Search

Background: Early detection of diseases like tuberculosis (TB) and diabetes mellitus (DM) is critical for preventive healthcare. However, integrating effective screening programs within existing workflows can be challenging. Objective: This study explores the feasibility and impact of integrating an electronic screening system (ESS) within electronic medical records (EMRs) in private primary care settings. The pilot study focuses on ScreenMy, an ESS engine designed for bi-directional TB-DM screening. Methods: A pilot study investigated the integration process of ScreenMy into an EMR system. Interviews with developers assessed factors like installation ease, flexibility, and impact on the EMR's functionality. Findings: The findings revealed a smooth integration process due to ScreenMy's external design (requiring only plugin injection) and clear documentation. The integration maintained EMR performance and efficiency, enhanced the developer experience, and offered flexibility for customization. Developers, unfamiliar with prior integrated screening systems, found ScreenMy user-friendly and expressed interest in further system flexibility concerning data privacy. Conclusion: This investigation highlights the potential for seamless integration of screening systems like ScreenMy within EMRs. This paves the way for improved preventive healthcare delivery in primary care settings.

There have been several initiatives within standards committees to overcome privacy issues, including user tracking activity based on Media Access Control (MAC) addresses. The implementation of randomized MAC addresses on captive portals, with user-specific connection limits to address privacy concerns, introduces some problems. To address this issue, device removal based on OUI classification was proposed. Connection data taken from the RADIUS server were divided into two distinct classes, either random or not. Gaussian Naïve Bayes was utilized to classify the data with 16 distinct thresholds, and the solution with the highest accuracy was selected. The research produced results showing that all classifications had an accuracy above 96%. Values of 6 and 50% for Mac address thresholds and random percentage thresholds gave the highest accuracy of 98.1139%. This indicates that random Mac address classification in the real world can be done using the result.

The Islamic banking industry in Indonesia continues to grow, as evidenced by the presence of technology-based services. This study aims to test the application of the theory of plan behavior in explaining customer intention to use Islamic financial technology by adding gender variables as moderators. Primary data were collected from 298 Islamic fintech users through direct and online surveys. The sample was selected based on the purposive sampling technique. Using PLS MGA analysis, this study found that attitude, subjective norms, and perceived behavioral control positively affect the intention to use Islamic fintech, except for perceived behavioral control in the male gender. Using the MGA, Parametric, and Welch-Satterthwait tests, the study also revealed no significant difference between males and females in utilizing Islamic fintech. This study expands the understanding of psychological and social factors in adopting Islamic fintech. It also contributes to the literature by filling the research gap that has not considered gender moderation in adopting Islamic fintech.

Twitter is a social media platform that is very important in the digital world. Fast communication and interaction make Twitter a vital information center in sentiment analysis. The purpose of this research is to classify public opinion about the presence of marketplaces in Indonesia, both positive and negative sentiments, using a Non-linear SVM algorithm based on 1276 tweets. This research involves the stages of data pre-processing, labeling, feature extraction using TF-IDF, and data division into three scenarios: 80% training data and 20% test data, 50% training data and 50% test data scenario, and 20% training data and 80% test data scenario. The last process, GridSearchCV, combines cross-validation and non-linear SVM parameters for model evaluation using a confusion matrix. The best SVM model resulting from the scenario was 80% training and 20% test data, with hyperparameters Gamma = 100 and C = 0.01, achieving 89% accuracy. When tested on never-before-seen data, the accuracy increased to 90%, with an f1-score of 91%, precision of 88%, and recall of 95% on negative sentiments. In conclusion, evaluating the performance of non-linear SVM kernels with a combination of hyperparameter values can improve accuracy, especially on public response information about online marketplaces and public sentiment.

Lulus tepat waktu adalah pencapaian paripurna ingin dicapai oleh semua mahasiswa atau calon mahasiswa. Kelulusan memiliki 2 klasifikasi seperti lulus tidak tepat waktu dan lulus tepat waktu. Kelulusan menjadi suatu penilaian akreditasi universitas dan penilaian oleh masyarakat secara luas. Perguruan tinggi meluluskan mahasiswa-mahasiwa dengan beberapa kriteria standar yang harus dimiliki. Diharapkan mahasiswa lulus memenuhi syarat standar kelulusan dalam waktu maksimal 4 tahun masa studi. Evaluasi dan pemantauan kelulusan sangat penting dilakukan, salah satunya dengan mempelajari data history mahasiswa yang telah lulus sebagai upaya mahasiswa lulus tidak melebihi waktu standar yang telah ditetapkan. Prediksi kelulusan yang dilakukan pada riset menggunakan kaidah klasifikasi K-Nearest Neighbor dengan objek penelitian yaitu mahasiswa. Atribut yang dipakai dalam penelitian metode klasifikasi yaitu nama, asal SMA/SMK, wilayah asal SMA/SMK, nilai rata-rata matematika dan lama studi. Tahapan penelitian diawali dengan pengumpulan data, pemilihan atribut, pembersihan data, transformasi data, pemilihan data testing dan data training. Pengujian akurasi yang didapatkan pada penelitian metode klasifikasi dengan klaster data k=1, k=2, k=3, k=4, k=5, k=6 dan k=7 menghasilkan klaster dengan nilai k=3 paling tinggi. Hasil pengujian akurasi prediksi penelitian menggunakan confusion matrix menghasilkan akurasi paling besar sesuai target yaitu mencapai 78% menggunakan objek penelitian sebanyak 93 data mahasiswa terdiri dari 78 training dan 12 data testing. Hasil pengujian point k=1 sampai point k=7, k=3 merupakan nilai akurasi prediksi yang paling tinggi sehingga hasil penelitian menjadi sumber pengetahuan untuk fakultas dalam prediksi kelulusan mahasiswa. Abstract Graduating on time is a plenary achievement to be achieved by all students or prospective students. Graduation has 2 classifications such as graduating not on time and graduating on time. Graduation becomes an assessment of university accreditation and an assessment by the wider community. Universities graduate students with several standard criteria that must be possessed. It is expected that graduating students meet the graduation standard requirements within a maximum of 4 years of study period. Evaluation and monitoring of graduation is very important to do, one of which is by studying the history data of students who have graduated as an effort for students to graduate not to exceed the standard time that has been set. The graduation predictions carried out in research use the K-Nearest Neighbor classification rules with the research object being students. The attributes used in the research classification method are name, high school/vocational high school origin, high school/vocational high school origin, average grade in mathematics and length of study. The research phase begins with data collection, attribute selection, data cleaning, data transformation, selection of testing data and training data. The accuracy test obtained in the classification method research with data clusters k = 1, k = 2, k = 3, k = 4, k = 5, k = 6 and k = 7 produces a cluster with the highest k = 3 value. The results of testing the accuracy of research predictions using the confusion matrix produced the greatest accuracy according to the target, reaching 78% using a research object of 93 student data consisting of 78 training and 12 testing data. The test results point k=1 to point k=7, k=3 is the highest prediction accuracy value so that the research results become a source of knowledge for the faculty in predicting student graduation.

Indonesia is one of the countries that is currently entering the political year for the election of President, Regional Heads, and Members of the Legislative in 2024. This has become a hot topic on social media, especially about the Presidential Election. Twitter is one of the platforms with the largest users in Indonesia. It is interesting to see the alignment of Twitter users towards presidential candidates who already have a carrying party, namely Ganjar Pranowo, Prabowo Subianto, and Anies Baswedan based on a sentiment analysis approach. User feedback data about Indonesian Presidential candidates are obtained from the Twitter platform using Twitter API with Python programming language. The data obtained was 30,000 data with each candidate as many as 10,000 data. Data is pulled in April 2023 with specific keywords. The time for data withdrawal is chosen based on the announcement of Presidential Candidates carried by political parties before the schedule for determining or campaigning for Presidential candidates. Current data can potentially be used again as a comparison of analysis of presidential candidates on campaign time spans and after campaigns or actual calculation results. The data that can be accessed is in CSV format and has gone through several stages such as labelling using Language experts, removing spam Tweets & empty cells and preprocessing.

To maximize and get population document services closer to the community, the Disdukcapil district of Alor provides mobile services by visiting people in remote villages which difficult-to-reach service centres in the city. Due to a large number of villages and limited time and costs, not all villages can be served, so the kNN algorithm is needed to determine which villages are eligible to be served. The criteria used in this determination are village distance, difficulty level, and document ownership (Birth Certificate, KIA, family card, and KTPel). The classes that will be determined are "Very eligible", "Eligible", and "Not eligible". By applying Z-Score normalization with the value of K=5, the classification gets 94.12% accuracy, while non-normalized only gets 88.24% accuracy. Thus, applying normalization to training data can improve the kNN algorithm's accuracy in determining eligible villages for "ball pick-up" or mobile services.

Facial recognition is an essential aspect of conducting criminal action investigations. Captured images from the camera or the recording video can reveal the perpetrator's identity if their faces are deliberately or accidentally captured. However, many of these digital imagery results display the results of image quality that is not good when seen by the human eye. Hence, the facial recognition process becomes more complex and takes longer. This research aims to analyze face recognition on a low-quality image with noise, blur and brightness problem to help digital forensic investigator do an investigation in recognizing faces that the human eye can’t do. The Viola-Jones algorithm method has several processes such as the Haar feature, integral image, adaboost, and cascade classifier for detecting a face in an image. Detected face will be passed to the next process for recognition call Fisher’s Linear Discriminant (FLD), Local Binary Pattern’s (LBP) and Principal Component analysis (PCA). The software's facial recognition feature shows one of the images in the database that the program suspects has the same face as the analyzed face image. In conclusion, from the analysis we determined that LBP approach is the best among the other recognition methods for blur and brightness problem, bet found PCA method is the best for recognize face in noise problem. The software's facial recognition feature shows one of the images in the database that the program suspects has the same face as the analyzed face image. The position of the face object in the image, whether or not there is an additional object that was not previously included in the image in the dataset, as well as the brightness level of an image and the color of the face's skin, all affect the accuracy rates.

Instant Messaging (IM) is a popular and widely used communication application. MiChat is a multi-platform instant chat service with several features that can attract various segments of the population to use it as a tool for committing cybercrimes. A forensic framework and several forensic tools are needed to carry out physical evidence investigation procedures. This study focuses on analyzing and comparing the forensic tools used during the research, based on defined digital evidence parameters and applying a specific mobile forensic framework. The results show that Final Mobile Forensic has the highest ability to obtain digital evidence and can recover deleted data, while Oxygen Forensic Detective has advantages in terms of audio, images, and video but cannot recover data. The best framework is DFRWS, which has the most complete stages so that it can support the investigation process. The best digital evidence is text chat and contacts, which can be used to support valid legal claims.

According to reports in 2021 by Kaspersky, requests for investigations into suspicious network activity, such as ARP Spoofing, which can result in sophisticated attacks, reached up to 22%. Several difficulties with examining network systems have been overcome thanks to network forensic investigations. This study aims to perform a network forensic analysis of ARP spoofing attacks using Wireshark forensic tools and Network Miner with a sniffer design process to capture traffic on the router side. In order to gather reliable evidence, this study employs the TAARA method as a network forensic investigation process. Based on the research conducted, it can be demonstrated that an attack took place from eight PCAP files. The information that was gathered, such as the IP address and MAC address of the attacker, the IP address and MAC address of the target, and the date and time of the attack are examples of evidence information that was gathered. This study also shows that network forensic operations can use the Wireshark forensic tool to obtain more detailed data.

As evidenced in the trial, between 2015 and the second quarter of 2022, there were 54 cases involving secure digital high capacity (SDHC) storage hardware as evidenced in trials. In 2021 there will be an increase in cases involving SDHC. The three cases with the highest number are corruption cases, special crimes, and ITE. SDHC is an advanced technology development of Secure Digital (SD) card hardware which functions as storage. SD Card only has a capacity of up to 2 gigabytes, while the largest SDHC capacity is 32 gigabytes. As a storage device that is small, thin, and has a fairly large capacity. this research needs to be done because of the increasingly widespread increase in cases involving SDHC. This study aims to perform digital forensic analysis on SDHC evidence using forensic applications that run on Linux, namely foremost and DC3DD. This study uses the DFRWS method to retrieve valid evidence in court. Based on the research conducted, it was found that the number of files that can be restored at the examination stage using foremost is 77%, and the accuracy of recovered files is 50% with string file hash validation. From this research, it can be concluded that the processing results of DC3DD and Foremost can be used as valid evidence.

Social Media, in addition to having a positive impact on society, also has a negative effect. Based on statistics, 95 percent of internet users in Indonesia use the internet to access social networks. Especially for young people, Instagram is more widely used than other social media such as Twitter and Facebook. In terms of cyberbullying cases, cases often occur through social media, Twitter, and Instagram. Several methods are commonly used to analyze cyberbullying cases, such as SVM (Support Vector Machine), NBC (Naïve Bayes Classifier), C45, and K-Nearest Neighbors. Application of a number of these methods is generally implemented on Twitter social media. Meanwhile, young users currently use Instagram more social media than Twitter. For this reason, the research focuses on analyzing cyberbullying on Instagram by applying the K-Mean Clustering algorithm. This algorithm is used to classify cyberbullying actions contained in comments. The dataset used in this study was taken from 2019 to 2021 with 650 records; there were 1827 words and already had labels. This study has successfully classified the tested data with a threshold value of 0.5. The results for grouping words containing bullying on Instagram resulted in the highest accuracy, which is 67.38%, a precision value of 76.70%, and a recall value of 67.48%. These results indicate that the k-means algorithm can make a grouping of comments into two clusters: bullying and non-bullying.

This study aims to determine the factors of acceptance of e-learning technology in students who use the technology acceptance model, namely perceived usefulness (PU), perceived ease of use (PEOU), an attitude of acceptance of use (ATU), and acceptance (IT) of the e-learning acceptance system. The population in this study were students of state Islamic religious institutes who had participated in the e-learning system. The respondents of this study were students of the Ambon State Islamic Institute of Religion, which collected 30 respondents. The method used in this study uses the technology acceptance model method in the process of data processing using quantitative analysis techniques in the process of analyzing data from research results. The analysis results show that the acceptance of e-learning technology by students of the Islamic Institute of Religion is very well received by users of the Ambon State Islamic Institute of Religion students. The study's results showed that the variable utilization percentage of 76.66% was stated to agree strongly. In comparison, the percentage of 61.66% agreed. Attitudes towards users 70.66% agreed. The study's results show that students in the learning process can accept using e-learning systems.

One of the popular cryptographic algorithms is the Vigenère Cipher. This algorithm is included in classical cryptographic algorithms, so its capabilities are limited to text-type data. Through this research, this research try to modify the Vigenère Cipher so that it can be used on digital image media. The improvement is performed using ASCII code as a Vigenère table and the key generated by the SHA512 hash technique with salt. The encryption and decryption process was carried out on ten jpg and ten png files and showed a 100% success rate. Speed and memory consumption tests on the encryption process by comparing it with the AES algorithm show that AES excels in speed with 409,467 Mb/s while Vigenère wins in memory consumption by utilizing only 5,0007 Kb for every Kilobytes of the processed digital image file.

Program pemberdayaan masyarakat ini bertujuan untuk menggunakan media Power Point dan Canva sebagai media penyampaian informasi yang inovatif dan meningkatkan soft skill desain. Pelatihan ini diikuti 15 mahasiswa baru program studi Sistem Informasi STIMIK Muhammadiyah Jakarta. Program ini melakukan 2 sesi pertemuan online melalui Zoom Meating karena Universitas mempraktikkan home learning, ada kebijakan tersebut terkait wabah Covid19. Pertemuan pertama memberikan materi tentang perkembangan teknologi dan media informasi sebagai tambahan wawasan. Pertemuan kedua memberikan tutorial tentang cara menggunakan Power Point dan tools Canva untuk mendesain informasi, yaitu desain sertifikat, desain undangan, desain animasi PPT, dan konten digital lainnya. Hasil tes pretest dan postest menunjukkan bahwa nilai presentase mahasiswa baru meningkat sebesar 13%. Hasil ini mengindikasikan adanya sedikit peningkatan dalam pengetahuan wawasan dan soft skill tentang teknologi media informasi.

The random noise signal is widely used as a test signal to identify a physical or biological system. In particular, the Gaussian distributed white noise signal (Gaussian White Noise) is popularly used to simulate environmental noise in telecommunications system testing, input noise in testing ADC (Analog to Digital Converter) devices, and testing other digital systems. Random noise signal generation can be done using resistors or diodes. The weakness of the noise generator system using physical components is the statistical distribution. An alternative solution is to use a Pseudo-Random System that can be adjusted for distribution and other statistical parameters. In this study, the implementation of the Gaussian distributed pseudo noise generation algorithm based on the Enhanced Box-Muller method is described. Prototype of noise generation system using a minimum system board based on Cortex Microcontroller or MCU-STM32F4. The test results found that the Enhanced Box-Muller (E Box-Muller) method can be applied to the MCU-STM32F4 efficiently, producing signal noise with Gaussian distribution. The resulting noise signal has an amplitude of ±1Volt, is Gaussian distributed, and has a relatively broad frequency spectrum. The noise signal can be used as a jamming device in a particular frequency band using an Analog modulator.

Media sosial sangat bermanfaat untuk mendapatkan informasi atau data dengan mudah dan cepat seiring dengan peningkatan jumlah pengguna smartphone terutama pada Android. Di sisi lain, mobile instant messangging aplications dan sosial media membuat prospek adanya tindak kejahatan dunia maya atau Cybercrime khususnya cyber espionage yaitu tindakan mata- mata terhadap data elektronik atau memanfaatkan jaringan internet. Penelitian ini diharapkan dapat membuka barang bukti digital pelaku cyber espionage yang ada di aplikasi Facebook berupa gambar dan teks untuk mendukung identifikasi aktivitas yang menuju pada cyber espionage. Kerangka kerja untuk menjalankan digital forensics pada pengkajian ini menggunakan metode Digital Forensics Research Workshop (DFRWS) dengan tahapan identification (identifikasi), Preservation (Pemeliharaan) Collection (Pengumpulan), Examination (Pemeriksaan), Analysis (Analisis), Presentation (Presentasi) . Tools yang digunakan adalah MobilEdit dengan cara kerja ektraksi dan analisis. Skenario yang dilakukan adalah kasus cyber espionage pada facebook. Harapan dari penelitian ini adalah menghasilkan Forensis Investigative analysis pada Facebook memakai metode DFRWS mampu mengungkap cyber espionage pada aplikasi Facebook.

Current technological developments make it easier for people to share information and carry out communication activities through instant messaging applications using multimedia features in the form of audio and video. Technology has been able to contribute and facilitate humans in a positive sense, but it can also be misused to carry out negative activities. In solving crime problems using instant messages, investigators need to carry out digital forensics, including on mobile devices such as smartphones. This study aims to obtain digital evidence of online drug sales scenarios via Facebook messenger and WhatsApp using four forensic tools, namely Belkasoft, Oxygen, MOBILedit, and Magnet Axiom. The National Institute of Justice (NIJ) is used as a framework with stages, namely identification, solution, testing, evaluation, and reporting of results. out of the four tools, MOBILedit cannot recover deleted audio and video while the other three tools can recover deleted audio and video.

E-mail is electronic mail used to send files, pictures, and others easily and quickly. However, as time goes by, there is a lot of misuse of e-mail, causing inconvenience to the recipient. One of them is spam e-mail sent to many people without prior permission from the intended owner. Hackers can forge e-mail headers anonymously for malicious purposes. The research object is to simulate sending spamming e-mails to 1 victim with a total of 40 spamming e-mails. The research follows the flow of the Network Forensics Development Life Cycle (NFDLC) method with the stages of initiation, acquisition, implementation, operation, and disposition. Simulation of sending e-mail using easy e-mail spammer tools and testing of e-mail using Wireshark tools. The test results show that 40 e-mails were successfully received or entered into the victim's inbox, and the test was successfully carried out by getting results based on predetermined parameters. The parameter is the IP address of the sender or spammer found is 72.125.68.109, the victim's IP address is 192.168.1.12.

User data security innovation is a particular concern in protecting one's privacy rights, which is one of the serious violations when an attacker can bypass the user authentication so that it looks like something legitimate and becomes legal. Based on these issues, the research aims at optimizing and evaluating the blockchain-based authentication systems to minimize data leakage, manipulate the data, and modify the data. Blockchain is one of the innovations that can solve this problem. Data or transactions in the blockchain are saved in hash form to make it difficult for hackers to break into them. The Blockchain implementation uses the Solidity programming language to build smart contracts and other tools such as MetaMask, Ganache, and Truffle. The Network Forensics Development Life Cycle (NFLDC) is used as a framework with the following five stages: Initiation, Acquisition, Implementation, Operation, and Disposition. Based on the research conducted, the attack strategy against blockchain-based systems consists of several scenarios covering the Burp Suite, XSS, SQL Injection, and DoS. The results show that the percentage of authentication optimization reaches a value of 90.1%, and 8.9% is the percentage for evaluating systems such as the possibility of cyberattack. Based on these results, this research has achieved its goals and may assist in further research. Doi: 10.28991/esj-2021-SP1-015 Full Text: PDF

The misuse of health data stored in the Electronic Health Record (EHR) system can be uncontrolled. For example, mishandling of privacy and data security related to Corona Virus Disease-19 (COVID-19), containing patient diagnosis and vaccine certificate in Indonesia. We propose a system framework design by utilizing the InterPlanetary File System (IPFS) and Blockchain technology to overcome this problem. The IPFS environment supports a large data storage with a distributed network powered by Ethereum blockchain. The combination of this technology allows data stored in the EHR to be secure and available at any time. All data are secured with a blockchain cryptographic algorithm and can only be accessed using a user's private key. System testing evaluates the mechanism and process of storing and accessing data from 346 computers connected to the IPFS network and Blockchain by considering several parameters, such as gas unit, CPU load, network latency, and bandwidth used. The obtained results show that 135205 gas units are used in each transaction based on the tests. The average execution speed ranges from 12.98 to 14.08 GHz, 26 KB/s is used for incoming, and 4 KB/s is for outgoing bandwidth. Our contribution is in designing a blockchain-based decentralized EHR system by maximizing the use of private keys as an access right to maintain the integrity of COVID-19 diagnosis and certificate data. We also provide alternative storage using a distributed IPFS to maintain data availability at all times as a solution to the problem of traditional cloud storage, which often ignores data availability. Doi: 10.28991/esj-2021-SP1-013 Full Text: PDF

Facial recognition is a significant part of criminal investigations because it may be used to identify the offender when the criminal's face is consciously or accidentally recorded on camera or video. However, a majority of these digital photos have poor picture quality, which complicates and lengthens the process of identifying a face image. The purpose of this study is to discover and identify faces in these low-quality digital photographs using the Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) face identification method and the Viola-Jones face recognition method. The success percentage for the labeled face in the wild (LFW) dataset is 63.33%, whereas the success rate for face94 is 46.66%, while LDA is only a maximum of 20% on noise and brightness. One of the names and faces from the dataset is displayed by the facial recognition system. The brightness of the image, where the facial item is located, and any new objects that have entered the scene have an impact on the success rate.

Today's technology makes communication very easy and can be used anywhere, even a distance of hundreds to thousands of kilometres is not a barrier in communicating. One of the tools or media that is widely used is via email. However, there are many disadvantages that may be obtained from the email, one of which is spamming or mail. The purpose of this research is to know the stages of spamming email analysis through header analysis. The method used in this study is the National Institute of Standards and Technology (NIST) and this method uses 4 stages, namely collection, examination, analysis, and reporting. The results of this study are expected to be able to find out the spam sender's email address, the spam email sender's IP address, and other information needed.

Keamanan adalah faktor penting yang harus diperhatikan dalam membangun sebuah web server. Pengujian Penetrasi didefinisikan sebagai upaya legal dan resmi untuk mengekploitasi sistem komputer dengan tujuan mencari kerentanan pada web server serta meningkatkan keamanan sistem. Pengujian penetrasi ini dilakukan pada web server yang merupakan Sistem Informasi Akademik pada perguruan tinggi. Metode yang digunakan dalam penelitian ini mencakup Information Gathering, Vullnerability Assessmant, gaining acces, maintaining acces, Clearing Track. Hasil penelitian menampilkan bahwa terdapat empat kelemahan pada web server yaitu level high, empat kelemahan level medium, dan dua kerentanan dengan level low. Ditemukannya beberapa port yang masih terbuka dalam web server yang menyebabkan peretas dengan mudah masuk kedalam sistem untuk mengekploitasi informasi yang terdapat dalam Sistem Informasi Akademik. Hasil ujicoba simulasi serangan terhadap sistem berhasil masuk dengan mendapatkan username dan password

Hiragana is one of the traditional Japanese letters used to translate native Japanese words. The introduction of an object requires a learning process, which is obtained through the characteristic in the form of unique features on similar objects, but manually it is quite difficult to distinguish these letters. This writing explains the discussion system to differentiate between hiragana letters starting from preprocess namely grayscale and threshold, then segmenting and normalization, while image classification uses the Template Matching Correlation method. The results of tests carried out assessing the test rate of around 76% using the Matching Template Correlation method. While the remaining 14% indicates that the object identified does not match the intended results.

Audio is one of the digital items that can reveal a happened case. However, audio evidence can also be manipulated and changed to hide information. Forensics audio is a technique to identify the sound’s owner from the audio using pitch, formant, and spectrogram parameters. The conducted research examines the similarity of the original sound with the manipulated voice to determine the owner of the sound. It analyzes the level of similarity or identical sound using spectrogram analysis with the Digital Forensics Research Workshop (DFRWS) Method. The research objects are original and manipulated files. Both files are in mp3 format, which is encoded to WAV format. Then, the live forensics method is used by picking up the data on a smartphone. Several applications are also used. The results show that the research successfully gets digital evidence on a smartphone with the Oxygen Forensic application. It extracts digital evidence in the form of two audio files and two video files. Then, by the hashing process, the four obtained files are proven to be authentic. Around 90% of the data are identical to the original voice recording. Only 10% of the data are not identical.

Teknologi informasi di era saat ini menunjukkan perkembangan yang pesat khususnya dalam bidang komputer berbasis jaringan. Di sisi lain, terdapat beberapa oknum-oknum tertentu yang menyalahgunakan teknologi tersebut salah satunya dengan melakukan serangan pada jaringan komputer. Router merupakan perangkat jaringan yang dapat membuat jaringan lokal bisa terhubung ke jaringan public. Router seringkali menjadi target serangan, hal ini dikarenakan Router menjadi jalur lalu lintas pengiriman data. Flooding Attack merupakan salah satu serangan pada jaringan komputer. Serangan yang dilakukan bertujuan membanjiri lalu lintas data pada jaringan sehingga dapat menyebabkan jaringan menjadi down (lumpuh) diakibatkan kelebihan beban. Untuk mendeteksi Flooding Attack diperlukan beberapa alat seperti Winbox yang digunakan untuk mendapatkan Log Activity, Log Traffics dan Ip Address serta Wireshark sebagai alat untuk mencari informasi yang terdapat pada Log Traffic yang dapat digunakan sebagai bukti digital dengan menggunakan metode Live Forensics. Dalam penelitian ini, informasi yang akan digali adalah Log Activity, Log Traffics dan IP Address. Untuk memperoleh informasi tersebut, maka dilakukan beberapa simulasi serangan pada Router. Dari simulasi yang dilakukan terjadi peningkatan signifikan pada lalulintas jaringan Router serta penggunaan sumber daya yang juga meningkat. Adapun output dari penelitian ini yaitu menemukan dan menarik data-data penting yang merupakan bukti digital berupa Log Activity serta Log Traffic. Informasi yang diperoleh pada file log tersebut yaitu ditemukan adanya IP Address yang terdeteksi melakukan serangan yaitu IP Address 192.168.2.252. Beberapa informasi yang terdapat pada log file yang telah ditarik juga dapat dijadikan sebagai barang bukti dalam persidangan.

Teknik penyembunyian pesan dalam media digital dikenal dengan istilah steganografi. Peneltitian diranccang untuk membuat steganografi video, pesan yang disisipkan berupa teks terlebih dahulu dienkripsi dengan algoritma Rijndael. Metode Penyisipan pesan pada video adalah metode End of File (EoF).Ektraksi frame pada video menggunakan ffmpeg. Pengujian kualitatif digunakan untuk melihat perubahan frame video dengan indera manusia. Pengujian kuantitatif dilakukan pada enam video dengan resolusi yang berbeda, disisipi pesan dengan ukuran byte yang bervariasi. Frame yang telah disisipi pesan diukur nois-nya dengan Peak Signal to Noise Ratio (PSNR). Keunggulan dari metode EoF dalam penelitian ini adalah frame video dapat menampung pesan dengan ukuran yang tidak terbatas. frame video setelah disisipi pesan dengan berbagai macam ukuran pesan tidak terjadi noise hal ini terlihat dari Nilai MSE nol dan PNSR bernilai Infinity dari hasil pengujian.

Zachman Framework (ZF) and The Open Group Architecture Framework (TOGAF) are Architecture Frameworks often used in Architecture Enterprise's implementation. Each side of the two architecture Frameworks has advantages and disadvantages. Sekolah Tinggi Manajemen Informatika dan Komputer Muhammadiyah Paguyangan Brebes (STMIK MPB) is a new university established on April 28, 2017; STMIK MPB as a new university has no plans in building an information system. The research will select the parts that exist in the ZF and TOGAF methodologies. The two methods will be combined and compiled to be applied to the Academic Information System modeling or blended methods. These research results are architectural blueprints that can be used as a reference in the development of academic information systems.

Viber is one of the most popular social media in the Instant Messenger application category that can be used to send text messages, make voice calls, send picture messages and video messages to other users. As many as 260 million people around the world have used this application. Increasing the number of viber users certainly brings positive and negative impacts, one of the negative impacts of this application is the use of digital forensic crime. This research simulates and removes digital crime evidence from the viber application on Android smartphones using the National Institute of Standards Technology (NIST) method, which is a method that has work guidelines on forensic policy and process standards to ensure each investigator follows the workflow the same so that their work is documented and the results can be accounted for. This study uses three forensic tools, MOBILedit Forensic Express, Belkasoft and Autopsy. The results in this study show that MOBILedit Forensic Express gets digital evidence with a percentage of 100% in getting accounts, contacts, pictures and videos. While proof of digital chat is only 50%. Belkasoft gets digital evidence with a percentage of 100% in getting accounts, contacts, pictures and videos. While proof of digital chat is only 50%. For Autopsy does not give the expected results in the extraction process, in other words the Autopsy application gives zero results. It can be concluded that MOBILedit Forensic Express and Belkasoft have a good performance compared to Autopsy and thus this research has been completed and succeeded in accordance with the expected goals.

Steganography is the science and art of hiding information so that confidential information cannot be known by others, except the sender and receiver. This research is designed to create a steganography system on video with mp4 format. The message is inserted in one of the video frames, first encrypted with the Rijndael algorithm. The method of inserting messages in the video frame is the Least Significant Bit (LSB) method. Extraction of frames on video using ffmpeg software. Qualitative testing used to identify changes in video frames with human senses. Quantitative testing was carried out by testing six videos with different resolutions, while there were five inserted messages with varying Byte lengths. The frame that has been inserted with a message is measured for noise with the Peak Signal to Noise Ratio (PNSR). The test results show that the LSB method cannot be used for message insertion whose Byte size is greater than the capacity of the cover video. There is a change in image quality if the size of the inserted message bytes is getting bigger.

The application of Blockchain technology has begun to be widely accommodated in industrial and business practitioner environments as a safeguard of transaction security so that now including the education sector, non-business institutions enjoy the use of this technology to support the learning process. Information on the protected Blockchain can be in the form of transactions, assets, identities, and other information packaged in digital form. Information is collected in the form of blocks that are interrelated by using the hash function as cryptographic encryption. This research uses Blockchain for online pocket money top-up transactions for students. The use of a centralized Blockchain is centralized to reduce server procurement costs, but to increase the security of transaction information, modification of each block series is carried out using the AES cryptographic approach. The results showed that the attack by inserting a Cross-Site Scripting (XSS) script if you want to know the value of the top-up transaction amount, you must be able to hack the cryptographic process. This is supported by chain validation testing to determine how many block changes have been changed.

The development of communication media continues to increase with the emergence of various communication applications on smartphones, which are currently very developed from limited communication media to social media. This change in the flow of communication applications gives a new color to communication, not just exchanging messages and sounds but also exchanging videos and pictures. This development was also followed by the rise of digital crimes in the form of defamation, fraud, and hoax news by spreading posts and then deleting them after the news spread widely. This research was conducted to obtain digital evidence with the help of special applications such as Belkasoft Evidence and Axiom Magnets using the NIST method. The results of this study show that the Magnet Axiom is better with an accuracy rate of 83.3% while Belkasoft Evidence is only 50%.

Nowadays developments in information technology are growing rapidly, especially in email. Email became one that almost the whole world had. Email is one of the results of developments in information and communication. Email is widely used to exchange information by sending and receiving data, such as document files, pictures, letters, and others. So much for the crimes that often occur in emails. Email crimes that often occur among them are email spoofing. Email spoofing is a forgery that occurs in the header of the email. So, the email is sent as if it were a valid email. Email spoofing is often used in spamming activities. Crimes committed by cybercrime must leave evidence such as IP Address, sender's email, and time of sending the email. This research will do forensics on email spoofing. The research uses the Live Forensics method, where the computer is used in a powered-on state. The research also uses the NIST (National Institute of Standards Technology) research flow. The email that will be analyzed is in the email header section using 3 tools, namely tracer email analyzer, email dossier, and mail header analysis. This analysis will compare and check the accuracy of the email headers using these tools. Emails suspected of email spoofing will be proven using tools. Based on the 'form' received' and 'Message-ID' headers. Based on the results, the tool that meets the value after the analysis is tracer email analysis.

Perkembangan teknologi citra digital yang semakin maju membuat mudahnya merekayasa suatu citra. Perubahan pada citra membuat informasi yang disampaikan menjadi berubah dan rawan dimanfaatkan menjadi aksi kejahatan digital. Salah satu cara menyelesaikan kasus kejahatan digital ini menggunakan forensik citra. Penelitian ini menggunakan metode teknik pendeteksian rekayasa foto digital Speeded Up Robust Features (SURF). Tahapan pertama melakukan mengakuisisi data kemudian melakukan proses ekstraksi dengan hasil akuisisi tersebut. Hasil yang sudah didapat dianalisis menggunakan algoritma SURF, algoritma ini mendeteksi adanya manipulasi pada foto dengan tidak adanya keypoint pada beberapa objek yang tidak terhubung. Rekayasa foto digital dapat dipastikan menggunakan perbandingkan kualitas citra pada setiap foto dengan perhitungan MSE, RMSE dan PSNR. Hasil perbandingan nilai kualitas didapat perbedaan antara nilai kualitas pada foto asli dan foto manipulasi, hal tersebut dapat membuktikan bahwa foto tersebut sudah dimanipulasi.

Current crime is increasing, one of which is the crime of using social media, although no crime does not leave digital evidence. Twitter application is a social media that is widely used by its users. Acts of crime such as fraud, insults, hate speech, and other crimes lately use many social media applications, especially Twitter. This research was conducted to find forensic evidence on the social media Twitter application that is accessed using a smartphone application using the Digital Forensics Research Workshop (DFRWS) method. These digital forensic stages include identification, preservation, collection, examination, analysis, and presentation in finding digital evidence of crime using the MOBILedit Forensic Express software and Belkasoft Evidence Center. Digital evidence sought on smartphones can be found using case scenarios and 16 variables that have been created so that digital proof in the form of smartphone specifications, Twitter accounts, application versions, conversations in the way of messages and status. This study's results indicate that MOBILedit Forensic Express digital forensic software is better with an accuracy rate of 85.75% while Belkasoft Evidence Center is 43.75%.

Web-based instant messaging applications vulnerability has become one of the main concerns for its users in line with the increasing number of cybercrimes that occur on social media. This research was conducted to determine the comparability of the vulnerability value of the web-based WhatsApp, Telegram, and Skype applications using the Association of Chief Police Officers (ACPO) method. Digital artifacts in the form of text messages, picture messages, video messages, telephone numbers, and user IDs have been acquired in this research process using FTK imager and OSForensic tools. The results of the study using the FTK imager and OSForensic tools show that the web-based Skype application has a vulnerability value of 92%, while WhatsApp and Web-based Telegram have the same vulnerability value with 67% each based on all digital artifacts that successfully acquired.

DVD-R is a type of optical drive that can store data in one burning process. However, there is a feature that allows erasing data in a read-only type, namely multisession. The research was conducted to implement the data acquisition process which was deleted from a DVD-R using Autopsy forensic tools and FTK Imager. The National Institute of Standards and Technology (NIST) is a method commonly used in digital forensics in scope storage with stages, namely collection, examination, analysis, and reporting. The acquisition results from Autopsy and FTK-Imager show the same results as the original file before being deleted, validated by matching the hash value. Based on the results obtained from the analysis and presentation stages, it can be concluded from the ten files resulting from data acquisition using the FTK Imager and Autopsy tools on DVD-R. FTK Imager detects two file systems, namely ISO9660 and Joliet, while the Autopsy tool only has one file system, namely UDF. The findings on the FTK Imager tool successfully acquired ten files with matching hash values and Autopsy Tools detected seven files with did not find three files with extensions, *.MOV, *.exe, *.rar. Based on the results of the comparative analysis of the performance test carried out on the FTK Imager, it got a value of 100% because it managed to find all deleted files and Autopsy got a value of 70% because 3 files were not detected because 3 files were not detected and the hash values ​​were empty with the extensions * .exe, * .rar and *.MOV. This is because the Autopsy tool cannot detect the three file extensions.

Steganalisis digunakan untuk mendeteksi ada atau tidaknya file steganografi. Salah satu kategori steganalisis adalah blind steganalisis, yaitu cara untuk mendeteksi file rahasia tanpa mengetahui metode steganografi apa yang digunakan. Sebuah penelitian mengusulkan bahwa metode Convolutional Neural Networks (CNN) dapat mendeteksi file steganografi menggunakan metode terbaru dengan nilai probabilitas kesalahan rendah dibandingkan metode lain, yaitu CNN Yedroudj-net. Sebagai metode steganalisis Machine Learning terbaru, diperlukan eksperimen untuk mengetahui apakah Yedroudj-net dapat menjadi steganalisis untuk keluaran dari tools steganografi yang biasa digunakan. Mengetahui kinerja CNN Yedroudj-net sangat penting, untuk mengukur tingkat kemampuannya dalam hal steganalisis dari beberapa tools. Apalagi sejauh ini, kinerja Machine Learning masih diragukan dalam blind steganalisis. Ditambah beberapa penelitian sebelumnya hanya berfokus pada metode tertentu untuk membuktikan kinerja teknik yang diusulkan, termasuk Yedroudj-net. Penelitian ini akan menggunakan lima alat yang cukup baik dalam hal steganografi, yaitu Hide In Picture (HIP), OpenStego, SilentEye, Steg dan S-Tools, yang tidak diketahui secara pasti metode steganografi apa yang digunakan pada alat tersebut. Metode Yedroudj-net akan diimplementasikan dalam file steganografi dari output lima alat. Kemudian perbandingan dengan tools steganalisis lain, yaitu StegSpy. Hasil penelitian menunjukkan bahwa Yedroudj-net bisa mendeteksi keberadaan file steganografi. Namun, jika dibandingkan dengan StegSpy hasil gambar yang tidak terdeteksi lebih tinggi. Abstract Steganalysis is used to detect the presence or absence of steganograpy files. One category of steganalysis is blind steganalysis, which is a way to detect secret files without knowing what steganography method is used. A study proposes that the Convolutional Neural Networks (CNN) method can detect steganographic files using the latest method with a low error probability value compared to other methods, namely CNN Yedroudj-net. As the latest Machine Learning steganalysis method, an experiment is needed to find out whether Yedroudj-net can be a steganalysis for the output of commonly used steganography tools. Knowing the performance of CNN Yedroudj-net is very important, to measure the level of ability in terms of steganalysis from several tools. Especially so far, Machine Learning performance is still doubtful in blind steganalysis. Plus some previous research only focused on certain methods to prove the performance of the proposed technique, including Yedroudj-net. This research will use five tools that are good enough in terms of steganography, namely Hide In Picture (HIP), OpenStego, SilentEye, Steg and S-Tools, which is not known exactly what steganography methods are used on the tool. The Yedroudj-net method will be implemented in a steganographic file from the output of five tools. Then compare with other steganalysis tools, namely StegSpy. The results showed that Yedroudj-net could detect the presence of steganographic files. However, when compared with StegSpy the results of undetected images are higher.

Cyberbullying in group conversations in one of the instant messaging applications is one of the conflicts that occur due to social media, specifically WhatsApp. This study conducted digital forensics to find evidence of cyberbullying by obtaining work in the Digital Forensic Research Workshop (DFRWS). The evidence was investigated using the MOBILedit Forensic Express tool as an application for evidence submission and the Cosine Similarity method to approve the purchase of cyberbullying cases. This research has been able to conduct procurement to reveal digital evidence on the agreement in the Group's features using text using MOBILedit. Identification using the Cosine method. Similarities have supported actions that lead to cyberbullying with different levels Improved Sqrt-Cosine (ISC) value, the largest 0.05 and the lowest 0.02 based on conversations against requests.

Open Journal System (OJS) merupakan perangkat lunak yang berfungsi sebagai sarana publikasi ilmiah dan digunakan diseluruh dunia. OJS yang tidak dipantau beresiko diserang oleh hacker. Kerentanan yang di timbulkan oleh hacker akan berakibat buruk terhadap performa dari sebuah OJS. Permasalahan yang dihadapi pada sistem OJS meliputi network, port discover, proses audit exploit sistem OJS. Proses audit sistem pada OJS mencakup SQL Injection, melewati firewall pembobolan password. Parameter input yang digunakan adalah IP address dan port open access. Metode yang digunakan adalah vulnerability assessment. Yang terdiri dari beberapa tahapan seperti information gathering atau footprinting, scanning vulnerability, reporting. Kegiatan ini bertujuan untuk mengidentifikasi celah keamanan pada website open journal system (OJS). Penelitian ini menggunakan open web application security project (OWASP). Pengujian yang telah dilakukan berhasil mengidentifikasi 70 kerentanan high, 1929 medium, 4050 low pada OJS, Total nilai vulnerability pada OJS yang di uji coba sebesar 6049. Hasil pengujian yang dilakukan menunjukkan bahwa pada OJS versi 2.4.7 memiliki banyak celah kerentanan atau vulnerability, tidak di rekomendasi untuk digunakan. Gunakanlah versi terbaru yang dikeluarkan oleh pihak OJS Public knowledge project (PKP). Abstract The Open Journal System (OJS) is A software that functions as a means of scientific publication and is used throughout the world. OJS that is not monitored is at risk of being attacked by hackers. Vulnerabilities caused by hackers will adversely affect the performance of an OJS. The problems faced by the OJS system include the network, port discover, OJS system audit exploit process. The system audit process on the OJS includes SQL Injection, bypassing the firewall breaking passwords. The input parameters used are the IP address and open access port. The method used is a vulnerability assessment. Which consists of several stages such as information gathering or footprinting, scanning vulnerability, reporting. This activity aims to identify security holes on the open journal system (OJS) website. This study uses an open web application security project (OWASP). Tests that have been carried out successfully identified 70 vulnerabilities high, 1929 medium, 4050 low in OJS, the total value of vulnerability in OJS which was tested was 6049. The results of tests conducted showed that in OJS version 2.4.7 had many vulnerabilities or vulnerabilities, not on recommendations for use. Use the latest version issued by the OJS Public Knowledge Project (PKP).

Penggunaan Website pada zaman sekarang sedang berkembang pesat, berbagai jenis aplikasi, layanan dari swasta sampai pemerintah banyak menggunakan website sebagai media interaksi antar berbagai platform. Biasanya saat mengunggah berkas pada website, sistem melakukan validasi dengan menyaring jenis berkas objek digital di server side (backend) atau dalam halaman website pada web browser dalam bentuk HTML atau Javascript (frontend) dengan memanfaatkan penyaringan File Signature atau Multipurpose Internet Mail Extensions (MIME), File Extention dan File Size pada setiap berkas yang diunggah tanpa mengecek isi kontennya sehingga berkas digital object yang corrupt atau yang disisipi selain gambar dapat diproses dalam fitur unggahan. Faktor keamanan sangatlah penting dikarenakan pada zaman yang semakin berkembang banyak sistem yang berupa digital. Ancaman serangan terhadap berbagai jenis sistem yang berbentuk digital atau server juga ikut berkembang, maka diperlukan sebuah penanganan terhadap ancaman atau serangan pada server dengan celah fitur unggahan. Penelitian ini bertujuan untuk meneliti teknik validasi PNG yang tidak hanya mengecek MIME, File Extention dan File Size tetapi memanfaatkan juga Metadata PNG dan nilai warna RGBA (Red, Green, Blue, Alpha) pada setiap pixel dengan Metode Pengembangan menggunakan Extreme Programming (XP). Hasil penelitian dengan sampel 10 gambar berisi metadata dan 10 gambar yang tidak berisi metadata dapat mengecek validasi secara khusus unggahan gambar pada PNG File dengan menyaring secara khusus sesuai keunikan dari file gambar yaitu mempunyai panjang dan lebar pada metadatanya yang harus tersedia (Width, Height, Bits, Mime) serta RGBA (Red, Green, Blue, Alpha) pada setiap piksel sesuai dengan panjang dan lebar sebuah gambar PNG.

Steganography is one of the anti-forensic techniques that allow criminals to hide information in other messages so that during the investigation, the investigator will experience problems and difficulty in getting evidence of original information on the crime. Therefore an investigator is required to have the ability to be able to find and extract (decoding) using the right tools when opening messages that have been inserted by steganography techniques. The purpose of this study is to analyze digital evidence using the static forensics method by applying the six stages to the Digital Forensics Research Workshop (DFRWS) framework and extracting steganography on files that have been compromised based on case scenarios involving digital crime. The tools used are FTK Imager, Autopsy, WinHex, Hiderman, and StegSpy. The results of extraction of 9 out of 10 files that were scanned by steganography files had 90% success and 10% of steganography files were not found, so it can be concluded that the extraction files in steganographic messages can be used as legal digital proofs according to law.

Cybercrime on Internet that keeps increasing does not only take place in the environment that running web applications traditionally under operating system, but also web applications that are running in more advance environment like container service. Docker is a currently popular container service in Linux operating system needs to be secured and implements incident response mechanisme that will investigate web server that was attacked by DDoS in fast, valid, and comprehesive way. This paper discusses the investigation using Grr Rapid Response framework on web server that was attacked by DDoS running in container service on Linux operating system, and the attacker using Windows oprating system that runs DDos script. This research has succesfully investigated digital evidence in the form of log file from web server running on container service and digital evidence through netstat on Windows computer.

Steganografi merupakan salah satu teknik anti forensik yang memungkinkan pelaku kejahatan untuk menyembunyikan suatu informasi kedalam pesan lainnya, sehingga pada saat pemeriksaan akan sulit untuk didapatkan bukti informasi kejahatan tersebut. Oleh karena itu diperlukan teknik untuk mendeteksi pesan tersembunyi di dalam suatu data. Teknik tersebut dikenal dengan istilah steganalisis. Steganalisis merupakan suatu ilmu anti-steganografi yang tujuan utamanya adalah mempelajari karakteristik penyembunyian suatu data pada media digital serta mendeteksi keberadaan pesan rahasia yang disembunyikan menggunakan teknik steganografi. Tujuan pada penelitian ini adalah menerapkan teknik steganalisis untuk mendeteksi keberadaan pesan yang disembunyikan dalam pesan lain dengan menggunakan metode forensik yaitu Digital Forensics Research Workshop (DFRWS). Pada penelitian ini, proses penyisipan pesan steganografi menggunakan aplikasi Hiderman, sedangkan proses steganalisis menggunakan aplikasi StegSpy. Hasil yang didapat pada penelitian ini adalah proses steganalisis dengan menggunakan bantuan aplikasi StegSpy terbukti berhasil mendeteksi keberadaan pesan tersembunyi pada keempat file yang diskenariokan telah disisipi pesan steganografi.

Kriptografi pengubahan pesan asli menjadi disamarkan berguna menjaga kerahasiaan, integritas, keaslian, autentikasi pesan ketika proses komunikasi. Kriptografi klasik dengan subtitusi polialfabetik Vigenere memiliki tabel alphabet 26 baris yang relatif sederhana menjamin kerahasiaan. Kini pendekatan pembelajaran mesin Jaringan Syaraf Tiruan (JST) menjadi solusi layak untuk kriptografi dengan membentuk kunci rahasia dalam bobot jaringan sulit terpecahkan. Kunci dihasilkan dari bidirectional learning, dua pohon paritas saling tersinkronisasi dengan paramater hidden neuron, input neuron dan bobot. Sinkronisasi pada saluran publik dengan mengadopsi cara kerja Tree Parity Machine (TPM) dengan tipe feed forward. Pendekatan Kriptografi JST bermanfaat sebagai perlindungan dan serangan kriptografi. Penelitian ini memanfaatkan kombinasi sinkronisasi JST dan Vigenere dalam bentuk generator untuk optimasi pesan. Hasil pengujian kombinasi metode tidak berpengaruh dengan jumlah tampungan karakter pesan dan nilai parameter. Keunggulan kunci yang dihasilkan tidak bisa digunakan secara berulang meski nilai parameter sama, namun panjang karakter kunci berjumlah sama. Sisi fungsionalitas menghasilkan nilai 100%. Kata kunci: Kriptografi, Jaringan Syaraf Tiruan (JST), Tree Parity Machine (TPM), Vigenere Cipher Abstract Cryptography changes the original message to be disguised useful to maintain the security message. Vigenere polyalphabetic substitution relatively simple 26-row alphabetical table guaranteeing confidentiality. Machine learning approach Artificial Neural Network (ANN) becomes feasible solution for cryptography by forming secret key in the weight of the network that’s difficult to solve. The key’s generated from bidirectional learning, two parity trees synchronized with hidden neurons, input neurons, and weights. Synchronize public channels by adopting the work of Tree Parity Machine (TPM) with feedforward type. This research utilizes the combination of synchronization ANN and Vigenere from generators. The result of testing the combination of methods doesn’t affect the number of message character and parameter values. The advantages of the resulting key cannot be used repeatedly even though the parameter values ​​are the same, but the key length is the same number of characters. The functionality produces 100% value. Keywords: Cryptography, Artificial Neural Networks (ANN), Tree Parity Machine (TPM), Vigenere Cipher

Bukti digital sangat penting dalam pembuktian kasus kejahatan komputer yang melibatkan perangkat penyimpanan. Salah satu media penyimpanan terkini saat ini adalah SSD NVMe, secara default sistem operasi Windows 10 terpasang TRIM dengan mode enable, fungsi TRIM mengoptimalkan kinerja kecepatan SSD NVMe dengan cara menghapus otomatis data lama pada sebuah sektor sebelum ditempatkan data baru sehingga menjadi tantangan investigator untuk mengembalikan bukti digital. Tujuan penelitian melakukan analisis bukti digital yang terhapus dengan metode penghapusan permanen dengan cara shift delete dan delete, delete recycle bin menggunakan tools forensics yang berbeda untuk mengembalikan bukti digital pada SSD NVMe TRIM enable. Metode yang digunakan static forensics sedangkan tools yang digunakan FTK Imager, Autopsy dan Recuva. Hasil analisis TRIM enable metode penghapusan shift delete tidak ditemukan bukti digital yang sesuai nilai hash dengan bukti digital asli. Sedangkan metode penghapusan delete, delete recycle bin bukti digital dapat dikembalikan dengan prosentase keberhasilan menggunakan tool Autopsy sebesar 90% dan 10% nilai hash bukti digital tidak valid, sedangkan tool Recuva 80% bukti digital berhasil dikembalikan dan 20% tidak berhasil dikembalikan, dapat disimpulkan hasil recovery penghapusan delete, delete recycle bin pada SSD NVME TRIM enable dapat dijadikan bukti digital yang sah menurut hukum. Kata-kata kunci: Forensika digital, Restorasi, Hapus Permanen, NVMe, NIST

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.

Identification of object boundaries in a digital image is developing rapidly in line with advances in computer technology for image processing. Edge detection becomes important because humans in recognizing the object of an image will pay attention to the edges contained in the image. Edge detection of an image is done because the edge of the object in the image contains very important information, the information obtained can be either size or shape. The edge detection method used in this study is Sobel operator, Prewitt operator, Laplace operator, Laplacian of Gaussian (LoG) operator and Kirsch operator which are compared and analyzed in the five methods. The results of the comparison show that the clear margins are the Sobel, Prewitt and Kirsch operators, with PSNR calculations that produce values ​​above 30 dB. Laplace and LoG operators only have an average PSNR value below 30 dB. Other quality comparisons use the histogram value and the contrast value with the highest value results in the Laplace and LoG operators with an average histogram value of 110 and a contrast value of 24. The lowest histogram and contrast value are owned by the Sobel and Prewitt operators.

Cryptography is one of the most popular methods in data security by making data very difficult to read or even unreadable. One of the well-known techniques or algorithms in cryptography is Vigenere Cipher. This classic algorithm is classified as a polyalphabetic substitution cipher-based algorithm. Therefore, this algorithm tends to only handle data in text form. By this research, a console-based application has been developed which is made from PHP programming language to be able to encrypt and decrypt digital image media using Vigenere Cipher. The encryption process is done by first converting a digital image into a base64 encoding format so that the encryption process can be carried out using the tabula recta containing the radix-64 letter arrangement used for base64 encoding. Conversely, the decryption process is carried out by restoring the encrypted file using radix-64 letters, so we get the image file in the base64 encoding format. Then, the image with the base64 encoding format is decoded into the original file. The encryption process took less than 0,2 seconds and 0.19 seconds for the decryption process and 33.34% for average file size addition on the encrypted file from the original file size. Testing on ten different images with different sizes and dimensions showed a 100% success rate which means this research was successfully carried out.