Table of contents

The International Conference on Science & Technology (2nd ICoST 2020) is an annual conference organized by Hemispheres. This year, the conference has been held on November 28, 2020. Hemispheres is committed to keeping the conference going even in difficult times due to the COVID-19 outbreak. This affected the implementation of this conference, which was originally offline due to large-scale restrictions and transportation policies, causing this conference to be held virtually. However, this conference was still well organized.

It is predicted that the corona virus pandemic will change the pattern of human life and the environment for a long time. The world of science and technology also cannot be separated from this influence. Long distance interaction and digital life will be a way of socializing. Challenges and ways to survive in difficult conditions make human creativity try to solve these problems. This prompted Hemispheres to take up the theme at this year's conference entitled "Challenges of globalization in the Pandemic Era". The papers included in this conference consist of predictive modeling and monitoring device prototyping of COVID-19, identification, classification and detection of diseases, development of smart green buildings, design of SIMO converters for mitigation, use of algorithms and other computational methods. Hopefully the papers in this conference will be able to contribute to the literature on the challenges in this pandemic era.

Editor of the 2020 2^nd ICoST

Ferry Wahyu Wibowo

ORCID ID: 0000-0003-1913-436X

Committee 2020 2nd International Conference on Science & Technology (2nd ICoST 2020)

List of Committee, Steering Committee, Organizing Committee and Committee Members are available in the pdf

2020 2nd International Conference on Science & Technology

(2nd ICoST 2020)

List of Additional Reviewers are available in this pdf

2020 2nd International Conference on Science & Technology

(2nd ICoST 2020)

Logos are available in this pdf.

2020 2nd International Conference on Science & Technology

(2nd ICoST 2020)

List of Technical Program Committee available in this pdf.

• All papers published in this volume of Journal of Physics: Conference Series have been peer reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.

• Type of peer review: The review process model at The International Conference on Science & Technology (2nd ICoST 2020) has used double-blindness. This process is carried out through the EDAS conference management system at the link: edas.info. First, we checked the template suitability of the Journal of Physics: Conference Series. If it doesn't match the template then we will return it. Second, the stage of checking the plagiarism of incoming papers has been provided by EDAS using docoloc. If the plagiarism is very high then we will reject it directly, on the other hand, if the plagiarism is low then we will continue to be reviewed by 3 reviewers. The status of being accepted or rejected for this stage depends on the assessment of the three reviewers.

• Conference submission management system: EDAS conference management system (https://edas.info)

• Number of submissions received: 63 papers

• Number of submissions sent for review: 63 papers

• Number of submissions accepted: 30 papers

• Acceptance Rate (Number of Submissions Accepted / Number of Submissions Received X 100): 47.62%

• Average number of reviews per paper: 1 reviews per paper

• Total number of reviewers involved: 190 reviewers

• Any additional info on review process: In this conference, only full papers are accepted for review. After being reviewed, the editor will decide on the status of the paper from the review results of the three reviewers. If more than two reviewers stated that they accepted the paper, the paper would be accepted, on the other hand, if more than two reviewers stated that they rejected the paper, the paper would be rejected. Some review forms used in this conference are,

Technical Criteria

• Scientific merit: notably scientific rigour, accuracy and correctness.

• Clarity of expression; communication of ideas; readability and discussion of concepts.

• Sufficient discussion of the context of the work, and suitable referencing. Quality Criteria

• Originality: Is the work relevant and novel?

• Motivation: Does the problem considered have a sound motivation? All papers should clearly demonstrate the scientific interest of the results.

• Repetition: Have significant parts of the manuscript already been published?

• Length: Is the content of the work of sufficient scientific interest to justify its length? Presentation Criteria

• Title: Is it adequate and appropriate for the content of the paper?

• Abstract: Does it contain the essential information of the paper? Is it complete? Is it suitable for inclusion by itself in an abstracting service?

• Diagrams, figures, tables and captions: Are they essential and clear?

• Text and mathematics: Are they brief but still clear? If you recommend shortening, please suggest what should be omitted.

• Conclusion: Does the paper contain a carefully written conclusion, summarizing what has been learned and why it is interesting and useful?

Before sending those papers to the publisher, the editor checks the suitability of the template, numbering of figures, tables, sections, citations, and others.

• Contact person for queries (please include: name, affiliation, institutional email address)

Sri Ngudi Wahyuni, Universitas Amikom Yogyakarta, yuni@amikom.ac.id

In modern times, the chatbot is implemented to store data collected through a question and answer system, which can be applied in the Python program. The data to be used in this program is the Cornell Movie Dialog Corpus which is a dataset containing a corpus which contains a large collection of metadata-rich fictional conversations extracted from film scripts. The application of chatbot in the Python program can use various models, the one specifically used in this program is the LSTM. The output results from the chatbot program with the application of the LSTM model are in the form of accuracy, as well as a data set that matches the information that the user enters in the chatbot dialog box input. The choice of models that can be applied is based on data that can affect program performance, with the aim of the program which can determine the high or low level of accuracy that will be generated from the results obtained through a program, which can be a major factor in determining the selected model. Based on the application of the LSTM model into the chatbot, it can be concluded that with all program test results consisting of a variety of different parameter pairs, it is stated that Parameter Pair 1 (size_layer 512, num_layers 2, embedded_size 256, learning_rate 0.001, batch_size 32, epoch 20) from File 3 is the LSTM Chatbot with the avg accuracy value of 0.994869 which uses the LSTM model is the best parameter pair.

Currently, the world is experiencing a prolonged pandemic known as Covid-19. Many prediction models of Covid-19 have been developed by the governments to make the right decisions to control the outbreak. In Indonesia, there is also much research on the prediction of Covid-19 using machine learning methods, which provide the statistics to predict the total cases, the total deaths, the peak and the end of the pandemic. This paper investigates three prediction models: Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM), and Decision Tree (DT) in predicting total cases and total deaths of Covid-19 in Indonesia. First, a preprocessing is applied to change the string data to the numerical dataset using a label encoder. Second, the models are trained using the Covid-19 Indonesia Time Series All Dataset (CITSAD) with 90% and 10% train/test split. The three models are then investigated to predict new cases and new deaths. The evaluation using the CITSAD of ten provinces in Indonesia shows that DT gives the highest accuracy of 93% and provides the fastest processing time of 48.4 seconds.

Dialect is a variation of the language used by a group of people, sometimes in a particular region. It plays an essential role in automatic speech recognition (ASR). In general, an ASR gives high accuracy for a dialect-specific case, but it obtains a low accuracy for the multi-dialect application, such as for the Indonesian language that has hundreds of dialects. In this research, a system to recognize various dialects in Indonesia is developed. First, an utterance is preprocessed using both normalization and framing. Second, its features are then extracted using the Mel frequency cepstrum coefficients (MFCC), which is one of the feature extraction methods for the best acoustic signals. Finally, a deep recurrent neural network (DRNN) is used to learn and classify dialect characteristics. Evaluation of the dataset of five major dialects in Indonesia shows that the greater the Epoch and Bath Size, the greater the accuracy produced by the DRNN. However, accuracy is not directly proportional to the value of both parameters. The Epoch of 30 and Batch Size of 30 are the optimum parameters that yield the highest accuracy of 87.0% for the training set. Evaluation of the testing set shows that it gives an accuracy of 85.4% for the unseen dialects.

Computer vision has the challenge to detect the facial emotions of humans. Recently, in computer vision and machine learning, it's possible to detect emotion from video or image accurate. In our research will propose to classify facial emotion using Haar-Cascade Classifier and Convolutional Neural Networks. The experiment uses the FER2013 dataset which was collected for the facial expression recognition dataset, and we proposed seven classified facial expression. The CNN model gain MSE and accuracy value based on epoch variety. The results showed that with the increase in the epoch value, the smaller MSE value would be obtained, likewise, the accuracy value would be increased. Thus, the proposed algorithm of CNN is proven to be effective for facial emotion detection.

Identifying the identity of a prisoner in a detention cell, through facial recognition automatically is a big, exciting problem and there are many different approaches to solve this problem because it must detect multiple faces (multi-face). Especially in uncontrolled real-life scenarios, faces will be seen from various sides and not always facing forward, which makes classification problems more difficult to solve. In this research, one method is combined deep neural networks that is Convolutional Neural Networks (CNN) and Haar Cascade Classifier as real-time facial recognition, which has proven to be very efficient in face classification. Methods are implemented with assistance library Open-CV for multi-face detection and 5MP CCTV camera devices. In preparing the architectural model Convolutional Neural Networks Do configuration parameter initialization to speed up the network training process. Test results on 51 test data using constructs Convolutional Neural Networks VGG16 models up to a depth of 16 layers of convolution layers with input from the extraction of the Haar Cascade Classifier resulting in facial recognition system performance reaching an accuracy rate of about 87%.

The COVID-19 is a dangerous virus that has been declared by the world health organization (WHO) as a pandemic. Many countries have taken policies to control the virus's spread and have played an active role in overcoming this global pandemic, including Indonesia. Indonesia consists of many islands, so the level of distribution varies. Although the mortality rate is shallow than the cure rate, this virus's spread must be controlled. This paper aims to model the prediction of infected cases, cases of recovery from COVID-19, and mortality for each province in Indonesia using the Long Short-Term Memory (LSTM) machine learning method. The results of the model evaluation of this method used the root mean squared error (RMSE) approach.

The Borneo black sweet Coelogyne Pandurata is one of the mascots of flora in East Kalimantan Tropical Rainforest. This orchid species only grows on the Borneo. The uniqueness of The Borneo black orchid Coelogyne Pandurata, has a black tongue (labellum) with a few green and hairy stripes. This research is to develop an expert system for identifying pests and diseases of black orchids, as a support for the conservation of biodiversity in the East Kalimantan tropical rainforests. The expert system is equipped with a knowledge base in diagnosing pests, symptoms, and diseases of black orchid using Bayes theorem. In this research 4 pests disturbed black orchids, namely bare snail pests, caterpillars pests, grasshoppers pests, and ant pests. The diseases that attacked black orchids were obtained, namely brown spot disease, fusarium wilt disease, soft rot disease, and root rot disease. The result of the calculation of the Bayes Theorem based on 5 symptoms chosen by the user that black orchid has a 40% chance of experiencing root rot disease.

The companies that are starting to renew their system using the ERP-based systems, since 2000, the percentage of success reached 75%, and 25% is a failure. The ERP implements have several issues, such as the quality of human resources, not user-friendly system, incorrect format for data recording, system errors, unstable connections, a long-time process in the system, etc. Related to the issue, the company, which is a provider in the ERP SAP marketing, assists by local support to help end-users regarding the recording of selected divisions that use this system for daily work. It makes the researcher do the analysis related to what factors influence the ERP SAP acceptance technology with local support or implementor as a support for users of those companies in the regional office. In this study, to analyze the ERP system's acceptance technology factors, we use the UTAUT2 method with two additional constructed variables, Trust and Learning Value, and for analyzing those hypotheses, we use the PLS-SEM method. The study results show that several variable factors significantly influence the technology acceptance of the ERP SAP in PT. XYZ, which is Hedonic Motivation, Price Value, and Habit. Local support associated with Effort Expectancy and Social Influence variables does not significantly influence the system's acceptance. Researchers recommend that three factors should be considered more closely by the ERP system providers as a material reference that is related to the further strategy development and system development, such as improving the quality of human resources, etc.

The intention of this project is to develop a smart irrigation and water management system for conventional farming. The project is conducted mainly to improve the irrigation scheduling and also to solve the over watering and under watering issues in traditional irrigation system. These problems can be solved by implementing soil moisture sensor as a smart component in the irrigation system. Smart irrigation system with the implementation of sensory-based system will be able to provide a proper irrigation scheduling, by monitoring the soil and weather condition of the farm. In this project, the sensory system consists of soil moisture sensor, temperature sensor and light intensity sensor, which basically used to monitor soil moisture level, temperature level, and light intensity level at the separate test area. Arduino Mega 2560 microcontroller will process the data from these sensors and a proper irrigation scheduling will be developed based on the data collected. Type of irrigation system that been used in this project is a sprinkler system because it has high uniformity of water distribution to the plant, which able to spread water efficiency and further optimize the water usage during irrigation process. Ultrasonic sensor is also implemented in the system to measure the amount of water used in each irrigation process performed. An offline data storage will be implemented in this project using a micro SD card module, which all the essential information such as sensory system readings and the amount of water used will be recorded and stored into a micro SD card. Thus, it allows user to monitor their farm's condition, and also gives a better view on what is really happening at their farm.

Reliability of generation system is an important aspect of planning, designing and operating for forecasting the plant capacity growth to make assurance that the totality generation is adequate to secure demand. The probability distributions correlating with the reliability indices may be utilized as complementary measures for accurate description and worthy information for system planners and operators. In the current research, the yearly load demand and its impact on the reliability of generating units was highlighted by some reliability indices that standardize against the international usefulness custom which are, Loss of Load Probability LOLP, Loss of Load Expectation LOLE, Loss of Energy Expectation LOEE, Loss of Energy Probability LOEP and Expected Energy Not Served EENS. This article is also dealing with the issue of generation capacity reserve assessment and the relation between the system reliability level and the expansion of the load. The notion of capacity extending analysis is clarify using a system of 4 stations. The effect on system reliability of adding a generation unit to the overall system can be observe in terms of decreasing the reliability indices and increasing the system Effective Load Carrying Capability (ELCC). This article has been used the Loss of Load Expectation LOLE in terms of day/ year as a critical limit for reliable and unreliable system.

Currently, the level of carbon dioxide (CO₂) emissions is at the highest level. One of the causes is the waste of electricity used. One of the most significant contributors to electrical energy consumption is in the High Rise Building (HRB) sector. This paper proposed an automation system in Heating, Ventilation, and Air Conditioning (HVAC) systems, lightings systems, and electronic systems, especially in the guest room area, where electrical energy consumption very much depends on the guest's behavior. The purpose of the proposed system is to save energy and to realize smart green buildings. The result shows that the proposed system provided an average energy saving of 294.882 kWh per month. This system could save the cost of electricity bills by 21,38% each month. Those results confirmed that the implementation of a room control automation system is feasible to realize smart green buildings.

Since 1968, Dengue Harmonic Fever's incidence in Indonesia has continued to rise and has become a public health issue. Indonesia has the largest number of Dengue Harmonic Fever cases than 30 other epidemic countries worldwide. It is very important to carry out research related to dengue cases' prediction to prevent the spread of Dengue. This literature review is intended to determine the extent of the dengue prediction approach carried out by previous researchers, and a research gap will be obtained. The algorithm used to cluster articles is a modularity algorithm, using several open-source tools to process data. The online databases used are Google Scholar and Crossref by using keywords: journal, algorithm, prediction, and Dengue. The data are taken from the expansion of 1928-2020. This study's results are 200 articles that are suitable and divided into four clusters of important articles. Also, several important parameters were obtained in the prediction study of dengue fever, namely humidity, temperature, rainfall, and population density.

This paper discusses the design of emergency power supply systems in disaster affected areas. Communication and information on post-disaster conditions is very important to be known by the family or authorities. However, a condition that often occurs after a disaster is that the communication system is cut off due to loss of electricity sources. The proposed system aims to provide backups of electrical energy especially in communication equipment such as cellphone chargers and Backup Battery systems on BTS. The flyback converter topology applied provides a multi output voltage of 5 volts for cellphone chargers and 13 volts for Battery systems on BTS, where each system is able to provide an SOC of 20-40%.

Fever is one of the initial presentations that a suspect of COVID-19 might have. Fever is indicated by body temperature higher than normal, which is more than 37.12°C. A thermometer gun is one device that is utilized to measure body temperature. But it requires a short line-of-sight distance between the device and the subjects (< 30 cm). In public facilities like shops, malls, schools, colleges, hospitals, and airports, the device's use can initiate crowded or queue that higher the COVID-19 infection potential. In this research, wearable glasses is designed to replace such device. The prototype was built to display the thermal-map and body temperature of a single suspect. It can measure body temperature up to 2.5 meters. Based on the evaluation, the average error was about 0.57°C. Recalling that the used thermal array sensor's inaccuracy is ±2.5°C, then the prototyping has a high potential for further use.

Indonesia is a tropical country and has a great potential in alternative source of solar energy. Solar energy is friendly for environmentally because it does not make pollution and is renewable energy. Using solar energy can reduce fossil energy which is this energy can't be renewed and if used continuously it will be used up. Sunlight is solar energy that can convert the light energy into electrical energy by using solar panels. This paper presents details the design of the SEPIC Converter to Supply Electrical Energy to a Smart Lamp with Solar Energy. Sunlight energy is not always in maximum condition, so to maximize the power produced by solar panels are needed a control system to maximize the output power of converter. This experiment use 2 solar panels, each of 100 WP and arranged in parallel. The control system use PI control. The function is to generate the output voltage for battery charging. Time response of PI control is 0.6 s to according to the set point value of 14 volt for battery charging with the battery capacity is 20 Ah 12 volt. Cohen Coon method is used to find the PI control parameter. So using PI control with Cohen Coon method can make battery charging according to the set point even though solar panels has shading.

The inverter is an electronic device which able to convert DC electricity into AC electricity. In the development of renewable energy resources, for example, solar power plants, inverters are needed. In this research, an inverter is made by real-time power monitoring. The inverter is made using unipolar PWM modulation and a full H bridge topology. PWM signals are generated from Arduino microcontrollers that will control MOSFET switching. Power monitoring is done by installing a DC voltage sensor and INA219 DC current sensor while on the output side using the PZEM 004t (v3) sensor and results will be displayed on the OLED. The experiment was successfully carried out by producing an approaching sine wave signal with a frequency of 50 Hz and 220 V AC voltage. The efficiency of the inverter is low because of loss from the transformer which has a no-load efficiency of 68.7%. When the 15W load has installed the efficiency of the inverter is 31.83% and when the 20W load has installed the efficiency of the inverter is 34.72%. Finally, when the smartphone's charger is installed the total efficiency was 49.96%.

In the last few decades, research on loudspeakers, especially at low frequencies and infrasound, has made significant developments. Among them, the loudspeaker is used as a low-frequency mechanical signal generator to simulate human arterial pulses. An electret condenser microphone (ECM), one of the alternative sensors that will be used to measure the arterial pulse which is simulated by the loudspeaker. Interestingly, neither the mechanical signal generator nor the sensor that will be used has data on infrasonic frequencies or it can be concluded that both of them have not been calibrated. This paper proposes that the infrasonic signal generated by a moving coil loudspeaker can be observed using a calibrated sensor, a microwave motion sensor. The main contribution of this study is to find the infrasonic loudspeaker frequency response data used in previous studies so that it can be used as a compensator to calibrate ECM as an alternative arterial pulse sensor. Microwave motion sensors have basic concepts such as the Doppler effect principle, which reads an object based on its displacement. Microwave motion sensors can observe the movement of the diaphragm cone of the loudspeaker requires several supporting instruments, including a signal conditioning circuit and an undisturbed environment. In the end, the microwave motion sensor can observe infrasonic acoustic waves and get a compensator value for the ECM as an alternative arterial pulse sensor.

Energy plays a very important role in human life. Every year, the demand for energy needs continues to increase and the majority of energy generation uses fossil fuels. So we need an energy source that is environmentally friendly. One of the environmentally friendly energy sources is a fuel cell. Fuel cells can produce electrical energy at a lower cost than the electrical energy generated by conventional power grids. In making a fuel cell system, a modeling is needed so that the fuel cell system can work properly and in accordance with the desired specifications. One method for modeling a fuel cell system is to use MATLAB. The use of a DC-DC boost converter with a properly designed closed loop PID controller has a very important role in regulating the PWM of the DC-DC boost converter switch and plays a very important role in controlling power regulation. In this research, a modeling analysis of NEXATM 1.2 kW hydrogen fuel cell with a DC-DC boost converter controlled by a PID controller was carried out for a compact Power Conditioning Unit (PCU) design. The purpose of this research is to model and analyze the characteristics of the performance of the hydrogen fuel cell system and the performance of the PID controller in regulating the DC-DC boost converter output voltage on the hydrogen fuel cell. The results showed that the performance of the hydrogen fuel cell was influenced by the pressure of oxygen gas, hydrogen, and temperature. The greater the value of oxygen gas pressure, hydrogen gas pressure, and temperature on the fuel cell, the greater the voltage and current output of the fuel cell. The simulation results show the fuel cell output voltage is 47.89 V with an error percentage of 4.22%, and the fuel cell output current is 23.94 A with an error percentage of 0.25%, and the fuel cell output power is 1147 W with an error percentage of 4.12%. The performance of the PID controller with the DC-DC boost converter in regulating the fuel cell output voltage is very good. This is indicated by the results of the response curve for the fuel cell output current, namely the value of rise time (tr) of 4 seconds, delay time (td) of 0.2 seconds, peak time (tp) of 4 seconds, settling time (ts) of 4 seconds, and a maximum overshoot (Mp) of 0%. For output voltage, the value of rise time (tr) is 4 seconds, delay time (td) is 0.2 seconds, peak time (tp) is 4 seconds, settling time (ts) is 4 seconds, and maximum overshoot (Mp) is 0% with the parameter value Proportional (P) of 0.001, Integral (I) of 10, and Derivative (D) of 0.

One of the most common brain disorders is epilepsy. A person who has epilepsy is not able to have normal days like the others. It's characterized by more than two unprovoked seizures. However, the faster detection and treatment of epileptic seizures, the quicker reduction of the disease abnormal level. Neurologists are still diagnosing, detecting, and testing a seizure manually by observing the Electroencephalogram (EEG) signals. This takes a very long time because of the irregularity of EEG signals. Hence, a Computer-Aided Diagnosis (CAD) is developed by many scientists to help neurologists in detecting seizures automatically. In this research, a CAD system was developed at CHB-MIT dataset. The EEG signals were processed at several stages through this system, namely pre-processing, decomposition, feature extraction, and classification. In pre-processing, the EEG signals were uniformed by selecting the most appropriate channels and filtered using Butterworth Bandpass Filter (BPF) to remove noise. The process continued to the decomposition and feature extraction stage using Empirical Mode Decomposition (EMD) and fractal dimension-based methods, i.e. Higuchi, Katz, and Sevcik, respectively. Then, the features were classified by Support Vector Machine (SVM). The proposed method achieved the highest accuracy at 94.72% on the Chb07 record. Meanwhile, the average accuracy was 81.2% for all records. The proposed study is expected to be applied for the detection of seizure onset in a real-time system.

Alzheimer's disease is a type of brain disease that indicate with memory impairment as the early symptoms. These symptoms occur because the nerve in the brain involved in learning, thinking and memory as cognitive function have been damaged. Alzheimer is one of diseases as the leading cause of death and cannot be cured, but the proper medical treatment can delay the severity of the disease. This study proposes the Convolutional Neural Network (CNN) using AlexNet architecture as a method to develop automated classification system of Alzheimer's disease. The experiment is conducted using Magnetic Resonance Imaging (MRI) datasets to classify Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented from 664 MRI datasets. From the experiment, this study achieved 95% of accuracy. The automated Alzheimer's disease classification can be helpful as assisting tool for medical personnel to diagnose the stage of Alzheimer's disease so that the appropriate medical treatment can be provided.

Research to test the performance of inner joint queries between MariaDB and the PostgreSQL database management system. Inner joint queries have the same output in MariaDB and PostgreSQL DBMS. This study aims to provide a comparative analysis of the response time performance of MariaDB and PostgreSQL databases in the use of inner join queries. The research test was conducted with 1,050,000 records using 21 response time data collection scenarios ranging from 50,000 data to 1,050,000 data collection with multiples of 50,000 data. The PostgreSQL DBMS was found to have better response times than MariaDB in all test scenarios. The results of the regression analysis to test the effect of using the F-test show that there is a significant effect on the amount of data and the relationship together on the response time in MariaDB and PostgreSQL. Then the T-test is carried out to strengthen the results of the study that PostgreSQL has a faster response time than MariaDB, testing 1 combined relationship shows a significant difference, testing 2 combined relationships shows a significant difference and testing 3 combined relationships shows a significant difference.

This research proposes Tempe Segar 'TEGAR' as mobile application for freshness determination of tempe based on tempe image on the Android operating system. Three kinds of freshness, including very good, good and not good were used to categorized tempe freshness. In this research, we used 50 tempe samples that were consisted of 25 tempe with plastic wrap and 25 tempe with leaf wrap. Tempe image was taken using mobile phone camera as digital tempe image then extracted using Local Binary Pattern (LBP). Detection accuracy and consumer satisfaction of TEGAR application were evaluated using questionnaire. The evaluation results show that TEGAR application is promising application to determine tempe freshness. TEGAR application will help consumer to determine tempe freshness as an important indicator of good quality tempe. The freshness of food directly or indirectly will affect the health of consumer.

A total of 11 % of children under the age of five years (toddlers) in Tangerang City experienced stunting. Stunting reflects chronic malnutrition during the most critical period of growth and development in early life, the first 1000 days of life. Monitoring the nutritional status is able to prevent stunting especially through Kartu Menuju Sehat (KMS) at an integrated service post (posyandu). Most of the data in KMS is recorded manually, so the risk of data loss or damage is very high. Therefore, mobile application that can monitor the nutritional status automatically is needed to develop. The nutrition monitoring application "Nutrimo" which monitors children's nutritional status was developed based on Android with anthropometric method and the Waterfall system development method. This application was completed with track record feature and suggestions that parents should take about the nutritional recommendations based on their respective nutritional status. The evaluation results showed that Nutrimo application was easy to use, informative and help to prevent stunting.

Proposed is an automated monitoring system for hydroponics vertical farming. This project aims to design and develop an automated system to monitor and maintain the level of nutrition solution for the vertical farming process. The monitoring condition includes Electrical Conductivity (EC), pH value, the liquid level as well as the water temperature of the nutrient solution stored in the rectangular PVC. Instead of using soil as the growing medium, the project used hydroponics method to grow the leafy vegetables, Bok Choy. The data monitored will be sent and processed by Arduino Mega microcontroller and upload to Ubidots Cloud using the ESP8266 NodeMCU. The system also provides control function to maintain the nutrient level and amount of solution flows into each layer of vegetables. It is expected that the implemented system would reduce the water and electrical consumption and allows the growth of the plant to be supervised from time to time without having a person to look after.

The use of e-commerce in companies or other types of business has supported them to develop and correspondingly cope with business pressures of high levels of competition. More consumer information can be gathered based on the interactive nature of e-commerce technology. In an e-commerce competition, all information relating to consumer behavior, such as the knowledge of the visitor interests in a product marketed by e-commerce, is of value to e-commerce players. Users can use the Web Usage Mining techniques to explore these interests. This study aimed to compare three classification algorithms by using the dynamic mining approach of user interest navigation pattern. The results of the study showed that the Decision Tree Classifier performed optimally in both the unbalanced data and independent or dependent data models.

The selection of a colleague or business is a process that must be thoroughly detailed, this will affect the development of a company. A decision support system is a solution to shorten a leader or staff in the cooperation section, where a company has several categories to be applied to the decision support system. The Profile Matching algorithm is an algorithm that is applied to build a system that can help provide a choice of potential partners or colleagues / business partners in certain companies, this profile matching algorithm requires many variables to be able to calculate the proposed output from the ranking value later. There are Core Factors and Secondary Factors, in the case of this discussion there are 3 prospective partners who are calculated for this profile matching algorithm. The distribution of variable data entered into the Profile Matching Algorithm, there are 8 categories, there is 4 categories included Core Factor and 4 categories included in the Secondary Factor, more then results of the GAP calculation show that the ranking value gets a maximum value of 4 (Partner 3), sequence No.2 is M1 and the last one M2 with each GAP value is 3.5.

Games are a part of children's development, but there are still a few developers who make games for early childhood ages. The purpose of this research is to create an educational game for early childhood age in order to enhance early childhood knowledge of animal shape and literacy in a relaxed and fun way with augmented reality features. This augmented reality game purpose is media for parents to teach their children while playing. The Scrum method is used in developing this game. The evaluation of this experiment was been done using testing and survey with 30 parents using game experience questionnaire (GEQ) and comparison to similar game. The survey result show that this game is suitable for the parents and childhood children and compared to others game, Kotak Edu had augmented reality as advantage.

The prediction of students' graduation outcomes has been an important field for higher education institutions because it provides planning for them to develop and expand any strategic programs that can help to improve student academics performance. Data mining techniques can cluster student academics performance in predicting student graduation. The aim of this study is to analysis the performance of data mining techniques for predicting students' graduation using the K-Means clustering algorithm. The data pre-processing used for data cleaning, and data reducing using Principle Component Analysis to determine any variables that affect the graduation time. This algorithm processes datasets of student academics performance numbering 241 students with 16 variables. Based on the clustering using K-means, the highest accuracy rate is 78.42% in the 3-cluster model and the smallest accuracy rate is 16.60% in the 4-cluster model. The influential variable in predicting student graduation based on the value of the loading factor is the GPA total of the 1st to 6th semester.

Handling of Covid-19 patients requires more medical equipment than normal conditions, increasing the amount of hazardous medical waste. The management of hazardous medical waste has many challenges; therefore, it needed a strategy to solve it using information technology. Based on a filter of 376 articles, this review adopted a Systematic Literature Review approach to evaluating the recent challenge and recommendation in the field of Hazardous Medical Waste Management amidst Covid-19. Through a four-phase workflow consisting of searching, screening, excluded, and included literature search, this study identified the most influential journals, scholars, and articles that have been influential in the domain of Hazardous Medical Waste Management. These literature review results are four challenges in Hazardous Medical Waste Management, including Regulation, Technology, Financial and Awareness. The other finding is IT application recommendations such as IoT, Big Data, DSS, AI and GIS. By providing the latest research about the challenges and recommendations in the domain of Hazardous Medical Waste Management amidst Covid-19, the paper serves as a preliminary recommendation for practitioners and researchers to link current research to future trends.

This study aims to find information about the major impact of the internet sites frequented by university alumni on the fate of those who are fast finding jobs and those who have not found work during the COVID-19 pandemic. This research uses a field survey method of university graduates, both those who have found jobs and those who have not. This study uses the manova algorithm with a GLM approach. The results of this study indicate that there is a very large impact on the types of internet sites that are most visited by people who are already working with people who have not worked. This research is only conducted in big cities and can be used to awaken the awareness of university alumni to find jobs more quickly by paying attention to their priorities every time they use the internet.