Search

Many classification algorithms are in the form of image pattern recognition; the approach to the complexity of the problem should be a feature of feasibility for representing images. The morphology of dairy cows greatly affects their health and milk production. The paper will apply several classification methods based on the morphology of Holstein Friesian dairy cows. To improve the accuracy of the model used, the segmentation process is the right step. In this paper, we compare several machine learning algorithms to get optimal accuracy. The algorithm used a support vector machine (SVM), artificial neural networks, random forests and logistic regression. Segmentation methods used are mask region-based convolutional neural network (R-CNN) and Canny; optimal accuracy is expected to create intelligent applications. The success of the method is measured with accuracy, precision, recall, and F1 Score, as well as testing by conducting a training-testing ratio of 90:10 and 80:20. This study discovered an artificial neural network optimal model with Canny with an accuracy of 82.50%, precision of 87.00%, recall of 79.00%, F1-score of 81.62%, and testing ratio of 90:10. While the models with the highest 80:20 ratio achieved 84.39% accuracy, 88.46% precision, 80.47%, and 83.00% F1-score with mask R-CNN with logistic regression.

Computer vision deals with image-based problems, such as deep learning, classification, and object detection. This study classifies the quality of dairy parents into three, namely high, medium, and low based on morphology by focusing on Bogor Indonesia farms. The morphological images used are the side and back of dairy cows and the challenge is to determine the optimal accuracy of the model for it to be implemented into an automated system. The 2-step mask region-based convolutional neural network (mask R-CNN) and Canny segmentation algorithm were continuously used to classify the convolutional neural network (CNN) in order to obtain optimal accuracy. When testing the model using training and testing ratios of 90:10 and 80:20, it was evaluated in terms of accuracy, precision, recall, and F1-score. The results showed that the highest model produced an accuracy of 85.44%, 87.12% precision, 83.79% recall, and 84.94% F1-score. Therefore, it was concluded that the test result with 2-stages of segmentation was the best.

Health is very important for all human beings, especially in Indonesia, because human health can do activities properly and have high performance for both work and other social life. The task of predicting the future values of a time series is a problem that applications have in areas such as sales, engineering, epidemiology, etc. Much research effort has been made in the development of predictive models and performance improvement. The level of public health in Indonesia from 1995 to 2018 varied with the percentage of the population who experienced health complaints. The purpose of this study is to predict the future health of the Indonesian public so that it can be used as a tool to determine government policies in the health sector. The method used in predicting is the Recurent Neural Network (RNN) with secondary data sourced from the Central Statistics Agency (BPS) in the form of data sets, and dividing the data sets into training data and test data. Before the data is used as training data, we clean and tidy up the data first so that when it is implemented there are no errors either during training or testing. The results showed that at the beginning of the method RNN, the prediction results were far from the data, after an interval of 7 and above the predicted results were actually the same. Based on Figures 5 and 6, it can be said that the RNN method is very good for the prediction method.

Weather conditions is an air condition in a place with a relatively short time, which is expressed by the value of parameters such as temperature, wind speed, pressure, rainfall, which is another atmospheric phenomenon as the main component. Human activities can be influenced by weather conditions, such as transportation, agriculture, plantation, construction or even sports. Therefore, for determining the weather, getting weather information needs to be made so that it can be utilized by the community. Problems that arise how to make weather predictions automatically so that it can be done by everyone. In this study proposed several algorithms Navie Bayes, Decision Tree, Random Forest to calculate the opportunities of one class from each of the existing group attributes and determine which class is the most optimal, meaning that grouping can be done based on the categories that users enter in the application. The prediction system has been made to obtain an accuracy rate of Navie Bayes of 77.22% with a standard deviation of 29%, a Decision Tree accuracy rate of 79.46% with a standard deviation of 15%, a random forest accuracy rate of 82.38% with a standard deviation of 43%.

Tingkat kesejahteraan masyarakat pedesaan yang terutama jauh dari perkotaan, masih banyak ditemukan dibawah garis kemiskinan. Mengingat akar permasalahannya adalah hampir semua desa tidak mempunyai data yang benar, akurat dan tepat tentang kondisi permasalahan dan potensi desa yang dimiliki. Padahal pemerintah pusat menyalurkan anggaran tiap tahun untuk setiap desa, hampir mencapai 1 milyar pertahun. Dengan tidak memiliki data yang akurat dan benar, sehingga pembangunan tidak tepat sasaran termasuk penyaluran beras rakyat miskin (Raskin), Bantuan langsung tunai (BLT). Masih ditemukan penyaluran yang tidak tepat sasaran, sesuai dengan yang rencanakan oleh pemerintah. Dengan penelitian ini diharapkan salah cara untuk menganalisa data penduduk, baik permasalahan dan potensi yang dimiliki. Sehingga penyaluran bantuan lainya tepat sasaran. Metode pengolahan data, untuk diimplementasikan agar desa memiliki data yang benar dan akurat. Untuk seleksi fitur dalam penelitian ini menggunakan algoritma Neural Network (Jaringan syaraf tiruan), hasil accuracy algoritma penelitian ini adalah 94.96 %. Sehingga dapat digunakan sebagai referensi untuk mengolah data untuk Bantuan dari pemerintah.

Computer vision deals with image-based problems, such as deep learning, classification, and object detection. This study classifies the quality of dairy parents into three, namely high, medium, and low based on morphology by focusing on Bogor Indonesia farms. The morphological images used are the side and back of dairy cows and the challenge is to determine the optimal accuracy of the model for it to be implemented into an automated system. The 2-step mask region-based convolutional neural network (mask R-CNN) and Canny segmentation algorithm were continuously used to classify the convolutional neural network (CNN) in order to obtain optimal accuracy. When testing the model using training and testing ratios of 90:10 and 80:20, it was evaluated in terms of accuracy, precision, recall, and F1-score. The results showed that the highest model produced an accuracy of 85.44%, 87.12% precision, 83.79% recall, and 84.94% F1-score. Therefore, it was concluded that the test result with 2-stages of segmentation was the best.

Indonesian is one of countries with economic development in the very good category. Economic growth is seen from several supporting fields, Indonesia has a lot of excess natural resources, which can support the economy compared to other countries. But the problem faced is the lack of maximum management of the economy, Indonesia has economic support categorized into 17 fields. Among the fields not in the same development because they are still stuck in one area, it turns out that Indonesia has all the potential to improve all fields. To increase the growth of all fields, the government must have correct, accurate and relevant data to group these fields. In this study using the Decision Tree algorithm to classify fields supporting economic growth automatically. The grouping results into three classes, namely high, medium, low. After the research was conducted the results were that the high category group was Mining and Excavation, Construction, transportation and warehousing, Provosion of accommodation and food Drinking, Information and Communication, Financial Services and Insurance, Real Estate, Educational Services, Health Services and Social Activities, medium groups were Procurement of Electricity and Gas, Company Services and low-income groups are in the fields of Agriculture, Forestry, and Fisheries, Processing Industry, water supply , waste management, Waste and Recycling, large Trade and retail, car and motorcycle repair, Government Administration, Defense and Compulsory Social Security, Other Services.

Indonesia is a country located in the equator, which has beautiful natural. It has a mountainous constellation, beaches and wider oceans than land, so that Indonesia has extraordinary natural beauty assets compared to other countries. Behind the beauty of natural it turns out that it has many potential natural disasters in almost all provinces in Indonesia, in the form of landslides, earthquakes, tsunamis, Mount Meletus and others. The problem is that the government must have accurate data to deal with disasters throughout the province, where disaster data can be in categories or groups of regions into very vulnerable, medium, and low disaster areas. It is often found when a disaster occurs, many found that the distribution of long-term assistance because the stock for disaster-prone areas is not well available. In the study, it will be proposed to group disaster-prone areas throughout the province in Indonesia using the k-means algorithm. The expected results can group all regions that are very prone to disasters. Thus, the results can be Province West java, central java very vulnerable categories, provinces Aceh, North Sumatera, West Sumatera, east Java and North Sulawesi in the medium category, provinces Bengkulu, Lampung, Riau Island, Babel, DIY, Bali, West Kalimantan, North Kalimantan, Central Sulawesi, West Sulawesi, Maluku, North Maluku, Papua, west Papua including of rare categories. With the results obtained in this study, the government can map disaster-prone areas as well as prepare emergency response assistance quickly. In order to reduce the death toll and it is important to improve the services of disaster victims. With accurate data can provide prompt and appropriate assistance for victims of natural disasters.

Mengetahui cuaca hal yang sangat penting untuk kehidupan manusia, yang dinyatakan dengan parameter seperti suhu, kecepatan angin, tekanan udara, curah hujan, yang menjadi komponen utama untuk cuaca. Tujuan mengetahui cuaca adalah terutama bagi masyarakat pedesaan yang bergerak dibidang pertanian, perkebunan dan lain lain. Karena itu untuk penentuan cuaca, mendapatkan informasi cuaca perlu dibuat sehingga dapat dimanfaatkan oleh masyarakat. Permasalahan yang muncul bagaimana membuat prediksi cuaca akurat dan otomatis sehingga dapat dilakukan oleh setiap orang. Dalam penelitian ini mengajukan esemble learning untuk menghitung peluang dari masing-masing atribut kelompok yang ada dan menentukan pedekatan mana yang paling optimal, artinya pengelompokan dapat dilakukan berdasarkan kategori yang pengguna masukkan pada aplikasi. Esemble learning melibatkan beberapa algoritme untuk mencari nilai rata rata akurasi. Hasil yang diharapkan bisa menjadi rujukan untuk membangun aplikasi perakiraan cuaca.hasil akurasi adalah 81.21% dan MSE 18.79%.

Nowadays social media has become one of the tools to express idea or opinion. They are more active expressing it on social media instead of speaking directly. Twitter is the most popular among them to express idea, also share news, picture, music and etc. Twitter users are increasing significantly each year as the result the information grows in same way. Due too much information flow, people get difficulties to make sure or clarify the news. For example, Looking for the information about a figure who will participate in a Pilkada. There are many researchers analyze subjectively and haven’t given the maximum result yet. This research is trying to clarify information and divided them into positive, negative and neutral information. It is using TF algorithm and Neutral Network as the tools. The dataset is taken from a figure’ twitter which is participate in Pilkada. And the result shows that accuracy 66.92%, positive precision 67.80%, negative precision 64.29%, neutral precision 73.33%, and positive recall 80%, negative recall 70%, neutral recall 36.67%.

Penggunaan media sosial seperti twitter adalah salah satu yang popular di masyarakat Indonesia dengan kemudahan dapat diakses oleh siapapun selama ia mempunyai alat pendukung dan koneksi internet, sekarang ini orang bisa ngetweet dari mana dan kapan saja melalui gadgetnya, Karena begitu mudahnya diakses semua orang dari berbagai kalangan dan latar belakang bisa berkomentar atau membuat status untuk mengomentari suatu produk, kejadian, ataupun tokoh. Dengan banyaknya isi kicauan atau tweet yang berhubungan dengan seorang tokoh, khususnya Pemilihan calon pemimpin Presiden, Pilkada yang ada di Indonesia. Isi tweet atau kicauan setiap orang pastinya berbeda – beda tetapi muatannya hanya dibatasi oleh tiga sentiment Posistif, Negatif dan Netral. Dengan adanya keputusan sentiment analisis dapat mencari isi kampanye yang sehat, mana yang negatif dan kampanye hitam. karakter untuk seleksi fitur menggunakan algoritma Neural Network (Jaringan syaraf tiruan) untuk mengklasifikasi sentimen secara otomatis, performance hasil yang didapatkan 53.33%.

Peraturan Pemerintah Republik Indonesia Nomor 13 Tahun 2015 Pasal 66 menjelaskan bahwa Ujian Nasional (UN) sangatlah penting karena menjadi suatu pencapaian kompetensi lulusan secara nasional pada mata pelajaran tertentu pada Sekolah Dasar (SD), Sekolah Menengah Pertama (SMP) dan Sekolah Menengah Atas (SMA). Berdasarkan data yang ditemukan pada website Kementrian Pendidikan dan Kebudayaan yaitu nilai rata-rata UN SMP, SMA dan SMK data yang disajikan tidak berdasarkan peringkat atau kategori tertentu sehingga informasi yang didapatkan menjadi kurang jelas. Dari permasalahan tersebut dilakukan sebuah penelitian untuk menambang data menjadi informasi, pada penelitian ini data yang digunakan adalah nilai rata-rata UN tingkat SMP di Provinsi Jawa Barat menggunakan teknik data mining . Penelitian dilakukan dengan cara perhitungan manual menggunakan Microsoft Excel Kemudian dievaluasi menggunakan tools Rapidminer 9.2.0. Penelitian ini menghasilkan Cluster Baik 10 Kabupaten/Kota, Cluster Cukup Baik 15 Kabupaten/Kota dan Cluster Kurang Baik 2 Kabupaten/Kota 2. Mata Pelajaran Matematika dan IPA saat ini tidak menentukan kategori, karena nilai yang didapat rata-rata lebih kecil dari Bahasa Inggris dan Bahasa Indonesia sehingga bagi Pemerintah Dinas Pendidikan untuk perlu meningkatkan lagi dalam proses pembelajaran di Provinsi Jawa Barat.

The welfare level of rural communities, especially the province of West Java, especially those living away from the cities, can not be separated from the primary revenue is in the agriculture sector. The agricultural industry covers many industries and still many lives under the poverty line. Because facilities and financing are still minimal from the local government. Given the root of the problem is that almost all villages in the city district do not have the correct data, accurate and precise about the condition of the issues and potential of the village-owned. This research is expected to be the wrong way to know the future development opportunities by analyzing the revenue data from the agriculture sector to better decision making. And this data processing technique can be implanted for the local government to measure the success of its agriculture. The selection of features in this study is to use the Decision Tree algorithm to classify data automatically. After this research, the Accuracy of 90% obtained.Keywords: DataMining, classification, Decision Tree, agriculture

The rapid of internet and social media users have changed the way people interact in their daily activities. For example, banking and retail began to use various social media, especially online media such as tweeter. The problem that arises is how to get information from thousands and even million data generated through social media, to be a decision as in predicting consumer satisfaction of the service or product.Another problem is the social media users in communicating using slang or local language. In sentiment analysis to predict the sentiment is not easy because it must be able to identify the words. In sentiment analysis, to overcome these problems the method used is text mining so as to process opinions from social media. The proposed approach is to analyze optimal term weighting between TF-IDF, frequency term (TF) and Binary Term Occurrence (BTO), using SVM algorithm. Target feature extraction for selection of datasets by predicting positive and negative sentiments. The result of weighting of terms approaching sentiment is using TF-IDFwith SVM.

Information retrieval (IR) system adalah sistem yang secara otomatis melakukan pencarian informasi yang relevan terhadap kebutuhan pengguna, yang diekspresikan dalam query, menjadi input bagi IR system dan selanjutnya diproses oleh system kemudian ditampilkan dokumen yang relevan dengan query tersebut. Salah satu metode pencarian informasi yang relevan dengan query adalah dengan pembobotan kata baik query maupun dokumen. Metode yang sering digunakan adalah pembobotan kata lokal dan pembobotan global, adapun pembobotan kata lokal yang digunakan tf, logaritmic tf, binary tf dan augmented tf dan pembobotan globalnya adalah idf, idfp, idfb. Dalam penelitian ini selain membandingkan algoritma pembobotan kata. Tingkat keberhasilan algoritma di ukur berdasarkan precision, recall dan niap. Penelitian ini setelah dilakukan perbandingan dan analisis hasil algoritma pembobotan, hasil algortima yang baru lebih baik daripada yang lama. Kedepan perlu dilakukan dikombinasikan pembobotan dengan algoritma semantic sehingga mendapatkan hasil yang lebih baik. Kata kunci : Sistem temu balik informasi, pembobotan, pembobotan kata lokal, pembobotan global, similarity ( kemiripan), vector space model.

Now finding relevant information is absolutely needed by users of the information. Actually, finding relevant information is more difficult than just looking for information. The presence information retrieval (IR) system is a system for automatically searching the relevant information to the user needs, which is expressed in the required query, and this query will be used as an input and processed by IR system and then will get relevant documents to the required query. One of methods of finding relevant information by query is term weighting by both query and document. The commonly used methods are the term weighting of local and global weighting, while the local term weighting algorithms that are used such as TF, TF logarithmic, binary TF and augmented TF and global weighting is IDF, IDFP, IDFB. In this research, besides of comparison of term weighting algorithms, it is also proposed new improvement in term weighting algorithms by adding global weight value that changes base 10 logarithmic to base 2 logarithmic and adds the number 1 in the global term weighting IDFP. Measurements result of this research are Precision, Recall and NIAP. In This research, the best result for precision and NAIP have been performed by new propose term weighting algorithms. After compare and analyze the result of the weighting algorithms. It is necessary to combine the weighting with semantic algorithms so that it will get better result.