Computer Science (CO-SCIENCE)

Manajemen Keamanan Internet Menggunakan Metode Firewall Filtering Untuk Penyaringan Konten Pada Router Mikrotik RB1100

Fri, 28 Jul 2023 00:00:00 +0700

The existence of security threats and internet abuse is often a problem for companies. Use of a VPN for access to web pages that contain negative and pornographic content which usually contain malware, viruses, trojans and others. This of course will have a detrimental effect on companies whose internet networks are exposed to attacks by malware, viruses or trojans due to employees' habit of accessing web pages that contain negative and pornographic content. To prevent these threats, a method of regulating access and use of the internet network is needed according to its purpose. Content filtering is used to filter sites or web addresses that are not allowed by the company because they are considered to have no direct connection with their field of work. The firewall filtering content method in the Winbox application is one of the methods to achieve the goal of blocking negative and pornographic content that can be accessed by employees during working hours. This research was implemented at PT. Indonesian Mighty Beasts. The results of this study, after the content filtering firewall is implemented, employees cannot access web pages that contain negative and pornographic content and of course are not work related so that the implications for work are more productive, efficient and optimal.

Sistem Informasi Pengaduan Perbaikan Jalan Desa (Program SIG) Berbasis Web

Hidayat Muhammad Nur, Vadlya Maarif — Fri, 28 Jul 2023 00:00:00 +0700

Several damaged roads in the Kebasen area during the rainy season are continuous work for the government. As an effort to assist this public service, it provides an opportunity for the public to submit complaints or complaints when public facilities have not met expectations. The following is an alternative to the procedure for submitting complaints or complaints for road repairs online which can help better communication. This study aims to build a GIS web-based road repair complaint information system. The system prototype was designed in stages with the development of the waterfall model system and the PHP programming language. In making this system the author uses the framework CodeIgniter (Ci) and Object Oriented Analysis and Design (OOAD). The interface for connecting several applications uses the Google Application Programming Interface (API) and MySQL database. The results of this study are expected to be the system of choice for conveying the aspirations of the people up to date in complaints about road repairs, environmental conditions, traffic conditions, public road management conditions, security conditions, street lighting conditions and presenting information optimally

Metode Design Thinking Pada Sistem Informasi Presensi Pegawai Kejaksaan Negeri Kota Bogor

Fri, 28 Jul 2023 00:00:00 +0700

Employee presence is an important factor for an agency or company to achieve goals, this is related to discipline and has an impact on the performance of each employee. But in reality, there are still several agencies that still use manual absences that have not been computerized, one of which is the Kejaksaan Negeri Kota Bogor's Office. The system used by the Kejaksaan Negeri Kota Bogor in the attendance process is still manual, namely using a daily attendance book which affects the efficiency and effectiveness of data collection, data search, and calculations and requires a relatively long time. Therefore, it is necessary to have special data collection to record attendance and absence so that work activities can be recorded in real-time and properly, one of which is by using a computerized system with Information Systems. The information system built on a website basis uses the CodeIgniter 3 framework and MySQL. The method used is the Design Thinking Method which has 5 stages. The output of this study is known to be tested with usability testing by user on the Learnability aspect of 75%, then on the efficiency aspect of 100% and the memorable aspect of 66.77%. The average result of the test is quite good at 80.56%. So by making this information system, it can facilitate the process of being on time, searching for data, calculating and summarizing timeliness and minimizing errors when recording presence data.

Rancang Bangun Sistem Informasi Akademik Berbasis Website Dengan Metode SDLC

Wati Erawati, Sujiliani Heristian, Rachmat Adi Purnama — Fri, 28 Jul 2023 00:00:00 +0700

In the conditions of today's globalization, information technology is developing rapidly. School really need an academic information system that supports and makes it easy for staff and parents of student.This research is motivated by a lack of information about children’s learning development. And because parents of schoolchildren lack information about their children's learning, the result is that parents do not know the development of their child’s school learning. The purpose of this research is of course to provide benefits for staff, teacher and parents to make it easier to get information or the results of school development from students. The method that the author uses in developing this software is the SDLC (Software Development Life Cycle) waterfall model. Therefore, researchers try to help with problems that exist in schools such as the lack of updating of data or information contained in schools. By creating a computerized system, it is hoped that it can work to help teacher provide information to parents of students. A web-based system that contains student attendance list, student daily activity plans, and report cards which are the end result of student development at school.The author tested this academic information system by using a regression test. The test results show that this system meets the test success criteria, such as acccuracy and speed in processing data. A website-based academic information system using the SDLC method can help users manage academic data easily, quicly and accurately. The SDLC method used can help develop a good and correct system, and according to user needs.

Komparasi Algoritma Machine Learning untuk Klasifikasi Gejala Coronavirus Disease 19 (Covid-19)

Musriatun Napiah, Rachmawati Darma Astuti, Eka Kusuma Pratama — Fri, 28 Jul 2023 00:00:00 +0700

COVID-19 or Corona Virus Disease 19 is a member of the extended family of coronaviruses that cause a spectrum of illnesses from mild to severe, including MERS and SARS. While the cause of COVID-19 transmission has not been confirmed, it is believed that the virus is transmitted from animals to humans, causing various symptoms such as cough, runny nose, fever, sore throat and loss of smell. Research was conducted to classify COVID-19 symptoms into low, medium, and high categories in patients. This study aims to classify patient data and determine the risk of COVID-19 infection based on the severity of symptoms, namely mild, moderate, and high. Machine learning methods, including Decision Tree and SVM algorithms, are introduced and compared with K-Nearest Neighbor (K-NN), Neural Network (NN), Random Forest (RF), and Naive Bayes. The dataset used contains 127 patient records from kaggle.com. The test results showed that SVM achieved 54% accuracy, while Decision Tree achieved 98%. This research provides important insights into the risk assessment of COVID-19 infection based on symptom severity, and the use of machine learning techniques is expected to improve analysis and prediction capabilities in the face of the COVID-19 pandemic.

Aplikasi Akuntansi Penerimaan Dan Pengeluaran Kas Pada PT Kinarya Gemilang Adhitama Menggunakan Model Waterfall

Tika Susilawati, Syarif Hidayatulloh — Fri, 28 Jul 2023 00:00:00 +0700

PT Kinarya Gemilang Adhitama manages cash receipts and disbursements using Microsoft Excel by recapitulating or calculating one by one transactions in the form of notes into financial reports. The cash management process tends to take a long time, and allows for a considerable risk of data redundancy and the quality of data and information to become inaccurate. Utilizing technology by building a cash receipts and disbursement application with the aim of developing and improving existing systems. By building a financial management application, it is hoped that it can help with the process of managing cash receipts and disbursements at PT Kinarya Gemilang Adhitama to become more efficient and effective. The software development method used in building the application is the SDLC method with the Waterfall model. The application is built with an automatic and unique cash number system so that it can reduce the risk of data redundancy. Furthermore, the application will be tested with Black Box which focuses on software in terms of logic and functionality which is carried out on the 4 main features of the application. The test results show valid results, which means that the application function is in accordance with the design.

Pendekatan Algoritma Klasifikasi Machine Learning untuk Deteksi Penyakit Demensia

Muhammad Iqbal, Hendri Mahmud Nawawi, Muhammad Rezki, Abdul Hamid, Sri Rahayu — Fri, 28 Jul 2023 00:00:00 +0700

Early detection of dementia through the use of machine learning classification algorithms is important for providing appropriate interventions to patients. In this context, this study aims to compare the performance of several machine learning classification algorithms in detecting dementia using the attribute selection method. In the early stages, patient data including medical history, cognitive test results, and other attributes were collected as input, an attribute selection algorithm was used to select the most informative attribute subset in detecting dementia. The subset of attributes used as input for training machine learning classification models, several classification algorithms such as Extra Trees (ET), Linear Discriminant Analysis (LDA), Random Forest (RF) and Ridge. In this study, accuracy is used as the main metric to compare algorithm performance. The evaluation results show that the Random Forest (RF) algorithm produces the best performance with an accuracy of 91.56%. The Extra Trees (ET) algorithm has an almost comparable accuracy of 91.44%, while Ridge and Linear Discriminant Analysis (LDA) have an accuracy of 90.44% respectively. In the context of dementia detection, the performance of the Random Forest algorithm with the attribute selection method proved to be the best with an accuracy of 91.56%. These results indicate that the developed model is capable of recognizing complex patterns and relationships between features that are relevant to dementia status. The use of the attribute selection method also contributes to increasing the accuracy and efficiency of the classification algorithm.

Sistem Informasi Pendalaman Materi Berbasis Web Pada SMA Cengkareng 1 Menggunakan Model Waterfall

Susafa'ati Susafa'ati, Nunung Hidayatun, Hidayanti Murtina — Fri, 28 Jul 2023 00:00:00 +0700

Cengkareng 1 High school as an educational institution providing senior secondary education in the city of West Jakarta. In every semester the school always conducts a study evaluation in the form of a written exam. The problem faced by the school is that the school wants to hold a deepening of the material for students to face the exam but is constrained by time, place, cost and teaching staff. From these problems, a system was created that could document the material, assignments and presentation of the questions as part of the implementation of deepening the material. Analysis and design by waterfall method. Research begins with conducting literature reviews, collecting data, analyzing systems and requirements, building system models using UML, designing application implementations, testing using black box testing, and maintaining system data. The results of this research are provided in the form of a web-based material immersion application. The application has the ability to provide materials, monitor student assignment uploads, and help students identify their limitations as they prepare for school and national exams.

Analisis Sentimen Terhadap Aplikasi Canva Menggunakan Algoritma Naive Bayes Dan K-Nearest Neighbors

Dany Pratmanto, Fabriyan Fandi Dwi Imaniawan — Fri, 28 Jul 2023 00:00:00 +0700

The sentiment analysis used in the Canva application involves collecting user reviews or feedback. Then, a sentiment analysis algorithm is applied to classify the reviews as positive or negative. Sentiment analysis can help the company understand user opinions about the Canva application and how the application can meet user needs. The process of sentiment analysis in the Canva application involves collecting user reviews or feedback, which are then classified using a sentiment analysis algorithm. The research results show that the KNN algorithm has an accuracy rate of 83.92%, while Naive Bayes only has an accuracy rate of 77.41%. The KNN algorithm also has higher recall and precision values than Naive Bayes, namely 83.66% and 84.49%, respectively. In addition, the AUC value generated by the KNN algorithm is also higher than Naive Bayes, namely 95.00% compared to 94.50%. Therefore, it can be concluded that the KNN algorithm is more suitable for data classification in this research. This research can contribute to the development of the Canva application and improve the quality of service for its users.

Prediksi Keberhasilan Pemasaran Layanan Jasa Perbankan Mengunnakan Algoritma Logistic Regreesion

Sari Dewi, Hanggaro Aji Al Kautsar, Dwi Yuni Utami — Fri, 28 Jul 2023 00:00:00 +0700

Determining public interest in marketing banking services using data mining techniques. Prospect segmentation is one of the processes used in the marketing strategy of the banking industry. Data mining support plays an important role in classifying potential bank customers and evaluating the success of marketing their services. This is important to support the conclusion about the success rate of telemarketers in carrying out bank marketing tasks. a product whose way of working requires information about potential customers. This is a classification technique that is often used to classify prospects using logistic regression according to research maps supporting prospect data mining. Defining an accurate data mining classification algorithm to predict telemarketing success based on a 2010 experiment. In marketing banking service products, the results of the evaluation process of this algorithm are determined by cross-validation, Confusion Matrix, ROC curve and T-test. The logistic regression algorithm is more accurate with an accuracy of 92.32% and an AUC value of 0.962, so the algorithm used is included in the good classification group.