Claim Missing Document
Check
Articles

Found 6 Documents
Search

A Implementasi Model Digital Forensik Procces Untuk Sosial Media Investigation Dengan Tools Hunchly Al Jum'ah, Muhammad Na'im; Wijaya, Hamid; Ismail, Rima Ruktiari
Cyber Security dan Forensik Digital Vol. 6 No. 2 (2023): Edisi Bulan November tahun 2023
Publisher : Fakultas Sains dan Teknologi UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/csecurity.2023.6.2.4265

Abstract

Perkembangan teknologi yang semakin pesat dapat menjadi dampak posistif dan dapat negatif. Dampak positifnya adalah proses penyebaran informasi yang semakin cepat, namun dampak negatifnya adalah banyaknya informasi hoax dan hate space yang terjadi di media sosial akibat tidak adanya filter dan pengecekan keabsahan informasi. Hal ini juga mengakibatkan banyaknya tindak kejahatan yang terjadi di media sosial. Salah satu pemecahan masalah dengan banyaknya kasus yang terjadi akibat penyalahgunaan media sosial adalah dengan melakukan proses invesitgasi forensic pada social media. Proses investigasi forensik ini dilakukan dengan metode live investigation menggunakan metode digital forensik proses yang terdiri dari proses Collection, Examination, Analysis dan Reporting. Proses pengumpulan barang bukti dengan menggunakan tools hunchly sehingga dapat dilakukan proses investigasi secara langsung. Hasil dari penelitian ini adalah dengan memanfaatkan metode digital forensik proses dan penggunaan tools hunchly untuk melakukan teknik live investigation untuk melakukan pengumpulan bukti digital dari akun-akun media sosial yang melakukan tindak kejahatan di media sosial sehingga dapat di proses sesuai dengan peraturan hukum yang telah berlaku Kata kunci: Bukti Digital, Media Sosial, Digital Forensik, Hunchly ------------------------------------------------------------------- The increasingly rapid development of technology can have both positive and negatif impacts. The positive impact is that the process of disseminating information is getting faster, but the negatif impact is the large amount of hoax information and hate space that occurs on social media due to the absence of filters and checking the validity of the information. This also results in many crimes occurring on social media. One solution to the problem with the many cases that occur due to misuse of social media is to carry out a forensic investigation process on social media. This forensic investigation process is carried out using the live investigation method using a digital forensic process method consisting of Collection, Examination, Analysis and Reporting processes. The process of collecting evidence uses powerful tools so that the investigation process can be carried out directly. The results of this research are by utilizing digital forensic process methods and using hunchly tools to carry out live investigation techniques to collect digital evidence from social media accounts that commit crimes on social media so that it can be processed in accordance with applicable legal regulations. Keywords: Sosial Media, Digital Forensics, Hunchly
Expert System for Determining Diseases and Pests in Seaweed Using Forward Chaining (Case Study : Watorumbe Village, Mawasangka Tengah) Asriani, Ika; Muchtar, Mutmainnah; Ismail, Rima Ruktiari; Paliling, Alders; Sya'ban, Kharis; Karim, Rahmat
Media of Computer Science Vol. 1 No. 1 (2024): June 2024
Publisher : CV. Digital Innovation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69616/mcs.v1i1.175

Abstract

Seaweed is a marine organism that plays a crucial role in both ecosystem and economy. However, it often faces attacks from diseases and pests that can jeopardize the productivity and sustainability of the seaweed industry. Hence, the development of an expert system to diagnose seaweed diseases and pests becomes imperative. This research aims to develop an Expert System for Determining Diseases and Pests in Seaweed using the Forward Chaining method, with a case study conducted in the Watorumbe Village, Mawasangka Tengah Sub-district, Southeast Sulawesi. The Forward Chaining method is employed to identify symptoms appearing in seaweed and determine potential diseases or pests. Testing is carried out with 30 data samples compared against expert diagnoses, resulting in an accuracy rate of 90%. Therefore, this system has the potential to assist seaweed farmers in diagnosing diseases and pests more quickly and accurately, thereby enhancing the productivity and sustainability of seaweed cultivation efforts.
Application of Tsukamoto Fuzzy Logic in Expert System Application for Diagnosing Web-Based Skin Diseases KN, Nurwijayanti; Rasna, Rasna; Ismail, Rima Ruktiari; Sugiharto, Agus; Nugroho, Fifto
International Journal of Engineering, Science and Information Technology Vol 5, No 2 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i2.827

Abstract

Skin health is essential for everyone. In addition to supporting someone who can reduce self-confidence, skin diseases can also interfere with a person's concentration in activities. An expert system is a system designed to be able to imitate the expertise of an expert in answering questions and solving a problem. The expert system will solve a problem obtained from a dialogue with the user. With the help of an expert system, someone who is not an expert can answer questions, solve problems, and make decisions that an expert usually makes. This needs to be anticipated and handled seriously, especially for types of skin diseases, some of which can be fatal, and some can even be classified as cancer. Experts are needed to diagnose each disease in this case, but consultation with experts requires costly funds. For this reason, this system is designed to help people diagnose skin diseases online, making it easier for sufferers to diagnose the diseases they suffer from by themselves. The method used is the fuzzy Tsukamoto method. Analysis of the introduction of the disease is carried out by identifying various symptoms of the disease. The types of diseases diagnosed include tinea versicolor [P001], scabies [P002], ringworm [P003], dandruff [P004], vitiligo [P005], pityriasis alba [P006], hives [P007], erythema multiforme [P008], acne [P009], keloids [P010], melanoma [P011], eczema [P012], boils [P013], measles [P014], psoriasis [P015], impetigo [P016], and herpes [P017]. Skin disease sufferers can diagnose their disease without consulting with a specialist directly. This system can be used as a substitute for a specialist in producing a diagnosis in the form of the name of the disease suffered by the system user (user). This system provides a solution for users regarding more economical disease diagnosis.
Implementation of Green IT-Based Cloud Computing for Energy Efficiency in Technology Companies Judijanto, Loso; Wijaya, Hamid; Ismail, Rima Ruktiari; Vandika, Arnes Yuli
West Science Information System and Technology Vol. 3 No. 01 (2025): West Science Information System and Technology
Publisher : Westscience Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/wsist.v3i01.1846

Abstract

The growing demand for energy-efficient and sustainable solutions has positioned Green IT-based cloud computing as a pivotal strategy for technology companies aiming to balance operational efficiency with environmental stewardship. This study conducts a systematic literature review of 15 Scopus-indexed documents to explore the benefits, challenges, and strategies associated with the adoption of Green IT-based cloud computing. The findings reveal that these practices significantly enhance energy efficiency, reduce operational costs, and minimize carbon footprints. However, challenges such as high implementation costs, technological complexity, and intermittent renewable energy sources impede widespread adoption. Strategies including the use of AI and machine learning, collaborations with renewable energy providers, and the establishment of standardized policies are identified as effective solutions. This study contributes to the growing discourse on sustainable IT practices and provides a roadmap for technology companies aiming to integrate Green IT principles into their cloud computing operations.
FUEL-INJECTED MOTORCYCLE PERFORMANCE OPTIMIZATION UTILISING PERTALITE-ETHANOL BLENDS AND DEEP NEURAL NETWORK-BASED ECU FOR EFFICIENCY IMPROVEMENT AND EMISSION REDUCTION Yunus, La Ode Ichlas Syahrullah; Putri, Farika Tono; Ismail, Rima Ruktiari
Jurnal Rekayasa Mesin Vol. 16 No. 2 (2025)
Publisher : Jurusan Teknik Mesin, Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jrm.v16i2.1946

Abstract

This study aims to optimize the performance of fuel-injected motorcycles through the application of a Deep Neural Network (DNN) in the Electronic Control Unit (ECU) and the use of ethanol-pertalite fuel blends. The ethanol blends used in the study were 0%, 5%, 10%, 15%, and 20%. Fuel consumption tests were conducted using the standard ECE/324 driving cycle, and emission tests were performed according to Euro 4 standards. Tests were conducted on a real track to evaluate fuel consumption performance and exhaust gas emissions. The results indicate that the 15% ethanol blend (E15) provided optimal engine efficiency, while the 20% ethanol blend (E20) resulted in the largest reduction in carbon monoxide (CO) and hydrocarbon (HC) emissions. Furthermore, the DNN model with 50 neurons and a Sigmoid activation function demonstrated the best balance between accuracy (R=0.9868) and generalization (MSE=0.3843) in optimizing ignition timing and injection timing. In conclusion, the ethanol blends and the application of DNN in the ECU have proven effective in enhancing fuel efficiency and reducing exhaust emissions, supporting the development of more sustainable transportation technologies.
Sistem Pakar Untuk Mendiagnosa Gangguan Somatisasi Menggunakan Metode K-Nearest Neighbors (KNN) Ismail, Rima Ruktiari; Wijaya, Hamid; Siregar, Juarni; Nugroho, Nurhasan
Jurnal Ilmiah FIFO Vol 16, No 2 (2024)
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/fifo.2024.v16i2.010

Abstract

Penelitian ini bertujuan untuk mengembangkan sistem pakar yang mampu mendiagnosa gangguan somatisasi menggunakan metode K-Nearest Neighbors (KNN). Gangguan somatisasi merupakan kondisi psikologis yang sulit didiagnosis karena gejalanya yang bersifat fisik namun berasal dari masalah psikologis. Ketidakjelasan gejala ini sering kali mengarah pada pemeriksaan medis yang tidak diperlukan dan mahal, menambah beban bagi pasien dan sistem kesehatan. KNN dipilih karena kemampuannya untuk melakukan klasifikasi dengan membandingkan data uji dengan data pelatihan berdasarkan kedekatan menggunakan Euclidean Distance. Euclidean Distance digunakan untuk mengukur jarak terpendek antara dua titik dalam ruang fitur, yang dihitung dengan mengakar kuadrat dari jumlah perbedaan kuadrat antara nilai-nilai fitur dari dua titik tersebut. Hasil penelitian menunjukkan bahwa sistem pakar yang dikembangkan memiliki akurasi yang tinggi, yaitu mencapai 92,5%, yang mengindikasikan bahwa metode KNN dengan Euclidean Distance efektif dalam mendiagnosa gangguan somatisasi. Faktor-faktor seperti pemilihan nilai K yang optimal dan normalisasi data berperan penting dalam keberhasilan sistem ini. Kontribusi signifikan dari penelitian ini adalah pembuktian bahwa KNN dapat diimplementasikan secara efektif dalam sistem pakar untuk mendukung tenaga medis dalam melakukan diagnosis gangguan somatisasi dengan akurasi yang tinggi dan keandalan yang baik.