Hetty Rohayani

Dr. Hetty Rohayani

orcid
Associate Profesor of Computer Science

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
1 January 2015 in Procedia Computer Science
Verified
Journal Article
Open access
HRHetty Rohayani
Hetty Rohayani
KUKurniabudi
Kurniabudi
SHSharipuddin
Sharipuddin
E-Readiness is recognizing as one the most critical aspect for achieving successfully implementation of E-learning programs in higher education. Understand the role of this factor could help university management to implement effective and efficient E-learning project. The Purpose of the study is to discuss the theory of E-learning Readiness Factors and investigate the readiness factors that have been found by previous researchers for measure e-readiness at higher education. This study applies literature review and meta-analysis as research methodology. Literature review conducts by review the relevant articles with topic “e-learning readiness”. The study found that skills and attitudes are the most significant factors influences E-learning readiness

1 January 2015 in Procedia Computer Science
Verified
Journal Article
Open access
BPBenni Purnama
Benni Purnama
HRHetty Rohayani
Hetty Rohayani
In a secret message, cryptography is more directed to the encrypted message while steganography is more directed at the hidden message. However, both methods have the same goal, namely the attempt to conceal the message. On the other side, it turns out the use of cryptography can often be solved / translated by another person or cryptanalyst. This is possible because usually a text message unreadable gives someone suspicion that the text message contains a certain meaning for the owner of the message. Thus, the cryptanalyst attempts to break the encrypted message. While the use of steganography owner of the information is difficult to determine the method or pattern to be formed in composing the message that will be hidden. In this paper, the authors modify the Caesar cipher method that produces ciphertext that can be read. With the ciphertext that can be read, then cryptanalysis not suspicious of the ciphertext. Caesar cipher modification is done by replacing the alphabet into two parts, the vocals were replaced with the alphabet vocal too, and the consonant alphabet was replaced with a consonantal alphabet. However, there are some alphabet consonants are not replaced, this is because the frequency of the alphabet is rarely used in an Indonesian text. From the test results obtained ciphertext that can be read. With the ciphertext that can be read, then the cryptanalyst not suspicious of the message so that the cryptanalyst does not attempt to solve the ciphertext

Verified
Journal Article
Open access
PDF file
DNDian Candra Rini Novitasari
Dian Candra Rini Novitasari
Fatmawati FatmawatiFatmawati Fatmawati
Fatmawati Fatmawati
RHRimuljo Hendradi
Rimuljo Hendradi
HRHetty Rohayani
Hetty Rohayani
RNRinda Nariswari
Rinda Nariswari
APArdhin Primadewi
Ardhin Primadewi
Diabetic retinopathy is the leading cause of blindness suffered by working-age adults. The increase in the population diagnosed with DR can be prevented by screening and early treatment of eye damage. This screening process can be conducted by utilizing deep learning techniques. In this study, the detection of DR severity was carried out using the hybrid CNN-DELM method (CDELM). The CNN architectures used were ResNet-18, ResNet-50, ResNet-101, GoogleNet, and DenseNet. The learning outcome features were further classified using the DELM algorithm. The comparison of CNN architecture aimed to find the best CNN architecture for fundus image features extraction. This research also compared the effect of using the kernel function on the performance of DELM in fundus image classification. All experiments using CDELM showed maximum results, with an accuracy of 100% in the DRIVE data and the two-class MESSIDOR data. Meanwhile, the best results obtained in the MESSIDOR 4 class data reached 98.20%. The advantage of the DELM method compared to the conventional CNN method is that the training time duration is much shorter. CNN takes an average of 30 min for training, while the CDELM method takes only an average of 2.5 min. Based on the value of accuracy and duration of training time, the CDELM method had better performance than the conventional CNN method.

1 January 2016
Verified
Conference Paper
Closed access
EFErick Fernando
Erick Fernando
SASetiawan Assegaff
Setiawan Assegaff
HRHetty Rohayani
Hetty Rohayani
ICT development is currently so fast, these developments affect the developing technology in all aspects, to the development of agriculture. Where the development of ICT transform traditional agriculture to modern. The purpose of this paper is to survey and analyze the available literature on Trend of Information technology in E-agriculture and also to identify gaps and state-of-the-art in research. This study use the Systematic literature reviews study by collecting the article from reputable database journals. We used recognize database journal such as “Emerald”, “Science Direct”, “IEEE xplore”, “Springer”, “Saga Publication” and “Google Scholar” to collect the articles. “Information technology in E-agriculture” is used as a keyword to search the relevant article. The selected articles are reviewed and analyzed. The result of analysis that e-commerce is the Trend research in information technology in agriculture. That is famous study by researchers, e-commerce to agriculture requires good marketing processes and successful in order to impact income of farmers. In addition, researching the sensor area that help a process of agriculture to increase yields from such a farm. With the use of information technology trends is became agriculture more modern.

31 December 2023 in Bulletin of Computer Science Research
Verified
Journal Article
Open access
PDF file
KKKevin Kurniawansyah
Kevin Kurniawansyah
NMNoneng Marthiawati
Noneng Marthiawati
HRHetty Rohayani
Hetty Rohayani
NONovitasari
Novitasari
Jambi Province Regional Development Bank or Bank Jambi is a bank in Indonesia. This bank was founded on February 12 1959 and is domiciled in Jambi City. Jambi Regional Development Bank is one of the banks that faces competition from other banks. It expects the council to use the greatest capacity accessible, to win over the opposition. One of the assistance techniques to change the implementation of data innovation that takes advantage of business goals is data innovation administration. The acceptance of innovation administration using the COBIT 2019 structure will have a huge effect in supporting the goals of the organization on the grounds that legitimate data innovation administration can help the organization in competing with different opponents. Different improvements have occurred during the modern time frame like now and have fundamentally affected various parts of society, including the business and production areas of online stores. Taking advantage of this, processes that have been recognized as significant processes, such as APO08 (Managed Relationship), APO12 (Managed Risk), APO13 (Managed Security), DSS04 (Managed Continuity), and DSS05 (Managed Security Services), must be continues to be focused on achieving the significant standards that have been set. By focusing on this cycle and continuously assessing and improving, companies can achieve better goals in using data innovation offices for corporate achievements.

31 July 2022 in Journal of Information System Research (JOSH)
Verified
Journal Article
Open access
PDF file
HRHetty Rohayani
Hetty Rohayani
MUMuhammad Choirul Umam
Muhammad Choirul Umam
In continuing higher education, the selection of study programs for students is considered difficult and confusing in choosing the right study program. Data Mining technique is a process of finding new knowledge from a set of databases that can help predict the selection of the appropriate study program. This prediction uses the Backpropagation Neural Network method which aims to assist in the selection of subjects according to student scores with a sample of 50 data to be trained and tested. There are seven input variables used, two hidden layers with varying number of nodes, and outputs that will be used as references in the selection of courses. In this study, the Artificial Neural Network Backpropagation method uses classification performance with Rapidminer software on the target that produces the greatest accuracy is 77.42%.