Lanny Sitanayah

Dr. Lanny Sitanayah


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
4 March 2011 in Sensors
Verified
Journal Article
Open access
PDF file
YZYuanyuan Zeng
Yuanyuan Zeng
CSCormac Sreenan
Cormac Sreenan
LSLanny Sitanayah
Lanny Sitanayah
Neal XiongNeal Xiong
Neal Xiong
JPJong Hyuk Park
Jong Hyuk Park
GZGuilin Zheng
Guilin Zheng
Fire hazard monitoring and evacuation for building environments is a novel application area for the deployment of wireless sensor networks. In this context, adaptive routing is essential in order to ensure safe and timely data delivery in building evacuation and fire fighting resource applications. Existing routing mechanisms for wireless sensor networks are not well suited for building fires, especially as they do not consider critical and dynamic network scenarios. In this paper, an emergency-adaptive, real-time and robust routing protocol is presented for emergency situations such as building fire hazard applications. The protocol adapts to handle dynamic emergency scenarios and works well with the routing hole problem. Theoretical analysis and simulation results indicate that our protocol provides a real-time routing mechanism that is well suited for dynamic emergency scenarios in building fires when compared with other related work.

1 January 2025 in Journal of Computing Theories and Applications
Verified
Journal Article
Open access
PDF file
AAApriandy Angdresey
Apriandy Angdresey
LSLanny Sitanayah
Lanny Sitanayah
ITIgnatius Lucky Henokh Tangka
Ignatius Lucky Henokh Tangka
The 2024 Indonesian Presidential Election marked the fifth general election in the country, aimed at electing a new President and Vice President for the 2024–2029 term. Candidates competed to succeed the outgoing president, who had served two constitutional terms. A key aspect of this election was the candidate debates, where each candidate presented their vision, allowing the public to assess their policies. These debates were broadcast on platforms like YouTube, giving the public a space to comment. However, analyzing YouTube comments presents challenges due to the volume of data, language diversity, and informal expressions. Sentiment analysis, crucial for understanding public opinion, uses algorithms such as Naïve Bayes, which is based on Bayes' Theorem and assumes feature independence. Naïve Bayes is widely used in text analysis for its speed and simplicity. When applied to YouTube comments from the 2024 debates, the algorithm demonstrated its effectiveness, especially with a balanced dataset through random oversampling. It achieved 85.155% accuracy, high precision, recall, and an AUC of 96.8% on an 80:20 data split. Its fast classification time (0.000998 seconds) makes it suitable for real-time sentiment analysis, validating its use for political events. Future applications may incorporate advanced techniques like BERT for more sophisticated analysis.

30 July 2014 in Journal of Heuristics
Verified
Journal Article
Closed access
PDF file
LSLanny Sitanayah
Lanny Sitanayah
KBKenneth Brown
Kenneth Brown
CSCormac Sreenan
Cormac Sreenan

Verified
Journal Article
Open access
PDF file
LSLanny Sitanayah
Lanny Sitanayah
CSCormac Sreenan
Cormac Sreenan
SFSzymon Fedor
Szymon Fedor
Contiki’s Cooja is a very popular wireless sensor network (WSN) simulator, but it lacks support for modelling sensing coverage, focusing instead on network connectivity and protocol performance. However, in practice, it is the ability of a sensor network to provide a satisfactory level of coverage that defines its ultimate utility for end-users. We introduce WSN-Maintain, a Cooja-based tool for coverage and network lifetime evaluation in an in-building WSN. To extend the network lifetime, but still maintain the required quality of coverage, the tool finds coverage redundant nodes, puts them to sleep and automatically turns them on when active nodes fail and coverage quality decreases. WSN-Maintain together with Cooja allow us to evaluate different approaches to maintain coverage. As use cases to the tool, we implement two redundant node algorithms: greedy-maintain, a centralised algorithm, and local-maintain, a localised algorithm to configure the initial network and to turn on redundant nodes. Using data from five real deployments, we show that our tool with simple redundant node algorithms and reading correlation can improve energy efficiency by putting more nodes to sleep.

28 February 2025 in Journal of Computing Theories and Applications
Verified
Journal Article
Open access
PDF file
LSLanny Sitanayah
Lanny Sitanayah
HJHizkia R.M. Joseph
Hizkia R.M. Joseph
JSJunaidy B. Sanger
Junaidy B. Sanger
The need for urban communities to consume vegetables is increasing. This has caused people to start cultivating vegetables using hydroponic techniques. However, due to their busy activities, they do not have enough time to monitor and control hydroponics, which must always be in ideal conditions. This paper designs and implements an Internet of Things-based monitoring system to help hydroponic owners monitor their hydroponics anywhere and anytime. The built system requires a monitoring device assembled using a NodeMCU ESP8266 microcontroller, a pH detection detector sensor, and a DHT22 temperature and humidity sensor. This system uses the Mamdani Fuzzy Logic algorithm to determine warnings to be displayed on the application interface when the water pH, temperature, and humidity are in certain conditions. The Mamdani Fuzzy Logic algorithm can interpret environmental data into a warning that humans can easily understand, even if they lack technical expertise. In addition to being able to help monitor, this system also allows owners to find out what elements need to be added or changed for their hydroponic place. Our evaluation results show that the defuzzification stage in the application has high accuracy, which is 99.92%, compared to Matlab’s results.

5 April 2023 in Journal of Electrical Engineering and Computer (JEECOM)
Verified
Journal Article
Open access
PDF file
SPSteven Pandelaki
Steven Pandelaki
LSLanny Sitanayah
Lanny Sitanayah
MLMicael Liem
Micael Liem
Jatuh merupakan kejadian yang cukup berbahaya karena dapat menimbulkan cedera pada tubuh. Risiko jatuh pada setiap orang berbeda-beda dan ditentukan oleh banyak faktor, mulai dari keadaan lingkungan, kondisi kebugaran tubuh, dan faktor usia. Jatuh tidak hanya menimbulkan bahaya pada orang lanjut usia tetapi juga pada orang di segala usia dan dapat menjadi pertanda dari kambuhnya penyakit-penyakit tertentu. Penyakit yang diderita dapat bermacam-macam, akan tetapi penyakit yang umumnya terjadi adalah penyakit jantung, penyakit ayan, dan tekanan darah tinggi. Untuk meminimalkan dampak dari kondisi jatuh maka akan dibuat suatu Sistem Pendeteksi Jatuh Berbasis Internet of Things. Sistem ini memanfaatkan nilai keluaran dari sensor accelerometer dan gyroscope MPU6050 dengan menggunakan mikrokontroler NodeMCU ESP8266 untuk mengirimkan data ke database. Sensor dan mikrokontroler ditempatkan pada posisi pinggang pengguna. Aplikasi kemudian mengambil data yang dikirimkan dan mengklasifikasikan data tersebut menggunakan algoritma C4.5. Jika hasil klasifikasi adalah jatuh maka aplikasi akan menampilkan peringatan serta bunyi notifikasi. Berdasarkan hasil pengujian yang telah dilakukan, diperoleh hasil bahwa sistem yang dibangun memiliki akurasi sebesar 95% dalam menampilkan peringatan kondisi jatuh.