Tutun Juhana

Tutun Juhana

Auto-generated profile, based on publicly available information

Tutun Juhana

School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jalan Ganesha 10 40132, Indonesia

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
27 November 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
HLHeng Liu
Heng Liu
JZJiayi Zhang
Jiayi Zhang
XZXiaodan Zhang
Xiaodan Zhang
AKAdit Kurniawan
Adit Kurniawan
TJTutun Juhana
Tutun Juhana
BABo Ai
Bo Ai
In this correspondence, an efficient pilot assignment scheme based on tabu search (TS) is proposed to mitigate the severe pilot contamination effect caused by pilot reuse in cell-free massive multiple-input multiple-output systems. By exploiting the local neighborhood search, we first define the neighborhood and search objective function. Then, the tabu list is introduced to record the prohibited solutions and to avoid being trapped in the local optimum. In addition, we consider a fair policy for the pilot reused times to further improve the system performance. We propose a TS-based pilot assignment scheme iteration to intelligently search the suboptimal pilot assignment result with low complexity. Numerical results verify that the proposed TS-based pilot assignment scheme can significantly improve the 95%-likely per-user net throughput with similar complexity compared to the conventional random and greedy schemes.

1 September 2020 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
Mi YangMi Yang
Mi Yang
BABo Ai
Bo Ai
RHRuisi He
Ruisi He
GWGongpu Wang
Gongpu Wang
LCLiang Chen
Liang Chen
TJTutun Juhana
Tutun Juhana

22 April 2024 in IEEE Access
Verified
Journal Article
Open access
SISetia Juli Irzal Ismail
Setia Juli Irzal Ismail
HEHendrawan
Hendrawan
BRBudi Rahardjo
Budi Rahardjo
TJTutun Juhana
Tutun Juhana
YMYasuo Musashi
Yasuo Musashi
Malware classification with supervised learning requires a large dataset, which needs an expensive and time-consuming labeling process. In this paper, we explore the efficacy of self-supervised learning techniques for malware classification. We propose MalSSL, a self-supervised learning-based method utilizing image representation to classify malware. MalSSL classifies unlabeled malware images using contrastive learning and data augmentation. The model is initially trained on an unlabeled Imagenette dataset as a pretext task and subsequently retrained on an unlabeled malware dataset in downstream tasks. Two downstream tasks were employed to evaluate the system: 1) malware family classification and 2) malware benign classification. The obtained results include an accuracy of 98.4% for the malware family classification experiment on the Malimg dataset and an accuracy of 96.2% for the malware and benign dataset (Maldeb dataset). Our findings suggest that the proposed system accurately classifies malware without the need for labeled data, displaying higher accuracy compared to other self-supervised methods. This research not only contributes to advancing the state-of-the-art in malware classification but also underscores the potential of self-supervised learning methods as a viable solution for addressing the dynamic landscape of malware threats.

1 October 2016
Verified
Conference Paper
Closed access
TJTutun Juhana
Tutun Juhana
VAVivi Gusti Anggraini
Vivi Gusti Anggraini
In this study, the implementation of monitoring system is made, aimed for home surveillance. The sensor of the system is camera. The camera will capture image of the room and will evaluate whether an intruder is detected or not, by subtracting the image with the background frame. When the intruder is detected, the system will automatically activate the alarm to alert the home occupant. In the same time, the image of the intruder is sent to the user's smartphone or PC over the internet to tell the intruder existence to the user remotely. So the user will feel more secure and be able to respond earlier when an intruder is detected in the house. With this system, user also has evidence, which is the intruder image, to user be able to recognize and capture the intruder redhanded.

8 December 2023 in IEEE Access
Verified
Journal Article
Open access
GNGalih Nugraha Nurkahfi
Galih Nugraha Nurkahfi
ATAndy Triwinarko
Andy Triwinarko
BPBudi Prawara
Budi Prawara
NANasrullah Armi
Nasrullah Armi
TJTutun Juhana
Tutun Juhana
IDIyad Dayoub
Iyad Dayoub
SDN’s ability to provide a global view, centralized control, and flexibility in orchestrating network infrastructure are expected to overcome challenges in the dynamic conditions of vehicular communications. We are looking to rely on SDN technologies to achieve Vehicular communications capacity and performance, which increase the safety of vehicles and transportation, save cost & energy, and increase the vehicles’ autonomy level. The usage of SDN in vehicular communications has been the subject of considerable research. Researchers address challenges such as low latency, high throughput, reliability, dense VANET, security, and scalability. Furthermore, this paper surveys the integration of SDN and other enabling technologies with vehicular communications, both for IEEE 802.11 and the C-V2X RAT families. It begins by discussing performance comparisons and coexistence between IEEE 802.11 and C-V2X standards, implementation of SDN in various use cases, integration of SDN with other enabling technologies, the study of particular SDN components to support vehicular communications performance, and SDN usage to support the specific issues vehicular communications. Finally, open directions and challenges of the research are discussed.

1 October 2016
Verified
Conference Paper
Closed access
HSHamonangan Situmorang
Hamonangan Situmorang
NSNana Rachmana Syambas
Nana Rachmana Syambas
TJTutun Juhana
Tutun Juhana
NDN (Named Data Networking) as one approach of the Content-Centric Networking (CCN) architecture, proposed by Jacobson, 2006, conceptually, has some advantages compares to the current Internet technology which build based on host-to-host TCP/IP protocol stack. However, technically, we have to examine the NDN approach, beside to prove the concept, also to get as much as able the opportunities of improvement the concept before implementation stage. Some challenges in Large topology such as the effectifity of Content Store size, should be considered first. Some researchers work by top down approach, it means they work by developing sophisticated NDN application to be run on trivial NDN for getting much the requirements for NDN to support the large range of applications. However we work based on bottom up approach, we do the deep examination on the NDN to get much knowledge of the behaviour of NDN itself in the perspective of network discipline by using one particular model of the application. We conduct some simmulation scenarios run on ndnSIM to examine our mathematical model of delay distribution in NDN instead of running the scenarios on a test-bed network that overlay the existing TCP/IP network. An TCP/IP overlay test-bed network will contain some `poisons' of host-to-host TCP communication. The scenarios consist of scalling the size of topology and also the size of content store. The topology choosen is grid topology in a number of size.