Claim Missing Document
Check
Articles

Found 33 Documents
Search

Identifikasi Jenis Kayu Menggunakan Support Vector Machine Berbasis Data Citra Gunawan, AA Gede Rai; Nurdiati, Sri; Arkeman, Yandra
Jurnal Ilmu Komputer dan Agri-Informatika Vol 3, No 1 (2014)
Publisher : Departemen Ilmu Komputer IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1644.643 KB)

Abstract

Identifikasi jenis kayu di Indonesia pada umumnya dilakukan secara manual, dengan cara memperhatikan pori kayu pada daerah penampang kayu menggunakan kaca pembesar atau mikroskop dengan pembesaran minimal 10 kali. Teknik komputerisasi belum banyak dilakukan terutama karena kurangnya penelitian di bidang ini dan sulitnya mendapatkan database kayu. Penelitian ini bertujuan mengembangkan sebuah sistem untuk mengklasifikasikan 4 jenis kayu yang diperdagangkan di Indonesia dengan metode support vector machine (SVM) berbasis citra. Teknik ekstraksi ciri yang digunakan adalah two-dimensional principal component analysis (2D-PCA). Sistem ini dapat mengidentifikasi kayu dalam waktu singkat sehingga mempercepat proses identifikasi jenis kayu. Hasil klasifikasi dari 120 kali percobaan dengan menggunakan 96 data citra dengan 4 jenis kayu menunjukkan akurasi terbaik sebesar 95.83% pada kernel Polinomial. Kata kunci: Citra mikroskopis, Identifikasi jenis kayu, SVM
ANALISIS PEMBENTUKAN POLA GRAF PADA KALIMAT BAHASA INDONESIA MENGGUNAKAN METODE KNOWLEDGE GRAPH Yusuf, Yasin; Nurdiati, Sri; Silalahi, Paruhum
Lingua Vol 10, No 1 (2014): January 2014
Publisher : Lingua

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

Abstract

Knowledge graph adalah sebuah pendekatan baru untuk memahami bahasa alami. Metodeini memiliki 9 relasi biner dan 4 relasi frame. Analisis suatu kalimat dengan menggunakanknowledge graph membutuhkan aturan pemotongan kalimat (chunking). Aturan chunkingsudah ada pada struktur kalimat bahasa Inggris dan Cina, tetapi belum ada untuk strukturkalimat bahasa Indonesia.Tujuan dari penelitian ini adalah membentuk aturan chunkingpada struktur kalimat bahasa Indonesia dan membuat pola graf kalimat bahasaIndonesia.Tahapan penelitian ini adalah dimulai dengan studi literatur awal, pembuatanchunk indicator, pemotongan kalimat (chunking), pembuatan chunk graph, dan diakhiridengan kontruksi sentence graph. Hasil penelitian ini adalah aturan chunking kalimatbahasa Indonesia dengan indicator sebanyak 8, yaitu koma dan titik, kata ganti petunjuk,kata kerja bantu, kata depan, jump, kata-kata logika, jeda nafas, kata sambung. Selain itu,diperoleh pula pola graf kalimat bahasa Indonesia yang sekaligus menunjukkan arti(aspek semantik) dari kalimat yang dianalisis. This research aimed to construct chunking rule on Indonesian language sentencestructure and make pattern of Indonesian language sentence graph. It was done sinceknowledge graph is a new approach to understand natural language. This method has 9(nine) binary relation and 4 (four) frame relation. A sentence analysis using this approachneeds rule of sentence chunking, This research method was started from beginning ofliterary studies, chunk indicator constructing, sentence chunking, chunk graphconstructing, and sentence graph constructing. Result of this research was there was ruleof Indonesian language sentence chunking with 8 (eight) indicators such as periods, fullstops, demonstratives, auxiliary verbs, prepositions, jump, logical words, pauses,conjunctions. Besides that, it had also been achieved pattern of Indonesian languagegraph which gives meaning (semantic aspect) from analyzed sentences at once.
ANALISIS PEMBENTUKAN POLA GRAF PADA KALIMAT BAHASA INDONESIA MENGGUNAKAN METODE KNOWLEDGE GRAPH Yusuf, Yasin; Nurdiati, Sri; Silalahi, Paruhum
Lingua Vol 10, No 1 (2014): January 2014
Publisher : Lingua

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

Abstract

Knowledge graph adalah sebuah pendekatan baru untuk memahami bahasa alami. Metodeini memiliki 9 relasi biner dan 4 relasi frame. Analisis suatu kalimat dengan menggunakanknowledge graph membutuhkan aturan pemotongan kalimat (chunking). Aturan chunkingsudah ada pada struktur kalimat bahasa Inggris dan Cina, tetapi belum ada untuk strukturkalimat bahasa Indonesia.Tujuan dari penelitian ini adalah membentuk aturan chunkingpada struktur kalimat bahasa Indonesia dan membuat pola graf kalimat bahasaIndonesia.Tahapan penelitian ini adalah dimulai dengan studi literatur awal, pembuatanchunk indicator, pemotongan kalimat (chunking), pembuatan chunk graph, dan diakhiridengan kontruksi sentence graph. Hasil penelitian ini adalah aturan chunking kalimatbahasa Indonesia dengan indicator sebanyak 8, yaitu koma dan titik, kata ganti petunjuk,kata kerja bantu, kata depan, jump, kata-kata logika, jeda nafas, kata sambung. Selain itu,diperoleh pula pola graf kalimat bahasa Indonesia yang sekaligus menunjukkan arti(aspek semantik) dari kalimat yang dianalisis. This research aimed to construct chunking rule on Indonesian language sentencestructure and make pattern of Indonesian language sentence graph. It was done sinceknowledge graph is a new approach to understand natural language. This method has 9(nine) binary relation and 4 (four) frame relation. A sentence analysis using this approachneeds rule of sentence chunking, This research method was started from beginning ofliterary studies, chunk indicator constructing, sentence chunking, chunk graphconstructing, and sentence graph constructing. Result of this research was there was ruleof Indonesian language sentence chunking with 8 (eight) indicators such as periods, fullstops, demonstratives, auxiliary verbs, prepositions, jump, logical words, pauses,conjunctions. Besides that, it had also been achieved pattern of Indonesian languagegraph which gives meaning (semantic aspect) from analyzed sentences at once.
REKONSTRUKSI MODEL 3D MENGGUNAKAN FOTO UDARA UNTUK MENDUGA TINGGI OBJEK Hanief, Hafzal; Nurdiati, Sri; Suwardhi, Deni
MAJALAH ILMIAH GLOBE Vol 15, No 2 (2013)
Publisher : Badan Informasi Geospasial

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (198.921 KB) | DOI: 10.24895/MIG.2013.15-2.80

Abstract

ABSTRAKRekonstruksi 3D, terutama untuk ekstraksi tinggi menggunakan foto udara digital yang diambil dari kamera nonmetrikdan Pesawat Udara Nir Awak (PUNA) adalah studi yang menantang. Tujuan dari penelitian ini adalah: (1) untukmenentukan presisi tinggi objek yang diungkapkan dari model 3D dan menetapkan prosedur untuk memberikan hasilyang optimal. Dua atau lebih tumpang tindih foto udara dapat dibangun ke dalam model 3D dengan menerapkanprinsip-prinsip collinearity dan geometri epipolar menggunakan algoritma rekonstruksi 3D. Karena ketidakstabilankamera digital non-metrik, kamera harus dikalibrasi sebelum rekonstruksi 3D diproses, dengan cara bahwa kualitasekstraksi spasial dapat kemudian diukur. Penelitian ini dilakukan dengan menggunakan 24 megapixel Resolusi SonyNEX7 kamera digital dan Hexacopter UAV. Kamera Kalibrasi Toolbox digunakan untuk menghitung parameter intrinsikkamera dan program yang spesifik dikembangkan dengan menggunakan MATLAB dalam rangka membangun model3D dan untuk memperoleh ketinggian objek. Hasil validasi dilakukan dengan membandingkan ketinggian model 3Ddengan satu pengukuran dengan menggunakan Electronic Total Station. Keakuratan tinggi objek hingga 1 mmberhasil dicapai, dengan ketinggian kesalahan prediksi terbesar mencapai 15,2 cm pada 70 m ketinggian terbang diatas permukaan tanah.Kata Kunci : Rekonstruksi 3D, Collinearity, Geometri Epipolar, PUNA.ABSTRACTReconstruction of 3D, especially on height extraction using digital aerial photos taken from a non-metric cameraand Unmanned Aerial Vehicle (UAV) is a challenging study. The purposes of this study are: (1) to determine theprecision of an object’s height reveal from a 3D model, and (2) to establish procedures to deliver the optimal result.Two or more overlapping aerial photos can be constructed into a 3D model by applying principles of collinearity andepipolar geometry using 3D reconstruction algorithm. Since there is an instability on a non-metric digital camera, thecamera must be calibrated before 3D reconstruction is process, in that way the quality of spatial extraction, then canbe measured. The study is conducted using 24 megapixels resolution Sony NEX7 digital camera and HexacopterUAV. Camera Calibration Toolbox was utilized to calculate intrinsic parameters of the camera and a specific programis developed using MATLAB in order to build the 3D model and to obtain the object’s height. The result validation isdone by comparing the height from 3D model with that one measured using Electronic Total Station. The accuracy ofthe object’s height up to 1 mm was successfully achieved, with largest height prediction error reaches of 15.2 cm at 70m flying height above ground level.Keyword : 3D Reconstruction, Collinearity, Epipolar Geometry, UAV.
Adaptive Mixed Finite Element Method for Elliptic Problems with Concentrated Source Terms Ilyas, Muhammad; Garnadi, Agah D.; Nurdiati, Sri
Indonesian Journal of Science and Technology Vol 4, No 2 (2019): IJOST: VOLUME 4, ISSUE 2, 2019
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/ijost.v4i2.18183

Abstract

An adaptive mixed finite element method using the Lagrange multiplier technique is used to solve elliptic problems with delta Dirac source terms. The problem arises in the use of Chow-Anderssen linear functional methodology to recover coefficients locally in parameter estimation of an elliptic equation from a point-wise measurement. In this article, we used a posterior error estimator based on averaging technique as refinement indicators to produce a cycle of mesh adaptation, which is experimentally shown to capture singularity phenomena. Our numerical results showed that the adaptive refinement process successfully refines elements around the center of the source terms. The results also showed that the global error estimation is better than uniform refinement process in terms of computation time.
Spatial and Temporal Analysis of El Niño Impact on Land and Forest Fire in Kalimantan and Sumatra Sri Nurdiati; Ardhasena Sopaheluwakan; Pandu Septiawan
Agromet Vol. 35 No. 1 (2021): JUNE 2021
Publisher : PERHIMPI (Indonesian Association of Agricultural Meteorology)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/j.agromet.35.1.1-10

Abstract

Land and forest fires in Kalimantan and Sumatra, Indonesia occurred annually at different magnitude and duration. Climate and sea interaction, like El Niño, influences the severity of dry seasons preceding the fires. However, research on the influence of El Niño intensity to fire regime in Kalimantan and Sumatra is limited. Therefore, this study aims to analyze the spatial and temporal patterns of the effects of El Niño intensity on land and forest fires in fire-prone provinces in Indonesia. Here, we applied the empirical orthogonal function analysis based on singular value decomposition to determine the dominant patterns of hotspots and rainfall data that evolve spatially and temporally. For analysis, the study required the following data: fire hotspots, dry-spell, and rainfall for period 2001-2019. This study revealed that El Niño intensity had a different impacts for each province. Generally, El Niño will influence the severity of forest fire events in Indonesia. However, we found that the impact of El Niño intensity varied for Kalimantan, South Sumatra, and Riau Province. Kalimantan was the most sensitive province to the El Niño event. The duration and number of hotspots in Kalimantan increased significantly even in moderate El Niño event. This was different for South Sumatra, where the duration and number of hotspots only increased significantly when a strong El Niño event occurred.
Identification of Global Warming Contribution to the El Niño Phenomenon Using Empirical Orthogonal Function Analysis Mochamad Tito Julianto; Septian Dhimas; Ardhasena Sopaheluwakan; Sri Nurdiati; Pandu Septiawan
Agromet Vol. 35 No. 1 (2021): JUNE 2021
Publisher : PERHIMPI (Indonesian Association of Agricultural Meteorology)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/j.agromet.35.1.11-19

Abstract

Sea surface temperature (SST) is identified as one of the essential climate/ocean variables. The increased SST levels worldwide is associated with global warming which is due to excessive amounts of greenhouse gases being released into the atmosphere causing the multi-decadal tendency to warmer SST. Moreover, global warming has caused more frequent extreme El Niño Southern Oscillation (ENSO) events, which are the most dominant mode in the coupled ocean-atmosphere system on an interannual time scale. The objective of this research is to calculate the contribution of global warming to the ENSO phenomenon. SST anomalies (SSTA) variability rosed from several mechanisms with differing timescales. Therefore, the Empirical Orthogonal Function in this study was used to analyze the data of Pacific Ocean sea surface temperature anomaly. By using EOF analysis, the pattern in data such as precipitation and drought pattern can be obtained. The result of this research showed that the most dominant EOF mode reveals the time series pattern of global warming, while the second most dominant EOF mode reveals the El Niño Southern Oscillation (ENSO). The modes from this EOF method have good performance with 95.8% accuracy rate.
Pengembangan Sistem Manajemen Pengetahuan di Organisasi Asosiasi Alumni Program Beasiswa Amerika - Indonesia (ALPHA-I) Muhammad Nurwegiono; Sri Nurdiati; Sony Hartono Wijaya
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 3: Juni 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020712249

Abstract

Organisasi ALPHA-I (Asosiasi Alumni Program Beasiswa Amerika – Indonesia) memiliki anggota lebih dari 400 orang yang tersebar di sepuluh daerah di Indonesia. Jumlah alumni penerima beasiswa pendidikan dari United States Agency for International Development (USAID) akan bertambah setiap tahun dan akan tergabung di organisasi ini. Hasil observasi menunjukkan bahwa organisasi ALPHA-I memiliki dua masalah utama. Permasalahan pertama adalah ALPHA-I belum menyediakan sarana berbagi pengetahuan tacit pada lima fokus bidang beasiswa USAID. Permasalahan kedua adalah pengetahuan explicit karyawan seperti Standar Operasional Prosedur (SOP), laporan kegiatan, laporan hasil rapat, daftar mitra dan dokumen penting lainnya yang masih dibukukan. Permasalahan tersebut dapat diselesaikan dengan membuat sistem manajemen pengetahuan. Tujuan penelitian ini adalah mengembangkan sistem manajemen pengetahuan yang dapat memudahkan proses menangkap, mengembangkan, membagikan, dan memanfaatkan pengetahuan tacit alumni dan pengetahuan explicit karyawan di organisasi ini. Penelitian ini dilakukan dengan menggunakan metode Knowledge Management System Life Cycle (KMSLC). Hasil dari penelitian ini adalah sistem manajemen pengetahuan yang dibangun dengan framework PHP dan MySQL sebagai Relational Database Management System (RDBMS) berbasis website. Hasil pengujian Black box dari 36 kasus uji yang telah dilakukan menyatakan bahwa semua fungsi pada sistem berjalan sesuai dengan perintah yang diberikan. AbstractThe ALPHA-I Organization (Alumni Association of US - Indonesia Scholarship Programs) has more than 400 members that have spread in ten regions (chapters) in Indonesia. The number of alumni who receive educational scholarships from United States Agency for International Development (USAID) will increase every year and will join this organization. The result of observation to ALPHA-I organization showed that there are two main problems. The first problem is ALPHA-I organization did not provide equipment for the alumni to share their tacit knowledge on five focused areas of USAID scholarships. The second problem is the explicit knowledge of employees to record the Standard Operational Procedure (SOP), activity reports, meeting report, partner list, and other relevant documents were written by books. These problems can be solved by creating a knowledge management system. The purpose of this study is to develop a knowledge management system that can facilitate the process of creation, development, share, and utilize tacit knowledge of alumni and explicit knowledge of employees at ALPHA-I. This research was conducted using the Knowledge Management System Life Cycle (KMSLC) method. The result of this study was a knowledge management system that was built with PHP framework and MySQL-as a Relational Database Management System (RDBMS) based on website. The result of black box testing from 36 case studies demonstrated that all functions in the system run according to the commands given.
Blockchain dan Kecerdasan Buatan dalam Pertanian : Studi Literatur Fajar Delli Wihartiko; Sri Nurdiati; Agus Buono; Edi Santosa
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8 No 1: Februari 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.0814059

Abstract

Dewasa ini teknologi blockchain dan kecerdasan buatan (artificial intelligence/AI) telah diimplementasikan dalam bidang pertanian. Teknologi blockchain menjanjikan keamanan dan peningkatan kepercayaan untuk pengguna. Teknologi kecerdasan buatan menjanjikan berbagai kemudahan bagi pengguna. Perpaduan kedua teknologi tersebut dapat meningkatan kepercayaan terhadap sistem kecerdasan buatan (blockchain for AI) atau dapat juga digunakan untuk meningkatkan kinerja sistem blockchain (AI for blockchain). Tujuan penelitian ini mengulas kedua teknologi tersebut dalam studi literatur serta memberikan tantangan riset ke depan terkait implementasinya di bidang pertanian.  Metodologi yang digunakan adalah Systematic Literature Review (SLR) dan text mining. Text mining digunakan untuk memberikan deskripsi riset yang ada berdasarkan kata-kata di setiap artikel terpilih. SLR digunakan untuk memberikan ulasan yang komprehensif terkait riset Blockchain dan kecerdasan Buatan dalam pertanian. Hasil penelitian menunjukan bahwa terdapat 10 % penelitian terkait penerapan blockchain dan AI dalam pertanian. Riset tersebut memiliki potensi besar untuk berkembang terlihat dari peningkatan jumlah publikasi dalam 2 tahun terakhir. Kontribusi penelitian ini meliputi posisi riset terkini dan usulan riset ke depan dengan mempertimbangkan kondisi pertanian Indonesia. Posisi riset tersebut didominasi komunitas peneliti dari negara-negara di Asia seperti India (33%), Pakistan (33%), China (14%) dan Korea (14%). Originalitas penelitian ini terletak pada studi literatur dari integrasi teknologi blockchain dan kecerdasan buatan dalam bidang pertanian menggunakan SLR dan text mining. AbstractArtificial intelligence and blockchain technology are being developed and implemented in Agriculture. Blockchain technology promises security and trust for users. Moreover, artificial intelligence technology promises convenience for users. The combination of these two technologies will increase trust in artificial intelligence systems. Besides, this combination can also increase security on the blockchain system through the application of artificial intelligence. This paper summarizes the application of both technologies and reviews them in a systematic literature review, presents a description of articles based on text mining, and provides future research challenges related to the implementation of blockchain and artificial intelligence in agriculture. The methodologies used are Systematic Literature Review (SLR) and text mining. Text mining is used to describe a description of existing research based on the words in each selected article. SLR is used to provide a comprehensive review of Blockchain research and Artificial intelligence in agriculture. The results showed that there were 10% of research related to the application of blockchain and AI in agriculture. This research has great potential for growth as seen from the increase in the number of publications in the last 2 years. The contribution of this research includes the latest research positions and future research proposals taking into account the conditions of Indonesian agriculture. The research position is dominated by the research community from countries in Asia such as India (33%), Pakistan (33%), China (14%) and Korea (14%). The originality of this research is a literature study on the integration of blockchain and artificial intelligence in agriculture using SLR and text mining.
Strategi Peningkatan Kinerja Karyawan Taman Buah Mekarsari Rika Kusumawati; M. Syamsul Maarif; Sri Nurdiati
Jurnal Aplikasi Bisnis dan Manajemen (JABM) Vol. 5 No. 1 (2019): JABM Vol. 5 No. 1, Januari 2019
Publisher : School of Business, Bogor Agricultural University (SB-IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17358/jabm.5.1.59

Abstract

Human resources are the main element of the organization. The organization goals will be achieved when ITS employees have high performance. The purposeS of this study were to analyze the effect of competency on employee motivation, the effect of competency on employee performance, and the effect of motivation on employee performance, and to formulate strategies for improving the employee performance at Mekarsari Fruit Garden. The respondents in this study were 167 employees selected with sampling technique using stratified random sampling. Analysis of the data used in this research included descriptive analysis of respondents, Spearman correlation test methods, analysis Structural Equation Modeling (SEM) with LISREL 8.51 and Analytical Hierarchy Process (AHP) with expert choice 2000. The results showed that 1) Competency had an effect on employee motivation at Mekarsari Fruit Garden; 2) Competency had an effect on employee performance at Mekarsari Fruit Garden; 3) Motivation had an effect on employee performance at Mekarsari Fruit Garden. The first strategy to improve employee performance was improving the prosperity of employees, and the highest factor in increasing employee performance was competency. The most influential actor was the President Director of Mekarsari Fruit Garden whereas the highest score of the objective was increasing the profit of Mekarsari Fruit Garden.Keywords: performance, competency, motivation, strategies, Mekarsari Fruit GardenAbstrak: Sumber Daya Manusia (SDM) merupakan elemen utama organisasi. Tujuan organisasi akan tercapai bila pegawai di dalamnya memiliki kinerja yang tinggi. Tujuan penelitian ini adalah untuk mengalisis pengaruh kompetensi terhadap motivasi karyawan, kompetensi terhadap kinerja karyawan dan motivasi terhadap kinerja karyawan serta merumuskan strategi dalam rangka peningkatan kinerja karyawan Taman Buah Mekarsari. Responden dalam penelitian ini sebanyak 167 karyawan dengan teknik penarikan contoh menggunakan Stratified Random Sampling. Analisis data yang digunakan dalam penelitian ini meliputi analisis deskriptif responden, uji korelasi dengan metode Spearman, analisis Structural Equation Modeling (SEM) dengan LISREL 8.5, dan analytical hierarchy process (AHP) menggunakan expert choice 2000. Hasil penelitian menunjukkan bahwa: 1) Kompetensi berpengaruh terhadap motivasi karyawan Taman Buah Mekarsari; 2) Kompetensi berpengaruh terhadap kinerja karyawan Taman Buah Mekarsari; 3) Motivasi berpengaruh terhadap kinerja karyawan Taman Buah Mekarsari. Strategi pertama untuk meningkatkan kinerja karyawan adalah meningkatkan kesejahteraan karyawaan, sementara faktor tertinggi dalam hal peningkatan kinerja adalah kompetensi. Aktor yang paling berpengaruh dalam peningkatan kinerja karyawan adalah Direktur Utama, sementara skor tertinggi dari tujuan adalah meningkatkan laba Taman Buah Mekarsari.Kata kunci: kinerja, kompetensi, motivasi, strategi, taman buah mekarsari