Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal Jurnal Sisfokom (Sistem Informasi dan Komputer) Jurnal Komtekinfo International Journal of Technology Vocational Education and Training (IJTVET)
Riati, Itin
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Identification of Signature Authenticity Using Binary Extraction and K-nearest Neighbor Feature Methods Vidyanti, Angela Citra; Riati, Itin; Ramadhanu, Agung
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 13, No 2 (2024): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i2.2063

Abstract

This research focuses on identifying the authenticity of signatures, which is an important part of the field of biometrics. Identification of signature authenticity has wide applications, including in document security, financial transactions, and identity verification in general. The problem to be resolved is the lack of an effective and efficient method for identifying signature authenticity. The method used is the binary extraction method and the K-nearest Neighbor feature. The main contribution of this research is to propose a new approach in identifying signature authenticity by combining binary extraction methods and K-nearest Neighbor features. This approach is expected to increase the accuracy and efficiency of the signature authenticity identification process. The results of this research are the development of a new model or algorithm for identifying the authenticity of signatures. After testing and validation, the accuracy level of the results of identifying the authenticity of this signature is 75%.
Penerapan Convolutional Neural Network Untuk Mengidentifikasi Penyakit Tanaman Kelapa Sawit Riati, Itin; Yuhandri; Nurcahyo, Gunadi Widi
Jurnal KomtekInfo Vol. 11 No. 4 (2024): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v11i4.554

Abstract

Pemanfaatan teknologi dapat dikembangkan di segala bidang seperti dalam bidang perkebunan kelapa sawit. Tanaman kelapa sawit merupakan komoditas perkebunan di Indonesia yang telah berkembang dengan pesat, faktor – faktor yang mempengaruhi pertumbuhan dan produktivitas kelapa sawit harus diperhatikan seperti adanya hama dan penyakit tanaman kelapa sawit. kecerdasan buatan merupakan teknologi masa kini yang konsepnya memindahkan kecerdasan manusia ke dalam mesin. Terdapat beberapa jenis kecerdasan buatan yang digunakan dalam pendidikan yakni Machine learning dan Deep Learning, salah satu algoritma Deep Learning yang merupakan pengembangan dari Multilayer Perceptron (MPL) yang dirancang untuk mengolah data dalam bentuk dua dimensi, misalnya gambar atau suara yaitu Convolutional Neural Network (CNN). Metode yang dapat digunakan dalam melakukan identifikasi ini yaitu Convolutional Neural Network (CNN) yang dapat memplajari objek pada pola citra. Penelitian ini bertujuan untuk meningkatkan akurasi dalam deteksi penyakit serta hama pada bibit kelapa sawit, menggunakan dataset yang terdiri dari gambar bibit yang terinfeksi dan sehat. Data yang di ambil yaitu 800 data gambar bibit kelapa sawit yang di bagi menjadi 3 kelas yaitu bagus, kulvularia sp dan antraknosa. Parameter yang diujikan pada penelitian ini yaitu hidden layer dan optimizer berpengaruh terhadap performa sistem yang berupa nilai akurasi, precision, recall, fl-score, dan loss. Pada penelitian ini didapatkan hasil terbaik dengan penggunaan empat hidden layer dan optimizer Adam didapatkan hasil akurasi sebesar 91,66%, precision, recall, fl score sebesar 90% dan loss sebesar 0,0047 serta grafik performa akurasi dan loss secara good fit. Hasil penelitian menunjukkan bahwa CNN dapat secara efektif mendeteksi berbagai jenis hama dan penyakit pada tanaman kelapa sawit dengan akurasi lebih dari 90%. penelitian ini menunjukkan potensi besar dalam pertanian modern dan dapat memfasilitasi praktik pertanian yang lebih berkelanjutan dan efisien.
DECISION SUPPORT SYSTEM FOR SELECTING THE BEST LECTURER USING THE WEIGHTED PRODUCT METHOD: SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN DOSEN TERBAIK MENGGUNAKAN METODE WEIGHTED PRODUCT Riati, Itin; Prima, Wahyu; Ali, Gunawan
International Journal of Technology Vocational Education and Training Vol. 4 No. 1 (2023): IJTVET Vol 4 No 1 (2023)
Publisher : Perkumpulan Doktor Indonesia Maju (PDIM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46643/ijtvet.v4i1.103

Abstract

The process of determining the best lecturers must comply with predetermined criteria. To assist in selecting a person who deserves to be the best lecturer, a decision support system is needed. One method that can be used for a decision support sys tem is using the Weighted Product (WP) method by considering the criteria and weights. This method was chosen because it is able to choose the best alternative, namely the best lecturer based on the criteria entered, then look for the weight value of eac h attribute, after the process of looking for rankings to get the best alternative, namely the best lecturer. The WP method is used in determining the best alternative or the order of importance of alternatives. The results of this study are a web -based system developed using sublime text that can be used by admins to manage lecturer data, criteria and alternatives. The system output displays the alternative order of lecturers as the best le The WP method is used in determining the best alternative or the order of importance of alternatives. The results of this study are a web-based system developed using sublime text that can be used by admins to manage lecturer data, criteria and alternatives. The system output displays the alternative order of lecturers as the best lecturer recommendations at the Universitas Dharmas Indonesia.
Identification of Signature Authenticity Using Binary Extraction and K-nearest Neighbor Feature Methods Vidyanti, Angela Citra; Riati, Itin; Ramadhanu, Agung
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 13 No. 2 (2024): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i2.2063

Abstract

This research focuses on identifying the authenticity of signatures, which is an important part of the field of biometrics. Identification of signature authenticity has wide applications, including in document security, financial transactions, and identity verification in general. The problem to be resolved is the lack of an effective and efficient method for identifying signature authenticity. The method used is the binary extraction method and the K-nearest Neighbor feature. The main contribution of this research is to propose a new approach in identifying signature authenticity by combining binary extraction methods and K-nearest Neighbor features. This approach is expected to increase the accuracy and efficiency of the signature authenticity identification process. The results of this research are the development of a new model or algorithm for identifying the authenticity of signatures. After testing and validation, the accuracy level of the results of identifying the authenticity of this signature is 75%.
Co-Authors Gunadi Widi Nurcahyo Gunawan Ali, Gunawan Prima, Wahyu Ramadhanu, Agung Vidyanti, Angela Citra Yuhandri