KMITL

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

Browse

Search Results

Now showing 1 - 10 of 16

Some of the metrics are blocked by your
consent settings
5.8 GHz wireless localization based weighted algorithm for home network applications
(2020-07-01)
Mankong, Thanadon
;
Maw, Myo Myint
;
Promwong, Sathaporn
New wireless network solution, the distributed network nodes short range area are unknown. This paper, consider the accuracy with weighted algorithm (WA) based on wireless network received signal strength is evaluated for localization. The wireless transmission model using wireless ISM band with four reference nodes and one target node operated at frequency of 5.8 GHz. Distance error is used to evaluate the precision of location approximation with respected to the CDF. The received signal strength in measurement field is presented in this paper. The contributes of this paper is useful for a study in an indoor positioning with 5.8 GHz for future home network applications.
Some of the metrics are blocked by your
consent settings
Traffic signal timings optimization based on genetic algorithm and gradient descent
(2020-05-01)
Yadav, Alok
;
Nuthong, Chaiwat
Traffic congestions are a recurring problem that results in significant losses both financially and environmentally. optimizing traffic signal timings is one of the most cost-effective ways to mitigate such effects. optimization of traffic signal timings capable of minimizing congestion is, however, computationally expensive. Research needs to be conducted to develop algorithms capable of better optimization using fewer computational resources. This paper presents a novel approach to traffic signal optimization that combines genetic algorithms and a gradient descent like algorithm to obtain optimized traffic signal timings. The genetic algorithm is used to arrive at a starting point for gradient descent; gradient descent is then used to obtain further improvement.
Some of the metrics are blocked by your
consent settings
A rule-based training for artificial neural network packet filtering firewall
(2019-11-01)
Khunkitti, Akharin
;
Chongsujjatham, Ponsuda
The Artificial Neural Network has been used in many network applications, including firewalls. Training process of neural network is very important to define the intelligence of the systems. Many artificial neural network firewalls used direct network packets for training process, which may be difficult to get training samples and may not follow their firewall's policies. This research work proposes a rule-based training for artificial neural network packet filtering firewall. The developed neural network model is trained by generating samples from legacy firewall ruleset. Each rule has been converted to random training samples. All firewall's rules are used to generate the training sample data, rule by rule. The accuracy results show high accuracy with some behavior studies. The number of samples per rule, number of rules and rule style, including default rule and rule-scope effects, have been studied for the best accuracy results. This study also concludes the styles of firewall ruleset for the best accuracy of the proposed system.
Some of the metrics are blocked by your
consent settings
Using doppler radar classify respiration by MFCC
(2019-07-01)
Tantasirin, Chayanan
;
Khaemphukhieo, Ratchaphon
;
Phasukkit, Pattarapong
Respiration rate is an important parameter to indicate whether the respiratory system is normal or abnormal. In general, respiration rate can be calculated and counted the number of inhale and exhale when a person is in resting condition in 1 minute. There are many methods that can evaluate respiratory data from a various biomedical signal such as Electrocardiogram (ECG) Signals, Blood Pressure (BP) and Photo-plethysmography (PPG). But it can not be used in all condition like sleeping all night comfortably. According to all of the previous methods, they are all contact devices. Therefore, this paper studies non-contact respiration measured by using doppler radar to receive the signal data, then use MFCC to extract the feature of the signal and feed the feature to DCNN. In the result, we got 85% of accuracy.
Some of the metrics are blocked by your
consent settings
Validation of acoustic emission railway track crack analysis using MFCC
(2019-07-01)
Vongserewattana, Narate
;
Suwansin, Wara
;
Phasukkit, Pattarapong
;
Phatsornsiri, Punnavich
Nowadays, railway track crack detection system has many techniques, such as Ultrasonic Techniques [1], Electromagnetic Techniques [2] and GSM Techniques [3]. For the propose of this research, we study characteristics of railway track using acoustic emission, the device which is widely used for application such as crack detection in aerospace space grade steel [4], detection of defect s in rolling element bearing [5], fatigue crack growth detection [6]. And use the MFCC ('Mel - Frequency Cepstral Coefficients') [7] method which is generally used for low frequency to extract the feature of each railway track. According to that, we chose to adjust the MFCC method for an acoustic feature extraction in order for condition to be suitable used for this system, because the railway track crack detection system, we are interested in concentrates at 100-400 kHz. According to the result of the experiment, it shows that this technique is able to extract and classify feature of the railway track crack.
Some of the metrics are blocked by your
consent settings
Rapid E. coli detection based on fluorescence technique
(2017-12-19)
Suwan, Supakorn
;
Phasuk, Kanchana
;
Chitsakul, Kitiphol
;
Piyawattanametha, Wibool
This research focuses on developing a prototype tool that is portable and develop method to detect Escherichia coli (E. coli) in water by measuring the light of fluorescence from an enzymatic reaction. The procedure can be done easily without need for laboratory professionals within 2 hours. Total coliforms can measure a minimum of at least 10 MPN/mL. This method is an alternative method to determine water quality. It can reduce the shipping water samples step to laboratories, reducing the time to wait for results. And reduces the cost of detecting E. coli, while the efficiency of this method is no different with the Most Probable Number method.
Some of the metrics are blocked by your
consent settings
Fingerprint matching by using 2D discrete cosine transform and 2D Fourier transforms
(2012-12-01)
Insankeovilay, Souksamay
;
Choomchuay, Somsak
;
Hamamoto, Kazuhiko
In this paper, we proposed a fingerprint matching using the two dimensional discrete cosine transform features. In this paper we crop input images from the size 480x640 pixels into 128x128 pixels, and then divided the image into 64 sub-images, earth sub-images have the size 16x16 pixels. We measure our algorithm performs by the correlation value of the 2D discrete cosine transform (DCT) and 2D Fourier transforms (FFT). And we used images for testing are obtained from FVC-2004 (DB-1A) and FVC - 2002 (DB2-A). From this evaluation and results, we can see that this method offers better performance when compared to other individual matching. Moreover, our method is not sensitive to rotational effect. The proposed technique is based on the availability of core point, therefore, the proposed technique introduce some errors if the core point cannot be located or improperly located. The matching is performed using the two dimensional discrete cosine transform and two dimensional Fourier transform to find the magnitude of the spectrum, spectrum phase, and the value of line angle. copy;2012 IEEE.
Some of the metrics are blocked by your
consent settings
Analysis of heat sink effect in hepatic cancer treatment near arterial for microwave ablation by using finite element method
(2012-12-01)
Yhamyindee, P.
;
Phasukkit, P.
;
Tungjitkusolmon, S.
;
Sanpanich, A.
This paper presents an analysis of heat sink effect in hepatic cancer treatment near arterial vessel for microwave ablation by using finite element method. We analyze the temperature distribution, Specific Absorbtion Rate (SAR) and coagulation area in two models. The first is hepatic tissue without artery and the second is hepatic tissue with artery. In the second model, we specify distance between antenna and artery at 10 mm. The initial condition is set as power at 50 watts, temperature at 37°C and blood perfusion rate is varied at 6.4 × 10-10, 6.4 × 10-3 and 6.4 × 104 l/s. The simulation results by using three-dimensional finite element analysis show that the temperature distribution in case of hepatic tissue with no artery is larger than the case with artery. We also found that blood perfusion rate affects to the temperature distribution in hepatic tissue. Higher blood perfusion rate, higher heat sink effect occur. ©2012 IEEE.
Some of the metrics are blocked by your
consent settings
Using intrinsic surface geometry and absolute invariants for 3D face alignment and registration
(2010-12-01)
Pintavirooj, Chuchart
;
Tosranon, Prasong
;
Cohen, Fernand S.
In this paper we derive novel surface fiducial points that are computed from the differential geometry of the surface. The fiducial intrinsic points are intrinsic, local, and relative invariants, i.e., they are preserved under similarity, affine, and nonlinear transformations that are piecewise affine. As the fiducial points are computed from high order surface shape derivatives, their sensitivity to any noise either due to measurement error or local distortion is high. To reduce these effects, we use a B-Spline curve/surface representation that smoothes out the curve/surface prior to the computation of these intrinsic invariant points. The fiducial points are used in a non-iterative geometric-based method for 3D shape matching and registration of human faces. The matching is achieved by establishing correspondences between fiducial points after a sorting based on a set of absolute local affine invariants derived from them. The performance of the matching based on these fiducial points although shown for face alignment, the overall approach is generic to the alignment a variety of objects for which these intrinsic fiducial points exist and for scenarios where the classes of nonlinear transformations are piecewise affine. © 2010 IEEE.
Some of the metrics are blocked by your
consent settings
Single-wall carbon nanotube modified glassy carbon electrode for electroanalytical determination of dopamine
(2010-11-29)
Chuekachang, Sopis
;
Kruefu, Viruntachar
;
Chaiyasit, Suwan
;
Phanichphant, Sukon
In this research, a glassy carbon electrode modified with single-wall carbon nanotubes for electrochemical determination of dopamine was studied by cyclicvoltammetry (CV) and differential pulse voltammetry (DPV). The oxidation and reduction potentials of dopamine using voltammetric technique were measured. The SWCNTs/GC 10 μL was used to test the linearity of anodic oxidation of dopamine by DPV. The peak current increased linearly with concentration of dopamine in the range of 2.5-25 ppm (R2=0.9766).For the life time of the SWCNTs/GC, the cut-off criterion of the DPV was detected in the reduction of current by 50 %. The lifetime of the SWCNTsmodified depended on the oxidation of dopamine because of fouling of the electrode surface due to the adsorption of oxidation products. 34 repetition cycles was obtained. The detection limit of the dopamine as obtained from the oxidation current in DPV was 0.021 ppm (S/N=3) with minimum current for the detection of dopamine of 0.033 μA. The reproducibility of electrocatalytical studies was better within 90% (10% RSD). The relative standard deviation (RSD) of 8.42% for 100 ppm dopamine (n=20) showed excellent reproducibility. Drug samples obtained from Radvitee hospital were tested as the mentioned procedure. The percentage recovery of dopamine in drug samples was 120. ©2010 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results