- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Embedded Systems Design Techniques
- Parallel Computing and Optimization Techniques
- VLSI and Analog Circuit Testing
- Interconnection Networks and Systems
- Anomaly Detection Techniques and Applications
- Experimental Learning in Engineering
- VLSI and FPGA Design Techniques
- Internet Traffic Analysis and Secure E-voting
- Water Quality Monitoring Technologies
- Cryptographic Implementations and Security
- Security and Verification in Computing
- Energy Efficient Wireless Sensor Networks
- Air Quality Monitoring and Forecasting
- Real-time simulation and control systems
- Analog and Mixed-Signal Circuit Design
- Adversarial Robustness in Machine Learning
- Topic Modeling
- Impact of Light on Environment and Health
- IoT and Edge/Fog Computing
- Real-Time Systems Scheduling
- Spam and Phishing Detection
- Image Processing Techniques and Applications
- Vehicular Ad Hoc Networks (VANETs)
Singapore University of Technology and Design
2017-2023
Nanyang Technological University
2007-2017
Since the effective and efficient system of water quality monitoring (WQM) are critical implementation for issue polluted globally, with increasing in development Wireless Sensor Network (WSN) technology Internet Things (IoT) environment, real time is remotely monitored by means real-time data acquisition, transmission processing. This paper presents a reconfigurable smart sensor interface device an IoT environment. The WQM consists Field Programmable Gate Array (FPGA) design board, sensors,...
Internet of Things (IoT) devices have become ubiquitous and spread across many application domains including the industry, transportation, healthcare, households. However, proliferation IoT has raised concerns about their security -- manufacturers focus only on core functionality products due to short time market low cost pressures, while neglecting aspects. Moreover, there is no established or standardized method for measuring ensuring devices. Consequently, vulnerabilities are left...
As Generative AI (GenAI) continues to gain prominence and utility across various sectors, their integration into the realm of Internet Things (IoT) security evolves rapidly. This work delves an examination state-of-the-art literature practical applications on how GenAI could improve be applied in landscape IoT. Our investigation aims map current state implementation within IoT security, exploring potential fortify measures further. Through compilation, synthesis, analysis latest advancements...
Internet of Things (IoT) has gained widespread popularity, revolutionizing industries and daily life. However, it also emerged as a prime target for attacks. Numerous efforts have been made to improve IoT security, substantial security threat information, such datasets reports, developed. existing research often falls short in leveraging these insights assist or guide users harnessing practices clear actionable way. In this paper, we propose ChatIoT, large language model (LLM)-based...
Nowadays, cities all over the globe are transforming into smart cities. Smart initiatives need to address environmental concerns such as air pollution provide clean air. A scalable and cost-effective monitoring system is imperative monitor control for city development. Air has notable effects on well-being of population a whole, global atmosphere, worldwide economy. This paper presents quality with low-cost sensors long-range communication protocol. The collect four parameters, temperature,...
Attacks on Internet of Things (IoT) devices, exploiting inherent vulnerabilities, have intensified over the last few years. Recent large-scale attacks, such as Persirai, Hakai, etc. corroborate concerns about security IoT devices. In this work, we propose an approach that allows easy integration commercial off-the-shelf devices into a general honeypot architecture. Our projects small number heterogeneous (that are physically at one location) many (geographically distributed) Internet, using...
In internet of things (IT) environment, a sensor interface device is essential for data collection in wireless network (WSN) system water quality monitoring (WQM) as the pollution critical issue globally. This paper presents design WSN based reconfigurable smart WQM an IoT environment. The consists Field Programmable Gate Array (FPGA) board, sensors, ZigBee communication module and personal computer (PC). FPGA board performs heart proposed it programmed very high speed integrated circuit...
Internet of Things (IoT) devices have become ubiquitous, with applications in many domains, including industry, transportation, and healthcare; these also household applications. The proliferation IoT has raised security privacy concerns, however manufacturers neglect aspects, focusing solely on the core functionality their products due to short time market need reduce product costs. Consequently, vulnerable are left unpatched, allowing attackers exploit them for various purposes, which...
Metropolitan cities around the world are putting effort towards a common goal of smart and sustainable urban development as initiative. To realize transportation systems part cities, automatic recognition vehicle license plates is essential for border checkpoint control, traffic red-light violation, monitoring vehicles entering leaving critical infrastructures government agencies. This paper presents an implementation plate system using in Myanmar case study. The proposed approach can be...
The nature of ever evolving anomalies have become more sophisticated and complex in attacking the defense schemes, thereby leading to serious compromises. Existing software based techniques aim protect a vulnerable with another which is also prone compromise like obfuscation-based attacks. On other hand, hardware performance counters offer robust detection mechanism that difficult since it easier tamper components than features. Hence, this paper, we propose hardware-based monitoring method...
This paper describes motivation and hardware architecture for resizing input image frames from the camera in order to support real-time scale-invariant object recognition. Conventional implementation of detection algorithms such as histogram oriented gradients (HOG) based feature extraction, face using Haar classifiers often perform during recognition process. Our investigation reveals that this incurs significant performance overhead due frequent memory accesses are required resizing. has...
This paper proposes a compiler-assisted technique to rapidly estimate performance of wide range FPGA processors without requiring actual execution on target processor or ISS. Experimental results show that this estimates widely-used with an average error 2% in the order seconds.
After distributed denial-of-service attacks by the Mirai malware in 2016, large-scale exploiting IoT devices raise significant security concerns for stakeholders involved. The efficacy of setting up honeypots to survey threat landscape and early detection threats is evident. However, availability dataset collected these advance research on has been scarce limited. With this paper, we contribute network traffic a high-interaction deployed wild 1.5 years during 2017-2018. are manifested 40...
FPGAs with integrated hard processors delivering a combination of performance, power savings and flexibility are becoming leading products in the market. Use this platform calls for efficient hardware-software partitioning, which is crucial to overall performance reliability these platforms. In paper, we present run-time partitioning technique called `KnapSim'. It employs two well-known heuristics - 0-1 Knapsack Simulated Annealing algorithms, provides near-optimal solutions. Experimental...
High-level synthesis tools are increasingly adopted for designing complex applications on FPGAs. These necessitate fast and accurate estimation of FPGA resources in order to produce good design solutions while minimizing time. Multiplication operations very commonly found signal processing, communication, video image processing applications. In this paper, we present a rapid technique estimate DSPs utilization different types multiplication during high-level synthesis. The proposed models...
Modern FPGA devices can implement a variety of processors with numerous configurable options. Rapid performance estimation plays vital role in embedded systems design to select processor that best fits the application requirements. Traditional evaluation techniques such as running software on target or using cycle accurate instruction set simulator are time-consuming and poses threat meeting stringent time-to-market pressure. In this paper, we propose framework rapidly estimate wide range...
This paper presents hardware-software code sign of Extended Kalman Filter (EKF) based motor control for a domain specific reconfigurable platform, which consists processor automotive applications and an FPGA application customization. Considering the existing MISRA C compliant software harnessing dedicated on chip peripherals, we employ methodology aiming to enable product differentiation through modest hardware accelerator implementation in logic thus meeting constraints under tight time...
Modern Autonomous Vehicles (AVs) leverage road context information collected through sensors (e.g., LiDAR, radar, and camera) to support the automated driving experience. Once such is collected, a neural network model predicts subsequent actions that AV executes. However, state-of-the-art research findings have shown possibility an attacker can compromise accuracy of in predicting tasks. Indeed, mispredicting cause harmful consequences user's safety.
This paper describes a teaching platform that comprises commercial FPGA-based board called the DE0 and custom complementary circuit of our design Teaching Auxiliary Board (TAB). The combination contains an ARM Cortex-M1 soft-core processor, numerous analogue digital peripherals, different types memory Cortex-M3 highly-integrated microcontroller. deliberate intention was to support laboratory experiments related embedded systems in manner greater educational benefit than using products alone....
Rapid evaluation of design metrics is essential for hardware-software co-design hybrid systems on FPGAs. However, acquisition from high-level programs costly and/or time-consuming, and this prohibits rapid space exploration. We will present a area-time estimation technique that capable obtaining hardware all the functions given C-based application in fraction time required by FPGA implementation. demonstrate proposed as part an open source synthesis tool. For considered, we show method,...