KMITL

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

Browse

Settings

Subject: search.filters.subject.deep neural network

Search Results

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Prediction of Flying Height Using Deep Neural Network Based on Particle Swarm Optimization in Hard Disk Drive Manufacturing Process
    (2024-01-01)
    Kanjanapruthipong, Worawit
    ;
    Prasitmeeboon, Pitcha
    ;
    Konghuayrob, Poom
    In contemporary hard disk drive (HDD) manufacturing processes, after the assembly of the HDD from the production line, a series of diverse calibration procedures are necessary to ensure standardization. These include capacity calibration, which determines the storage space in terabytes (TB) presently available, and flying height (FH) calibration, which evaluates the distance between the head and the disk by applying electric current to the heater coil element to achieve the desired FH, thus optimizing the writing and reading performance and tailoring it to each HDD. Additionally, electric current is saved in a digital-to-analog converter (DAC) unit for the utilization of a read/write head, while a preamp collaborates with the drive firmware to convert the electric current in the DAC unit to milliwatts. In the present scenario, multiple calibrations of flying heights (FHs), specifically flying height 1 (FH1) and flying height 2 (FH2), are performed. Each FH calibration requires a testing time of approximately 5 h owing to the separation of measurement points into 240 locations across the disk surface, referred to as test zones, with a total of 20 heads. The primary objective of this study is to reduce the testing time by using a combination of deep neural network (DNN) and particle swarm optimization techniques to predict the DAC profiles of FH2 as it approaches FH1, where FH1 is the input for the DNN model.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Location Prediction of Rogue Access Point Based on Deep Neural Network Approach
    (2022-01-01)
    Ketkhaw, Apisak
    ;
    Thipchaksurat, Sakchai
    One of the serious security problems in wireless local networks (WLAN) is the existence of the rogue access points (RAPs). To prevent our network from the RAP attacks, we need to identify the RAPs by using the RAP detection methods. However, the identification of RAP location is also a challenging task. The objective of this paper is to propose the location prediction scheme for the RAP.We call our proposed scheme as the location prediction of rogue access point (LPRAP). The LPRAP scheme consists of two mechanisms, the RAP detection mechanism and the RAP location prediction mechanism. We apply the concept of the fingerprint in the RAP detection mechanism by considering the SSID, time duration of broadcasting beacon frame and MAC address. We show that this mechanism can detect the number of RAP. For the RAP location prediction mechanism, we utilize the deep neuron network (DNN) to predict the location of RAPs and evaluate its effectiveness. We evaluate the performance of LPRAP by comparing with those of other machine learning methods such as Support Vector Machine (SVM), KNearest Neighbor (KNN), Naive Bayes, and Multi-layer Perceptron (MLP). We also compare with particle swarm optimization algorithm. The results show that LPRAP can accurately predict the location of RAP up to 99.29%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Deep Learning-Based Human Recognition Through the Wall using UWB radar
    (2021-01-01)
    Assawaroongsakul, Pongpol
    ;
    Khumdee, Mawin
    ;
    Phasukkit, Pattarapong
    ;
    Houngkamhang, Nongluck
    Human activity detection in obscured or invisible area, for instance, human detection through the wall has become an interesting topic because it has potential for security, rescue, activity analysis application, etc. UWB radar, a detection system produces short radio frequency pulses and measures the reflected signals which UWB pulses have high spatial resolution and enable penetration in dielectric materials, was used to collect human activity through the wall signals at the frequency range of 3 GHz in this research. Subsequently, we applied signal data with the Deep Neural Network model to classify 5 classes of human activity including standing, walking, sitting, laying, and no-human gave the F1 score up to 96.94%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Hybrid of Shallow and Deep Learning for Odor Classification Based on Adaptive Boosting
    (2019-11-01)
    Grodniyomchai, Boonyawee
    ;
    Chalapat, Khattiya
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Jaiyen, Saichon
    An electronic nose is very useful for identifying an odor that is harmful to humans. To get the most accurate odor predictions from an electronic nose, we combined the models of traditional machine learning and deep learning, including deep neural network (DNN), support vector machine (SVM) and decision tree, to make a new hybrid model that adopts the AdaBoost algorithm to adjust the weights of weak classifiers to build a strong classifier using odor data. Experimental results from our model were compared with other models, including a single deep neural network, an ensemble of SVM models and an ensemble of decision trees. Our model achieved an averaged accuracy of 99.58%, which is better than other models, and the standard deviation, 0.67%, is also less than other models.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A deep learning model for odor classification using deep neural network
    (2019-07-01)
    Grodniyomchai, Boonyawee
    ;
    Chalapat, Khattiya
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Jaiyen, Saichon
    The odor is an environment that surrounds us. However, to identify the odor by using the human nose in order to prove the odor is very dangerous. Therefore, the artificial intelligent (AI) system should be built based on machine learning in order to achieve more accurate results. This research adopts the Deep Neural Network (DNN) model to identify some types of odor including odorless, beer odor, whisky odor, and wine odor. Each contains 60 instances that are obtained from seven sensors of the electronic nose. The experiments are conducted, and the results are compared to the comparative machine learning methods including Multilayer Perceptron (MLP), Decision Tree and Naïve Bayes (NB). From the experimental results, it can signify that the proposed deep learning model can achieve the best average accuracy.