Surya Sumpeno

Surya Sumpeno

Auto-generated profile, based on publicly available information

Surya Sumpeno

Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 September 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
WAWiwik Anggraeni
Wiwik Anggraeni
EYEko Mulyanto Yuniarno
Eko Mulyanto Yuniarno
RRReza Fuad Rachmadi
Reza Fuad Rachmadi
SSSurya Sumpeno
Surya Sumpeno
PPPujiadi Pujiadi
Pujiadi Pujiadi
MPMauridhi Hery Purnomo
Mauridhi Hery Purnomo

1 August 2017
Verified
Conference Paper
Closed access
MLM Lailiyah
M Lailiyah
SSS Sumpeno
S Sumpeno
IPI. K. E Purnama
I. K. E Purnama
Public complaints were one of the kinds of public participation and awareness to public service implementation. Information from public complaints can be used by the government to improve public satisfaction. In addition, the government can obtain public sentiment from public complaints either on media social or the official government site. Many kinds of research on sentiment analysis have been done, either used statistical method approach, semantic method approach or both. Statistical method approach was widely used. While semantic method approach being the hot topic recently. On semantic method approach, lexical resource was an important component to classily sentiment on text. Namely Sentiwordnet and Indonesian sentiment lexicon. Currently, Indonesian lexical resources for sentiment analysis has grown. But the lexicon doesn't have polarity score that can be measure emotion on text like Sentiwordnet. Sentiwordnet has been widely used on research in English. In this research, we apply Sentiwordnet to classify sentiment on Indonesian public complaints with accuracy 47% either on media Twitter and 56.85% on the official government website's data. Furthermore, we compare it with Indonesian sentiment lexical and get the accuracy 65.4% on media Twitter and 81.4% on the of Ticial government website.

14 January 2020 in Scientometrics
Verified
Journal Article
Closed access
PDF file
DPDiana Purwitasari
Diana Purwitasari
CFChastine Fatichah
Chastine Fatichah
SSSurya Sumpeno
Surya Sumpeno
CSChristian Steglich
Christian Steglich
MPMauridhi Hery Purnomo
Mauridhi Hery Purnomo

1 January 2017 in Procedia Computer Science
Verified
Journal Article
Open access
MPMauridhi Hery Purnomo
Mauridhi Hery Purnomo
SSSurya Sumpeno
Surya Sumpeno
ESEsther Irawati Setiawan
Esther Irawati Setiawan
DPDiana Purwitasari
Diana Purwitasari
Biomedical engineering research trend can be healthcare models with unobtrusive smart systems for monitoring vital signs and physical activity. Detecting infant facial cry because of inability to communicate pain, recognizing facial emotion to understand dysfunction mechanisms through micro expression or transform captured human expression with motion device into three-dimensional objects are some of the applied systems. Nowadays, collaborated with biomedical research, mining and analyzing social network can improve public and private health care sectors as well such as research health news shared on social media about pharmaceutical drugs, pandemics, or viral outbreaks. Due to the vast amount of shared news, there is an urgency to select and filter information to prevent the spread of hoax or fake news. We explored in depth some steps to classify hoaxes written as news articles. This discussion also encourages on how technologies of social network analysis could be used to make new kinds improvement in health care sectors. Then close with a description of limitless future possibilities of biomedical engineering research in social media.

1 August 2018
Verified
Conference Paper
Closed access
ANAlfin Naharuddin
Alfin Naharuddin
AWAdhi Dharma Wibawa
Adhi Dharma Wibawa
SSSurya Sumpeno
Surya Sumpeno
Due to its light and multiplatform feature, plain text is widely used to transmit the information in news and social media online. However, it is vulnerable to attacks (e.g. unauthorized access or misuse of the information where the text is modified for particular purposes). To deal with the problem, secret text (ST) is embedded in overall plain texts appearing as a cover text (CT) so that any changes on CT can be detected. The present study proposes ST embedding method in CT by mapping ST binary digit onto binary digit of CT using ASCII characters-involving spaces, punctuation, and symbols. Prior to embedding process, the ST text was firstly encrypted with a One Time Pad (OTP) into ciphertext and each character was converted into binary number representing 7-bits long. Unlike the ST text, the CT text was immediately converted into 7 bits of binary number. The embedding process was conducted by mapping one bit of ST onto the first bit of CT character containing the same number of bit (e.g. mapping bit 1 of ST character onto the first bit 1 of CT character). Such a process was repeatedly carried out to ensure all bit of ST was completely embedded in CT. The system recorded each bit position as a stego key for any bit of ST had its position on bit of CT. The stego key served as a key to extract ST embedded in CT. The result of embedding process did not change the appearance of CT and therefore the method worked well with hidden information serving as text steganography or as watermark. In short, all CT characters can be used as a medium to hide ST where 1 character of ST required 7 characters of CT. In addition, the stego texts produced appeared identical to CT, as measured in similarity distance with Jaro-Winkler Distance of 1.

29 May 2020 in Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Verified
Journal Article
Open access
PDF file
NFNurul Zainal Fanani
Nurul Zainal Fanani
ASAdri Gabriel Sooai
Adri Gabriel Sooai
SSSurya Sumpeno
Surya Sumpeno
MPMauridhi Hery Purnomo
Mauridhi Hery Purnomo
Penilaian Kemampuan Motorik Halus (KMH) untuk anak pada awal usia sekolah sangat penting untuk mendapatkan informasi tentang kesiapan sekolah anak. Selama ini proses pengukuran KMH dilakukan dengan cara observasi pada anak, baik secara langsung maupun dari hasil sketsa atau hasil tulisan anak. Proses pengamatan ini sangat bergantung pada persepsi pengamat, sehingga dapat mengakibatkan kurangnya objektivitas dalam penilaian. Makalah ini bertujuan untuk menentukan KMH anak menggunakan aksara jawa (Hanacaraka). Makalah ini mengembangkan metode baru untuk menentukan KMH anak sekolah dasar dari proses menulis aksara jawa. Sistem melakukan perekaman data secara langsung pada saat anak menulis aksara jawa. Pengambilan data rekaman proses menulis melibatkan empat belas siswa kelas 1 dan kelas 2 dari tiga sekolah dasar di Kabupaten Jember. Proses perekaman data dari setiap siswa menghasilkan data raw yang cukup besar. Oleh karena itu, digunakan metode klasifikasi random forest karena metode ini dapat melakukan proses klasifikasi pada data dalam jumlah yang besar dengan menggabungkan beberapa pohon keputusan. Metode klasifikasi lain, termasuk naïve Bayes dan k-NN, juga diuji sebagai perbandingan. Hasil uji coba menunjukkan bahwa metode klasifikasi random forest merupakan metode terbaik dalam penelitian ini, yaitu dengan akurasi mencapai 98,7%.