Search

Arrhythmia is an abnormality often encountered in patients with cardiac problems. The presence of arrhythmia can be detected by an electrocardiogram (ECG) test. Automatic observation based on machine learning has been developed for long time. Unfortunately, only few of them have capability of explaining the knowledge inside themselves. Thus, transparency is important to improve human understanding of knowledge. To achieve this goal, a method based on cascaded transparent classifier is proposed. Firstly, ECG signals were separated and every single signal was extracted using feature extraction method. Several of extracted feature’s attributes were selected, and the final step was classifying data using cascade classifier which consists of decision tree and the rule based classifier. Classification performance was evaluated with publicly available dataset, the MIT-BIH Physionet Dataset. The methods were tested using 10-fold cross validation. The average of both accuracy and number of rules generated was considered. The best result using rule-based classifier achieves the accuracy and the number of rules 92.40% and 40, respectively. And the best result using cascade classifier achieves the accuracy and the number of rules 92.84% and 80, respectively. As a conclusion, transparent classifier shows a competitive performance with reasonable accuracy compared with previous research and promising in addressing the need for interpretability model.

E-commerce or online stores appear to provide convenience for the public in the field of information technology, Budi Luhur is a shop in the field of selling household needs such as cabinets, plate racks, spring beds, sofas, and electronics. But the problem is that until now, how to market their products still using manuals such as brochures, posters, and orders that are still recorded manually with books, so that the store requires costs that are sometimes not small in number to print brochures which will later be used to convey information to customers manually. To overcome these problems, it is necessary to create a system at the Budi Luhur store that can make it easier for customers and shop owners to make transactions. The design of Budi Luhur's E-Commerce System uses a Software development methodology, namely the waterfall method. This method is used by researchers to develop Software systems by having a Software life flow sequentially starting from analysis, design, coding and testing. To design the system using E-CRM (Electronic Electronic Customer Relationship Management), CodeIgniter Framework, PHP programming language and MySQL database.

There was a revolution in the learning process in schools during the Covid-19 pandemic. At this time, the digital era plays a very important role in replacing human interaction in carrying out all life activities in almost all fields. Currently the teaching and learning process is carried out online. However, for the field of motion learning in physical education, students still have to be able to practice the sports movements that have been arranged in the curriculum. This study aims to determine what learning models are used in providing motion learning materials during this pandemic. Methods: This study used is a survey method with descriptive analysis. The sample in this study were physical education teachers in Junior High Schools in Jakarta. Results: This study showed that the online physical education learning model that is most widely mastered and used in the teaching and learning process. Conclusion: The most widely used media in learning physical education are live youtube and motion learning videos.

Deteksi Covid-19 umumnya menggunakan tes laboratorium dengan metode RT-PCR untuk mendapatkan hasil yang akurat. Sayangnya, tes ini membutuhkan waktu yang cukup lama yaitu sekitar 24 jam untuk mendapatkan hasil. Selain menggunakan RT-PCR, beberapa penelitian menunjukkan bahwa deteksi menggunakan citra sinar-X menunjukkan hasil yang cukup akurat dengan waktu prediksi yang lebih cepat. Citra sinar-X yang didominasi warna dalam jangkauan grayscale dapat dikatakan memiliki karakteristik yang berbeda jika dibandingkan dengan citra secara umum, sehingga dalam penelitian ini eksperimen dilakukan terhadap pelatihan untuk kasus klasifikasi citra sinar-X dengan melatih model dari awal (scratch). Namun seringkali model yang dilatih tanpa adanya pretraining menyebabkan model tidak dapat mencapai performa yang cukup baik. Salah satu bentuk metode pretraining yang dapat digunakan adalah penggunaan autoencoder sebagai model untuk rekonstruksi citra. Dalam penelitian ini pelatihan menggunakan pretraining autoencoder menghasilkan akurasi terbaik sebesar 81.78% dengan tambahan metode CutMix, color manipulation, dan rotation sebagai augmentasi. Kami juga menunjukkan bahwa penambahan pretraining autoencoder secara konsisten dapat meningkatkan akurasi hingga 2.58% pada model yang dilatih dari awal (scratch).

This research aims to describe the development process of a problem-based learning management system-supported smartphone (PBLMS3) application using the ADDIE Model (analysis, design, development, implementation, and evaluation) and to determine its effectiveness in improving digital literacy. Data were collected from 40 physics education students in Tasikmalaya, consisting of 13 males and 27 females with an average age of 20 years. Data collection techniques included a literature study, expert validation, digital literacy test, and a questionnaire on student perceptions. Expert validation was obtained from three experts using a Likert scale and processed by the validation value equation developed by Aiken. The expert validation resulted in a value of 0.92, which met the minimum validation requirements. Furthermore, the effectiveness of the PBLMS3 application in improving digital literacy in online physics learning was determined by a statistical process using the Wilcoxon test. Based on its results, the t-value was ?0.4752, with a p-value of 0.00 < 0.05. This means that the PBLMS3 application is effective for and capable of improving students’ digital literacy. Further research is recommended to determine other factors capable of improving digital literacy. https://doi.org/10.26803/ijlter.20.11.7

Usaha Mikro, Kecil dan Menengah (UMKM) memegang peranan penting dalam pengembangan perekonomian Indonesia. Menghadapi persaingan yang makin ketat, ditambah pandemi COVID-19 yang melanda seluruh dunia, sangat penting bagi UMKM Indonesia untuk memiliki informasi keuangan yang dapat diandalkan. Keterbatasan sumber daya manusia yang dimiliki UMKM adalah kendala yang menghambat pemanfaatan software Enterprise Resource Planning (ERP) di dalam bisnis mereka. Kegiatan pengabdian ini bertujuan untuk memberdayakan UMKM Indonesia dalam penyusunan laporan keuangan sederhana. Kegiatan ini dilakukan dalam bentuk pelatihan dan pendampingan penyusunan neraca awal, penyusunan basis data serta posting transaksi dengan menggunakan software Fin@count. Metode pendampingan dalam kegiatan ini lebih efektif dalam membantu para pelaku UMKM untuk memahami dan dapat menggunakan bantuan software Fin@count di dalam bisnisnya. Kegiatan ini telah diikuti oleh 10 UMKM dan melalui kegiatan ini, masing-masing UMKM telah memiliki basis data dan laporan keuangan yang memadai. Kegiatan pendampingan terbukti efektif untuk membantu UMKM dalam tahap awal implementasi software ERP. Dengan demikian para pelaku UMKM akan lebih mudah untuk melanjutkan penggunaan software tersebut. Kegiatan pendampingan ini juga melibatkan sejumlah mahasiswa S1 Program Studi Akuntansi Fakultas Ekonomi Dan Bisnis Unika Soegijapranata. Melalui kesempatan ini, para mahasiswa dapat mendapatkan kesempatan praktik penyusunan anggaran dan laporan keuangan sederhana dalam kondisi aktual.

Recently, several methods for SARS-CoV-2 detection have been developed to obtain rapid, portable, cheap, and easy-to-use diagnostic tools. This review paper summarizes and discusses studies on the development of point-of-care devices for SARS-CoV-2 diagnosis with comparisons between them from several aspects. Various detection methods of the recently developed portable COVID-19 biosensor will be presented in this review. The discussion is divided into four major classifications based on the target biomarkers of SARS-CoV-2, such as antibodies, nucleic acids, antigens, and metabolic products. An overview of the potential development for future study is also provided. Moreover, basic knowledge of biosensors is also explained for tutoring the implementation of theory into the research of COVID-19 biosensors. This review paper is aimed to provide a tutorial by collecting the information on the development of a point-of-care device for SARS-CoV-2 detection to provide information for further research and propose the new COVID-19 portable diagnostic tool.

– The task of Army Aviation Operations is carried out in remote areas where airport services are still minimal, the process related to refueling for pilot helicopters is an obstacle in carrying out the pilot's main tasks. So, we need tools to make the process more effective. This research uses a method that will obtain quantitative data for research to prove the hypothesis. The method is known as the Development Life Cycle Waterfall Diagram and experimental research. Currently still using a hand pump, therefore it is necessary to have a tool that is portable and uses an electric pump. specifically for fuel which is controlled by Arduino and the android application as input for a filling command and can store charging data. In this case the tool system uses supporting components, namely batteries, Bluetooth hc 05, 5v relays and flow sensors. With the research on portable pump tools, the process can be more efficient than hand pumps. When refueling the helicopter, it is enough to enter the charging value from the android application, the charging is already running, and the charging data is stored in the android file.

Combat technology in the military world has undergone a very rapid development in both close combat and long-range combat. Long-range combat is identical to a rocket weapon where the rocket works because of the presence of an igniter that serves to burn the propellant so that when the propellant burns it will produce pressure that will push the rocket hurtling towards a predetermined target. Igniter is very important in the launch of rockets where the filling of the igniter is black powder that has been difficult to obtain because of the difficult manufacturing process and risk of explosion. This research aims to design a tool that can produce black powder with a large enough capacity and good quality and reduce the risk of explosions to support the manufacture of igniters for rocket launches, especially those owned by Indonesian Army. This research used pure experimental quantitative method with empirical calculations to obtain tools with the desired specifications. The results obtained after the calculation are the volume of octagonal prism tubes 2942.5 cm3, the total volume of steel balls with two size variations is 979.5 cm3, the maximum lendutan that occurs on the shaft of the player is 0.108 mm, so it is said to be safe.

The implementation of the use of PLC in this study was designed for a small scale in the process of stirring coffee drinks at a speed of 600 RPM. To get a stable speed so that the water does not overflow, a control system is needed. To get optimal results, a system design that can control the stirring speed is arranged automatically using a Programmable Logic Controller (PLC). This system is designed using a rotary encoder sensor C38S6G5-600B-G24N as a speed reader obtained from the movement of the motor, DC Motor JGA25-370 12V as an actuator or stirrer. PLC OMRON CP1E-NA20DR-A is used as a motor speed control device using the Proportional Integral Derivative (PID) algorithm to control the system according to the setpoint entered. The motor speed control system with the PID algorithm shows a system response that works well according to the researchers' expectations. The response of the system obtained is fast enough to achieve a stable speed with a small overshoot value. Thus this system was successfully designed to control the stirring process of coffee drinks automatically and produce stable stirring by giving a set point of 600 RPM at the parameter constant Proportional band is 720%; Integral time is 1.6s; and Derivative time is 0.2s with a rise time value is 1.3s; settling time is 11s; overshoot is 1.1%; and steady-state error is 0.5%.

The rapid development of technology today is very useful for humans in various aspects of life. One of the impacts of these technological developments is IoT (Internet of Things). Currently, IoT has been widely used in various fields such as manufacturing, offices, public transportation, and education. One of the uses of IoT in the field of education is to create a biometric attendance system using fingerprints. The purpose why use the fingerprints is to reduce cheating committed by students such as leaving absent. By using the fingerprint IoT attendance system, this is difficult to do because everyone has a different form of fingerprint. In addition, this project integrates fingerprint attendance with the Telegram messenger application. All fingerprints and student attendance data are stored on the website. Based on the experimental results, the success rate of this attendance system is 80%, and the accuracy is 89%.

Perangkat komputer sangat dibutuhkan dalam menyelesaikan pekerjaan – pekerjaan pada sebuah perusahaan, untuk memudahkan dalam pengambilan data yang terpusat berbagi sumber daya maka komputer harus terhubung dengan jaringan lokal area network. Menggunakan ip address setiap komputer yang berbeda-beda dapat terhubung ke jaringan lokal area network yang dihubungkan dengan kabel atau perantara wirkabel, dalam memudahkan akses sebuah server dapat menerapkan domain name server sehingga mudah untuk mengingat nama domainnya ketimbang harus mengingat ip address nya. Penelitian ini menggunakan beberapa tahapan metode yaitu dimulai dengan analysis yaitu melakukan Analisa kebutuhan perangkat keras dan perangkat lunak, kedua desain yaitu melakukan rancangangan topologi jaringan, ketiga implementasi yaitu melakukan penerapan konfigurasi pada ubuntu server 16.04 dan keempat testing yaitu melakukan pengujian terhadap hasil implementasi. pada pengujian dilakukan, pengujian koneksi menggunakan ip address dan domain dari pengguna ke server menghasilkan terhubung, serta pengujian query dengan perintah nslookup dari pc user ke server menghasilkan dapat menerjemahkan alamat domain dengan ip address

The firing system on the S-60 57mm cannon uses the foot of the cannon crew, which is very dangerous with the position of the crew on top of the cannon when firing. So, a firing system that can be remotely controlled by a computer is required. The design of the S-60 57mm gun firing control system uses a personal computer (PC) as the firing command input, with data communication using WiFi received by the Atmega8535 microcontroller as a voltage regulator for solenoids. The solenoid has a tensile force to drive the hydraulic system where the actuator functions to drive the firing cylinder. Accelero sensor MMA7361, as a variable controller in firing, provides input data simulating the tilt position of the cannon, the position of the 0g sensor is simulated by the cannon in a balanced position. From the test results, there is a difference in sensor designation data with arc angles i.e., angle X by 2.83 degrees and angle Y by 1.86 degrees. The magnetic field produced by the solenoid 0.53 T can attract a maximum load of 20 kg. By changing the distance ratio of mechanical lever to 39.11 cm and 8.89 cm, the solenoid can drive an 88-kg firing cylinder.

Facial expression recognition is one of the types of non-verbal communication that is not only commons for human but also plays an essential role in everyday lives. The development of science and technology allows the machine to automatically detect human facial expressions based on images and videos. Numerous facial expression detection methods have been proposed in the literature. This paper presents a method to find three basic facial expressions (neutral, happy, and angry) from two parameter values: smile and eyes-open. The analysis involves a preprocessing step using a combination of pre-designed proprietary algorithm and Luxand library. Firstly, the parameters were mapped into two-dimensional space and then grouped into three clusters using K-means, a popular heuristic clustering method. Secondly, more than 50,000 frames for each video were experimented using the proprietary research data. The result shows that the proposed method successfully performed a simple video analysis of facial expressions.

The essence of man in life is to conduct communication activities. An individual is said to communicate with others if both have an understanding of the meaning of the message conveyed in his interaction. Advances in information communication technology provide opportunities for individuals to more easily interact over the internet. Of the recorded internet users, 130 million are active on social media. New Media Communication, or communication based on information technology, makes social media a prima donna for individuals to interact socially in cyberspace. Text-based communication platforms such as WhatsApp and LINE make it easier for individuals or those in cyberspace referred to as digital natives to interact. These digital natives in their interactions do the continuous thing as a habit that eventually becomes a culture of communication. In this research, the focus of research is the evolution of communication between users in the new media era in LINE users as a text application-based social media with a constructivist approach, qualitative research methodology with virtual ethnographic research methods and descriptive analysis levels. Data collection with online interviews, as well as chat history observations and the use of LINE sticker features. The purpose of the study is: (1) to find out the communication of digital natives on the LINE application platform, (2) to find out the evolution of interpersona communication formed from the results of native digital interactions on the LINE application platform using a virtual ethnographic approach.

Sistem komputerisasi sudah menjadi hal yang biasa, melihat perkembangan teknologi di Indonesia pada saat ini. Sistem pendaftaran, pengolahan nilai dan absensi guru pada SDN 17 Prabumulih masih manual. Sehingga terkadang menyebabkan kurang efektif dan sering terjadinya kekeliruan, Maka dari itu dibuatkan sebuah sistem informasi yang terkomputerisasi sehingga proses pendaftaran, pengolahan nilai siswa dan absensi guru maupun staff TU pada SDN 17 Prabumulih dapat dilakukan dengan maksimal. Metode yang diajukan dalam pembuatan sistem ini yaitu dengan metode Pengembangan Prototype dengan menggunakan Unified Modeling Language (UML) sebagai bahasa pemodelannya menggunakan PHP sebagai programnya serta MySQL sebagai databasenya. Dengan adanya sistem informasi ini, maka calon siswa baru dapat melakukan pendaftaran secara online, pengolahan nilai siswa dan absensi guru serta staff TU sudah terkomputerisasi. Kata kunci—Sistem Informasi, UML, PHP, & MySQL

The aim of this study was to produce a mathematics worksheet on absolute value material based on the Realistic Mathematical Education (RME) approach. The location of this research is Tribhuwana Tunggadewi University. The development model in this research is designed based on ADDIE, which includes: (A) analysis, which is about curriculum analysis and needs analysis; (D) design, containing the preparation of the worksheet; (D) development, intended in the process of developing an RME-based absolute value worksheet; (I) implementation, namely product testing conducted for small groups and for large groups with the aim of obtaining practical data and data on mathematical thinking skills; (E) evaluation, which is carried out in data analysis refers to the implementation stage. The results of product validation through a google form questionnaire conducted by media experts were 92%, material experts 87%, small group test 91%, large group test 88%, and students' mathematical thinking ability test results reached 83%. Based on these data, it shows that the designed worksheet is feasible and practical in improving the mathematical thinking skills of Tribhuwana Tunggadewi University students.

Not all mushrooms are edible because some are poisonous. The edible or poisonous mushrooms can be identified by paying attention to the morphological characteristics of mushrooms, such as shape, color, and texture. There is an issue: some poisonous mushrooms have morphological features that are very similar to edible mushrooms. It can lead to the misidentification of mushrooms. This work aims to recognize edible or poisonous mushrooms using a Deep Learning approach, typically Convolutional Neural Networks. Because the training process will take a long time, Transfer Learning was applied to accelerate the learning process. Transfer learning uses an existing model as a base model in our neural network by transferring information from the related domain. There are Four base models are used, namely MobileNets, MobileNetV2, ResNet50, and VGG19. Each base model will be subjected to several experimental scenarios, such as setting the different learning rate values for pre-training and fine-tuning. The results show that the Convolutional Neural Network with transfer learning method can recognize edible or poisonous mushrooms with more than 86% accuracy. Moreover, the best accuracy result is 92.19% obtained from the base model of MobileNetsV2 with a learning rate of 0,00001 at the pre-training stage and 0,0001 at the fine-tuning stage.

Tujuan penelitian ini adalah untuk merencanakan aktifitas preventive maintenanance yang efektif sehingga dapat menjamin kehandalan sistem, agar dapat beroperai tanpa mengalami kerusakan komponen yang menyebabkan kegagalan sistem. Sistem kerja Ram Air Actuator Part Number 541674-4 pesawat Boeing 737 NG sering mengalami kerusakan sehingga mengakibatkan kegagalan pada operasional sistem, penyebab kegagalan sistem operasional adalah Kerusakan pada komponen wear and bearing damage, housing assembly, problem bearing damge, wear damage, electrical problem stuck. Permasalah tesebut mendorong dilakukannya penelitian untuk menanggulagi kerusakan dan kegagalan pada sistem Ram Air Actuator pesawat boeing 737 NG. Penelitian dilaksanakan dengan analisis kualitatif dan analisis kuantitatif, analisis kualitatif yang dilaksankan dengan menggunakan metode FMEA (failure mode effect analysis) untuk mengetahui dan mengidentifikasi penyebab kegagalan pada sistem Ram Air Actuator, analisis kuantitatif dilaksanakan dengan perhitungan reliability menggunakan distribusi weibull sehingga di ketahui batas critical life time part atau komponen Ram Air Actuator. Berdasarkan hasil analisis reliability didapatkan nilai batas waktu operasional, dimana sistem akan mengalami masa kritis ketika mencapai waktu operasional yaitu Mechanical system = 1680 jam dengan nilai reliability 72%, Electrical system = 3401 jam dengan nilai reliability 72%, Pneumatik system = 3201 jam dengan nilai reliability 70%. Setelah mengetahui batas masa kritis komponen (critical life time), maka akan dilakukan perencanaan preventive maintenance terhadap part dan komponen penyebab kegagalan sehingga tidak terjadi lagi kegegalan sistem Ram Air Actuator pesawat boeing 737 NG.

Scientific journals develop very rapidly along with the development of science. Reporting from labs.semanticscholar.org/corpus, the number of scientific journals has reached over 39 million. The large number of scientific journals makes it challenging to grouping scientific journals. Grouping become more difficult because each scientific journal can have more than one topic. Therefore, special methods are needed to group the scientific journals.One of the well-known topic modeling methods is Latent Dirichlet Allocation (LDA). This research is an implementation of the LDA algorithm to do topic modeling in scientific journals. The topic modeling in this study uses the title as a corpus. Various titles are processed into bag of words in the pre-processing process so that they can be used to distribute. The results of the distribution stage are used for sampling with the Gibbs Sampling method. Through the sampling process, testing can also be done to determine the optimal parameters. The testing in this study used perplexity to find the most optimal number of iterations and topics. The result from this research are that LDA Algorithm successfully performs topic modeling in scientific journals by generating a list of keywords for each topic and grouping documents on each topic. The optimal parameters based on the results of perplexity comparison are 3 topics and 500 iterations.

Pertumbuhan ekonomi merupakan laju pertumbuhan yang terbentuk dari berbagai macam sektor ekonomi yang tidak langsung menggambarkan tingkat perubahan ekonomi yang terjadi. Analisa ini ditujukan untuk mencari faktor-faktor yang mempengaruhi pertumbuhan ekonomi di Kabupaten Mojokerto yang nantinya akan diketahui signifikan tidaknya faktor tersebut terhadap pertumbuhan ekonomi di Kabupaten Mojokerto. Penelitian ini bertujuan untuk mengetahui variabel apa yang memiliki pengaruh terbesar terhadap pertumbuhan ekonomi di Kabupaten Mojokerto. Variabel yang diuji adalah investasi, jumlah industri, kurs valuta asing dan ekspor. Penelitian ini menggunakan data sekunder yang diambil dari Badan Pusat Statistik Kabupaten Mojokerto, dengan time series data Tahun 2002-2018. Model analisis yang digunakan adalah analisis regresi linier berganda dengan asumsi BLUE (Best Linier Unbiased Estimate) dengan tujuan untuk mengetahui koefisiensi pada persamaan tersebut benar (tidak bias). Berdasarkan hasil uji regresi linier berganda yang dilakukan, diperoleh hasil bahwa variabel jumlah industri sangat berpengaruh terhadap pertumbuhan ekonomi di Kabupaten Mojokerto, sedangkan ketiga faktor lainnya yakni investasi, kurs dan ekspor tidak berpengaruh secara signifikan terhadap pertumbuhan ekonomi di Kabupaten Mojokerto.

Modern technology today, especially in the world of technology Robots are developing very rapidly. Many developed countries are competing and vying to make increasingly sophisticated robots. In Indonesia, robots have also begun to develop. Developments in the field of robotics are also able to have a positive impact in the industrial sector. One example is the process of moving an item/object from one place to another. This study aims to test the motion system, namely a DC motor that functions as a motor for carrying goods. The method used is input from commands given by the user via a smartphone with voice access. As an intermediary, a bluetooth connection is used so that commands can be sent from a smartphone to the control circuit. The controller used is the AVR type, namely atmega 328 on the Arduino Uno board. At the output, there are relays and current amplifiers that function as motor drivers. The user will give orders via a smartphone where on the smartphone runs an application, namely a voice to text converter. The application will convert the human voice into text and send via bluetooth to the controller. The Arduino controller will identify the command code and execute it, namely controlling the robot's motion in the direction desired by the user, for example forward, backward left and right or towards a predetermined point.

Personality provides a deep insight of someone and has an important part in someone’s job performance. Predicting personality through social media has been studied on several research. The problem is how to improve the performance of personality prediction system. The purpose of this research is to predict personality on Twitter users and increase the performance of the personality prediction system. An online survey using Big Five Inventory (BFI) questionnaire has been distributed and gathered 295 Twitter users with 511,617 tweets data. In this research, we experiment on two different methods using Support Vector Machine (SVM), and the combination of SVM and BERT as the semantic approach. This research also implements Linguistic Inquiry Word Count (LIWC) as the linguistic feature for personality prediction system. The results showed that combination of these two methods achieve 79.35% accuracy score and with the implementation of LIWC can improve the accuracy score up to 80.07%. Overall, these results showed that the combination of SVM and BERT as the semantic approach with the implementation of LIWC is recommended to gain a better performance for the personality prediction system. &nbsp, Personality provides a deep insight of someone and has an important part in someone’s job performance. Predicting personality through social media has been studied on several research. The problem is how to improve the performance of personality prediction system. The purpose of this research is to predict personality on Twitter users and increase the performance of the personality prediction system. An online survey using Big Five Inventory (BFI) questionnaire has been distributed and gathered 295 Twitter users with 511,617 tweets data. In this research, we experiment on two different methods using Support Vector Machine (SVM), and the combination of SVM and BERT as the semantic approach. This research also implements Linguistic Inquiry Word Count (LIWC) as the linguistic feature for personality prediction system. The results showed that combination of these two methods achieve 79.35% accuracy score and with the implementation of LIWC can improve the accuracy score up to 80.07%. Overall, these results showed that the combination of SVM and BERT as the semantic approach with the implementation of LIWC is recommended to gain a better performance for the personality prediction system.

Facial recognition merupakan salah satu teknik biometrik. Teknik yang dapat disebut juga pengenalan wajah ini telah menjadi topik yang cukup diminati untuk diteliti. Pada peneitian ini dilakukan proses pengenalan wajah dengan menggunakan metode CNN (Convolutional Neural Network). Penelitian ini memiliki tujuan untuk mengimplementasikan metode CNN ke dalam pengenalan wajah dengan menggunakan library Tensorflow. Metode ini digunakan karena proses pembelajaran dilakukan dengan mendalam (deep learning). Metode CNN yang digunakan memiliki beberapa lapisan pada proses training yang dilakukan, yaitu lapisan Conv2D, MaxPooling2d, Flatten, dan Dense. Face recognition yang dihasilkan terdapat pendeteksi wajah menggunakan Haar Cascade dengan bantuan library Opencv di dalamnya. Jumlah dataset juga diketahui dapat mempengaruhi hasil pengenalan dan proses pengenalan wajah dengan CNN juga memerlukan dataset yang besar. Adapun jumlah citra wajah yang digunakan dalam penelitian ini sebanyak 90.000 gambar wajah yang berasal dari 36 himpunan gambar dan menghasilkan tingkat akurasi sebesar 97%.

Purpose: The research aims to design a performance improvement framework for a new model of sports shoes to increase the ramp-up process time. Methodology/Approach: The approach used the problem-solving system of 8 disciplines, Single Minute Exchange Dies, Visual Management, and the Just In Time principle. Findings: By using the methods described above, the research findings will have a positive impact on the company. Model changeover time was reduced from 600 minutes to 102 minutes, and ramp-up time was reduced from 20 days to 2 days. Research Limitation/Implication: The limitation of this study was that only the CK2946 model was still done as a case study. The cost and other inhibiting factors were also not included in the discussion of this rump-up process. Originality/Value of paper: By integrating SMED, Just In Time, visual management, and using 8-Dicipline, the researcher developed a framework for improved performance for ramping up a new model of sports shoes.

The many types of production of goods in a company spearhead the progress of this company in industrial competition in Indonesia, the variety of types of products and large production capacity makes this company need a large number of employees to balance the variety and production capacity. This large number of employees creates its own problems, one of the problems is employee performance appraisal, employee performance appraisal in this company is only centered on the highest supervisor's consideration in one section. From that problem, the researcher wants to solve the problem using the Balanced Score Card (BSC) method by using the determination and weighting of Key Performance Indicators (KPI). The final result of the research conducted at PT Alam Jaya Primanusa in May 2018 the results of the following employee achievement grades and categories: Average material value: 76.65 Fair category, Operator's average value: 85.51 Good category, Average value - Selector section average: 89.79 Good category, Packer section average value: 94.98 Good category, Values ​​in each of these sections become the basis for calculations for all injection division production, so conclusions are drawn for the final value and achievement category of all injection division production the value of 83.37 in the Fair category.

Value Stream Mapping (VSM) is a technique used in the lean principle that helps analyze the flow of materials and information needed to bring a product or service to the customer. VSM has received a lot of attention in the industrial sector from both the manufacturing industry and the service industry. The development of VSM tools has grown rapidly. Much of the research using VSM tools is carried out in industry and universities. This literature review aims to provide an overview of the implementation of Value Stream Mapping in the service industry and to find out its implications. This paper involves a review study of 45 papers related to a case study of VSM implementation in the service industry. The study was conducted using the Google Scholar database, Researchgate, ProQuest, Elsevier. This paper provides an advantage for the service industry to find problems related to waiting times. This paper extends the knowledge and study of the application of VSM as an unexplored tool in several branches of industry. VSM can also serve as a complementary approach, capable of increasing outcomes in many areas other than services. This paper also provides benefits for future researchers to add insights and references for studies related to VSM in the service industry sector.

The amount of retrievable smartphone data is escalating; while some apps on the smartphone are evidently exploiting and leaking users’ data. These phenomena potentially violate privacy and personal data protection laws as various studies have showed that technologies such as artificial intelligence could transform smartphone data into personal data by generating user identification and user profiling. User identification identifies specific users among the data based upon the users’ characteristics and users profiling generates users’ traits (e.g. age and personality) by exploring how data is correlated with personal information. Nevertheless, the comprehensive review papers discussing both of the topics are limited. This paper thus aims to provide a comprehensive review of user identification and user profiling using smartphone data. Compared to the existing review papers, this paper has a broader lens by reviewing the general applications of smartphone data before focusing on smartphone usage data. This paper also discusses some possible data sources that can be used in this research topic.

The news platform has moved from traditional newspapers to online communities in the technologically advanced area of Artificial Intelligence. Because Twitter and Facebook allow us to consume news much faster and with less restricted editing, false information continues to spread at an impressive rate and volume. Online Fake News Detection is a promising field in research and captivates the attention of researchers. The sprawl of huge chunks of misinformation in social network platforms is vulnerable to global risk. This article recommends using a Machine Learning optimization technique for automated news article classification on Facebook and Twitter. The emergence of the research is facilitated by the strategic implementation of Natural Language Processing for social forum fake news findings in order to distort news reports from non-recurrent outlets. The relent from the study is outstanding with text document frequency words, which act as extraction technique’s attribute, and the classifier is acted upon by Hybrid Support Vector Machine by achieving 91.23% accuracy.

Sometimes, some people do not throw trash in their place because they are lazy, so it happens to children. Many children prefer to throw trash at anywhere and become one of the problems in the school or community environment. . This is a bad habit because there is no awareness to keep the environment clean. This research is to produce an Arduino-based TCT (Trash Can Talk) rubbish bin with a solar cell system for learning tools for orderly behavior of garbage disposal in children. TCT was made using an arduino uno R3 microcontroller, a PIR sensor to detect the presence of children so that the trash can emit 2 sounds from the DF mini mp3 player through the speaker alternately to attract the attention of children and "open" voice commands detected by the voice recognition sensor to open the trash can automatically and the "close" voice command to close the trash can then make a third sound from the DF mini mp3 player through speakers for children who have disposed of garbage in an orderly manner. The fourth sound from the DF mini mp3 player through the speaker as a full notification and the trash can can't open.

Learning activities are one of the processes of delivering information or messages from teachers to students. SMPN 4 Sidoarjo is a State Junior High School (JHS) located in Sidoarjo Regency. During the learning process, the collected academic score data were still not well organized by teachers and school principals in monitoring student learning performance. The score data is from Bahasa Indonesia subject from a teacher with 222 data included at 2019/2020 school year. The method used in student clustering is K-Means. The number of clusters are determined using the elbow method and displayed in graphic form. Clustering result can be used as a reference for teachers in determining study groups and determining the best treatment for each cluster. The best clustering results are proven by validation score using Davies-Bouldin Index, Silhouette Width, and Calinski-Harabasz Index. Three clusters were obtained for each class level of data, while the cluster ranges from two to five for the data for each study group. The dashboard is used in order to visualize the clustering result. Usability testing using System Usability Scale (SUS) has a score value of 87.5, which means that the dashboard can be accepted by SMPN 4 Sidoarjo.

Kata Kunci : High Fidelity, Low Fidelity, Usability Testing, User-centered Design, User Experience, User Interface, , User Interview, User Persona, User Survey. PMB STIKI Online memanfaatkan website sebagai media untuk memberikan informasi terkait perkuliahan di STIKI Malang. Pengembangan sebuah website harus melalui beberapa pedoman usability untuk memastikan tujuan website tersebut dapat dicapai. Pendekatan penelitian dilakukan menggunakan user-centered design dengan melibatkan pengguna pada proses perancangan desain untuk menghasilkan tampilan website yang dapat diterima pengguna. STIKI PMB Online sebelumnya belum pernah dievaluasi terkait masalah – masalah yang dihadapi oleh calon mahasiswa salah satunya, sulitnya menemukan informasi yang ingin didapatkan. Permasalahan – permasalahan yang terdapat pada STIKI PMB Online tersebut diharapkan dapat terselesaikan pada solusi desain yang akan dilakukan, yang mana akan dibuat lebih sederhana dan memudahkan pengguna menemukan tujuannya. Penelitian ini membahas mulai dari penetapan konteks penggunaan dan spesifikasi kebutuhan pengguna, analisis permasalahan, perancangan desain solusi, dan hasil evaluasi desain. Hasil penelitian ini menunjukkan bahwa permasalahan yang terjadi dapat terselesaikan dengan aturan desain yang terdapat dalam standarisasi usability seperti : kemampuan belajar, efisiensi, ingatan, kesalahan dan kepuasan.

The garment supply chain is one of the most common supply chains in the world. In this supply chain, quality and cost are the most important factors that are strongly related to the selection of suppliers and the allocation of orders to them. Accordingly, the purpose of this paper is to integrate decisions for supplier selection, order allocation, and multi- source, multi-mode, multi-product shipping plans with consideration of discounts under uncertainty. For this purpose, a multi-objective mixed-integer mathematical model is presented, including the objectives of minimizing costs and products with delays and maximizing the total purchase value. In this mathematical model, the policy of purchasing materials and determining the number and type of transport equipment are specified. To solve this mathematical model, a goal-flexible programming approach with a utility function is presented. In the solution algorithm, a new possibility-flexible programming method has been developed to deal with the uncertainties in the model, which is based on the expected value method and chance constraint. Finally, using a numerical problem, the establishment of the above model in the garment supply chain is investigated. As indicated by the outcomes, the proposed model was touchy to certain boundaries, including blended leaders’ mentality, a boundary identified with fluffy imperatives, and the degree of certainty characterized by the chief for not exactly equivalent limitations.

Drop-foot is an inability to lift the foot when walking due to muscle weakness or paralysis. One of the common rehabilitation aids for stroke sufferers with drop-foot is Ankle Foot Orthosis (AFO). This tool serves as a stabilizer for road pattern balance. However, most of the AFO used is passive, so it doesn't help users run properly. Therefore, an active AFO system has been designed as a rehabilitation aid. This AFO is designed with motor control from myoelectric feedback signal (EMG) and also a semi-dynamic ankle joint so that it is more flexible to help the user when stepping. The AFO movement set of to the foot's position in Dorsi and Plantarflexion conditions based on the EMG parameter received by the control unit. Then, the angle sensor standardizes the user's ankle position so that the foot fits the states that have set. This design uses the fuzzy logic method, which functions to control the rotation of the servo motor. The interface system is for monitoring parameters. In this design, pressure sensors (force), EMG, and angle sensors transmitted wirelessly to a computer are used for data analysis under the needs of real-time statistical data processing.

Most research about the inflow and outflow currency in Indonesia showed that these data contained both linear and nonlinear patterns with calendar variation effect. The goal of this research is to propose a hybrid model by combining ARIMAX and Deep Neural Network (DNN), known as hybrid ARIMAX-DNN, for improving the forecast accuracy in the currency prediction in East Java, Indonesia. ARIMAX is class of classical time series models that could accurately handle linear pattern and calendar variation effect. Whereas, DNN is known as a machine learning method that powerful to tackle a nonlinear pattern. Data about 32 denominations of inflow and outflow currency in East Java are used as case studies. The best model was selected based on the smallest value of RMSE and sMAPE at the testing dataset. The results showed that the hybrid ARIMAX-DNN model improved the forecast accuracy and outperformed the individual models, both ARIMAX and DNN, at 26 denominations of inflow and outflow currency. Hence, it can be concluded that hybrid classical time series and machine learning methods tend to yield more accurate forecasts than individual models, both classical time series and machine learning methods.

Accidents caused by malfunctioning of the brake light system are increasing in line with the rise in road facilities. It provides space for drivers to drive vehicles quickly. To overcome this problem, a system that can signal the driver must rapidly identify the damaged brake lights. The purpose of this study was to produce a car brake indicator tool. This tool is an electronic device that functions to determine the brake light when one of the brake lights is off by automatically giving a signal on the car's dashboard. The method used to produce brake work indicator tools consists of designing, manufacturing, and testing. The testing process has been carried out through a lux meter, and the test variables include testing the use of electric current, voltage when the tool is working, and trying the performance of the device on the car. From testing this tool, the results obtained when the current usage of the tool is working, namely before the induction works of 2 amperes and when the induction works it is 0.5 amperes. The magnitude of the voltage when the device is used is 11.8 volts. Based on the experiments that have been carried out, there are no disturbances in the lighting system or other systems on the car when this tool is working. This tool can work well to provide convenience and comfort when driving by car. Based on the experiments that have been carried out, there are no disturbances in the lighting system or other systems on the vehicle when this tool is working. This tool can work well to provide convenience and comfort when driving by car. Based on the experiments that have been carried out, there are no disturbances in the lighting system or other systems on the vehicle when this tool is working. This tool can work well to provide convenience and comfort when driving by car.

Data is an important thing as a base of an analytic or a hypothesis for concluding participant vote data in the Indonesian General Election. The data needs to be processed and secured, so the integrity of the data is in good condition. It also needs to protect the participant voting rights, so the information is correctly displayed. The research problems include creating a system that protects the integrity of election data and creating a system that protects election rights for each voter. Based on the problems, this research discusses a blockchain-based electronic voting information system that would secure the integrity of data and also protecting the participant voting rights in a General Election. The system uses Ethereum as a blockchain with Solidity as a programming language to build a smart contract and is built in Microsoft Windows platform. In this research, consortium blockchain and biometric fingerprint authentication are used as a problem-solving method, and waterfall steps is used as a system development method. The result of this research is a proposed design of the e-voting system. The conclusion based on this research is a blockchain-based e-voting system that secures the integrity of the data in a selection process and ensures protection to each vote right. Index Terms—Authentication; Blockchain; Data; Integrity; E-Voting; System

This study discusses how Finite State Automata (FSA) can be used as a model to design a Tajweed Science game application as a business diagram. This study aims to facilitate early childhood in learning the science of recitation by grouping hijaiyah letters into grouping the science of recitation by using a touch of the hand. The type of automata theory used is a non-deterministic finite automata with epsilon transition (E) or better known as E-NFA. Each transition, input, state that exists from the NFA, is basically to show the characteristics or states that occur in a game application. The importance of this research, in addition to learning recitation from an early age, is to show that automata theory can be used to help design a system in making game applications. The results of this Tajweed Science game application design are a rough display because there will still be further development stages and can ensure that game applications can be built from E-NFA modeling.

Recently, Sentiment Analysis is used for expression detection of products or services. Sentiment Analysis is one category type with a level of aspect focused on extracting product aspects. One of the common methods used for aspect extraction is Latent Dirichlet Allocation (LDA) using random topic identification, but this method has not been able to find an acceptable topic with some aspects having been found. Undeterminable topics are referred to as the hidden topics. This study purpose is to evaluate and compare the suitability of identifying hidden topics between human and computer evaluation. The study is also focused on aspect extraction using a variety of LDA innovations. The data used in this study used case studies on e-Commerce. Data were processed using feature selection and grouped using LDA development. Then the data results are processed using Latent Topic Identification based on subjective and objective evaluations. The identification of hidden topic results was evaluated using several semantic and lexicon tests. The evaluation results indicate the comparison of two hidden topic identification assessment values is quite relevant with the average difference in value reaching 6%. As a result, computer calculations assist humans in determining topics if each topic has a low coherence value. &nbsp, atau jasa. Sentiment Analysis mempunyai beberapa klasifikasi dan tingkatan, salah satu jenis Sentiment Analysis tersebut adalah tingkat aspek yang berfokus pada ekstraksi aspek suatu produk. Penelitian ini menggunakan metode yang populer saat ini, yaitu, Latent Dirichlet Allocation (LDA) yang menggunakan identifikasi topik secara acak. Akan tetapi metode ini belum dapat menentukan topik yang sesuai dengan aspek-aspek yang diperoleh. Topik yang belum bisa ditentukan tersebut juga bisa disebut dengan topik tersembunyi. Fokus penelitian ini adalah evaluasi dan perbandingan kesesuaian dari identifikasi topik yang tersembunyi antara penilaian manusia dan perhitungan komputer. Penelitian ini didasarkan pada ekstraksi aspek menggunakan beberapa pengembangan LDA. Data yang digunakan pada penelitian ini menggunakan studi kasus pada e-Commerce dengan jumlah ulasan sebanyak 28.222. Pengolahan data menggunakan seleksi fitur dengan nilai α sebesar 0,99 dan dikelompokkan menggunakan pengembangan LDA yang ditentukan dengan nilai hyperparameter α sebesar 0,9 dan β sebesar 0,05. Kemudian hasil data tersebut diolah menggunakan Latent Topic Identification berdasarkan penilaian subjektif dan objektif. Hasil identifikasi topik tersembunyi dievaluasi menggunakan beberapa pengujian semantik dan leksikon. Hasil evaluasi mengindikasikan bahwa nilai perbandingan kedua penilaian identifikasi topik tersembunyi cukup relevan dengan rata-rata selisih nilai mencapai 6%. Sehingga perhitungan komputer dapat membantu manusia untuk menentukan topik jika setiap aspek memiliki nilai koherensi yang rendah.

The research used in assessing the performance of internal business processes in this study uses strategic management theory and operations management through the Resource-Based View approach, Market-Based View aspects and Organization Culture. The Banking Industry has to think about the business processes and workflows to empower employees and what they need to do to stay competitive in the face of rapidly changing competition. The method used in this research is a Literature Review with a descriptive approach that will produce a conceptual model. The resulting conceptual model development was adopted from DeLone and McLean's Model about the success of the Information System which was combined with the input variables studied to produce an implementation model for the integration of business functions to improve the performance of internal business processes.

The success of information systems research has begun to decline in the past few years, but existing research is still inaccurate in its definition and in the factors that affect the success of the information system. The purpose of this research is to find out, study, and analyze the effectiveness of implementing academic information systems in universities to improve the quality of information. The research was conducted using a qualitative approach and case studies, namely problem formulation, study proposition, analysis unit, data linkage to the proposition, the criteria for interpreting the findings, and making conclusions and recommendations. From the results of the research data analysis, several conclusions were obtained, namely, the academic information system running in universities has not met expectations. The performance of academic information systems that can support the smooth operation of the universities is not well understood. It is necessary to formulate an optimal academic information system strengthening strategy that can support the smooth operation of the universities.

The CBU type motorcycle (completely built up) had components imported from abroad. The advantages of handling a light motorbike, a large motor power and a DOHC engine. One of the weaknesses of which is the engine that heats up quickly even though it uses a radiator as the cooling system. In the performance test of the CBU Yamaha R6 and Honda CBR600F4I motorbike engines, the fuel was used for the Pertamax turbo type with an octane value of 98 to make the engine stable at high compression. The resulting performance of the gasoline motor is in the form of torque and power data using a dynamometer. How to see the performance data of a gasoline motor can make measurements on the crankshaft, input the temperature and output of the combustion system chamber as well as the ambient temperature. The research aims to see the performance data of the two machines. The method will produce experimental data analysis in graphs and tables. The biggest performance was obtained from the CBU type Honda CBR600F4I motorbike engine with Pertamax turbo fuel, namely with a torque of 46.74 Nm, at 13,630 rpm and a power of 114.48 Hp, while the Yamaha R6 motorbike engine with Pertamax turbo fuel only had a torque of 40.65 Nm, at 12,600 rpm and a power of 90.81 Hp

Presentation is a type of public speaking which requires special skills besides language competency. Presentation skill in English is a lesson or subject which can be found in some educational institutions in Indonesia. Besides presentation, public speaking can be in a form of speech, debate, and meeting. In public speaking, a speaker can face more than two people or even hundreds or thousands of people. While in ordinary conversation, the speakers and the listener called interlocutors are limited to only a few people. Presentation class is meant to improve the students’ performance in English public speaking. Feedback is usually given after a presentation activity is completed. In this case, the students who were trained were given feedback by the teacher. Feedback is given thoroughly on the language, content, and method of presentation. Research on feedback or assessment on oral presentation is underexplored. The present research is proof supported with empirical data which suggests that the role of feedback is important and statistically assessed as significant in making the later performance better. The main factor that determines the quality of a presentation is language skill. However, there are other aspects that are quite decisive such as the material or topic of the presentation and the presentation method.

Detecting the sentence boundary is one of the crucial pre-processing steps in natural language processing. It can define the boundary of a sentence since the border between a sentence, and another sentence might be ambiguous. Because there are multiple separators and dynamic sentence patterns, using a full stop at the end of a sentence is sometimes inappropriate. This research uses a deep learning approach to split each sentence from an Indonesian news document. Hence, there is no need to define any handcrafted features or rules. In Part of Speech Tagging and Named Entity Recognition, we use sequence labeling to determine sentence boundaries. Two labels will be used, namely O as a non-boundary token and E as the last token marker in the sentence. To do this, we used the Bi-LSTM approach, which has been widely used in sequence labeling. We have proved that our approach works for Indonesian text using pre-trained embedding in Indonesian, as in previous studies. This study achieved an F1-Score value of 98.49 percent. When compared to previous studies, the achieved performance represents a significant increase in outcomes..

Cilacap State Polytechnic (PNC) is a Polytechnic that has several scholarships in it. Bidikmisi is one of the scholarships available at PNC. Bidikmisi scholarship recipients are required to report their achievements every semester to the Biro Administrasi Akademik dan Kemahasiswaan (BAAK) which still often experiences problems, including student delays in collecting achievement reports, BAAK finds it difficult to monitor the progress of student achievement, especially in the non-academic field because all the data is in each student. This research focuses on monitoring related to student achievement. Making this system using the waterfall method because it is systematic. The results of the questionnaire show that this system can assist in the process of managing and monitoring student achievement with a percentage of around 60% stating it is good and can help students to notify the results of their achievements and can be accessed at any time without having to wait for information or visit the BAAK room with a high percentage. obtained from the results of the questionnaire about 70% stated good

In the generator set (genset), the voltage stability system is affected by the excitation system controlled by control circuit called AVR (Automatic Voltage Regulator). One of the important components in the AVR system is the algorithm of the controller. The application of the PID control method has been widely used in the design of AVR controllers. This study applies the GWO-GA (Grey Wolf Optimization - Genetic Algorithm) hybrid method on PID parameters setting. The best transient automatic voltage regulator (AVR) response results were obtained when using the hybrid genetic algorithm - grey wolf optimization (HGAGW) method with a fitness score of 4.3039, the Grey wolf optimization (GWO) method with a fitness score of 4.5059, and the genetic algorithm (GA) method with a fitness score of 6.0214.

The development of sophisticated technology in the era of the industrial revolution 4.0, namely the collaboration between automation technology and the internet, causing changes in the combat and reconnaissance model to be remotely. The internet of things based omni wheel robot is divided into three module units, the main module, the data processing module, and the drive module. This concept uses a telemetry control system that is integrated with computers and the internet for data processing. The omni wheel robot is used in urban terrain for autonomous mobile surveillance operations and webcam monitoring via a web server. The omni wheel robot is designed to use four omni wheel controls and a trajectory as the main autonomous drive for the robot, the raspberry pi 3 is a microcontroller for processing programs on the robot and the webcam is used to take pictures of the terrain the robot passes through. All controls on the omni wheel robot use a telemetry system by using Wi-Fi internet network access remotely to minimize losses for TNI soldiers’ personnel in carrying out reconnaissance tasks.