Search

The COVID-19 pandemic has lasted 2 years which has resulted in the rapid development of the world of information technology, especially in the world of education. Online and hybrid learning have been carried out, especially in primary school education. In 2021, the design of the tutoring application concept has been carried out to be used by the English Teacher Working Group (Kelompok Kerja Guru-KKG) at the elementary level. This application can be used if teachers can arrange material in digital form in the form of subject matter, quiz questions, puzzles, and audio-video material. Teachers as pioneers of educational success must continue to be able to innovate in preparing interesting and interactive presentation materials to reduce the level of saturation of elementary school students. Therefore, training in making interactive materials for the English KKG is very necessary. The method of implementing this activity is to provide 2 online and hybrid trainings. The training was conducted for 2 types of software commonly used to create presentation materials, namely Microsoft PowerPoint and Google Slides. Based on the evaluation form filled out by participants from the English KKG, the result of this activity was that 100% of the participants understood how to access PowerPoint from Office 365 and understood how to use Morph transitions and animation features. 100% of participants can also know how to access Google Slides and know how to make classes and assignments using Google Classroom.

Siswa/i kelas 1 sampai 5 SD Immanuel mayoritas menggunakan smartphone berbasis Android. Beberapa tahun belakangan merupakan perubahan yang signifikan dalam penggunaan teknologi dalam proses belajar mengajar yang disebabkan oleh pandemi. Hal ini menyebabkan sekolah menuntut seluruh siswa/i untuk menggunakan smartphone demi lancarnya kegiatan belajar mengajar. Siswa/i SD sudah dapat menggunakan smartphone secara mandiri, mulai dari mengunduh game dan aplikasi dari Play Store, penelusuran internet, dan aktivitas lainnya. Dengan bantuan dari tim PKM, SD Immanuel membuat aplikasi percakapan virtual atau chatbot untuk menjadi media pembelajaran berbasis Android yang akan diajarkan kepada siswa/i SD Immanuel dengan cara mengunduh secara pribadi. Proses pelatihan ini diutamakan untuk membantu siswa/i dalam meningkatkan pengetahuan dalam penggunaan aplikasi percakapan virtual berbasis Android. Aplikasi percakapan virtual atau chatbot sendiri merupakan suatu program komputer yang dibuat sedemikian rupa sehingga dapat melakukan suatu percakapan dengan manusia dalam bentuk teks maupun audio. Aplikasi chatbot yang sudah dibentuk diberikan kepada siswa/i SD Immanuel agar dapat digunakan untuk mencari informasi terkait materi pembelajaran di sekolah. Peserta pada pelatihan ini merupakan seluruh siswa/i SD Immanuel yang berjumlahkan 196 siswa/i. Siswa/i memberikan penilaian kepada aplikasi secara langsung melalui Play Store. Sebanyak 110 peserta yang merespon secara langsung melalui Play Store menghasilkan rating yang bagus sebesar 4.8 dari 5 bintang.

The growth of the food and beverage industry is the pillar of national and manufacturing economic growth. At present the food and beverage sector continues to be excellent, especially in the tourism industry sector which develops culinary tourism. In the sale of food and beverages in the world of tourism, it is made to attract the attention of consumers by making promotional packages. This promotional package aims to attract buyers to want to buy products from a restaurant. One way to make a promotion is by using association rules. Association rules are the results that will issue a combination of numbers from each transaction data. This was done to help increase the sales of Ling Ling Restaurant. To find the results of association rules whose combinations are used for promotion, here we use the Apriori method. The results that come out will be in the form of a food or drink menu that has been combined into two, three, or more according to the number of association rules that came out by going through the Apriori method. The results of the association rules that come out later will be displayed on the chatbot display contained in the program. The chatbot here will display the results of the association rules obtained using the Apriori method and also display several question options using questions that have been created in the chatbot.

Motorized vehicles are one of the main needs of every human being and also the most common form of transportation used by people. To choose a motorized vehicle, people should not choosing it in a hurry because it takes good consideration to choose the right brand, type, and the need for the vehicle. In making their choice, usually people will read the reviews from vehicle review sites such as Carmudi.co.id, OTO.com, KobaYogas.com, and so on. The purpose of this thesis is to help provide web-based vehicle recommendations using the values of rating and criteria selected by the user. User rating values are calculated with collaborative filtering. In addition to the rating value, users can also get vehicle recommendations by providing specifications of the vehicle needs. Rating values from the program users will be processed by using adjusted cosine similarity to determine their similarity score to the rating values from vehicle review sites and other users so the vehicle recommendations can be obtained according to the similarity of the other user ratings. Based on the results of User Acceptance Testing (UAT) from 21 respondents, the testing got an average score of 83.95% so the program can be categorized as “Very Good”.

In Google Play Store there are lots of application ready to be explored and downloaded. Google Play Store is a place where many developers can sell applications that they have made. Apart from being a place for searching and downloading applications, Google Play Store can also be used to conduct a research. E-Wallet is one of a technological development that can be used to do many transactions. Doing transaction with e-wallet can be done anywhere you want. E-wallet in Indonesia is growing very rapidly especially in the present time where covid-19 is growing rapidly. This is one of the reasons why many people now using e-wallet for doing transcations. Many interesting promotions that were given is also one of the reason why people start using e-wallet. This research had the objective to visualize people’s emotion on e-wallet based on user opinion in Google Play Store. The research stage starts from scrapping data from Google Play Store, preprocessing data, classification with Support Vector Machine, evaluation with confusion matrix. Data were scrapped from google play store using google_play_scrapper API. This research uses OVO review of 500 data, DANA review of 500 data, LinkAja review of 500 data. The classification results will then be evaluated using a confusion matrix. The highest accuracy results will be used as a model for the classification stage. The classification results will be displayed in the form of tables and pie charts that describe the percentage results of sentiment classification.

The definition of an expedition is the delivery of goods or a company that transports goods. Expeditions for shipping goods are now often found in Indonesia because of the large number of people who make transactions via online. There is a J&T Express expedition service which is one of the shipping services that is able to serve deliveries within cities, between cities and between provinces. J&T Express has problems in determining permanent warehouse employees. The determination of warehouse employees for permanent employees at J&T Express is still done individually by the Supervisor of each J&T Express branch. The Simple Additive Weighting method is one method to make it easier for Supervisors to choose permanent warehouse employees with rankings. The way it works is that the user selects the 7 criteria provided, namely performance, attendance, manners, appearance, ability, knowledge, and responsibility.

Setiap guru kelas wajib untuk memberikan soal secara rutin baik untuk latihan sehari-hari, penilaian harian, tengah semester atau akhir semester.Pada saat menyiapkan naskah soal dan mengetiknya, secara tidak sadar kesalahan pengetikan dapat terjadi.Walaupun pihak guru sudah berusaha untuk memeriksa ulang dan memperbaiki naskah soal, masih juga terdapat beberapa kesalahan pengetikan yang dapat saja terjadi.Beberapa kesalahan kurang huruf, kelebihan huruf atau huruf yang tertukar adalah kesalahan yang umum terjadi. SD. Tiara Kasih adalah salah satu sekolah yang cukup ketat dalam proses memeriksa soal. Kepala sekolah selalu memeriksa kembali setiap naskah soal yang akan diberikan kepada siswa. Namun banyaknya soal dan surat lainnya yang bertumpuk membuat ketelitian pemeriksaan kurang maksimal. Saat ini aplikasi word processing sudah memiliki auto spelling correction yang dapat digunakan untuk membantu memberikan koreksi pada ejaan yang salah.Namun biasanya tersedia untuk Bahasa Inggris dan langsung memeriksa setiap kata yang diketik dan mengkoreksi kata tersebut.Sekolah membutuhkan aplikasi yang dapat memeriksa dan memberikan koreksi setelah naskah selesai dibuat.Sehingga setelah naskah dibuat, naskah dapat diperiksa kembali oleh guru lainnya sebagai peningkatan kualitas soal agar bebas dari kesalahan pengetikan.Tim PKM membuat aplikasi Sistem Koreksi Ejaan Bahasa Indonesia (SKEBI) sesuai kebutuhan sekolah untuk memeriksa naskah soal.

Merdeka Belajar – Kampus Merdeka (MBKM), merupakan kebijakan Menteri Pendidikan dan Kebudayaan Riset dan Teknologi, yang bertujuan mendorong mahasiswa untuk menguasai berbagai keilmuan yang berguna untuk memasuki dunia kerja. Pada program studi Teknik Informatika dan Desain Interior, kegiatan magang/praktik kerja telah dilaksanakan mahasiswa, dalam kurun waktu 6 – 12 bulan pada perusahaan atau organisasi yang menjadi mitra program studi. Penelitian ini bertujuan untuk mengetahui dampak kegiatan magang dan studi independen dalam meningkatkan kompetensi mahasiswa. Responden yang telah mengisi kuesioner berjumlah 227 mahasiswa, terdiri dari 158 mahasiswa peserta magang dan studi independen dan 69 mahasiswa yang belum mengikuti magang dan studi independent. Kegiatan magang dan studi independen sangat membantu meningkatkan kompetensi mahasiswa baik secara hard skill maupun soft skill. Kegiatan magang dan studi independen juga memberikan kesempatan bagi mahasiswa belajar secara langsung (experiential learning) di tempat kerja/industri yang dapat menjadi bekal bagi mahasiswa untuk menghadapi dunia kerja setelah lulus dari perguruan tinggi.

During this pandemic, the Immanuel Elementary School followed the government's direction, which was to carry out online learning. In increasing the spirit of learning, many learning methods have been developed. The development of learning methods is accompanied by the availability of various current technologies. Chatbot is one technology that has been widely used in various form to make humans get information. Chatbots can be useful for providing flight information, product sales, weather and more. SD Immanuel needs a solution to find new ways of learning that can increase students' enthusiasm. We provide a solution by creating a Chatbot as one of the new learning innovations that can provide new method in the learning process. We carried out two activities, namely the development of a Chatbot application with the Agile method and training teachers with the Hybrid Learning method. We develop GuruManuel web application which is used by teachers and ManuelBot which can be used by students through the LINE application. Based on a survey, 100% of teachers agree this application can be useful in the learning process and help students to find information. As many as 82% of teachers agree with the appearance and usability of this application.BAHASA INDONESIA ABSTRACT: Pada masa pandemi ini, Sekolah Immanuel mengikuti arahan pemerintah yaitu melaksanakan pembelajaran secara daring. Dalam meningkatkan semangat pembelajaran, banyak dilakukan pengembangan metode belajar. Pengembangan metode belajar diiringi dengan tersedianya berbagai teknologi saat ini. Chatbot adalah salah satu teknologi yang sudah banyak digunakan saat ini dalam berbagai kegunaan yang dapat memudahkan manusia mendapatkan informasi. Chatbot dapat berguna untuk memberikan informasi penerbangan, penjualan produk, cuaca dan lainnya. SD Immanuel membutuhkan solusi untuk menemukan cara belajar baru yang dapat meningkatkan semangat siswa. Tim PKM memberikan solusi dengan membuat sebuah Chatbot sebagai salah satu inovasi pembelajaran baru yang dapat memberi semangat dan warna baru dalam proses pembelajaran. Pada PKM ini, dilakukan dua kegiatan sebagai solusi untuk menghasilkan inovasi pembelajaran yaitu pembuatan aplikasi Chatbot (ManuelBot) dengan metode Agile yang merupakan salah satu metode dalam pembuatan aplikasi dan pelatihan kepada guru dengan metode Hybrid Learning. Hasil dari PKM ini adalah aplikasi GuruManuel yang digunakan oleh guru sebagai admin dan ManuelBot yang dapat digunakan oleh siswa melalui aplikasi LINE. Berdasarkan survei 100% guru setuju aplikasi ini dapat berguna dalam proses pembelajaran dan membantu siswa untuk mencari jawaban. Sebesar 82% guru-guru menyetujui bentuk tampilan, kegunaan dan penggunaan aplikasi ini.

This research was intended to create Spelling Correction Application to help teachers examine questions scripts with the capability to found typographical error and give suggestion for non-real word error. This application is built with simple Damerau-Levenshtein Distance method to detect errors and give word suggestions from the typo word. This application can be used by the teacher to examine documents in the form of short answer, essay and multiple choices then save them back in the form of original documents. This application is built using a dictionary lookup consist of 41 312 words in Indonesian. The first test result is the application can detect non-real word errors from 50 sentences that have non-real word error in each sentence and produce an accuracy of 88 %. The second test is try to detect typographical error in exam test script that consist of 15 sample questions, consisting of five essay questions, five short answer, and five multiple choices.

Graduating from college is something that students really want. By graduating from college, it has become a sign for a student to become a worthy scholar to continue and enter the next level. Graduation time is influenced by the academic value obtained from a student. If a student gets a high score, the student's graduation will be faster or on time. On the other hand, if a student gets a score below the average, the student's graduation time will be longer. At this time, one of the causes of students getting low grades is because students who are so busy playing games neglect their lectures and lose concentration while studying. So this can affect the time of their graduation. Students should be able to control themselves to manage their time playing online games and lectures in order to complete their obligations as a student, and students who get low grades for playing games should also be aware that getting low grades continuously will result in the student being threatened with dropping out (DO).Therefore, an information system program was designed that can be used by students who like to play games to be able to predict their graduation time so that they can find out their graduation time. The design of this program applies the K-Nearest Neighbor method which is a classification technique for objects based on learning data that is closest to the object.The final result of the application of the K-Nearest Neighbor method in the program has its advantages and disadvantages. The classification process is strongly influenced by the large amount of training data, and the determined value of 'K' (neighbors). The more the amount of training data, the level of accuracy can be reduced. The level of accuracy in testing using training data is 230 data, and using test data as much as 30 data with several specified 'K' values, namely, 2, 3, 4, 10. Accuracy results with 4 K values used can reach an accuracy rate of 90% .

The development of information technology is growing from year to year. To support the smooth flow of information, there are many internet service providers circulating in Indonesia to support their needs. Some of the largest internet service providers in Indonesia such as Indihome, First media, and Biznet Home definitely have their own advantages and disadvantages.At this time, internet provider providers only accept customer complaints or suggestions through the customer service (CS) call center. Meanwhile, many young Indonesians currently use one of the popular Social Media services, namely Twitter as a user-friendly microblogging service so that users can easily use it, especially in delivering messages in the form of tweets. Therefore, a sentiment analysis program was designed for several internet providers in Indonesia. Opinions or Opinions will be analyzed to determine public sentiment. These sentiments will be classified into 3 sentiments, namely negative, positive, and neutral sentiments. The sentiment classification process can be done manually, but if there is too much data, it requires a system equipped with a classification method, so that the determination of classification can be done quickly. The design of this program applies the Naive Bayes Classifier method. Because this method is supervised learning, it requires training datasets with labels. Labeling will be done automatically using the K-means method. K-Means will sort tweets into groups which are divided into 3 labels. The results of the K-means clustering accuracy are 73.4%. The results of this application are divided into 2 parts, namely a pie chart which is divided into slices that describe the results of the percentage of tweet classifications and a table of classification results containing the number, content of the tweet, and the results of the classification. The best level of accuracy in testing uses 220 training data, and 54 training data. The results of the accuracy of 83.3%.

The advance of technology and the increased number of internet usage, have caused many companies to build their online store as a way to market their product. But getting the attention of people isn’t an easy thing to achieve, so livechat and chatbot are implemented into the system to increase the quality of services. This chatbot was developed using the Vector Space Model which will calculate the similarity of each question and the input, before using the vector space model each question will be weighted with term weighting. The chatbot was tested directly and the result is calculated to get the precision of 0.813, recall of 0.751, and f-measurement of 0.766. From the results, we can say the performance of the chatbot is quite decent for it has increased the quality of the services which the online store provided.

Typing errors in a document are human errors that are difficult to avoid as a result of which the message to be conveyed is not optimal. Using the Spelling Corrector feature is one way to check typing errors. The Spelling Corrector feature is able to provide only one word suggestion and correct it immediately. The combination of Peter Norvig and Ngram's methods was able to come up with one word suggestion and correct it right away. Both methods of looking for word suggestions use the probability value of the words that appear most frequently in the dictionary. The difference between the two methods is that Peter Norvig uses an algorithm that combines the delete, insert, replace, and transpose processes for the wrong word. Meanwhile, Ngram uses an algorithm that pays attention to the words before and after them based on the sentences in the dictionary. The dictionary used is a dictionary of word lists from KBBI and also a dictionary of sentences taken from several articles on the internet. This combination of methods was tested using 55 documents containing sentences that had one misspelled word. The test results show that the combination of the two methods provides an accuracy rate of 73,684% and a success rate of 37,037% for the total accuracy of this application is 69.09%. These two methods can be used to correct typing errors, although they cannot correct words with an error rate of two or more letters. This is because Peter Norvig was unable to correct a word with a two-letter error rate and needed a good corpus.

E-recruitment is a web-based application that is used to recruit employees for several available companies. The e-recruitment system has a plagiarism checker feature. Plagiarism itself has the meaning of actions that are considered fraud by taking someone's idea or writing without mentioning a reference and claiming it as their own. So that the e-recruitment application requires a plagiarism detector which functions to make it easier for companies to assess the characteristics of their prospective employees. The plagiarism checker feature applies a string matching algorithm to a text to search for common words between texts. There are several algorithms used for string matching, two of which are the Rabin-Karp and Jaro-Winkler algorithms. The Rabin-Karp algorithm is one of the algorithms that is suitable for solving multi-string pattern problems, while the Jaro Winkler Distance algorithm has advantages in terms of accuracy. An e-recruitment application with a plagiarism detection feature is developed and tested on various types of text, namely in the form of a self-description text of the prospective employee. From the experimental results, it was found that the two algorithms can be used to detect plagiarism in the applicant's self-description text, but it still has shortcomings in checking it.

One area of life that is affected by the rapid development and advancement of technology is the automotive sector. Information technology bridges various groups who participate in automotive transaction activities. Therefore, the physical condition and performance of an automotive are determining factors for a buyer who wants to make a purchase.Not all types of automotive offered meet the buyers' standards, nor do they have a selling price in accordance with the quality described by the seller. The Analytical Hierarchy Process (AHP) method helps determine the type of automotive that suits the buyers' wishes and the Naïve Bayes method helps determine the selling price according to the quality of the automotive offered.The Analytical Hierarchy Process (AHP) method is a decision support model that describes a complex multi-factor or multi-criteria problem into a hierarchy, which in turn can organize complex problems into a more orderly and systematic manner. The Naïve Bayes method is a classification using probability and statistical methods that predict future opportunities based on past experiences. Naïve Bayes calculates a set of probabilities by adding up the frequency and value combinations from the given dataset. Based on the comparison of the calculation results with the tests carried out, the AHP method obtains an accuracy rate of 100% in displaying the criteria for cars being sold. Meanwhile, the Naïve Bayes method obtains an accuracy rate of 100% in determining whether a dealer is interested in buying a car or not.

The rapid development in Indonesia is information technology. Today's computer technology can collaborate with other fields of science. One of them is a Computer Based Decision Support System (DSS). Decision Support System (DSS) is a system that is useful for increasing effectiveness in terms of decision making. A credit card is a payment instrument in the form of a card that has a credit facility to the owner in lieu of cash payment, where at maturity it can be paid with the minimum payment amount and the rest is used as credit. In applying for credit card closure, it can be combined with a decision support system. The decision support system for this case uses the Analytical Hierarchy Process (AHP) method and the Preference Ranking Organization Methods for Enrichment Evaluations (Promethee). The Analytic Hierarchy Process (AHP) method has proven its reliability in weighting the criteria value and the Preference Ranking Organization Methods for Enrichment Evaluations (Promethee) is used to rank the alternatives provided. Establishing this decision support system will produce fast and accurate recommendations to credit card management on this issue.

This research aims to produce an application that assesses copywriting headline sentences with correct grammar and word mismatches. Copywriting is an activity of a work through writing to made the readers get response that the writers want to convey and in it there is one of the constituent elements, namely the headline which is a sentence that will be seen first before reading the main content of the work and in the headline there is an RTO formula for making it.In this research, the problem raised was implementing the shift reduce parsing method as a detection of sentence patterns and grammar in the headline copywriting from the preprocessing stage which provides part-of-speech (POS) labels using the HMM model with an accuracy value of 94.69% to the steps parsing and grading of sentences. In making this application, the SDLC waterfall model is carried out in a sequence of several processes in stages in designing and developing a system.The result of this research is an application with the form of a web framework using ASP.net as a web interface. After the application has been built, it will be tested using the blackbox test which results in 98% successful parsing that goes according to design.

News is information about facts or opinions that are interesting to know. News can be obtained from various media such as newspapers and the internet. As is well known, news has various topics, such as politics, sports and others. There is also the same story written with the addition of a little information. This causes it to take more time to get the headline of the news. Therefore we need a system for news clustering using the K-Means method and news summarizing using the Maximum Marginal Relevance (MMR) method in order to obtain information from news more easily and efficiently. News that is processed in the form of a collection of files (multi document) with the extension txt. The summarization process goes through the text preprocessing stage, which consists of sentence segmentation, case folding, tokenizing, filtering, stemming. The next step is TF-IDF calculation to calculate word weight then Cosine Similarity to calculate the similarity between documents. After that, enter the K-Means stage for clustering division and proceed with determining the summary with MMR. Based on the results testing that has been done, this application is running well, the results of clustering and summarizing news can make it easier for users to get news summaries from some similar news.

Song identification dan query by humming is an application that is developed using Mel-frequency cepstral coefficients (MFCC) and Long Short-Term Memory (LSTM) algorithm.The application purpose is to detect and recognize humming from the input data. In this application the humming input will be divided into two parts, namely the training audio and test audio. For the training audio, the training audio will be divided into two process stages, namely recognizing humming and searching for the unique features of a humming audio.To recognize the humming feature, the humming will be processed using the MFCC method. After obtaining a part of the MFCC Features, the MFCC features will be saved as a vector model. The feature that has been extracted will be learned by the LSTM method. For the test audio of the stages carried out as in the training audio, after the MFCC Feature is detected, an introduction will be made based on learning that has been done with the LSTM method to obtain output in the form of a song name that is successfully recognized and detected will be labeled by the application.

Prediction credit card submission is a system that is able to provide an assessment of alternatives in order to help credit card applicants in making decisions. Many methods can be used in building a prediction system for credit card submissions. This research will compare two methods in predicting credit card submission, namely the naïve bayes method and c4.5 algorithm, case study of Credit Card Submission Prediction, the results of the research are, knowing the level of accuracy of the two methods. Criteria that form the basis of decision making include age, sex, recent education, marital status, number of dependents, type of company, monthly income, and salary slip. The final result found that the naïve bayes method and the c4.5 algorithm are relatively the same.

Difficulty in finding information about levels maturity based on the type of fruit using data textual, make a search system using image as query needed. The concept of Content-Based Image Retrieval (CBIR) will search and display images again which are relevant based on the visual features query image. In this study an application was made to classify 5 classes of fruit, Star fruit, Mango, Melon, Banana and Tomato. Which in each class divided again into 52 subclasses consisting of the type and level of fruit maturity with a total of 5030 training data images. The method used to classify and extract images features is Convolutional Neural Network (CNN). After the image is classified, the search process is carried out to determine the fruit that is similar to the classified image. The results of the classification accuracy of 1294 images are 61%. While the retrieval of 50 images has a precision value of 88.93%.

Natural Language Processing or NLP is a branch of Artificial Intelligence that focuses on processing language. One of the implementation of NLP is in the field of customer service in the form of chatbots. Tarumanagara University itself already has a customer service called Admission Tarumanagara. Admission can be contacted by telephone or sending an e-mail message. Making Chatbot will add ways to get information about Tarumanagara University. Chatbot is a computer program based on artificial intelligence that can simulate conversations between people. The system created is a Retrieval Based Chatbot system that can recognize user questions and answer user questions directly. Making a chatbot system will use a model with the Multilayer Perceptron method. The process for the system will go through two stages, namely the preprocessing stage and the introduction stage. The preprocessing stage consists of case lowering, tokenizing, and stemming. After that the model is made and the introduction phase of the trained model is carried out. Chatbot that has been made can be accessed using the LINE application via LINE ID @764vvcfm.

This paper is about web based application of doctor selection classification, derive from patient complaints by utilizing the C4.5 method and K-Nearest Neighbor. Classification is the process of grouping things based on classes with the characteristics of similarities and differences. This objects or entities are labeled as user complaints. User complaints are classified and produce a category of doctor that matches the user’s complaints. This application will be using sample data from ascertain the opinions and experience of Doctor Yohannes Cahyadi who practices at the Griya Kasih Indah Clinic and from the website alodokter, hellosehat, docdoc.com, cicendoeyehospital, and the eye clinic Nusantara. The purpose of making a doctor selection classification application based on patient complaints is so that the user can find out the doctor’s category recommendations in accordance with user complaints input on this application. The test results obtained said that the best classification accuracy is to use the K-Nearest Neighbor method with an accuracy value of 100%, this shows that the use of the C4.5 method and K-Nearest Neighbor can provide recommendations for the right doctor with user complaints.

The development of technology, especially in the data security system in maintaining the security of information data has been growing rapidly. In maintaining the security of information data there are branches of science in its development such as cryptography and steganography. In its application is not only done on one security technique, but can be done in combination with information security data. This study aims to create a data security system by implementing cryptography on messages in the live chat application. The message security in live chat applies a combination of AES and RSA algorithms. The AES (Advanced Encryption Standard) method is a cryptographic algorithm that can be used to secure data, the AES algorithm is a symmetric chipertext block that can encrypt and decrypt information, and the RSA Method is the RSA Algorithm is a block cipher algorithm (an algorithm that works per block of data) that groups plaintext into blocks first before being encrypted to become ciphertext. This application aims to secure messages sent by the sender to stay safe when received by the recipient. The system will be based on a website using the PHP programming language, using a codeigniter framework and a MySQL database. This information system is in the form of live chat which will be encrypted by 2 methods. The sender will send a message through the live chat website then the message is encrypted so that its security is guaranteed, the message stored in the database will be automatically encrypted by the two methods applied then after arriving at the recipient the message is automatically described. The message sent is in the form of text and png files.

This paper is about web based application of recommendation medical specialty doctors based on user symptoms using the C4.5 method and K-Nearest Neighbor. Classification is the process of grouping things based on classes with the characteristics of similarities and differences. This objects or entities are labeled as user symptoms. User symptoms are classified and produce a category of doctor that matches the user’s symptoms. This application will be using sample data from ascertain the opinions and experience of Doctor Yohannes Cahyadi who practices at the Griya Kasih Indah Clinic and from the website alodokter, hellosehat, docdoc.com, cicendoeyehospital, and the eye clinic nusantara. The purpose of making this application is to choose the right specialist doctor based on human symptoms or medical need. The test results obtained said that the best classification accuracy is to use the K-Nearest Neighbor method with an accuracy value of 100%, this shows that the use of the C4.5 method and K-Nearest Neighbor can provide recommendations for the right doctor with user symptoms.

This implementation aims to decide which employees to get salary increases. waspas is one of multi criteria decision making method that using multiple criteria to find the highest value from all data criteria. This implementation number of criteria, criteria weight and level of importance can be changed as needed, in this case data of employees is using from toko nasional utama and criteria, value of criteria, and level of importance was given from toko nasional utama owner. Based the testing result is choose 3 employees with highest value using 5 data of employees and 10 criteria from the owner, the result Nico is 0.8116, Eko is 0.6902, Djajantono is 0.6347. The gap between Nico and Eko or Eko and Djajantono because assessment from owner to employees is different based on their performance and that effected on the result. Based on the result that obtained it can be concluded that waspas can be used for make a recommendations with multiple criteria.

Information extraction resume is a system used to carry out the automatic information extraction process on resumes of prospective employees to obtain key information including information on names, skills, educational experience, work experience, awards which are the main components in a curriculum vitae of prospective employees. Conditional Random Field (CRF) is one method that can be used to extract information. The step taken in the information extraction process is an annotation documents, tokenization, labeling on each token in the document, feature extraction, and the formation of models that will be used at the classification stage. In this study a system was built that could be used to extract CVs from users in pdf format. This study uses a CV from LinkedIn. Information extraction is done using 15 features and 11 classes. The evaluation of information extraction system for the employee’s resume has a precision value of 85,052%, a recall value of 85,052%, and an f-measure of 78,527%.

Recent improvement in natural language understanding research can be attributed to the availability of large scale datasets. Those datasets are mainly in English. In this work, we develop a web crawler with the purpose of extracting Indonesian news content from the DetikNews website and building a large dataset of texts. The web crawler is developed by following the waterfall model using Python, Scrapy, and BeautifulSoup4. It collects more than 790k news from DetikNews, spanning from 2011 to 2020, which consists of a total number of more than 190 million words, almost 2 million unique words, and more than 14 million sentences.

Sistem aplikasi Pendeteksi Kemiripan Teks adalah aplikasi yang menggunakan Metode Latent Semantic Analysis (LSA). Aplikasi ini dapat memberikan informasi mengenai hubungan antar dokumen teks yang direpresentasikan menggunakan term dokumen matrix. Term dokumen matrix berguna untuk memberikan nilai kemiripan pada setiap kata dalam dokumen. Metode LSA tidak memperhatikan tata letak kata pada dokumen dengan kata lain makna yang terkandung di dalam teks tidak berpengaruh terhadap perhitungan kemiripan. Bila terdapat dua buah dokumen yang saling salin namum struktur kalimatnya telah diubah dan ketika dibandingkan menggunakan metode LSA dengan perhitungan kemiripan menggunakan metode cosine similarity maka akan didapat hasil presetase kemiripan yang sama. Aplikasi ini dibangun menggunakan bahasa pemrograman PHP dan juga bahasa pemrograman python. Aplikasi ini dilakukan pengujian menggunakan metode blackbox testing.

This study aims to produce an application that is useful for improving the quality of student theses. The use of the spell-checking application can help reduce spelling errors in abstracts inputted by students. Making this application can help students to produce theses that avoid copying with the previous thesis. The results of this study have resulted in the design and manufacture of a thesis registration system that is equipped with a spelling correction menu and a plagiarism check. The spelling correction menu is created using the D-LD method to examine abstract documents. While the Rabin Karp method is used to check the similarity of documents with other documents. In this study the user can see misspelled words based on the mark that appears on each wrong word. Users can see the percentage of thesis similarity with other theses. AbstrakPenelitian ini bertujuan untuk menghasilkan sebuah aplikasi yang berguna untuk meningkatkan kualitas skripsi mahasiswa. Penggunaan aplikasi pemeriksa ejaan dapat membantu mengatasi kesalahan ejaan pada abstrak yang diinput oleh mahasiswa yang nantinya akan ditampilkan pada abstrak skripsi setiap mahasiswa. Pembuatan aplikasi ini juga akan membantu mahasiswa untuk menghasilkan skripsi yang terhindar dari penjiplakan dengan skripsi sebelumnya. Hasil penelitian ini telah menghasilkan perancangan dan pembuatan sistem pendaftaran skripsi dengan dilengkapi menu spelling correction dan cek plagiat.Menu spelling correction dibuat dengan metode D-LD yang dapat memeriksa dokumen abstrak. Sedangkan menu untuk memeriksa plagiat menggunakan metode Rabin Karp untuk memeriksa kemiripan dokumen dengan dokumen lainnya.Pada penelitian ini telah diakukan penelitian untuk memperbaiki hasil koreksi ejaan dengan D-LD dan menambahkan menu pemeriksaan plagiat dengan metode Rabin Karp.

Any mistake in writing of a document will cause the information to be told falsely. These days, most of the document is written with a computer. For that reason, spelling correction is needed to solve any writing mistakes. This design process discuss about the making of spelling correction for document text in Indonesian language with document's text as its input and a .txt file as its output. For the realization, 5 000 news articles have been used as training data. Methods used includes Finite State Automata (FSA), Levenshtein distance, and N-gram. The results of this designing process are shown by perplexity evaluation, correction hit rate and false positive rate. Perplexity with the smallest value is a unigram with value 1.14. On the other hand, the highest percentage of correction hit rate is bigram and trigram with value 71.20 %, but bigram is superior in processing time average which is 01:21.23 min. The false positive rate of unigram, bigram, and trigram has the same percentage which is 4.15 %. Due to the disadvantages at using FSA method, modification is done and produce bigram's correction hit rate as high as 85.44 %.

In the world of education, e-learning system is a system that can be used to support the educational process. E-learning system is usually used by educators to learners in evaluating learning outcomes. In the process of evaluating learning outcomes in the e-learning system, the form type of exam questions that are often used are multiple choice and short stuffing. For exam questions in the form of essays are rarely used in the evaluation process of educational because of the difference in the subjectivity and time consuming in the assessment process. In this design aims to create an automatic essay scoring feature on e-learning system that can be used to support the learning process. The method used in automatic essay scoring is Latent Semantic Analysis (LSA) with n-gram feature. The evaluation results of the design features automatic essay scoring showed that the accuracy of the average achieved in the amount of 78.65 %, 58.89 %, 14.91 %, 71.37 %, 64.49 % in the LSA unigram, bigram, trigram, unigram + bigram, unigram + bigram + trigram.

Question answering system is a system that can give an answer from the user. In general, question answering can generate answer to text questions. This paper reports the result of question answering system that can receive input questions from speech and text. Hidden Markov Model (HMM) used to recognize the voice provided by the user. The HMM speech recognition used the feature value obtained from Mel Frequency Cepstrum Coefficients method (MFCC). The question answering system used Vector Space Model from Lucene search engine to retrieve relevant documents. The result shows that HMM speech recognition system's success rate in recognizing words is 83.31% which obtained from 13 tested questions. The result also shows that question answering system can answer 4 out of 6 questions that correctly identified by speech recognition system.

Searching images from digital image dataset can be done using sketch-based image retrieval that performs retrieval based on the similarity between dataset images and sketch image input. Preprocessing is done by using Canny Edge Detection to detect edges of dataset images. Feature extraction will be done using Histogram of Oriented Gradients and Hierarchical Centroid on the sketch image and all the preprocessed dataset images. The features distance between sketch image and all dataset images is calculated by Euclidean Distance. Dataset images used in the test consist of 10 classes. The test results show Histogram of Oriented Gradients, Hierarchical Centroid, and combination of both methods with low and high threshold of 0.05 and 0.5 have average precision and recall values of 90.8 % and 13.45 %, 70 % and 10.64 %, 91.4 % and 13.58 %. The average precision and recall values with low and high threshold of 0.01 and 0.1, 0.3 and 0.7 are 87.2 % and 13.19 %, 86.7 % and 12.57 %. Combination of the Histogram of Oriented Gradients and Hierarchical Centroid methods with low and high threshold of 0.05 and 0.5 produce better retrieval results than using the method individually or using other low and high threshold.

Application of cell phone parts recommendations and product sales predictions for each customer for Brader Parts is an application that is made aiming to provide predictions of each customer's buying habits as well as recommendations in selecting what items are most salable to sell and most sought after. This application was designed using the ASP.Net programming language. Method of Calculating application using Apriori. The design of the application uses the System Development Life Cycle. The test results are performed using the User Acceptance Test method and user satisfaction testing. With this application, it is expected that the process of consideration and selection of goods at the Brader Parts company can be helped.

It is proposed that a beverage package is determined based on customer orders by looking for different frequent itemset patterns in the transaction data that has occurred. These data can be analyzed to be more useful. The method used is the association method. With the predicted beverage package the company can increase sales. With so many transaction data stored, the difficulty in managing data requires a method called the association method. Frequent Pattern Growth Algorithm is an alternative algorithm that is quite effective for finding the set of data that most often appears (frequent itemset) in a large data set. The test results from the Frequent Pattern Growth method can determine a number of packages that meet the minimum value of support and confidence with a combination of two itemset

This research was intended to create Indonesian Text Spelling Correction system with the capability to handle and make correction to both kind of spelling errors, non-word and real-word errors. Existing spelling correction system was analyzed and made some adjustment and modifications to boost its accuracy. The proposed spelling correction system is built with Damerau-Levenshtein Distance that used in existing spelling correction system along with the adjustment and modifications. The result that achieved by the system that uses by existing spelling correction with the word level accuracy of 40.6% and an average processing speed of 18.4 ms per sentence while the result that achieved by the system that uses Damerau-Levenshtein Distance and Recurrent Neural Network with the word level accuracy of 21.3% and an average processing speed of 29.21 ms per sentence. The result of retest text that achieved by the system that uses Damerau-Levenshtein Distance and Recurrent Neural Network with the word level accuracy of 74%. Tujuan dari penelitian ini adalah untuk membuat sistem pengoreksian ejaan teks Bahasa Indonesia, yang memiliki kemampuan untuk menangani dan memperbaiki kesalahan ejaan, baik kesalahan kata tidak sah maupun kesalahan kata sah. Sistem koreksi ejaan yang sudah ada dianalisis kembali dan dilakukan beberapa penyesuaian dan koreksi untuk meningkatkan akurasi. Sistem koreksi ejaan yang diusulkan dibuat dengan metode Damerau-Levenshtein, yang digunakan dengan penyesuaian dan koreksi dalam sistem koreksi ejaan yang sudah ada. Pencapaian yang dicapai oleh sistem koreksi ejaan yang sudah ada menghasilkan akurasi kata sebesar 40,6% dan kecepatan pemrosesan rata-rata 18,4 milidetik per kalimat dibandingkan hasil yang dicapai oleh sistem yang menggunakan Damerau-Levenshtein Distance dan Recurrent Neural Network Akurasi menghasilkan akurasi kata sebesar 21,3% dan kecepatan pemrosesan rata-rata adalah 29,21 milidetik per kalimat. Hasil pengujian ulang teks yang dicapai oleh sistem menggunakan Damerau-Levenshtein Distance dan Recurrent Neural Network menunjukkan akurasi kata sebesar dari 74%.

ive Text Summarization try to creates a shorter version of a text while preserve its meaning. We try to use Recurrent Neural Network (RNN) to create summaries of Bahasa Indonesia text. We get corpus from Detik dan Kompas site news. We used word2vec to create word embedding from our corpus then train our data set with RNN to create a model. This model used to generate news. We search the best model by changing word2vec size and RNN hidden states. We use system evaluation and Q&A Evaluation to evaluate our model. System evaluation showed that model with 6457 data set, 200 word2vec size, and 256 RNN hidden states gives best accuracy for 99.8810%. This model evaluated by Q&A Evaluation. Q&A Evaluation showed that the model gives 46.65% accurary.

The ease of accessing information makes easier to do plagiarism. Plagiarism not only applied to written essay, but these day copying other people’s program is also considered as plagiarism. This paper will researching an method to automatically calculating the similarity of pair of source code. The method used are fingerprint based distance and Levenshtein Distance. The result will be measured in accuracy, precision, and recall. The result is in some dataset, levenshtein distance is better than fingerprint based distance for detecting plagiarism in student’s code especially beginner in C++.

In a spiritual worship, choosing the relevant song with theme is very important to reflection for the congregation in the service. In the fact, the people often having a difficult to choose some relevant songs because, they must see, search and read the song one by one. The problem is a motivation that it needs a searching system for the people. In the system, using a Vector Space Model after that the system does a clustering from the relevant songs using K-Means method. In the searching system, It is to search by unigram and bigram with the maximum keywords are six keywords. The system using NKB (Nyanyian Kidung Baru) as data which nuance of hymne. The Result of precision evaluation from the relevant documents using MAP (Mean Average Precision), was getting the searching with unigram is the good result than bigram with the percentages is 70.41%. While, the clustering evaluation, using purity with the some trials for k values, was getting k = 4 and unigram given the good result with the percentages is 76.88%.

Knights Fantasy Online adalah game online multiplayer dengan genre role-playing. Game ini dibuat menggunakan ActionScript 3.0 dengan Adobe Flash sebagai sisi klien dan Java sebagai servernya. Desain dari game ini dibuat dengan Adobe illustrator. Dalam game ini, pemain memulai petualangannya di dunia bernama Edenia, sebagai ksatria dari kerajaan yang bernama Aurum. Pemain bertugas mengkontrol jumlah populasi monster. Pemain dapat mengambil quest, mengumpulkan equipment dan meningkatkan ability karakternya.