Geographically Semarang regency as one of the regencies in Central Java province has an area of 95,020.67 hectares. In this study, the sub-district areas in Semarang regency is calculated using Circle Approach method and Karney s Polygon method using Google Earth and GADM database in the form of latitude and longitude coordinates. The results of the study show that the land area of 19 districts in Semarang regency is 11.61% more than of the reference areas based on the coordinates of the latitude and longitude on Google Earth using the circle approach method. While the percentage for the area referring to GADM data using the Karney s Polygon method is 9.71% more than of the reference areas and the difference is 13.55% more than the reference areas using Circle Approach. The results of the three comparisons show that GADM data using the Karney s Polygon method can produce better results than other methods.

Android smartphone is one of the items that really help humans in living life today.A person gets information through an internet connection using an Android smartphone whenever and wherever he is. Home Services is a vehicle repair service on site. Thus, customers still get service without leaving activity. The Home Service System is still manual so that it gives customers the opportunity to find out about ordering and scheduling vehicle services. Therefore, the researchers tried to build an Android-based Home Service application using the First Come First Served algorithm to facilitate scheduling. Analytical methods conducted by researchers by collecting data through Literature Studies and Interviews. Thus, resulting in an easier, practical, simple, and efficient Home Services application where customers can schedule vehicle services via an Android Smartphone.

Prediction of student satisfaction with academic services needs to be done to evaluate the performance of higher education institutions in the academic field, especially at Pandanaran University. In this study, using the Decision Tree C4.5 algorithm data mining method in classifying student data through a questionnaire on aspects of tangible, reliability, assurance, responsiveness and empathy. The results of classifying student data using the Decision Tree C4.5 algorithm produce a decision tree model with an accuracy value of 87.92% and AUC 0.990.

Pengenalan karakter plat nomor kendaraan memiliki peran penting untuk tujuan identifikasi secara resmi, penerapanya telah banyak dilakukan untuk identifikasi otomatis seperti pada tol elektronik, tempat parkir, dsb. Penelitian berkaitan dengan pengenalan karakter setidaknya memiliki fase-fase seperti segmentasi, fitur extraksi dan klasifikasi dimana tiap fase memiliki proses yang rumit. Keberhasilan dalam proses pengenalan karakter sangat tergantung dalam proses fitur ekstraksi, Sehingga pemilihan metode fitur ekstraksi yang dapat mengekstrak fitur-fitur yang relevan perlu dilakukan agar tingkat akurasi sistem pengenalan karakter dapat ditingkatkan. discrete wavelet transform telah banyak digunakan sebagai metode untuk ekstraksi fitur, metode ini melakukan ekstraksi dengan melakukan dekomposisi pada  ruang vektor ke dalam ruang vektor bersarang dengan resolusi yang berbeda. Dalam penelitian ini metode discrete wavelet transform dikombinasikan dengan support vector machine untuk meningkatkan akurasi pengenalan karakter. Penelitian dilakukan dengan mengukur tingkat akurasi dari 100 citra plat nomor, dengan penambahan metode discrete wavelet transform dan support vector machine tingkat akurasi klasifikasi mencapai 92% yang artinya   mendapatkan peningkatan akurasi sebesar 8% dibanding klasifikasi menggunakan SVM standar.

Agriculture is a pillar of the economy a nation, with the system and the implementation of good agricultural, so will go the nation economic.One of the causes of the lack of agricultural productivity in Indonesian that is some farmers in Indonesian still relied on climate change rain without blemish. Climate change has caused planting patterns the farmers, so that in the end agricultural products planted could not stable , any process planting .The instability caused the price of agricultural products to be very significant plant at a certain season.This is what causes the thing farmers have to produce more energy and the cost of extra do watering manually so that of the trees can grow fertile and can be harvest pakcoy especially in plants .To overcome the problems hence writers try to make sprinkler system plant with using microcontroller Wemos D1 R1 of experiment to the republic of Indonesian that in arable land plant with using soil moisture capacitive sensors that is going to be the moisture the ground in plants can be monitored over long distances through the android application named Blynk. The system will shut when discharging is out of danger at the boundary moisture expected means of sensors the humidity and turn off water pump.

Indonesia adalah negara tropis yang memiliki keanekaragaman jenis tumbuhan. Tumbuhan terdiri atas tiga organ dasar yaitu akar, batang dan daun. Daun merupakan salah satu bagian yang sering digunakan untuk mengklasifikasikan tanaman, karena setiap jenis tanaman memiliki ciri yang berbeda. Bentuk tepian daun bisa digunakan untuk acuan klasifikasi daun. Otak manusia memiliki keterbatasan dalam mengolah atau mengignat informasi jenis-jenis tanaman yang berdasarkan daun. Oleh karena itu dibutuhkan peralihan pengetahuan manual ke suatu sistem digital. Maka dalam penelitian ini dibuat sistem yang mampu melakukan pengenalan daun menggunakan ekstraksi ciri pada daun menggunakan metide Linear Discriminant Analysis ( LDA ) dan jarak Minkowski.Proses pengenalan pola citra daun diawali dengan pengambilan citra daun, kemudian masuk ke tahap prapengolahan untuk membedakan objek dengan latar belakang. Setelah itu masuk ke tahap ekstraksi ciri menggunakan Linear Discriminant Analysis (LDA ) untuk mendapatkan karakteristik ciri dari citra dan Jarak Minkowski untuk melakukan pengenalan dari pola daun.                       Berdasarkan hasil penelitian dengan jumlah data sebanyak 40 kelas dengan masing-masing kelas sebanyak 6 citra, dengan citra latih sebanyak 160 citra daun dan citra uji sebanyak 80 citra daun. Saat pengenalan menggunakan jarak minkowski menggunakan 3 koefisien yaitu koefisien minkowski 1, 2, dan 3. Dari ­ ­masing-masing koefisien minkowski didapatkan persentase keakurasian. Persentasi keakurasian saat menggunakan koefisien minkowski 1 sebesar 41,25%, koefisien minkowski 2 sebesar 33,75%, dan koefisien minkowski 3 sebesar 30%. Persentase keakurasian pada penelitian ini tidak dapat menghasilkan diangka 80% dikarenakan jumlah data sangat mempengaruhi hasil persentase, semakin banyak data yang ada maka nilai persentase juga akan semakin kecil.

Customer loyalty is an important factor to the survival of a company. The problem facting today is related to the descreasing number of customer loyalty that happened to PT MNC Play. If this is allowed   to continue it is not impossible this will endanger the continuity of the company s business.Keep in mind the factors that cause customers to have loyal and disloyal status, data mining classification techniques can be used to classify loyal and disloyal customers. Many data mining classification algorithms can be used, so it needs to be comparative to know the accuracy of each algorithm, the algorithem used is C4.5 and Na ve Bayes. The data used were 28,899MNC Play customer of Semarang City.The results of the classification   process were evaluated using cross validation, confusion matrix, ROC Curve to find the more accurate data mining classification algorithm to determine loyal and disloyal customers.Keywords: Classification, Customers Loyalty, Na ve Bayes, C4.5.

Social media is a service that is very supportive for government activities, especially in providing openness and community-based government. One form of its implementation is the Semarang City government through the Center for Community Complaints Management (P3M), whose task is to manage community complaints that enter one of the communication channels namely social media twitter. The number of public complaints that enter every day is very varied. This is certainly quite difficult for managers in categorizing complaints reports according to the relevant Local Government Organizations (OPD). This paper focuses on the problem of how to conduct clustering of community complaints. The data source comes from Twitter using the keyword "Laporhendi". Text document data from community complaint tweets was analyzed by text mining methods. A number of pre-processing of text data processing begins with the process of case folding, tokenizing, stemming, stopword removal and word robbering with tf-idf. In conducting cluster mapping, clustering algorithm will be used in dividing the complaint cluster, namely the k-means algorithm. Evaluation of cluster results is done by using purity to determine the accuracy of the results of grouping or clustering.

Kemajuan teknologi kesehatan yang cepat dan akurat semakin menjadi kebutuhan utama para pengambil keputusan. Rumah sakit, klinik, puskesmas sebagai institusi yang menyimpan begitu banyak data juga membutuhkan pengolahan data yang benar dan tepat sehingga dapat disajikan dalam bentuk laporan. Sedangkan untuk menyimpan arsip rekam medis tradisional membutuhkan lahan yang luas dan rawan terkena dampak bencana alam dan kebakaran. Menurut sudut pandang pasien, dokumen fisik rekam medis seperti kartu medik, rontgen, hasil USG, hasil EKG dan lain-lain juga berisiko hilang atau rusak sehingga menjadi masalah. Dengan metode riset & development Borg and Gall yang dimodifikasi, Metode deskriptif dipergunakan untuk menghimpun kondisi yang ada di lapangan. Metode evaluatif dipergunakan untuk mengevaluasi Sistem Informasi Rekam Medis Pasien di Pelayanan Kesehatan Kota Tegal yang diwujudkan dalam bentuk Aplikasi Implementasi Big Data dengan NIK, melalui evaluasi produk dan proses uji coba tersebut diharapkan dapat diperoleh masukan tentang kelebihan-kelebihan dan kekurangan-kekurangan dari produk tersebut. Dengan dibuatnya aplikasi rekam medis dapat mempermudah kinerja staff puskesmas dan dokter, serta sistem yang lebih efektif dan efisien dan data NIK sudah teritegrasi dengan sistem online.

Covid-19 forces the traditional classroom learning method to go online; while teachers nowadays struggle to adapt to this new technology, the EdTech firm's market is increasing. That 44 startups were categorized as Unicorn in 2020. Rather than just referring to the analysis of EdTech's functions that help schools conventionally, this study also looks at the theory of economic-based interaction between education-based organizations that threaten schools' meaning and function that shift during this pandemic to online. Based on this premise, we can identify the features of EdTech, which overlap with conventional schools. Our method is conducting Descriptive Analysis based on observed data derived from validated formal research and put them into three dimensional business model patterns to get evidence of the organization’s strategic or tactical operations. This research aims to address whether the emerging of EdTech firms becomes a threat to traditional schools. This work also finds the core value, which drives student's motivation toward learning outcomes in Indonesia. Based on the research, superior ICT technology adaptation plays an essential key in educational activities. It means that EdTech can provide dependence on schools which not yet comply with these features so that when they had cooperation, EdTech can direct or even changing the school’s original values. This cooperation dependency can challenge the school’s operation cost, increasing the risk of supply and management, involving consumer-related decision-making that always benefited EdTech rather than schools.