Claim Missing Document
Check
Articles

Found 7 Documents
Search

Analisis Index Vegetation Wilayah Terdampak Kebakaran Hutan Riau Menggunakan Citra Landsat-8 dan Sentinel-2 Risna Sari; Liana Trihardianingsih; Rizki Firdaus Mulya; M. Ilham Arief; Kusrini Kusrini
CogITo Smart Journal Vol. 8 No. 2 (2022): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v8i2.439.282-294

Abstract

Kebakaran hutan telah diidentifikasi sebagai salah satu isu lingkungan utama yang memiliki dampak terhadap keanekaragaman hayati dan iklim global jangka panjang. Riau merupakan salah satu wilayah di Indonesia yang sering mengalami kebakaran hutan. Upaya untuk memulihkan hutan pasca kebakaran dapat dilakukan dengan pengawasan lahan seperti mengamati tingkat vegetasi pada kawasan kebakaran. Dalam penelitian ini, dilakukan analisis untuk mengklasifikasikan tingkat vegetasi kawasan pasca kebakaran dengan memanfaatkan indeks vegetasi dengan tujuan mengetahui tingkat vegetasi pasca kebakaran pada wilayah rawan kebakaran di kabupaten Riau. Model yang digunakan pada penelitian ini memakai algoritma Random Forest dan variabel penentu yang digunakan adalah NDVI, NBR, EVI, dan SAVI. Penelitian ini dilakukan dengan menggunakan 2 citra satelit, yaitu Citra Landsat 8 dan Sentinel-2. Dasaset yang didapatkan menggunakan landsat-8 adalah 1871 data, sedangkan dengan menggunakan sentinel-2 diperoleh 606 data. Akurasi data testing maksimal yang diperoleh dengan menggunakan landsat-8 adalah sebesar 99%, sedangkan dengan menggunakan sentinel-2, diperoleh akurasi maksimal sebesar 94%.
Analysis Of The Implementation Of Web-Based Customer Relationship Management In Optimizing SME Services In Indonesia Liana Trihardianingsih; Hanifah Permatasari
Proceeding of International Conference on Science, Health, And Technology 2021: Proceeding of the 2nd International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (401.365 KB) | DOI: 10.47701/icohetech.v1i1.1117

Abstract

Customer Relationship Management (CRM) is a fundamental and important business strategy for a company. Including one of them for Micro, Small and Medium Enterprises (SMEs) in Indonesia, which is increasingly active. The purpose of this study is to analyze the application of website-based CRM for SMEs in improving and helping service optimization. Optimization of this service discount sense that a company can not only optimize when a business process is going, but also how the service can continue to operate optimally after all transactions have been resolved. The study used a qualitative descriptive analysis that relied on sources from literature studies. Several scientific articles discussing the application of CRM in the Indonesian SME sector have been collected for analysis. It is used to discover usage facts, the modules used, and how SMEs can maximize services using the tools. Results from this study is there some CRM services are popular among SMEs and always to continue optimized functionality. This is supported CRM capabilities in facilitating the interaction between consumers and businesses when the business process occurs. All information, data, and services can be processed more easily and quickly with based websites. The existence of this web based CRM makes SMEs can improve the services provided which have an impact on customer satisfaction and loyalty efficiently.
Systematic Literature Review of Trend and Characteristic Agile Model Liana Trihardianingsih; Maie Istighosah; Ariel Yonatan Alin; Muhammad Ryandy Ghonim Asgar
JURNAL TEKNIK INFORMATIKA Vol 16, No 1 (2023): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v16i1.28995

Abstract

Agile is a methodology and engineering approach for software development that encourages change in collaboration through tasks carried out at various stages of the software development life cycle. Scaled Agile Framework, Kanban, Scrum, Lean, Extreme Programming, Crystal, Dynamic System Development Method, and Feature Driven Development are a few of the approaches that go along with agile. Each of these approaches has distinct traits and qualities of its own. Every engineer and researcher needs to be aware of the benefits and characteristics of each method before deciding to use one. In order to assist engineers and researchers who will use one of these methods, this research will analyze it. The method used in this paper is a systematic literature review, which involved at 52 papers published in the previous eight years, from 2018 to 2022. This method is carried out by determining research questions, determining library initiation and selection, determining inclusion and exclusion criteria, and finally performing data extraction. This essay seeks to establish: (i) Study trends on each agile technique from 2018 to 2022 and (ii) Each agile method's characteristics. The results of this literature review indicate that Scrum and Extreme Programming have overtaken other agile methodologies as the most popular agile techniques over the last eight years. Through an analysis of the characteristics of each methodology, namely the development approach, suggested iteration time period, team communication, project size, project documentation, design, workflow approach, project coordinator, role assignment, coding, testing, and the nature of customer interaction, it is found that Scrum and Extreme Programming do have several advantages over other methodologies.
Classification of Tea Leaf Diseases Based on ResNet-50 and Inception V3 Trihardianingsih, Liana; Sunyoto, Andi; Tonny Hidayat
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 3 (2023): Article Research Volume 7 Issue 3, July 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i3.12604

Abstract

Technological advances have made a major contribution to controlling plant diseases. One method for resolving issues with plant disease identification is the use of deep learning for digital image processing. Tea leaf disease is a plant disease that requires fast and effective control. So, in this study, we adopted the Convolutional Neural Network (CNN) architectures, namely ResNet-50 and Inception V3, to classify six types of diseases that attack leaves. The amount of data used was 5867, which were divided into six classes, namely healthy leaf, algal spot, brown blight, gray blight, helopeltis, and red spot. The process of distributing the data involves randomly splitting it into three portions, with an allocation of 80% for training, 10% for validation, and 10% for testing. The process of classification is carried out by adjusting the use of batch sizes in the training process to maximizehyperparameters. The batch sizes used are 16, 32, and 64. Using three different batch size scenarios for each model, it shows that ResNet-50 has better performance on batch size 32 with an accuracy value of 97.44%, while Inception V3 has the best performance on batch size 64 with an accuracy of 97.62%..
PENGARUH OPTIMIZER TERHADAP AKURASI KLASIFIKASI PISTACHIO MENGGUNAKAN MOBILENETV2 Liana Trihardianingsih; Hanifah Permatasari
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 7 No 2 (2025): EDISI 24
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v7i2.5571

Abstract

Inovasi teknologi di bidang pertanian berperan penting dalam meningkatkan produktivitas hasil panen serta berkontribusi pada kesejahteraan petani. Salah satu komoditas pertanian bernilai tinggi adalah kacang pistachio. Pada penelitian ini diusulkan klasifikasi jenis pistachio dengan mengambil dua varietas utama yang sering dijumpai, yaitu Kirmizi dan Siirt menggunakan model MobileNetV2. Proses pendistribusian dataset dilakukan secara acak menjadi tiga bagian train, validasi, dan testing menggunakan rasio 80:10:10. Proses klasifikasi dilakukan dengan menggunakan batch size 32, epoch 50, dan learning rate 1e-4. Untuk mengoptimalkan kinerja MobileNetV2, dilakukan pengujian menggunakan dua jenis optimizer yang berbeda, yaitu Adam dan SGD. Hasil penelitian menunjukkan bahwa penggunaan optimizer Adam pada MobileNetV2 menghasilkan akurasi yang lebih tinggi dibanding penggunaan optimizer SGD. Dengan menggunakan Adam diperoleh akurasi sebesar 96,30% sedangkan pada SGD diperoleh akurasi yang lebih rendah yaitu 91,20%. Hal ini membuktikan bahwa Adam memiliki kemampuan yang dapat menggabungkan keunggulan dari momentum dan adaptive learning rate, yang membuatnya lebih efisien dalam konvergensi serta lebih stabil dalam menemukan titik optimal sehingga memperoleh akurasi yang lebih tinggi dibanding menggunakan SGD
Optimasi Hyperparameter GridSearchCV pada Klasifikasi Kualitas Udara menggunakan Support Vector Machine Trihardianingsih, Liana; Lasatira, Gerry Santos
Jurnal Informasi dan Teknologi Vol 1 No 2 (2024): JITU: Jurnal Informasi dan Teknologi Universitas Cokroaminoto Palopo
Publisher : Universitas Cokroaminoto Palopo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30605/jitu.v1i2.65

Abstract

Kualitas udara adalah salah satu faktor kritis yang memberian dampak secara langsung pada kesehatan manusia. Zat-zat yang terkandung pada udara sangat beragam diantaranya adalah partikel halus (PM2.5 dan PM10), karbon monoksida (CO), nitrogen dioksida (NO2), dan sulfur dioksida (SO2). Semakin tinggi nilai dari kandungan-kandungan tersebut akan sangat berpengaruh terhadap kualitas udara yang dihasilkan. Data-data tersebut dapat diproses dan di olah menggunakan teknik data mining, salah satunya adalah SVM. Dalam penelitian ini, model klasifikasi data mining SVM diusulkan. Oleh karena itu, studi ini bertujuan untuk membuat model klasifikasi SVM menggunakan pendekatan baru, yang melibatkan peningkatan pemrosesan data yang memungkinkan pengaturan hyperparameter menggunakan GridSearchCV. Berdasarkan penelitian yang telah dilakukan untuk proses klasifikasi kualitas udara, kernel rbf digunakan untuk menghasilkan parameter yang paling akurat, dengan nilai C = 100 dan gamma 0.1. Sebelum optimasi, akurasi menggunakan SVM adalah 96%, presisi 97%, recall 91%, dan F1-Score 94%. Setelah optimasi, akurasi meningkat sebesar 2%, menjadi 98%. Nilai presisi, recall, dan F1-Score juga meningkat, masing-masing menjadi 97%, 96%, dan 96%, masing-masing.
E-Farm Livestock Platform Requirements Engineering Using Loucopoulos and Karakostas Iterative Process Model Liana Trihardianingsih; Maie Istighosah; Ariel Yonatan Alin; Muhammad Ryandy Ghonim Asgar
International Journal of Innovation in Enterprise System Vol. 8 No. 1 (2024): International Journal of Innovation in Enterprise System
Publisher : School of Industrial and System Engineering, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/ijies.v8i01.206

Abstract

Global human population growth has forced farms to evolve in order to produce more livestockproducts more efficiently while also paying attention to public health, environmental sustainability,and animal welfare. However, problems arise when some diseases appear to affect farm animals andlarge companies providing livestock products dominate the market. It is necessary to develop aplatform or application that can be used to solve these two problems, especially for breeders who havefarms on a small scale. This study aims to outline the process of understanding engineeringrequirements by utilizing the Loucopoulos and Karakostas Requirements Engineering Process Modelmethod, which consists of elicitation of requirements, specification of requirements, as well asvalidation and verification of requirements. The development process is carried out by hiring breedersand potential customers to determine the priority needs of the platform. The results showed that of the25 defined functional needs, there were 22 final functional needs that were validated with valuesabove 50%. The E Farm platform should be further developed based on the defined demands since atotal of 22 validated needs have been determined to be able to represent 88% of the needs required byusers.