried out using the logistic regression method. The purpose of this study is to distinguish or classify between spam and non-spam SMS (ham). The dataset in this study amounted to 1143 data, there are two columns, namely the text column and the label column. The number for spam messages is 566 messages and the number for non-spam messages is 577. The proposed method gets a better accuracy of 95%.]]>
<![CDATA[Perancangan Sistem Perhitungan Debit Air Otomatis Berbasis Internet of Things pada PDM Tirta Garut ]]>
<![CDATA[Ayu Latifah Latifah]]>;
<![CDATA[Yosep Septiana]]>;
<![CDATA[Abdul Aziz Nurhakim]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 3 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i3.181
<![CDATA[The service process in calculating water discharge for PDAM customers is still using conventional water meters as a result, the process of delivering information cannot be optimally accepted by various related parties and often the process that occurs requires officers to directly visit the customer's place then automatically manually recorded, the results from conventional meters and are often wrong in recording and calculating, of course this requires a solution. This research was carried out with the aim of changing the current conventional water discharge calculation system to be automatic using a Microcontroller and based on IoT as a solution that can be done from the current problems for calculating water discharge. The design method used is the Prototype Model from Sommerville, with Listen to Customer stages / listen to complaints for system needs, Build / Revise mock-ups to design and create systems and Customer test drive mock-ups to test the system that has been made and use Unifed modeling. Modeling Language for system representation in an easy-to-understand picture. This research produces tools and applications that can calculate water discharge automatically with integrated data using Internet of Things technology, apart from that, web application media are designed to provide information to customers and companies regarding the amount of usage along with the amount of bills charged to customers. customer. who can provide solutions to problems in PDAM Tirta Garut.]]>
<![CDATA[Optimasi Parameter Pengukuran Dimensi dan Defect Ubin Keramik dengan Metode Taguchi ]]>
<![CDATA[Denny Sukma Eka Atmaja]]>;
<![CDATA[Muhammad Kusumawan Herliansyah]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 4 No. 3 (2021) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v4i3.182
<![CDATA[The ceramics industry in Indonesia has a large contribution to the growth of various aspects in Indonesia. But in reality, there is still an imbalance between exports and imports for ceramic products. One way is to improve the quality of the ceramic industry in Indonesia. In fact, the ceramic quality inspection process in the ceramic industry is still done manually which can make mistakes in identifying defects. In this study, the design of variable identification system of ceramics was carried out specifically in the area of ceramics and dry spot defects on ceramic surfaces using image processing. Whereas to get a low error rate against the applicable variables, a design of experiment with the Taguchi approach is carried out. The results show that 50 cm distance, 300 lux light, 1x resize and 0.06 threshold can produce an image that has the smallest error value when identifying ceramic area and dry spot defects on the ceramic surface.]]>
<![CDATA[Darknet, Malware, KNN, Forensik Prediksi Jaringan TOR dan VPN menggunakan Algoritma K-Nearest Neighbour pada Trafik Darknet ]]>
<![CDATA[Aay Ramdan ramdan]]>;
<![CDATA[Nur Widyasono]]>;
<![CDATA[Husni Mubarok]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 5 No. 1 (2022) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v5i1.167
<![CDATA[Proses network forensic untuk menganalisis malware telah dilakukan peneliti sebelumnya dengan menerapkan metode manual diantaranya metode Anomali Behaviour pada file capture trafik jaringan. Network forensik tersebut memerlukan proses yang lebih lama dan tidak akurat dengan hasil yang diinginkan. Perkembangan articial intelligence berkembang pesat pada setiap bidang teknologi dapat memberikan peluang terhadap bidang malware analisis dan digital forensik agar dapat melakukan proses analisis lebih cepat dan tepat terutama penggunaan Machine Learning. Trafik darknet merupakan jaringan internet yang didalamnya terdapat berbagai ancaman kejahatan cyber. Penelitian terhadap analisis malware terutama klasifikasi trafik darknet dengan menggunakan algoritma machine learning telah banyak dilakukan, namun hasil yang didapat berupa pengukuran kinerja pada setiap algoritma machine learning terhadap proses analisis malware tanpa adanya pembaruan dataset ataupun implementasi dalam sebuah aplikasi. Pembaruan dataset sangat diperlukan agar analisa malware dapat mengidentifikasi perkembangan malware terbaru dan implementasi dilakukan agar dapat diketahui kinerja dari sebuah algoritma yang diterapkan, oleh karena hal tersebut dalam penelitian ini akan dibahas tentang proses analisis ancaman malware pada trafik darknet dengan menggunakan algoritma machine learning yaitu K-Nearest Neighbour untuk memprediksi sebuah ancaman serangan malware dengan dataset CICDarknet 2020. Hasil pengukuran performa dataset menggunakan KNN memiliki nilai akurasi 96,17% dengan menerapkan pemilihan fitur dengan information gain.]]>
<![CDATA[Oksimeter Militer Pemantau Stres Prajurit TNI Berbasis Internet of Military Things ]]>
<![CDATA[Dananjaya Ariateja]]>;
<![CDATA[Iqbal Ahmad Dahlan]]>;
<![CDATA[Uvi Desi Fatmawati]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 5 No. 1 (2022) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v5i1.174
<![CDATA[In carrying out their duties, TNI soldiers often experience pressure and threats that attack both physically and psychologically. This can trigger stress. Uncontrolled stress will cause disease disorders such as arrhythmias and hypoxemia. We offer a solution by building an Internet of Military Things (IoMT) based military oximeter for soldier stress monitoring. The proposed tool is real-time and portable, can monitor heart rate (BPM) and blood oxygen saturation (SpO2) when soldiers are on duty in conflict areas. This military oximeter is equipped with notifications and alarms that are integrated with applications installed on smartphones, so commanders can monitor the condition of their soldiers directly and view their health history. Based on the test results, obtained an accuracy of 99.7% and 99.88% for measuring heart rate and oxygen saturation in the blood. This military oximeter can be used as a medical aid to monitor the health condition of soldiers while on duty.]]>
<![CDATA[Prototype Penyiraman Otomatis Berbasis IOT untuk Multi Zona Tanaman Hias ]]>
<![CDATA[Hafiyyan Putra Pratama]]>;
<![CDATA[Dewi Indriati Hadi Putri]]>;
<![CDATA[Sudjani]]>
<![CDATA[ Jurnal Sistem Cerdas Vol. 5 No. 1 (2022) ]]>
Publisher : <![CDATA[APIC ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37396/jsc.v5i1.180
<![CDATA[The greenhouse concept for the cultivation of ornamental plants can optimize the conditioning of a good planting environment because it can protect plants from direct rain, can distribute temperature, divide sunlight evenly and regulate the intensity of watering plants regularly. The important thing to pay attention to in the cultivation of ornamental plants is the intensity of watering plants. Regular watering of plants can be optimized with the help of Internet of Things (IoT) technology so that the process of watering plants becomes a smart watering system. In this study, automatic watering of ornamental plants was divided into 3 zones based on the characteristics of humidity, watering time, and required water quantity. The smart watering system for 3 zones is implemented in the form of a prototype including a monitoring system based on the MQTT protocol]]>
