Hargyo T. N. Ignatius

Dr. Hargyo T. N. Ignatius


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 October 2016
Verified
Conference Paper
Closed access
VAVania
Vania
kanisius Karyonokanisius Karyono
kanisius Karyono
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius
Regular feeding is one of the problems in dog's maintenance. Owners often forget to feed their pets because of their work. Smart Dog Feeder is the answer to these problems. This device can provide regular feeding without disrupting owner's work. Owners can monitor feeding process with their Android smartphone virtually. Smart Dog Feeder can give authentication with RFID, set feeding time and portion per serving through Android smartphone, send feeding report (eaten or partially eaten), and dog arrival when the feeding time has arrived. Every setting about feeding time, portion, stock and waiting time will be set on Android with minimum requirement of Jelly Bean version, SDK 18 and has been installed with Appliance Hub application. Smart Dog Feeder has stock information, feed schedule, waiting time and owner's name from server uses MQTT protocol. All information will be sent in JSON format and will be processed by Smart Dog Feeder, Android and server. Smart Dog Feeder will save the schedule and set RTC alarm which will interrupt when the feed time has arrived. Authentication process is done by checking RFID tag which is attached on dog collar. Food will be served based on user's setting and be measured by load cell. Experiment is done by seeing punctuality, portion congruence, delivery of settings and notification within devices. The result of experiment is Smart Dog Feeder can receive messages from server and do feeding at the right time. Next development can be done by adding other devices in Appliance Hub system.

1 July 2014 in Microprocessors and Microsystems
Verified
Journal Article
Closed access
YLYu-Kuen Lai
Yu-Kuen Lai
CLChun-Chieh Lee
Chun-Chieh Lee
BHBo-Hsun Huang
Bo-Hsun Huang
TWTheophilus Wellem
Theophilus Wellem
NWNan-Cheng Wang
Nan-Cheng Wang
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius

1 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
DHDrixter Velayo Hernandez
Drixter Velayo Hernandez
Yu-Kuen LaiYu-Kuen Lai
Yu-Kuen Lai
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius
The exponential growth of Distributed Denial-of-Service (DDoS) attacks in high-speed networks presents significant real-time detection and mitigation challenges. The existing detection frameworks are categorized into flow-based and packet-based detection approaches. Flow-based approaches usually suffer from high latency and controller overhead in high-volume traffic. In contrast, packet-based approaches are prone to high false-positive rates and limited attack classification, resulting in delayed mitigation responses. To address these limitations, we propose a real-time DDoS detection architecture that combines hardware-accelerated statistical preprocessing with GPU-accelerated deep learning models. The raw packet header information is transformed into multivariate time series data to enable classification of complex traffic patterns using Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM) networks, and Transformer architectures. We evaluated the proposed system using experiments conducted under low to high-volume background traffic to validate each model’s robustness and adaptability in a real-time network environment. The experiments are conducted across different time window lengths to determine the trade-offs between detection accuracy and latency. The results show that larger observation windows improve detection accuracy using TCN and LSTM models and consistently outperform the Transformer in high-volume scenarios. Regarding model latency, TCN and Transformer exhibit constant latency across all window sizes. We also used SHAP (Shapley Additive exPlanations) analysis to identify the most discriminative traffic features, enhancing model interpretability and supporting feature selection for computational efficiency. Among the experimented models, TCN achieves the most balance between detection performance and latency, making it an applicable model for the proposed architecture. These findings validate the feasibility of the proposed architecture and support its potential as a real-time DDoS detection application in a realistic high-speed network.

13 October 2023 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius
RBRami Bahsoon
Rami Bahsoon
Industry 5.0 utilizes the Internet of Things (IoT) and autonomous computing to facilitate human–machine collaboration, where humans and machines coexist in a competitive economic ecosystem. In conventional workplaces, fairness is widely recognized as a driving force behind human motivation, loyalty, and productive collaboration. However, current fairness-aware task allocation methods have primarily focused on homogeneous workers, concentrating on either equity or equality as the sole fairness principle. With the rising trend of diverse worker fleets consisting of autonomous robots/vehicles and human-in-the-loop as service providers (e.g., crowdsourced logistics), novel approaches are necessary. Our contribution entails a fairness-aware task allocation approach for heterogeneous workers, leveraging the digital twin to understand the system’s behavior and facilitate real-time adaptation. Our proposed solution considers equity, equality, and need, utilizing the maximum-weight bipartite matching algorithm. Multiple incentive scenarios are utilized to evaluate the potential of the approach. The experimental results suggest that our multi-objective approach yields better overall fairness in various scenarios than the baselines.

1 April 2019 in TELKOMNIKA (Telecommunication Computing Electronics and Control)
Verified
Journal Article
Open access
PDF file
SPSunderi Pranata
Sunderi Pranata
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius
2FYSH: two-factor authentication you should have for password replacement

1 February 2014
Verified
Conference Paper
Closed access
NONovianti
Novianti
HIHargyo T. N. Ignatius
Hargyo T. N. Ignatius
The development of Content Management System (CMS) technology undoubtedly eases website content organization. Creative writing is a common challenge in producing written content. One solution is to use synonyms, which conventionally can be found in a thesaurus. In this research, Simple Knowledge Organization System (SKOS) data model, which is suitable for organizing knowledge such as thesauri, is implemented as a plugin for searching synonyms in Bahasa Indonesia. This plugin will complement the default text editor on CMS to edit the written content in a convenient way. This plugin also provides a feature for getting definitions using the XML web service from Kateglo, so that users can understand exactly the meaning of synonyms they use. Based on experiments done in this research, SKOS data can be loaded into triplestore by ARC2 in shorter time than the regular MySQL database which uses integrity constraints. Moreover, the experiments have also shown that time stability for getting synonyms from triplestore using ARC2 can be more maintained than obtaining synonyms from XML document.