Article Per Year (5 Year)
p-Index From 2021 - 2026
2.255
P-Index
This Author published in this journals
All Journal Nuansa Informatika JEJARING Buffer Informatika Empowerment : Jurnal Pengabdian Masyarakat Jurnal Computer Science and Information Technology (CoSciTech) Algoritme Jurnal Mahasiswa Teknik Informatika Nuansa Informatika Buffer Informatika Indonesian Journal of Accounting and Governance
Iwan Lesmana
FKOM UNIKU
Computer Science & IT Economics, Econometrics & Finance Education Law, Crime, Criminology & Criminal Justice Social Sciences

Published : 21 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 21 Documents
Search

 1   2   3 
Implementasi Convolutional Neural Network (CNN) untuk Sistem Presensi Mahasiswa Berbasis Pengenalan Wajah Yusuf, Fahmi; Iwan Lesmana; Hegar Paningkat Bagja
Buffer Informatika Vol. 11 No. 1 (2025): Buffer Informatika
Publisher : Department of Informatics Engineering, Faculty of Computer Science, University of Kuningan, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sistem presensi sangat banyak digunakan di sekolah-sekolah, universitas-universitas maupun perusahaan-perusahaan. Kehadiran atau presensi sangat penting dalam proses pembelajaran dan proses akademik di Fakultas Ilmu Komputer Universitas Kuningan. Sistem Presensi yang digunakan Fakultas Ilmu Komputer Universitas Kuningan masih menggunakan metode konvensional yaitu melalui lembar atau sheet dalam bentuk hard copy yang kemudian di tanda tangani dan dikumpulkan kembali setelah ditanda tangani. Permasalahan dan kekurangan dari sistem absensi melalui metode konvensioanal seperti membutuhkan waktu yang cukup lama dalam merekap data presensi mahasiswa ke sistem akademik, adanya manipulasi tanda-tangan yang dilakukan mahasiswa dan lainnya. Hal itu membuat teknologi face recognition dapat diterapkan untuk masalah tersebut. Convolutional Neural Network (CNN) merupakan pengembangan dari metode Multi-layer Perceptron (MLP) yang didesain untuk proses pengolahan data dua dimensi. Dengan model pengembangan yaitu prototype, yang dapat digunakan untuk memperjelas spesifikasi kebutuhan user berkomunikasi dan memberikan informasi yang terdiri dari mendengarkan pelanggan atau analisa kebutuhan, membuat rancangan (mockup) dan pengujian rancangan. Hasil dari identifikasi dari citra wajah menghasilkan output berupa deskripsi fitur yang merepresentasikan karakteristik dari wajah yang teridentifikasi, kemudian deskripsi fitur wajah tersebut dibandingkan dengan deskripsi fitur wajah dari database untuk pencocokan. Dimana hasil akurasi dan validasi model dengan pengujian K-Fold sebesar 92%.
Implementasi CNN untuk identifikasi penyakit daun jagung Gumelar, Gilang; Tito Sugiharto; Iwan Lesmana
Computer Science and Information Technology Vol 6 No 2 (2025): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v6i2.9462

Abstract

Maize is an important commodity in Indonesia's agricultural sector. However, disease attacks on the leaves can reduce the quality and quantity of the harvest. At SMK Negeri 1 Kuningan, disease identification is still done manually, so there is a risk of errors. This research aims to design and build an Android application to automatically detect corn leaf diseases using the Convolutional Neural Network (CNN) algorithm. The development method used is Rapid Application Development (RAD), with a CNN model based on MobileNetV2 architecture trained using a dataset of diseased and healthy corn leaf images. Evaluation using test images resulted in an accuracy of 96.2%. The model was able to detect five categories: leaf spot, downy mildew, leaf blight, leaf rust, and healthy leaves. The F1-Score is 94% Leaf Spot, 96% Leaf Blight, 96% Healthy Leaf, 97% Leaf Blight, and 96% Leaf Rust, respectively. The precision and recall values of all classes are above 94%. These results show that the integration of CNN in mobile applications is effective in helping the automatic identification of corn leaf diseases in an educational environment.
KLASIFIKASI JENIS TANAMAN PHILODENDRON BERDASARKAN CITRA DAUN MENGGUNAKAN ALGORITMA CNN Alif, Muhammad Alif Fathan; Tito Sugiharto; Iwan Lesmana
Computer Science and Information Technology Vol 6 No 2 (2025): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v6i2.9484

Abstract

Accurate identification of ornamental plants is becoming important as public interest in tropical plant collections increases, one of which is from the Philodendron genus. This ornamental plant has many varieties that are often difficult to distinguish due to visual similarities in the shape and pattern of their leaves. This research aims to develop a system for Philodendron type classification based on leaf images using the Convolutional Neural Network (CNN) algorithm to help the identification process. The method used is with a dataset of 5000 leaf images of five Philodendron species, which are divided into 80% training data, 10% validation data, and 10% test data. A CNN model with MobileNetV2 FPNLite SSD architecture was implemented and trained for 50,000 steps, then optimised for mobile devices using TensorFlow Lite. Performance analysis was conducted using confusion matrix to evaluate accuracy, precision, recall, and F1-Score metrics. The results show that the developed model is able to accurately classify leaf images, both in the form of static images and in real-time. This system has been successfully implemented in an Android application that is expected to be a practical identification tool for general users and ornamental plant enthusiasts.
ANALYSIS OF JOINT COST ALLOCATION IN DETERMINING COST OF GOODS PRODUCTION Sugiarto, Lawberto; Handayani, Sri; Bintara, dheny; Lesmana, Iwan
Indonesian Journal of Accounting and Governance Vol. 8 No. 1 (2024): JUNE
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/sr7r9583

Abstract

This scientific research paper aims to provide a detailed understanding of joint cost analysis using the 4(four) methods: physical, sales value at split-off point, net realizable value and constant-gross matgin method. This is research aims to provide information for cake store X on how to manage the costs of production, and to improve the management strategies, for it is known that the store uses the simplest recording of accounting which records only the purchase of inventory while deducting it from the sales of finished goods to determine the profit for the year. The results from this research is the most effective joint cost allocation method for cake shop X is the physical method because it is easy to implement.
THE IMPACT OF CLAIM EXPENSES, UNDERWRITING RISK, PROFITABILITY, COMPANY SIZE AND RETENTION RATIO ON SOLVENCY OF INSURANCE INDUSTRY Sutanto, Shelby; Lesmana, Iwan; Sitardja, Meco; Bintara, dheny
Indonesian Journal of Accounting and Governance Vol. 7 No. 2 (2023): DECEMBER
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/r4xd3j64

Abstract

The main purpose of this research is to analyze Claim Expenses, Underwriting Risk, Profitability, Company Size, and Retention Ratio on Solvency of Insurance Industry. The purpose of this research is to help future investors in choosing the right insurance company. This research was a quantitative descriptive research method. The sample used in this research is secondary data of Insurance Industry on the period from 2015 to 2020. Using SPSS (statistical package for the social sciences), methods of analysis used in this study include tolerance and VIF test, Kolmogorov-Smirnov test, multivariate cointegration tests: Test, SRESID and ZPRED estimation, t-statistical tests, F-statistical test, coefficient of determination (R²), and Pearson Correlation Product Moment.The result of this research shows claim expense, underwriting risk, ROA, and company size have significant influence on insurance industry’s solvency, but retention ratio has no significant influence on insurance industry’s solvency. All the independent variables simultaneously from a good model to explain the solvency since the magnitude of the effect value is 83,4%, while remaining 16,6% is explained by other variables besides claim expense, underwriting risk, ROA, company size, and retention ratio. The linear regression produced a formula to calculate the solvency, so this formula could be used in monitoring the financial health of an insurance company.
RISIKO OPERASIONAL BANK DAN PERMODELANNYA Lesmana, Iwan
Indonesian Journal of Accounting and Governance Vol. 1 No. 1 (2017): JUNE
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/54xhtb25

Abstract

Managing bank’s operational risks becoming an important feature of sound risk management practice in modern financial markets. The most important types of operational risk involve breakdown in internal controls and corporate governance, which could lead to financial losses through fraud, error or failure to perform. Development of statistic has accelarated banks to create internal operational risk models in different ways. Although those models created in different ways, they surely use the pattern of risk management that is developed by Basel Committee on Banking Supervision. Basel Committee on Banking Supervision has proposed three increasingly sophisticated approaches of operational risk, i.e basic indicator approach, standardized approach and advanced measurement approach. Applying those approaches will help banks to eliminate the operational risk, that will lead them to a better intermediation process.
FAKTOR MOTIVASI DAN INDIKATOR EKONOMI DALAM UJI KELAYAKAN JUSTICE COLLABORATOR Lesmana, Iwan; Biantara, Dheny; Sitardja, Meco
Indonesian Journal of Accounting and Governance Vol. 5 No. 1 (2021): JUNE
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/2m06aa19

Abstract

The purpose of this observation is to find the indicator of a person will meet the offering of being a justice collaborator. The population of this observation are the cases of person who is being suspected or accused by Komisi Pemberantasan Korupsi (KPK) commiting corruption in Indonesia. Participants for this study were sampled using the random sampling cases in observation, theory and the rules of law. Datas amd informations that were used for this observation were obtained through secondary data from cases in KPK’s website and the result of the previous research in motivation. Observation’s result indicates that age, education, experience, salary, job title and spiritual capital drive someone to be motivated. These factors do not act separately, but they are a part of mutually connected network of specific relations. Employee level of motivation and employee performance can be influenced by means of their detailed knowledge, esperience, maturity of thought and spiritual aspect. Economic indicators that were represented by the value of loss, value of gratification and the punishment charge can be considered in valuing somenone feasible become a justice collaborator. The final results of this observation are factors that affect motivation and economic indicators in court session might be used in measuring that someone would become a justice collaborator.
FAKTOR-FAKTOR YANG MEMPENGARUHI PERTUMBUHAN VOLUME TRANSAKSI SAHAM Virginia, Chyntia Augustia; Lesmana, Iwan; Rumondang, Safrida
Indonesian Journal of Accounting and Governance Vol. 6 No. 1 (2022): JUNE
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/1cfv4t33

Abstract

This research aims to analyze factors that affect the growth in share transaction volume. Thevariables in this study are share price growth, earning per share (EPS), return on equity (ROE), anddebt to equity ratio (DER). The sample used in this research is secondary data of trading volume stockin Indonesia Stock Exchange on the period from 2016 to 2019. Using SPSS (statistical package for thesocial sciences), methods of analysis used in this study include tolerance and VIF test, Kolmogorov-Smirnov test, multivariate cointegration tests: Test, SRESID and ZPRED estimation, PearsonCorrelation Product Moment, t- statistical tests, F-statistical test, and coefficient of determination (R2).The result of this research show that earning per share (EPS), return on equity (ROE), have significantinfluence on the growth in share transaction volume, but price growth and debt to equity ratio (DER)have no significant influence on the growth in share transaction volume. All the independent variablessimultaneously from a good model to explain the growth in stock transaction volume since themagnitude of the effect value is 99.1%, while 0.9% is explained by other variables besides the growthof stock prices, earnings per share (EPS), return on equity (ROE), and debt to equity ratio. (DER).
ANALISIS PERAN REGULATOR DAN ASPEK BIAYA DALAM PENCEGAHAN PRAKTIK PREDATORY PRICING DI ECOMMERCE INDONESIA Biantara, Dheny; Margaretha, Viona; Lesmana, Iwan
Indonesian Journal of Accounting and Governance Vol. 6 No. 1 (2022): JUNE
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/tf881d52

Abstract

This study analyzes the role of regulators in Indonesia and the cost aspects that can preventpredatory pricing in an E-Commerce. Cross-border sellers who are successful in offering lower pricesin Indonesian E-Commerce bring concerns and threats to local MSMEs. The government as theregulator decided to prohibit the import of 13 product categories in the E-Commerce marketplace toanticipate unhealthy business practices. This phenomenon is also known as predatory pricing. . Theparameters used in this study are product similarity, selling price and other information that can beused to support research analysis. Grouping product categories and confirming products is a way tounderstand the phenomena that occur in data taken from the Shopee E-Commerce marketplace whichfocuses on competition between domestic sellers where there are 13 products with "overseas" locationfilters no longer found. The analysis of this study shows that all categories experience marketingpractices, and predatory pricing practices can be prevented.
IMPACT OF ENVIRONMENTAL COSTS, ENVIRONMENTAL PERFORMANCE AND ENVIRONMENTAL DISCLOSURE ON COMPANY VALUE IN BASIC MATERIALS SECTOR COMPANIES LISTED ON THE INDONESIA STOCK EXCHANGE FOR PERIOD 2017-2019 Savira, Winnie; Handayani, Sri; Rumondang, Safrida; Lesmana, Iwan
Indonesian Journal of Accounting and Governance Vol. 6 No. 2 (2022): DECEMBER
Publisher : School of Accountancy, University of Agung Podomoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36766/te5y7a45

Abstract

This study aims to determine the effect of environmental costs, environmental performanceand environmental disclosure on company value. A number of previous literatures have found asignificant positive effect of the implementation of each of the three variables on company value, butthe number of studies examining the impact of these three variables on company value is still limited,while stakeholders are straving on sustainable reporting, this research can be able to emphasize theimportance of sustainable reporting. We build this research model based on environmentalcommitment, legitimacy theory and signal theory. Data testing is done by using the regression methodin testing the effect of these three variables on company value. The results showed that environmentalcost has significant positive impact to company value, environment performance has negative notsignificant impact to company value and environmental disclosure has positive impact but notsignificant to company value. In other result for the regression model that used in this research showedthat the model can significantly predict the dependent variable.
Co-Authors Alif, Muhammad Alif Fathan Bambang Setiono Biantara, Dheny Bintara, dheny Dede Irawan Deni . Didin Lukmanudin Encep Sayid Amrulloh Fahmi Yusuf Fauzan, Farhan Gumelar, Gilang Handayani, Sri Hegar Paningkat Bagja Margaretha, Viona Nunu Nugraha Purnama, Agung Andri Tri Rasul, Muh Abi RIO ANDRIYAT KRISDIAWAN Rohmawati, Lutfi Rumondang, Safrida Savira, Winnie Sitardja, Meco Sugeng Supriyadi Sugiarto, Lawberto Sutanto, Shelby Tito Sugiharto Virginia, Chyntia Augustia Yati Nurhayati Yulyanto Yulyanto