Perbandingan Algoritma K-Nearest Neighbour (KNN) dan Naive Bayes pada Intrusion Detection System (IDS)

Machine learning techniques are widely used to develop Intrusion Detection Systems (IDS) to detect and classify cyber attacks at the network level and the host level in a timely and automated manner. However, many challenges arise as malicious attacks are constantly changing and occurring in very large volumes requiring a scalable solution. Therefore, this study conducted a comparison of the K-Nearest Neighbor (KNN) and Naive Bayes algorithms. The dataset used in this study is the Ddos features-IDS 2017 dataset published in 2019. This research analyzes the comparison of methods generated from the classification process based on metric accuracy, specificity and sensitivity parameters. The classification process using the K-Nearest Neighbor (KNN) and Naive Bayes algorithms, it can be concluded that the results of the three tests with a percentage split of 60%, 70% and 80% show that the K-Nearest Neighbor (KNN) algorithm gets a higher value than Naive Bayes except the error rate because the error rate indicates that the data failed to be classified properly. Testing on a percentage split of 60% KNN parameter accuracy gets a value of 99.53%, specificity 94.05%, sensitivity 75.20%, testing on a percentage split 70% KNN parameter accuracy gets a value of 99.69%, specificity 94.59%, sensitivity 78.40% and testing on percetage split 80%, KNN parameter accuracy parameter got a value of 99.70%, specificity 94.44%, sensitivity 75.85%.

Sistem Pakar Untuk Mendeteksi Kerusakan Pada Diesel Pump Dengan Metode Forward Chaining Berbasis Web

Frequent fires can occur in or like buildings of buildings or high rise buildings. The losses incurred by the fire disaster are enormous. Care and maintenance standards for diesel engine pumps must be observed. All technicians must have expertise in the maintenance and maintenance of the diesel pump engine. Such expertise can be obtained from official training conducted by the education center, reading guidelines for dealing with diesel pump engine damage obtained from diesel pump manufacturing plants and additional knowledge gained from learning while attending education and training. In this study the researchers set "Symptoms of Damage to the diesel engine of the Fire Pump" as a variable. The expert system application detects web-based diesel pump damage with a forward chaining method that has been made, after conducting an expert analysis test then testing the user's response to this expert system application, the test is carried out by consulting using this expert system application. Expert systems are components and elements that are combined into one to achieve certain goals. The system design is done after analyzing the diesel pump damage data and designing a web-based expert system. Chaining forward method is a method of inference that makes sense from a problem to a solution. Damage to the diesel pump by using the forward chaining method provides the right solution of the problem at hand. Based on these suggestions it can be concluded that an expert system detects damage to a web-based diesel pump that has been made can help all users in analyzing the problem based on consultation

Implementasi Quick Response (QR) Code Pada Transaksi Pembayaran Dengan Enkripsi Message-Digest Algortihm 5

The rapid development of the times has made the community busy with various activities that collide with the limited time they have. This causes people to always look for ways to be able to carry out all the demands of these activities effectively and efficiently. Technological innovations such as electronic payment systems and virtual queues are one of the answers that can be used to help people carry out activities. The existence of this electronic payment system makes it easier for people to make payment transactions with this virtual queue which is a solution to solving queuing problems which usually take a long time, so that this virtual queue can help people to cut the time that is usually used to queue and allocate it for activities other.

Implementasi Speech Recognition Menggunakan API IBM Watson

Lack of skill English is a major problem for someone who wants to learn to speak English in the pronunciation section. A person often feels insecure to speak English with other people even though in his own understanding it can be said to understand English. English learning applications, it can help to learn and practice good and correct pronunciation or pronunciation in English without having to involve other people. Using the Extreme Programming development method, it is found that the use of technology can be a solution for learning to speak English without having to be seen and valued by others. With the help of Speech Recognition, the process of recognizing a person's voice from a spoken phrase is the result that can be obtained. This English learning application is used to learn English spelling, so you can know how to pronounce English words and sentences properly and correctly.

Perbandingan Algoritma Naïve Bayes Classifier dan Algoritma Decision Tree untuk Analisa Sistem Klasifikasi Judul Skripsi

Penelitian ini mengkaji tentang perbandingan klasifikasi judul skripsi menggunakan algoritma naïve bayes classifier dan algoritma decision tree. Tujuan dari penelitian ini adalah untuk membandingkan dua algoritma dalam pengklasifikasian judul skripsi. Proses pengumpulan data dilakukan dengan cara studi pustaka dan literature sejenis. Hasil pengumpulan data akan di analisis dengan menggunakan algoritma naïve bayes classifier dan algoritma decision tree dengan tools rapidminer. Hasil penenlitian ini menemukan perbandingan yang cukup signifikan dengan hasil akurasi 80,33% untuk algoritma naïve bayes classifier dan 60,33% untuk algoritma decision tree dari 52 data judul skripsi yang digunakan.

Sistem Informasi Koperasi Simpan Pinjam Pada PT Meiwa Indonesia Berbasis Java

The purpose of this research is to make a Java-based savings and loan cooperative information system design to accelerate and facilitate performance in managing the search and storage of loan data at cooperatives as well as to produce a Java-based savings and credit cooperative information system. The research method used by researchers is the grounded research method, which is a research method based on facts and uses comparative analysis with the aim of conducting empirical generation, establishing concepts, proving theories, developing theories, collecting data and analyzing data in the same time. The results obtained are designing a savings and loan cooperative information system to assist in processing employee data. The construction of this information system is expected to simplify and provide maximum service for employees as well as to facilitate cooperative staff in collecting loan transaction data for reporting, data and information management processes become more effective, produce faster outputs and there is no misappropriation of loan data input or the occurrence of data duplication.

Penerapan Decision Tree untuk Prediksi Kepuasan Pengguna Bus Transjakarta

Transjakarta buses are one of the public transportation facilities used by residents of the capital city of Jakarta. The existence of Transjakarta Buses, transportation access is easier and easier for its users. With so many users, there are several things that must be considered in the facilities and infrastructure provided by the Transjakarta Bus. User satisfaction is an assessment given by a user of a service, whether satisfied or not. This research was conducted to analyze the satisfaction of Transjakarta Bus users who are students of Syarif Hidayatullah State Islamic University Jakarta. The attributes to be taken in the study include the rates, facilities, and services provided by the Transjakarta Bus where the questionnaire results will be processed using the C4.5 Decision Tree method. The results showed that an accuracy of 92.86% was obtained with accuracy in Good Classification using Confusion Matrix.

Aplikasi Penggajian Karyawan Pada CV System Comutama

CV System Comutama is a business entity engaged in the sale of computer accessories. The payroll system contained in the CV System Comutama has not been carried out to the full potential for it requires a payroll application that can support the delivery of data more effectively and efficiently. The purpose of this research is to design employee payroll applications on the CV System Comutama effectively and efficiently, facilitate the financial department to be able to calculate employee payroll quickly and minimize errors and to facilitate the achievement of reports that are fast, accurate, valid, effective and efficient. The research method used is the grounded research method to collect data and analyze data at the same time. The modeling system used is the Data Flow Diagram (DFD) method using the java programming language while the database uses MySQL. With the employee payroll application is expected to facilitate the calculation of employee salaries and provide employee salary data reports that are stored neatly, safely, and accurately in a database that is systematic.

Implementasi Manajemen Bandwidth Menggunakan Metode Queue Tree Pada Jaringan Internet

SMKN 5 Batam City is an educational institution located in Kavling Bukit Kamboja, Sungai Pelunggut, Kec, Sagulung, Batam City, Riau Islands. The availability of network infrastructure to be institutionalized by education will expedite the educational process including internet network services at SMKN 5 Batam City. The networks used in SMKN 5 Kota Batam are the Local Area Network (LAN) and Wireless Local Area Network (WLAN). Batam City Vocational School 5 has 82 PCs (Personal Computers) connected to the network and Access Points as access to the hotspot network, which uses an indie home ISP with a bandwidth capacity of 100Mbps and 5Mbps using an astinet ISP. Problems that occur on the internet network at SMKN 5 Kota Batam, do not yet have an allocation of bandwidth distribution for network users, causing unstable and uninterrupted network access. Therefore there must be proper bandwidth management controls, implementing bandwidth management and optimizing security authentication. So that the available bandwidth can be used fairly, by applying the queue method. And from the tests carried out, authentication of security and bandwidth management using the tree queue method, fair and even bandwidth can be used as well as the tree queue method proven to be able to use bandwidth both for downloading and downloading. uploaded.

Digital Watermarking Using Advanced Encryption Standard (AES) And Steganography Methods to Increase The Level Of Security Of User Data In The Image Files On Internet Network

The spread of digital media on the internet was very broad, fast, and cannot be monitored in a structured manner about what media has been uploaded and distributed on the internet network. The spread of digital media like this was very difficult to detect whether the media that shared was privately owned or that of others that is re-shared by media theft or digital media piracy. One step to overcome the theft of digital works is to give them a watermark, which is an identity that is placed on top of the work. However, this is still considered unsafe because the identity attached can be cut and manipulated again until it is not visible. In addition, the use of Steganography method to hide messages in an image can still be manipulated by adding messages continuously so that it accumulates and damages the original owner of the image. In this article, the author provides a solution called Digital Watermarking, a step of encrypting the data of the original owner of the work and putting it into the image of his work. This watermark cannot be seen clearly, but actually in the media there is encrypted data with a strong Advanced Encryption Standard (AES) method. As a result, a tool that can improve the security of media owner data by combining the AES and Steganogaphy methods in the formation of new media that cannot be changed anymore. So, when the media is stolen and used by others and has been edited, the owner's personal data can never be changed.