DIES NATALIS KE-20
UNIVERSITAS NUSA MANDIRI
"Merdeka Dalam Kemandirian"
20 Riset Terbaik Mahasiswa
1
Identifikasi Citra Beras Menggunakan Algoritma Multi-SVM Dan Neural Network Pada Segmentasi K-Means
Mahasiswa:
Ridan Nurfalah
Dosen Pembimbing:
Dr. Dwiza Riana, S.Si, MM, M.Kom
Tahun:
2021
Indonesia is a country with high rice needs because it is a staple food for more than 90% of populations. High demand requires high stock so imports are carried out in accordance with Permendagri Number 19/M-DAG/PER/3/2014 which explains rice import standards. There are many types of rice imported into Indonesia with various quality, color and import requirements such as for health or price stabilization. In terms of colors, imported white rice is the most consumed rice by Indonesians. One example is jasmine rice from Thailand. Meanwhile, in terms of imports, both for health and stabilizing the price of japonica rice (Japan) and Basmati (Pakistan) are the most imported to Indonesia. But there are still many who are not familiar with those three rices. In this research, the three types of rice were identified by comparing the Multi-SVM algorithm and Neural Network algorithm. Image acquisition is done using a flatbed scanner which produces 90 images divided into 63 training images and 27 testing images. K-Means becomes an image segmentation method and image binary converts. Feature extraction using morphological features with the regionprop method combined with the Gray Level Co-Occence Matrix (GLCM) produces 9 features that can produce 96.296% accuracy for Multi-SVM and 88.89% Neural Network
2
Segmentasi dan Pengorakan Citra Mikroskopik Pap Smear Menggunakan Algoritma K-means dan J48
Mahasiswa:
Sri Hadianti
Dosen Pembimbing:
Dr. Dwiza Riana, S.Si, MM, M.Kom
Tahun:
2021
A Pap smear is used to early detection cervical cancer. This study proposes the segmentation and analysis method of Pap smear cells images using the K-means algorithm so that cytoplasmic cells, nuclear cells, and inflammatory cells can be segmented automatically. The results of the feature analysis from the cytoplasmic, nuclear, and inflammatory cell images were classified using the J48 algorithm with 37 training data. The training resulted in an accuracy of 94.594 %, precision of 95 %, and sensitivity of 94.6 %. The classification of 24 testing images resulted in an accuracy of 91.6%, a precision of 92.5 %, and a sensitivity of 91.7 %.
3
Swietenia Mahagoni Wood Defects Segmentation Using YIQ Color Space and Thresholding
Mahasiswa:
Sri Rahayu
Jajang Jaya Purnama
Dosen Pembimbing:
Nurul Qhomariyah, M.Si.
Dr. Dwiza Riana, S.Si, MM, M.Kom
Yuni Eka Achyani, M.Kom
Fattya Ariani, M.Kom
Tahun:
2020
The biggest income from Southeast Asian countries came from timber production export activities. The potential for timber exports in Indonesia continued to increase every year. This skyrocketing potential needed to be improved by maintaining quality so that trust and good cooperation continued to be established. The quality of wood has closely related to wood defects, the faster detection of wood defects would be the faster also determines the quality of wood. Current technology has being developing rapidly to help productive human activities, image processing has being a breakthrough to be able to detect wood defects. This study aims to detect wood defects by segmenting Swietenia Mahagoni wood images by using the YIQ color space and Thresholding has resulted in a fairly good segmentation that is successful in segmenting the types of bark grown wood defects on bontos and defects in healthy knot on the body of wood with each percentage of 83.3%
4
Sentiment Analysis On E-Sports For Education Curriculum Using Naive Bayes And Support Vector Machine
Mahasiswa:
Rian Ardianto
Tri Rivanie
Yuris Alkhalifi
Fitra Septia Nugraha
Dosen Pembimbing:
Dr. Windu Gata, M.Kom
Tahun:
2020
The development of e-sports education is not just playing games, but about start making, development, marketing, research and other forms education aimed at training skills and providing knowledge in fostering character. The opinions expressed by the public can take form support, criticism and input. Very large volume of comments need to be analyzed accurately in order separate positive and negative sentiments. This research was conducted to measure opinions or separate positive and negative sentiments towards e-sports education, so that valuable information can be sought from social media. Data used in this study was obtained by crawling on social media Twitter. This study uses a classification algorithm, Naïve Bayes and Support Vector Machine. Comparison two algorithms produces predictions obtained that the Naïve Bayes algorithm with SMOTE gets accuracy value 70.32%, and AUC value 0.954. While Support Vector Machine with SMOTE gets accuracy value 66.92% and AUC value 0.832. From these results can be concluded that Naïve Bayes algorithm has a higher accuracy compared to Support Vector Machine algorithm, it can be seen that the accuracy difference between naïve Bayes and the vector machine support is 3.4%. Naïve Bayes algorithm can thus better predict the achievement of e-sports for students’ learning curriculum.
5
Analisis Kinerja Algoritma CART dan Naive Bayes Berbasis Particle Swarm Optimization (PSO) untuk Klasifikasi Kelayakan Kredit Koperasi
Mahasiswa:
Eko Arif Riyanto
Tri Juninisvianty
Doddy Ferdian Nasution
Dosen Pembimbing:
Dr. Risnandar, Ph.D.
Tahun:
2021
Credit Union have an important role especially to the small and medium society. One of the problem that credit union have is an analyzing credit manually and only based on closeness personally that can be an unexpected bad credit for credit union. Therefore, it is necessary to build a systematic calculation to give a credit for debtor. Classification technic in data mining is one of the technic that can use to classify the credit properness. The purpose of this study is to get the best method to classify the credit properness using Rapidminer by compare the calculation of CART, Naive Bayes and the optimization of CART+PSO and Naive Bayes+PSO. The study using 113 data member of credit union. From the calculation reference to the criteria of occupation, income, age, gender, loan amount, loan term, will get the best method for this study. The best method from this study is the Naive Bayes+PSO. The accuracy value obtained from this study was 96.43%, the recall value was 94.12%, and the precision value is 100%. AUC value of 0.963 indicates that this study is included in the good classification. The results of this study can be used as a consideration for the classification of the credit properness of credit union
6
Kombinasi K-NN dan Gradient Boosted Trees untuk Klasifikasi Penerima Program Bantuan Sosial
Mahasiswa:
Elly Firasari
Umi Khultsum
Monikka Nur Winnarto
Dosen Pembimbing:
Dr. Risnandar, Ph.D.
Tahun:
2020
Poverty for the Indonesian government is a problem that is difficult to solve. The efforts made by the government in overcoming poverty in Indonesia are through social assistance programs including BLT (Bantuan Langsung Tunai), PKH (Program Keluarga Harapan), Raskin (Beras Miskin), and others. In the implementation of the social assistance program when it was still very limited, the acceptance of the aid program was not on target. Data mining helps to determine decisions in predicting data in the future. Gradient Boosted Trees and K-NN are data mining methods for data classification. Each of these methods has weaknesses. Gradient Boosted Trees produce lower accuracy percentage values than the K-NN method. From these problems, a proposed method of combination of K-NN and Gradient Boosted Trees is used to improve the accuracy of the implementation of social assistance programs so that it is right on target. The K-NN, Gradient Boosted Trees, and K-NN-Gradient Boosted Trees methods are tested on the same data to get a comparison of the accuracy values. The test results prove that the combination produced a high percentage value compared to the K-NN or Gradient Boosted Trees method that is 98.17%.
7
Analysis of Sentiment of Moving a National Capital with Feature Selection Naive Bayes Algorithm and Support Vector Machine
Mahasiswa:
Faried Zamachsari
Gabriel Vangeran Saragih
Dosen Pembimbing:
Susafa’ati, M.Kom
Dr. Windu Gata, M.Kom
Tahun:
2020
The decision to move Indonesia’s capital city to East Kalimantan received mixed responses on social media. When the poverty rate is still high and the country’s finances are difficult to be a factor in disapproval of the relocation of the national capital. Twitter as one of the popular social media, is used by the public to express these opinions. How is the tendency of community responses related to the move of the National Capital and how to do public opinion sentiment analysis related to the move of the National Capital with Feature Selection Naive Bayes Algorithm and Support Vector Machine to get the highest accuracy value is the goal in this study. Sentiment analysis data will take from public opinion using Indonesian from Twitter social media tweets in a crawling manner. Search words used are #IbuKotaBaru and #PindahIbuKota. The stages of the research consisted of collecting data through social media Twitter, polarity, preprocessing consisting of the process of transform case, cleansing, tokenizing, filtering and stemming. The use of feature selection to increase the accuracy value will then enter the ratio that has been determined to be used by data testing and training. The next step is the comparison between the Support Vector Machine and Naive Bayes methods to determine which method is more accurate. In the data period above it was found 24.26% positive sentiment 75.74% negative sentiment related to the move of a new capital city. Accuracy results using Rapid Miner software, the best accuracy value of Naive Bayes with Feature Selection is at a ratio of 9:1 with an accuracy of 88.24% while the best accuracy results Support Vector Machine with Feature Selection is at a ratio of 5:5 with an accuracy of 78.77%.
8
Understanding Impact of M-banking on Individual Performance of the DeLone & McLean Method and TTF Perpective
Mahasiswa:
Qudsiah Nur Azizah
Taopik Hidayat
Dosen Pembimbing:
Dr. Dwiza Riana, S.Si, MM, M.Kom
Tino Dwiantoro, M.Kom
Suhardoyo, M.Kom
Saghifa Fitriana, M.Kom
Tahun:
2020
Currently the public has a curiosity about e-commerce applications that are growing rapidly, such as Mobile banking (m-banking). The development of m-banking can be seen from user satisfaction, end-user interest and the success of everyone using m-banking. This study adds the Task Technology Fit (TTF) model to the DeLone & McLean model for the purpose of knowing the success of individuals using m-banking. We used 102 respondents to answer all the questions in the questionnaire. The results show that of the 14 hypotheses used there were 8 accepted hypotheses. This shows that in individual achievement, usage and user satisfaction are not important. Users consider the importance of individual performance to simplify the use of TTF. User satisfaction is influenced by system quality, information quality, and service quality
9
Sentiment Analysis of Online Transportation Service using the Naïve Bayes Methods
Mahasiswa:
M Tika Adilah
Dosen Pembimbing:
Hendra Supendar, M.Kom
Rahayu Ningsih, M.Kom
Sri Muryani, M.Kom
Kusmayanti Solecha, M.Kom
Tahun:
2020
Sentiment analysis is a computational study of opinions and emotions expressed textually. Sentiment analysis will group text in sentences or documents to find out the opinions expressed in the sentence or document, whether negative or positive. This sentiment analysis research was conducted on the online taxi transportation service. Gojek uses a lot of social media to communicate with its customers, one of the social media used is Instagram. This research takes 1000 comments from the Instagram of the Gojek page which is used to see the public opinion of the online Gojek transportation services. Comments from the page are processed by doing text preprocessing and then classified using the Naive Bayes Classifier (NBC) method to obtain the value of the public value for online transportation services. The results of this study using the Naive Bayes method resulted in an accuracy value of 81.00%, which means that from all the comments on the Instagram page, the subject of the NBC method could be accurately classified by 81.00% whether the comments were negative or positive comments.
10
User satisfaction of covid19 Kota Bogor website using webqual 4.0
Mahasiswa:
A Andrian
S R Cakrawijaya
Dosen Pembimbing:
Dr. Dwiza Riana, S.Si, MM, M.Kom
Nicodias Palasara, M.Kom
Albert Riyandi, M.Kom
Ibnu Rusdi, M.Kom
Tahun:
2020
Nowadays E-Government has a huge impact on supporting and running governments around the world. And a government site is a tool for interacting between the government and its citizens. Recent studies have shown that the quality of the website becomes something that the government mandatory. This research examines the overall quality of the website Covid19 Bogor City. Using the Webqual methodology to assess the quality of the website and to see how the Bogor city government maintains the expectations of its citizens or users. From a three-dimensional variable that has been given by webqual and from 119 respondents as a sample of this research, the author finds that all three variables have significant results for the satisfied citizens or users with certain aspects of the facilities, contents, and menus of the website. Majority respondents who have accessed and using the website of Bogor City Covid19 satisfied with the facilities.
11
Evaluasi Metode ISO/IEC 9126 Pada Kinerja Website Sistem Informasi Akademik Perguruan Tinggi
Mahasiswa:
Muh Jamil
Surya Fajar Saputra
Muhammad Irwan Wahid
Dosen Pembimbing:
Dr. Dwiza Riana, S.Si, MM, M.Kom
Tahun:
2021
Kualitas sebuah website menjadi hal yang sangat penting untuk dipertimbangkan. Mengingat bahwa website masih menjadi salah satu teknologi yang masih banyak digunakan dalam berbagai hal. Salah satu contoh yang paling sering dijumpai adalah sistem informasi akademik perguruan tinggi yang jumlah penggunanya kian bertambah dari waktu ke waktu sehingga tentunya website sistem informasi yang ada harus memiliki kualitas dan kehandalan yang baik untuk dapat memberikan layanan yang optimal kepada penggunanya, maka dari itu penelitian ini dilakukan untuk mengevalusi website SIA Stmik Nusa Mandiri dengan menggunakan pendekatan model ISO/IEC 9126 yang dimana dalam penelitian ini lebih berfokus untuk mengukur kinerja 4 karakteristik yang terdapat pada model ISO/IEC 9126 yaitu karakteristik usability,reliability,efficiency dan portability, uji karakteristik usability dilakukan dengan alat ukur berupa angket dan kemudian diolah untuk dapat membuktikan hipotesa yang ada, untuk karakteristik reliability, efficiency dan portability digunakan sebuah tool untuk dapat mengukur dan melihat perilaku website SIA Stmik Nusa Mandiri. Dari hasil uji yang dilakukan menunjukkan hasil yang cukup memuaskan pada website SIA Stmik Nusa Mandiri dengan beberapa hal yang harus menjadi perhatian untuk optimalisasi website yang ada, sehingga hasil penelitian ini diharapkan dapat menjadi bahan evaluasi bagi pihak Stmik Nusa Mandiri kedepannya.
12
Deteksi Defect Coffee Pada Citra Tunggal Green Beans Menggunakan Metode Ensamble Decision Tree
Mahasiswa:
Ami Rahmawati
Dosen Pembimbing:
Dr. Yan Rianto, M.Eng.
Dr. Dwiza Riana, S.Si, MM, M.Kom
Tahun:
2021
Kopi merupakan salah satu komoditas minuman unggulan, sehingga permintaan biji kopi meningkat dari tahun ke tahun. Permintaan biji kopi didasarkan pada kualitas. Terdapat bebarapa faktor yang mempengaruhi kualitas antara lain bagaimana kopi ditanam dan dipanen, adapun kurangnya nutrisi dan perlindungan tanaman yang tidak memadai, maka akan menghasilkan kopi yang berkualitas rendah. Biji kopi berkualitas rendah sering kali disebut defects. Identifikasi defects coffee sangat penting khususnya bagi para petani dan pengusaha kopi agar dapat memilih biji kopi yang berkualitas tinggi sehingga meningkatkan nilai jual biji kopi. Pada beberapa industri kopi maupun makanan, teknik untuk mengidentifikasi cacat biji kopi biasa dengan cara seleksi manual dan mekanik, yang mana membutuhkan waktu yang lama dan dapat merusak biji kopi. Oleh karena itu diperlukan suatu pendekatan yang lebih modern dalam mengidentifikasi cacat biji kopi seperti pengolahan citra. Untuk itu penelitian ini bertujuan melakukan pengolahan citra berupa segmentasi pada citra green beans coffee menggunakan metode thresholding. Setelah itu dilakukan analisis tekstur menggunakan GLCM (Grey Level Co-occurence Matrix) dan dilanjutkan dengan pemodelan klasifikasi menggunakan algoritma C4.5 dengan bagging. Dari hasil penelitian yang diperoleh, akurasi dari penggunaan algoritma C4.5 dengan bagging sebesar 94%.
13
Twitter Sentiment Analysis Of Post Natural Disasters Using Comparative Classification Algorithm Support Vector Machine And Naïve Bayes
Mahasiswa:
Ainun Zumarniansyah
Rangga Pebrianto
Dosen Pembimbing:
Normah, M.Kom
Dr. Windu Gata, M.Kom
Tahun:
2020
Natural disasters trigger people, especially Twitter users to provide information or opinions in the form of tweets. The Tweet can be an expression of sadness, concern, or complaint. Processing of data from these tweets will create trends that can be used for information needs such as education, economics, and others. Natural disasters are events that threaten human life caused by nature, including in the form of earthquakes. The method used is the Support Vector Machine and Naive Bayes from the tweet. The data collected is filtered from tweets by deleting duplicate data. In calculating the Natural Disaster sentiment analysis using a comparison of the Support Vector Machine and the Naive Bayes algorithm, the difference in accuracy is 3.07% where the results of the Support Vector Machine are greater than Naive Bayes. The purpose of this research is to analyze sentiment for the distribution of disaster aid that does not flow information due to information & coordination in the field. so as to provide information on the location of natural disasters, natural disaster management, and its presentation to victims that can be shared evenly in an efficient time due to information and natural management so that the distribution of aid is hampered
14
Classification Of The Prospects For City Trees Life Expectancy Using Naive Bayes Method
Mahasiswa:
Muhammad Rifqi Firdaus
Abdul Latif
Dosen Pembimbing:
Ipin Sugiyarto, M.Kom
Dr. Windu Gata, M.Kom
Tahun:
2020
Besides the city is a large and extensive residential area. as a center for the activities of its citizens, both from economic, cultural, and development activities. Development in the city leads to the physical development of the city with the many facilities and infrastructure in the city, making activities in the city cause some pollution problems. To overcome this problem, the government often creates green open space in the middle of the city. Planting shade trees will help to balance the problem of pollution due to development. Trees can reduce temperatures, in addition to absorbing air and climate pollution. trees can help save energy. Naive Bayes is a classification with probability and statistical methods, namely predicting future opportunities based on experience based on the assumption of simplification that attribute values are conditionally free if given an output value. Data processing with Naive Bayes produces a Precision value of 0.840%, a recall value of 0.848%, and an AUC of 0.873%. These results indicate that the results are included in the excellent category.
15
Classification Of Liver Disease By Applying Random Forest Algorithm And Backward Elimination
Mahasiswa:
Irwan Herliawan
Muhammad Iqbal
Jajang Jaya Purnama
Dosen Pembimbing:
Dr. Windu Gata, M.Kom
Achmad Rifai, M.Kom
Tahun:
2020
Cancer is a type of disease that is not realized by most people because most people associated with this disease lack understanding of cancer itself and are doing early detection of cancer, due to the majority of cancers found at an advanced stage and difficult to overcome to facilitate large expenditure to help cancer. Early detection of liver or liver cancer is very important to overcome the very high risk of death caused by liver or liver cancer. This study aims to help classify liver or liver cancer based on data from routine examination results of patients summarized in the Indian Liver Data Patient (ILDP) dataset. The method used in the classification process in this research is backward elimination modeling for testing optimization and Random Forest algorithm and split validation to validate the model. The results of this study yielded 76.00% and value of AUC 0.758 results. These results indicate that the results of this study are good enough to help classify breast cancer
16
Integrasi Metode Decision Tree dan SMOTE untuk Klasifikasi Data Kecelakaan Lalu Lintas
Mahasiswa:
Afrilio Franseda
Wawan Kurniawan
Dosen Pembimbing:
Sita Anggraeni, M.Kom
Dr. Windu Gata, M.Kom
Tahun:
2020
Kecelakaan lalu lintas merupakan suatu peristiwa yang tidak dapat diprediksi dengan pasti dan dapat mengakibatkan korban jiwa, korban luka ringan, korban luka berat atau kerugian materil seperti benda berharga. Permasalahan ini terjadi di seluruh dunia, tidak terkecuali Australia Selatan yang merupakan salah satu wilayah di Australia. Tercatat bahwa wilayah tersebut memiliki total kecelakaan yang memakan korban 4.953 pada tahun 2018. Oleh karena itu, dibutuhkan analisis untuk mengantisipasi kecelakaan agar tidak terulang kembali kejadian dengan faktor yang sama. Salah satu solusi untuk permasalahan ini yaitu diperlukan metode klasifikasi untuk mengelompokkan faktor-faktor yang mempengaruhi kecelakaan lalu lintas. Metode klasifikasi yang digunakan sebagai pengolah data adalah metode Decision Tree. Metode pada permasalahan ketidakseimbangan kelas menggunakan metode Synthetic MinorityOver-sampling Technique (SMOTE). Untuk proses dalam meningkatkan evaluasi pada penelitian ini menggunakan proses Knowledge Discovery in Database (KDD). Pengujian dilakukan dengan tiga desain model yaitu Split Validation Decision Tree dan SMOTE diperoleh akurasi 69.23%. Pengujian menggunakan Cross Validation Decision Tree dan SMOTE diperoleh akurasi 63.56%. Pengujian menggunakan Decision Tree dan SMOTE Split Data diperoleh akurasi 71.12% dengan perbandingan 1:9. Sehingga, setelah ketiga desain model tersebut dibandingkan, maka Decision Tree dan SMOTE Split Data mendapatkan akurasi yang paling baik. Selain itu diperoleh pula presisi 89.71% (3:7) dan area under curve (AUC) sebesar 0.773 (1:9). Penelitian ini masuk kedalam kategori fair classification (cukup)
17
Identifikasi dan Recovery File JPEG dengan Metode Signature-Based Carving dalam Model Automata
Mahasiswa:
Ardiansyah
Nila Hardi
Dosen Pembimbing:
Dr. Windu Gata, M.Kom
Tahun:
2020
The use of JPEG image formats is increasing along with the increase in digital photo production triggered by the emergence of smartphones and the development of social media. Even in 2017 it is predicted that each person will produce 1,600 digital photos in one year. This makes JPEG files play an important role in digital forensic processes so that many JPEG file identification and recovery methods are developed. This paper attempts to look at the process of identifying and recovering JPEG files with the Signature-Based Carving method, the simplest carving method, with a Finite State Automata (FSA) diagram model, a basic algorithm model in computational theory. The FSA model that was created was then tested using data in the form of a disk image made publicly available from DigitalCorpora.org. The result is that the FSA model can identify and recover JPEG files with the Signature-Based Carving method with certain terms and conditions, including unfragmented, full headers and footers, and no thumbnail or embedded JPEG files in the JPEG file.
18
Komparasi Algoritma Klasifikasi untuk Prediksi Minat Sekolah Tinggi Pelajar pada Students Alcohol Consumption
Mahasiswa:
M. Rangga Ramadhan Saelan
Deni Anugrah Sahputra
Widiastuti
Dosen Pembimbing:
Dr. Windu Gata, M.Kom
Tahun:
2020
Terdapat banyak faktor yang menjadi kriteria penentu kinerja pelajar salah satu diantaranya adalah konsumsi alkohol oleh pelajar, hal ini dapat mempengaruhi pengambilan keputusan negatif yang menjadi faktor keberhasilan kinerja pelajar. Pada penelitian ini digunakan teknik klasifikasi untuk memprediksi minat pelajar dalam mengambil Langkah untuk melanjutkan pendidikan ke jenjang yang lebih tinggi yang dipengaruhi oleh berbagai faktor, salah satunya adalah tingkat konsumsi alkohol oleh pelajar. Dengan membuat model menggunakan algoritma klasifikasi Nae Bayes dan Decision Tree yang diujikan pada data konsumsi alkohol oleh pelajar menggunakan tools Rapid Miner. Kemudian model yang dihasilkan dikomparasi untuk menentukan algoritma terbaik dalam mengidentifikasi kinerja pelajar. Dengan menggunakan Teknik Cross Validation didapatkan statistik yang menunjukan bahwa Algoritma Decision Tree memiliki kinerja lebih baik jika diabandingkan dengan Nae Bayes. Algoritma Decision Tree memiliki tingkat akurasi sebesar 86.44% sedangkan Nae Bayes hanya memiliki tingkat akurasi sebesar 82.60%. Dan berdasarkan statistic ROC, bisa dikatakan bahwa Nae Bayes memiliki kinerja yang cukup buruk dengan tingkat Equal Error Rate (EER) sebesar 65%, sedangkan Decision Tree memiliki tingkat EER lebih rendah yaitu sebesar 55%. Dengan begitu algoritma Decision Tree memiliki kinerja lebih baik dalam mengidentifikasi kinerja pelajar dengan pengaruh berbagai faktor salah satunya alkohol.
19
Analisa Asosiasi Data Mining Penjualan Meubel Menggunakan Algoritma Apriori Pada Master Borneo Pontianak Selatan
Mahasiswa:
Rabiatus
Badariatul Lailiah
Muhammad Ifan Rifani Ihsan
Dosen Pembimbing:
Dr. Windu Gata, M.Kom
Tahun:
2020
Dunia bisnis khususnya dalam industri penjualan dimana-mana tidak di ambil kemungkinan banyak resiko yang di hadapi pembisnis untuk bisa melangsungkan usaha yang telah di dirikan akan selalu ada dan mendapatkan konsumen yang tetap membeli barang yang telah disediakan maka dari itu seorang entrepreneur dituntut untuk memiliki strategi dalam membaca peluang. Untuk menyiasati hal tersebut, tentunya pihak manajemen harus mampu menganalisa data yang ada untuk dijadikan bahan acuan untuk strategi diperlukan untuk komputerisasi. Pencarian judul penelitian dan abstraknya dipermudah dengan kata-kata kunci tersebut. berbisnis selanjutnya. Meubel Master borneo merupakan salah satu perusahaan yang memiliki resiko mendapatkan konsumen yang tetap dan harus memberikan atau meyediakan barang yang memiiki kualitas tinggi dan memberikan pelayanan yang akan diberikan kepada pelanggan yang setia membeli produk yang telah disediakan. Dengan menggunakan data mining yang merupakan knowledge discovery dikarenakan bidang yang berupaya untuk menemukan informasi yang memiliki arti yang berguna dari jumlah data yang besar, untuk menemukan pola (pattern) data dan memprediksi kelakuan (trend) dimasa mendatang [7]. Untuk mengetahui produk yang sering terjual dalam periode bulan Januari sampai bulan Mei 2019 diperlukan algoritma apriori yang ada di data mining. Dengan melakukan analisa keranjang belanja menggunakan metode asosiasi dengan Algoritma Apriori, dimana kombinasi itemset transaksi penjualan barang pada meubel master borneo menghasilkan 6 rules dimana minimum confidence sebesar 41,6 % dan minimum support sebesar 0,08% berdasarkan 35 transaksi penjualan dari 63 jenis barang pada meubel Master Borneo.
20
Penerapan Algoritma Random Forest dengan Kombinasi Ekstraksi Fitur Untuk Klasifikasi Penyakit Daun Tomat
Mahasiswa:
Umi Khultsum
Dosen Pembimbing:
Dr. Agus Subekti, S.T., M.T.
Tahun:
2021
The tomato plant is widely consumed by the community and is widely cultivated by farmers. Tomato plants are susceptible to disease attacks. Plant diseases cause a decrease in the quality and quantity of crops or agricultural produce. The idea of the 4.0 agricultural revolution emerged as a result of the 4.0 industrial revolution. Farmers are not ready to face increasingly rapid technological advances. It is important to identify the disease in tomato leaves correctly in the efficiency of disease management for efforts to control so that disease in tomato leaves does not develop. The main objective of the proposed method is to develop a technique for identifying foliar diseases in tomato plants by increasing the classification accuracy. The novelty of this research is a combination of several feature extractions to improve classification accuracy. The features used are the color feature, the Hu-Moment feature, and the firur haralick. In the classification process, the Random Forest algorithm and other classification algorithms are applied for comparison. In this study, the Random Forest method and the combination of extraction features have shown an increase in accuracy, the accuracy obtained is 96%.
Share YUK !
Copyright © 2021 - Universitas Nusa Mandiri