Article Per Year (5 Year)
p-Index From 2021 - 2026
9.778
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi Jurnal Buana Informatika Jurnal Informatika Jurnal Teknologi Informasi dan Ilmu Komputer JUITA : Jurnal Informatika Jurnas Nasional Teknologi dan Sistem Informasi POSITIF Edu Komputika Journal Sistemasi: Jurnal Sistem Informasi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Computatio : Journal of Computer Science and Information Systems RABIT: Jurnal Teknologi dan Sistem Informasi Univrab Jurnal Khatulistiwa Informatika JIKO (Jurnal Informatika dan Komputer) JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Pilar Nusa Mandiri JTERA (Jurnal Teknologi Rekayasa) Jurnal Sains dan Informatika INOVTEK Polbeng - Seri Informatika Matrix : Jurnal Manajemen Teknologi dan Informatika SINTECH (Science and Information Technology) Journal Jurnal Informatika Universitas Pamulang Jurnal Teknoinfo Jurnal Sisfokom (Sistem Informasi dan Komputer) KACANEGARA Jurnal Pengabdian pada Masyarakat MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Indonesian Journal of Applied Informatics KOMPUTIKA - Jurnal Sistem Komputer KOMPUTA : Jurnal Ilmiah Komputer dan Informatika Jurnal Riset Informatika JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal Teknologi Terapan Jurnal Teknologi Terpadu EDUMATIC: Jurnal Pendidikan Informatika EVOLUSI : Jurnal Sains dan Manajemen Building of Informatics, Technology and Science JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) JISKa (Jurnal Informatika Sunan Kalijaga) Jurnal Teknologi Informasi dan Multimedia Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) JUSTINDO (Jurnal Sistem dan Teknologi Informasi Indonesia) JISA (Jurnal Informatika dan Sains) International Journal of Engineering, Technology and Natural Sciences (IJETS) JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Jurnal Sistem Komputer dan Informatika (JSON) TIN: TERAPAN INFORMATIKA NUSANTARA Idealis : Indonesia Journal Information System Jurnal Teknik Informatika (JUTIF) Jurnal Digit : Digital of Information Technology Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Science in Information Technology Letters Journal of Soft Computing Exploration Jurnal Indonesia : Manajemen Informatika dan Komunikasi Bulletin of Computer Science Research KLIK: Kajian Ilmiah Informatika dan Komputer International Journal Software Engineering and Computer Science (IJSECS) Jurnal Sains dan Teknologi International Journal Science and Technology (IJST) Malcom: Indonesian Journal of Machine Learning and Computer Science Journal of Scientific Research, Education, and Technology Journal of Data Science Theory and Application NERO (Networking Engineering Research Operation) SmartComp Jurnal Indonesia : Manajemen Informatika dan Komunikasi Emitor: Jurnal Teknik Elektro IJISCS (International Journal of Information System and Computer Science)
Donny Avianto
Universitas Teknologi Yogyakarta
Aerospace Engineering Arts Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Veterinary Other

Published : 83 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 83 Documents
Search

 5   6   7   8   9 
Fuzzy Mamdani for Equality of Employee Salary Fakharudin, Panji Rangga Adzan Fajar; Avianto, Donny
Sistemasi: Jurnal Sistem Informasi Vol 13, No 1 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i1.3621

Abstract

Every job in a coffee shop has a salary. Salary is a form of recognition or imbalance for the results achieved. Salary is often also called wages, which is an imbalance in the services provided regularly to employees. Fuzzy has several methods, one of which is Fuzzy Mamdani which is used to make inferences or take the best decision in a problem that has subtle values. In 1975, Ebrahim Mamdani proposed the Fuzzy Mamdani method. Fuzzy Mamdani is a method that uses linguistic rules and has a fuzzy algorithm so that it can be explained mathematically and is easy to understand. The input values for the criteria for length of work are 8, experience 8, and dependents 4. The output is based on Fuzzy Mamdani's calculations, the employee gets a salary of IDR 2.21 million. The results of this study research that the wage income offered by Warkop IN`DA to its employees is good and not far from the minimum wage of the coffee shop. This third variable has a big influence on the final calculation results. The system created is quite good because the MAE result is 0.567 and the MAPE result is 36.720%.
Implementasi Speech Recognition Menggunakan Long Short-Term Memory untuk Software Presentasi Adhitama, Satriya; Avianto, Donny
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.6950

Abstract

Presentation is one of the methods for delivering thoughts, ideas, and concepts to an audience verbally. Presentation activities can be supported by presentation software that can be used to organize the sequence of material to be presented with visually appealing visuals. Operating presentation software requires technical assistance such as a remote, mouse, keyboard, and even a personal assistant, which can be distracting to the presenter as it limits their freedom in delivering the material. This distraction can be addressed through the implementation of speech recognition as a command to operate presentation software, making it easier for the presenter. A speech recognition system is developed using Long Short-Term Memory (LSTM), which can handle the issues of long-term dependency and vanishing gradient associated with Recurrent Neural Networks (RNN). There are 10 command words used to operate the presentation software. LSTM demonstrates superior performance when compared to alternative techniques like DNN, CNN, and SimpleRNN, achieving a training accuracy of 96.5%, a validation accuracy of 94.8%, and a testing accuracy of 94%. The LSTM method can be effectively used for sequential data to recognize real-time speech.
PENGENALAN CITRA RAMBU LALU LINTAS MENGGUNAKAN EKSTRAKSI FITUR MOMENWARNA DAN K-NEAREST NEIGHBOR Rizarta, Rusma Eko Fiddy; Avianto, Donny
Computatio : Journal of Computer Science and Information Systems Vol. 3 No. 1 (2019): COMPUTATIO : JOURNAL OF COMPUTER SCIENCE AND INFORMATION SYSTEMS
Publisher : Faculty of Information Technology, Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/computatio.v3i1.4272

Abstract

The traffic signs are signs with specific shape and symbols, letters, numbers, or words which have the aim to warn or inform the road users. However, there are many road users who are not aware of the meaning of each signs. In this research, we develop an application which can classify a road sign image into three classes, priority four-way crossroad, do-not-park sign, and follow-this-road sign. Initially, the system will do preprocessing step such as grays calling, histogram equalization, and input image segmentation. Next, the feature extraction step will be conducted, namely the spatial moment feature extraction, normalized centering, and color statistics. Lastly, the feature representation from both extraction methods will be used to classify the image using K-nearest neighbor. Experiment result shows that the combination of both feature extraction methods gives promising result. From 21 training images and 15 testing images, the system can recognize the traffic signs with 100% accuracy with K=3, 86.6% with K=5, and 86.6% with K=7. Rambu lalu lintas merupakan salah satu alat perlengkapan jalan dalam bentuk tertentu yang memuat lambang, huruf, angka, kalimat yang digunakan untuk memberikan perintah, larangan, peringatan dan petunjuk bagi pengguna jalan agar tertib berlalu lintas. Namun, banyak di antara pengguna jalan yang belum mengetahui arti dari setiap rambu lalu lintas yang terpasang.Pada penelitian ini, dibuatlah suatu aplikasi yang mampu melakukan klasifikasi citra rambu ke dalam 3 kelas yaitu: peringatan simpang empat prioritas, larangan parkir dan perintah memasuki jalur atau lajur yang ditunjuk. Mula-mula sistem akan melakukan prapemrosesan seperti seperti: grayscalling, histogram equalization, dan segmentasi pada citra input. Selanjutnya, tahap ekstraksi ciri akan dilakukan pada citra hasil pra-pemrosesan. Adapun metode ekstraksi ciri yang digunakan pada penelitian kali ini adalah ekstraksi fitur momen spasial dan pusat ternormalisai (momen) dan ekstraksi fitur statistika warna (warna). Terakhir, nilai fitur yang dihasilkan oleh kedua metode tersebut akan diklasifikasi mengguakan K-Nearest Neighbor. Hasil uji coba menunjukkan bahwa metode ekstraksi fitur gabungan momen-warna memberikan hasil yang menjanjikan. Dari 21 citra latih dan 15 citra uji yang digunakan, sistem mampu mengenali rambu dengan tepat 100% pada K=3 , 86,6% pada K=5, dan 86,6% pada K=7. 
Analisis Komparasi Algoritma K-Means Dan K-Medoids Dalam Segmentasi Data Untuk Strategi Promosi Mahasiswa Baru Di Universitas X Syafrudin, Teguh; Teguh Syafrudin; Arief Hermawan; Donny Avianto; Indra Maulana
Komputika : Jurnal Sistem Komputer Vol. 14 No. 2 (2025): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v14i2.16698

Abstract

Persaingan dalam merekrut mahasiswa baru semakin ketat, sehingga perguruan tinggi memerlukan strategi promosi yang efektif dan tepat sasaran. Salah satu cara untuk meningkatkan efektivitas promosi adalah dengan melakukan segmentasi calon mahasiswa berdasarkan data penerimaan. Penelitian ini menawarkan solusi dengan membandingkan performa algoritma K-Means dan K-Medoids dalam segmentasi data Penerimaan Mahasiswa Baru (PMB) Universitas X tahun 2024. Metode yang digunakan meliputi tahapan pengumpulan data, preprocessing (pembersihan, normalisasi, dan transformasi), implementasi algoritma K-Means dan K-Medoids, serta evaluasi kualitas klaster menggunakan Davies-Bouldin Index (DBI). Hasil penelitian menunjukkan bahwa konfigurasi tiga klaster (K=3) memberikan nilai DBI terendah, dengan K-Medoids mencapai 1,038, lebih baik dibandingkan K-Means sebesar 1,059. Klaster dominan menunjukkan bahwa lulusan SMK mendominasi sebesar 40,45% dan cenderung memilih program studi Pendidikan TIK. Kontribusi penelitian ini adalah memberikan panduan bagi institusi pendidikan dalam memilih algoritma klasterisasi yang paling sesuai untuk mendukung strategi promosi yang lebih akurat, efisien, dan terarah.
ANALISIS KINERJA SUPPORT VECTOR MACHINE DAN NAÏVE BAYES CLASSIFIER DALAM KLASIFIKASI SENTIMEN DAN EMOSI PADA UMPAN BALIK MAHASISWA TERHADAP KINERJA DOSEN Syafrudin, Teguh; Hermawan, Arief; Avianto, Donny
Jurnal Digit : Digital of Information Technology Vol 15, No 2 (2025)
Publisher : Universitas Catur Insan Cendekia (CIC) Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51920/jd.v15i2.442

Abstract

Evaluasi kinerja dosen melalui umpan balik mahasiswa merupakan komponen penting dalam meningkatkan mutu pembelajaran di perguruan tinggi. Penelitian ini bertujuan untuk mengembangkan model klasifikasi sentimen dan emosi menggunakan pendekatan hybrid machine learning dengan mengombinasikan algoritma Naïve Bayes dan Support Vector Machine (SVM). Dataset berasal dari umpan balik mahasiswa yang telah dianotasi secara manual ke dalam tiga kategori sentimen positif, netral, negatif dan delapan kategori emosi. Proses preprocessing dilakukan melalui tokenisasi, stemming, dan transformasi data ke dalam bentuk TF-IDF. Hasil klasifikasi menunjukkan bahwa SVM memiliki performa terbaik untuk klasifikasi sentimen dengan akurasi mencapai 90%, mengungguli Naïve Bayes yang hanya memperoleh akurasi 80%. Sebaliknya, performa klasifikasi emosi jauh lebih rendah, dengan akurasi maksimum 35% pada model SVM dan 20% pada Naïve Bayes. Beberapa emosi seperti “marah”, “termotivasi”, dan “senang” tidak dapat dikenali oleh model karena ketidakseimbangan distribusi data dan konteks emosi yang sulit ditangkap dari teks pendek. Temuan ini menunjukkan bahwa pendekatan hybrid efektif untuk klasifikasi sentimen dalam kondisi data terbatas, namun klasifikasi emosi memerlukan pendekatan lanjutan seperti reduksi label atau penggunaan model berbasis konteks untuk mencapai hasil yang lebih baik.Kata kunci: Kinerja Dosen, Naïve Bayes Classifier (NBC), Support Vector Machine (SVM), Umpan Balik Mahasiswa.
Implementasi Sistem Klasifikasi Batik Menggunakan MobileNet dengan Integrasi Chatbot Retrieval Augmented Generation Purnomo Pratama, Rizki; Avianto, Donny
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.863

Abstract

As an Indonesian cultural heritage recognized by UNESCO, batik features various motifs laden with philosophical values, yet public knowledge about batik patterns and their significance remains limited. This study presents a mobile-based batik classification system integrating MobileNetV2 architecture with a Retrieval-Augmented Generation (RAG) chatbot to provide interactive learning experiences, enabling users to identify batik patterns through image recognition while obtaining detailed information via conversational AI.This study adopts MobileNetV2 considering its efficiency on mobile devices. This model achieves an optimal balance between accuracy and computational performance. Model was trained on a balanced dataset of 5,000 images covering five pattern classes (Parang, Truntum, Kawung, Mega mendung, and Merak), achieving training accuracy of 98.97% and testing accuracy of 96.8%. The RAG-based chatbot, orchestrated using LangChain and Qdrant, enhances user interaction by retrieving relevant information from a curated knowledge base, ensuring contextual factual responses about batik's history, philosophy, and cultural significance. React Native was adopted as the development framework to ensure cross-platform operability. This implementation contributes to cultural heritage preservation by making batik knowledge more accessible through modern technology, combining computer vision and natural language processing in a unified platform.
Implementasi Convolutional Neural Network Untuk Pengenalan Tulisan Tangan Akasara Sunda Ngalangéna Azizah, Rahma Nur; Avianto, Donny
TIN: Terapan Informatika Nusantara Vol 6 No 7 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v6i7.8703

Abstract

Efforts to preserve the Sundanese script as a cultural heritage face challenges in the digital era, one of which is the limited resources for pattern recognition. This research aims to develop an effective custom Convolutional Neural Network (CNN) model for the classification of handwritten Sundanese script. Facing the constraint of no available public dataset, this study utilizes a primary dataset (Swaraksara Dataset) created by the author, consisting of 6,500 handwritten images evenly distributed across 13 classes (combinations of the "Na" script with rarangkén). The methodology applied includes a comprehensive data preprocessing stage, covering grayscale conversion, resizing to 200x200 pixels, normalization, and data augmentation techniques to prevent overfitting. The custom CNN architecture was designed with five convolutional layers (filters 32 to 512) and the Adam optimizer. The experimental results show that the optimal configuration was achieved with a learning rate of 0.001 and 50 training epochs, resulting in very high model performance. In the evaluation using test data, the model achieved an accuracy of 99.54% with a loss value of 0.0175. The optimal performance of this model is driven by the quality of the primary dataset supported by comprehensive image preprocessing stages, thus ensuring clean, uniform, and significantly noise-free data input. Analysis of the confusion matrix and learning curves also confirmed the model's excellent generalization ability with no indications of overfitting. This model has been successfully implemented in the "Swaraksara" web application as a Sundanese script recognition system.
Speech-Based Virtual Assistant for Mental Health Support Through Natural Interaction Kurniawan, Dimas Rizqi; Avianto, Donny
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 6 (2025): December 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i6.6585

Abstract

Mental health is a significant global concern. Indonesia has reported high rates of depression and anxiety, compounded by limited emotional outlets. Although AI virtual assistants are prevalent in e-commerce and education, their application in mental health remains underexplored. Existing solutions are predominantly text-based and transactional, which restricts empathetic and natural interactions. This study develops a voice-based assistant by integrating Automatic Speech Recognition (ASR), a generative AI for empathetic responses, and a Text-to-Speech (TTS) module fine-tuned on an Indonesian dataset to adapt accent and prosody. The system underwent both technical evaluation and human testing to assess its feasibility and user experience. The results showed that the TTS model converged effectively with low loss. Human evaluation indicated 'good' interaction (MS = 3.91, SD = 0.02), 'good' AI responses (MS = 3.83, SD = 0.26), and 'fair' TTS naturalness (MOS = 3.27, SD = 0.05). Most participants found the assistant's responses meaningful, pleasant, and helpful in managing low to moderate anxiety. These results suggest that a voice-based assistant has the potential to support mental health in Indonesia. Future work should enhance speech naturalness and utilize a larger participant pool for evaluation.
Global Horizontal Irradiance Prediction using the Algorithm of Moving Average and Exponential Smoothing Syahab, Alfin Syarifuddin; Hermawan, Arief; Avianto, Donny
JISA(Jurnal Informatika dan Sains) Vol 6, No 1 (2023): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v6i1.1649

Abstract

To reduce the discrepancy between the results of the expected data and the actual data, prediction is a procedure that is calculated systematically based on owned historical and present information. For the creation of solar energy projects and for decision-making in other connected domains, solar radiation intensity prediction is essential. This study aims to create a predictive model on monthly global horizontal irradiance data. The method used is the Simple Moving Average algorithm, Exponentially Weighted Moving Average and Single Exponential Smoothing. The stages carried out in this study include data collection, data preprocessing, testing of predictive models, interpretation of data visualization, and performance evaluation. The results of calculating the error value and correlation produce an evaluation of the performance of the prediction model. The SES method, which obtained an MAE value of 7.13, a MAPE of 0.02%, an MSE of 88.07, an RMSE of 9.38, and an R2 of 0.94, was determined to be the best prediction model by the calculation of the prediction model performance evaluation. A MAE value of 9.45, a MAPE of 0.02%, an MSE of 150.16, an RMSE of 12.25, and an R2 of 0.91 were obtained by the EWMA method, which is also the method that produced the second-best result. A MAE value of 14.38, a MAPE of 0.04%, an MSE of 367.59, an RMSE of 19.17, and an R2 of 0.77 were obtained by the SMA method, which is the third-best result.
Learning Accuracy with Particle Swarm Optimization for Music Genre Classification Using Recurrent Neural Networks Muhammad Rizki; Arief Hermawan; Donny Avianto
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3037

Abstract

Deep learning has revolutionized many fields, but its success often depends on optimal selection hyperparameters, this research aims to compare two sets of learning rates, namely the learning set rates from previous research and rates optimized for Particle Swarm Optimization. Particle Swarm Optimization is learned by mimicking the collective foraging behavior of a swarm of particles, and repeatedly adjusting to improve performance. The results show that the level of Particle Swarm Optimization is better previous level, achieving the highest accuracy of 0.955 compared to the previous best accuracy level of 0.933. In particular, specific levels generated by Particle Swarm Optimization, for example, 0.00163064, achieving competitive accuracy of 0.942-0.945 with shorter computing time compared to the previous rate. These findings underscore the importance of choosing the right learning rate for optimizing the accuracy of Recurrent Neural Networks and demonstrating the potential of Particle Swarm Optimization to exceed existing research benchmarks. Future work will explore comparative analysis different optimization algorithms to obtain the learning rate and assess their computational efficiency. These further investigations promise to improve the performance optimization of Recurrent Neural Networks goes beyond the limitations of previous research.
Co-Authors Adhitama, Satriya Adicahya, Bina Sukma Adityo Permana Wibowo Alwani, Adie G. Amalia Rizki Wulandari Apriansyah, Ferryma Arba Ardiansyah, Diky Aribowo Aribowo Arief Hermawan Arieska Restu Harpian Dwika Arif Hermawan, Arif Ashari, Nadia Aziz Perdana Baiq Nurul Azmi Bimantoro, Nazar Iqbal Bowo Hirwono Budiyanto, Irfan Dewi, Amelia Citra Dian Wijayanti Dimas Dwi Kurniawan Dwi Ratnawati, Dwi Edi Priyanto Enggar Novianto Enggar Novianto Erfin Nur Rohma Khakim Fadhila, Arifa Farras Fadilah, Faiz Fahri Putra Herlambang Fakharudin, Panji Rangga Adzan Fajar Faqih, Allan Bil Febiansyah Annaufal Ahnaf Fauzi Ferdinandus Edwin Penalun Gumilang, Muhammad Satrio Gunawan, Asrul Hanif, Rifqi Fadhlurrahman Hardiyantari, Oktavia Herdy Andriksen Iin Rohmatika Aulia Ilmy Eka Handayani Imantoko Imantoko Indra Maulana Iqbal, Muhammad Izza Jagad Raya Ramadhan Kurniawan, Dimas Rizqi Kusban, Muhammad Kusumastuti, Asriana Dyah Maulana, Adha Muh Arifandi Muhammad Irsyad Indra Fata Muhammad Rizki Muhammad Rizki Nasmah Nur Amiroh Novaldy, Olwin Kirab Nur Widiastuti Nurazila, Siti Octavianus, Yonathan Perdana, Aziz Purba, Yurjaa Ghoniyyan Purnomo Pratama, Rizki Putra, Kristianto Pratama Dessan Rahma Nur Azizah Reski Noviana Rian Oktafiani Rian Oktafiani Rianto Rianto Rizarta, Rusma Eko Fiddy Rizky Samudra Falasyfa Roy Fasti Rubangi Rubangi Rudi, Rudiono Rusma Eko Fiddy Rizarta Saputra, Candra Heru Setiawan, Muhhamad Ajun Siti Rokhanah Soraya Fatmawati Sri Wulandari SRI WULANDARI Sutarman Sutarman Syafrudin, Teguh Syahab, Alfin Syarifuddin Teguh Syafrudin Tri Untoro, Iwan Hartadi Tri Widodo Vivianti Wahid, Ach. Nur Aqil Widyastuti, Evi