KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 8 of 8

Some of the metrics are blocked by your
consent settings
Traffic Signal Control with State-Optimizing Deep Reinforcement Learning and Fuzzy Logic
(2024-09-01)
Meepokgit, Teerapun
;
Wisayataksin, Sumek
Traffic lights are the most commonly used tool to manage urban traffic to reduce congestion and accidents. However, the poor management of traffic lights can result in further problems. Consequently, many studies on traffic light control have been conducted using deep reinforcement learning in the past few years. In this study, we propose a traffic light control method in which a Deep Q-network with fuzzy logic is used to reduce waiting time while enhancing the efficiency of the method. Nevertheless, existing studies using the Deep Q-network may yield suboptimal results because of the reward function, leading to the system favoring straight vehicles, which results in left-turning vehicles waiting too long. Therefore, we modified the reward function to consider the waiting time in each lane. For the experiment, Simulation of Urban Mobility (SUMO) software version 1.18.0 was used for various environments and vehicle types. The results show that, when using the proposed method in a prototype environment, the average total waiting time could be reduced by 18.46% compared with the traffic light control method using a conventional Deep Q-network with fuzzy logic. Additionally, an ambulance prioritization system was implemented that significantly reduced the ambulance waiting time. In summary, the proposed method yielded better results in all environments.
Some of the metrics are blocked by your
consent settings
Improvement of Electrical Bio-Impedance Measurement: Mixed Signal Approach
(2023-01-01)
Sribua, Phongpitch
;
Wisayataksin, Sumek
;
Thanachayanont, Apinunt
This article deploys a 5-level shorten rectangular wave technique to measure lock-in electrical bio-impedance (EBI) in medical diagnosis. The new shorten rectangular EBI signal has better properties in eliminating odd harmonics compared to the conventional 3-level shorten rectangular wave technique. The results show that the measurement errors in the 3-component EBI are reduced about 0.3% for R, X, Z and 3% for Phase(Φ) when the 5-level signal is used instead 3-level signal.
Some of the metrics are blocked by your
consent settings
Vegetation Health Monitoring System for Smart Farm using NDVI Analysis
(2022-01-01)
Wisayataksin, Sumek
;
Junta, Nontaput
;
Kuanpreeyawat, Jirat
We adapt the technique of normalized difference vegetation index (NDVI) to smart farms for monitoring the health of plants remotely over the IoT network. The system consists of a camera with 2 filters attached. The first one is an RGB filter to capture the visible light image, whereas another one is an infrared range filter. Two images are taken from a camera module and analyzed on Raspberry Pi 4 before being transmitted the NDVI image to the webserver for remote controlling and monitoring. The experimental results from actual plants reveal that our methodology can distinguish the healthy and unhealthy plants easily and efficiently.
Some of the metrics are blocked by your
consent settings
Configurable Hardware Architecture of Multidimensional Convolution Coprocessor
(2021-01-20)
Boonyuu, Geranun
;
Wisayataksin, Sumek
We propose a configurable coprocessor for the convolutional neural network (CNN) that suit various models of CNN. It can operate 2D standard convolution, 2D depthwise separable convolution, 3D convolution, and a fully connected layer. The proposed processing cluster consists of 72 processing units (PUs) of half-precision floating-point to assist the main processor in embedded systems. The experimental results on Artix-7 FPGA revealed that our design has 12.16 GOPs per cluster. Moreover, this architecture was designed to be scalable for the systems with higher performance.
Some of the metrics are blocked by your
consent settings
4-ary Odor-Shift Keying Using Multi-channel Olfactory Display
(2019-10-01)
Wisayataksin, Sumek
;
Angkasuwan, Panupong
;
Ariyakul, Yossiri
Odor-shift keying, a data modulation technique that encodes digital data by varying odor presentation, was proposed in this paper. A multi-channel olfactory display was used as modulator to release multiple odors whose blending ratio representing different digital data. On the demodulator side, an odor sensing system is used to measure the released smells, revert them into electrical form which is then decoded into the original data by using digital signal processing. The proposed technique can enhance data transfer rate of the communication through odor as carrier. A preliminary experiment was conducted to validate the possibility of the concept of varying the presented odors to represent different binary data. Finally, a string was practically modulated and transmitted by using the proposed technique. The demodulation process can be performed successfully and the data transfer rate was doubled from the previous work.
Some of the metrics are blocked by your
consent settings
An efficient hardware architecture of Codec2 low bit-rate speech decoder
(2019-07-01)
Wisayataksin, Sumek
Speech coding algorithms have been developed for years to digitalize human voice to a few binary bits as possible while maintaining reasonable quality. Codec2 vocoder algorithm is one of an efficient sinusoidal coding with very high compression rate down to 450 bit/s. In this paper, an efficient hardware architecture of Codec2 decoder is proposed to increase the performance of voice decoding process and reduce comprehensive tasks from a host processor. Although the sinusoidal decoding algorithm is complicated with many arithmetic operations such as the arithmetic of complex numbers, FFT, FIR filter, division, trigonometry, exponential and logarithm functions, several techniques were explored to optimize and parallelize a datapath of the proposed hardware. The implementation on Xilinx Artix-7 FPGA revealed that the proposed architecture could reduce the processing time up to 20 times, compared to the conventional Cortex-M4 CPU running with the original software.
Some of the metrics are blocked by your
consent settings
A programmable artificial neural network coprocessor for handwritten digit recognition
(2019-07-01)
Wisayataksin, Sumek
;
Boonyuu, Geranun
This paper proposes the hardware architecture of an artificial neural network coprocessor that its structure can be programmable. The number of neurons in each layer of a feedforward network can be set by writing configuration registers. The processing unit with four MACs and the sigmoid calculation engine are connected in eight pipeline stages to enhance the processing speed. The application of handwritten digit recognition from the MNIST database was performed to verify the performance of proposed architecture. The design was developed with Verilog HDL and implemented on the Xilinx Artix-7 XC7A35T FPGA. The experimental results revealed that the speed of back-propagation learning and validation process can be up to 47 times faster than computation on ARM Cortex-A4 CPU, while the recognition rate is still the same.
Some of the metrics are blocked by your
consent settings
Data Modulation Technique Using Concentration of Odor Molecules
(2018-12-26)
Ariyakul, Yossiri
;
Wisayataksin, Sumek
This study proposed a novel data modulation technique for digital communication by using a concentration of odor molecules. The information is encapsulated in an odor with controlled concentration levels in accordance with the binary representation of the message by using an olfactory display. The released odor is then measured by an odor sensing system where it is converted into electrical form that can be demodulated into the original data by using a digital filter and decision decoder. The experiments of sending a message by mean of odor in the UART format were performed to evaluate the possibility of the proposed molecular communication approach. The results reveal that the shape of signals detected by the odor sensor is associated with the information in the message, which confirms the reliability of data communication using this method.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results