Techno Nusa Mandiri

RECOGNITION OF REALTIME BASED PRIMITIVE GEOMETRY OBJECTS USING PERCEPTRON NETWORK

Cut Lika Mestika Sandy — 2023-03-03

The purpose of this study is to analyze the perceptron model on pattern recognition of primitive geometric objects in real time based on video images. The samples used in this study were cubes, prisms, tubes and balls. The system was built using the Delphi 7 programming language with pre-processing stages system training includes the process of calculating matrix values from the original image, then proceed with the grayscale and edge detection processes using convolution with a kernel, namely the sobel operator and then the matrix results from the edge detection process are transformed using a perceptron network to obtain energy from the image of the object, then the resulting energy The transformation is stored in the database as a system test reference pattern recognition energy. Measurement of system performance evaluation in this study uses two parameters, namely detection rate and false positive rate. The recognition rate of primitive geometric objects using the perceptron network model in this study reaches 60.00% to 80.00%. The detection rate percentage shows that this model can be used as a supporting approach for the recognition of geometric objects in video.

SENTIMENT ANALYSIS WITH A CASE STUDY OF PRACTICE CARD ON TWITTER SOCIAL MEDIA USING NAIVE BAYES METHOD

Asthakhuroh Asthakhuroh — 2023-03-10

-In early March 2022, Indonesia experienced a coronavirus pandemic which caused COVID-19 to enter for the first time. Since then, all sectors have been affected by the COVID-19 pandemic, not only health, the economic sector has also been seriously affected by this pandemic. In overcoming employment problems, the government makes a policy of the Pre-Employment Card program. The Pre-Employment Card Program is one of the government's efforts to expand job opportunities and to increase competitiveness which later became one of the social assistance for the community to overcome the Covid-19 pandemic. The implementation of the Pre-Employment Card program received pros and cons from the community, one of which was on Twitter social media. The results of the sentiment analysis of the pre-employment card program are mostly positive. The test results show that the Naïve Bayes Classifier method is successful in classifying sentiment with the highest accuracy value of 96%, the highest precision value of 98%, and the highest recall value of 96%, and AUC of 96%.

DIGITAL IMAGE IDENTIFICATION OF PLANKTON USING REGIONPROPS AND BAGGING DECISION TREE ALGORITHM

Hikmatulloh Hikmatulloh — 2023-03-10

Peranan plankton sangat penting bagi kehidupan organisme disekitarnya, sehingga penelitian prihal plankton sangatlah dibutuhkan karena kaitannya dengan kelangsungan kehidupan mahluk hidup lainnya. Kendala yang sering didapatkan dalam hal penelitian plankton khususnya dalam hal pengidentifikasian plankton yaitu tidak efisiennya dalam aspek waktu dan organisme ini memiliki ukuran rata-rata yang sangat kecil. Dalam hal ini diperlukan alternatif yang lebih baik dalam pengidentifikasian jenis plankton ini dengan cara pemrosesan gambar pada citra plankton secara digital atau biasa disebut dengan istilah “Digital Image Processing”. Penelitian ini bertujuan untuk melakukan pengolahan citra digital plankton sebanyak 144 citra yang yang dibagi menjadi 75% sebagai data pelatihan dan 25% sebagai data pengujian, dan citra tersebut didapatkan dari riset pada yayasan Kanopi Indonesia. Dalam prosesnya citra ini dianalisa bentuk menggunakan fungsi Regionprops sehingga didapatkan fitur pembeda dari masing-masing jenis plankton. Setelah citra terekstraksi fitur nya selanjutnya dilakukan pengolahan data dengan mengklasifikasikan setiap jenis plankton tersebut. Untuk menghasilkan sebuah klasifikasi data yang lebih baik, dalam penelitian ini menggunakan algoritma Bagging Decision Tree dalam pengolahan data nya dan menghasilkan akurasi sebesar 92.59%. Algoritma Bagging Decision Tree ini cukup baik dan mudah untuk di implemntasikan kedalam sebuah program identifikasi jenis plankton, terbukti dengan pengujian pada data citra pengujian menghasilkan 33 citra teridentifikasi dengan benar dari total pengujian sebanyak 36 citra.

AUDIT OF THE REGIONAL DEVELOPMENT PLANNING INFORMATION SYSTEM (SIPD) USING COBIT 5.0 FRAMEWORK

Marliana Rahmawati Nurhanifah — 2023-03-14

Tasikmalaya Regional Representative Council’s is one of the legislative institutions that runs the local government. In carrying out the duties and functions of the Leadership and Members of the Regional People's Representative Council in the regional development planning sector, the Secretariat of the Regional People's Representative Council of Tasikmalaya City has implemented information technology in the regional development planning process, namely the Regional Development Information System. This information system is inseparable from problems that can hinder the regional planning process. This study aims to find out how effective and efficient the use of this information system is based on the maturity level of COBIT 5. This research only focuses on the domains EDM05, APO03, APO07, BAI09, DSS01, and MEA03. Data collection techniques are carried out through observation, interviews, and the dissemination of questionnaires. Tasikmalaya Regional Representative Council’s has implemented IT governance at level 3, namely the Established Process. The results of the questionnaire processing obtained an average value of 3. 04 from a value scale of 0 to 5. The results showed weaknesses in the governance of the regional development planning information system found in the APO07 sub-domain which has the lowest maturity level value from other sub-domains, namely 1. 86.

IMPLEMENTATION OF WEIGHTED PRODUCT METHOD IN DETERMINING SELECTION THE BEST MUSIC STREAMING SERVICE APPLICATION

Lilyani Asri Utami — 2023-03-16

At this time, the music streaming service is a platform that is often easily found on every device, either through downloads from the Playstore and Appstore or the default application from the device itself. Many companies in the world are competing to create platforms and applications that provide the most complete songs. For example, several well-known music streaming service applications in Indonesia have their own innovations and characteristics, such as Spotify, Joox, Youtube Music, Apple Music, SoundCloud, and so on. This causes users to have difficulties because of several considerations in deciding how to use the application according to their needs. This study aims to assist in providing solutions to music streaming service subscribers by recommending several music streaming service applications according to the ranking results, which are the best choice for the user version of the application through a Decision Support System using the Weighted Product method based on 5 criteria: subscription rates, available features, streaming quality, music, application design, and application efficiency. The final result of this study is the ranking of applications that have the highest score in accordance with the criteria provided, namely that in first place with a value of 0.415 is Spotify as a recommendation for the best music streaming service application, and Apple Music ranks last out of the 6 alternatives that have been provided.

ANALYSIS OF GOODS MANAGEMENT SYSTEM IN THE COMMUNICATION AND INFORMATICS DEPARTMENT OF SERDANG BEDAGAI DISTRICT

Cut Try Utari — 2023-03-28

The current problem is that the Serdang Bedagai district communication and informatics office is experiencing difficulties in managing incoming and outgoing goods. Management is currently carried out manually and cannot be viewed online so that many errors occur, one of which is a mismatch between the stock of goods recorded and the physical stock of existing goods. The goods management system that will be built in this study uses the waterfall model and PHP and HTML programming languages as well as CSS to design the web appearance. The system has 9 entities, namely: officer, user, sender, person in charge, goods, recipient, detail_recipient, expenditure and data_dinas. The results of the implementation of the proposed system are more optimal management of goods and help the performance of the warehouse admin in making real-time stock update reports and borrowing goods

COMPARISON ANALYSIS OF BANDWIDTH SPEED USING MIKROTIK ROUTERBOARD 750

Ericky Benna Perolihin Manurung — 2023-03-31

The purpose of this study is to analyze and optimize bandwidth management at aminet cafes which often experience bandwidth leakage problems where users can access the internet without any bandwidth restrictions. Bandwidth management in this study uses a proxy and Queue Tree with the Network Development Life Cycle (NDLC) system development method. The results of the study show that bandwidth management runs optimally with balanced upload and download speeds for each user because the bandwidth distribution process has been carried out. The average upload speed is 121 kbps and the download speed is 732kbps.