Search results for: automatic identification system

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 187

Authors: Nikhat Nawaz, S. Srinivasulu, P. Kesava Rao

Abstract:

Feature extraction plays an important role in many remote sensing applications. Automatic extraction of water bodies is of great significance in many remote sensing applications like change detection, image retrieval etc. This paper presents a procedure for automatic extraction of water information from remote sensing images. The algorithm uses the relative location of R-colour component of the chromaticity diagram. This method is then integrated with the effectiveness of the spatial scale transformation of whole method. The whole method is based on water index fitted from spectral library. Experimental results demonstrate the improved accuracy and effectiveness of the integrated method for automatic extraction of water bodies.

Keywords: feature extraction, remote sensing, image retrieval, chromaticity, water index, spectral library, integrated method

Procedia PDF Downloads 384

Authors: Kavita Bodke

Abstract:

Structural health monitoring (SHM) is experiencing growth, necessitating the development of distinct methodologies to address its expanding scope effectively. In this study, we developed automatic structure damage identification, which incorporates three unique types of a building’s structural integrity. The first pertains to the presence of fractures within the structure, the second relates to the issue of dampness within the structure, and the third involves corrosion inside the structure. This study employs image classification techniques to discern between intact and impaired structures within structural data. The aim of this research is to find automatic damage detection with the probability of each damage class being present in one image. Based on this probability, we know which class has a higher probability or is more affected than the other classes. Utilizing photographs captured by a mobile camera serves as the input for an image classification system. Image classification was employed in our study to perform multi-class and multi-label classification. The objective was to categorize structural data based on the presence of cracks, moisture, and corrosion. In the context of multi-class image classification, our study employed three distinct methodologies: Random Forest, Multilayer Perceptron, and CNN. For the task of multi-label image classification, the models employed were Rasnet, Xceptionet, and Inception.

Keywords: SHM, CNN, deep learning, multi-class classification, multi-label classification

Procedia PDF Downloads 36

Authors: Leah Wilck

Abstract:

Eyewitness identification is arguably one of the most utilized practices within our legal system; however, exoneration cases indicate that this practice may lead to accuracy and conviction errors. The purpose of this study was to examine the effects of the cross-race effect, the phenomena in which people are able to more easily and accurately identify faces from within their racial category, on the accuracy of eyewitness identification. Participants watched three separate videos of a perpetrator trying to steal a bicycle. In each video, the perpetrator was of a different race and gender. Participants watched a video where the perpetrator was a Black male, a White male, and a White female. Following the completion of watching each video, participants were asked to recall everything they could about the perpetrator they witnessed. The initial results of the study did not find the expected cross-race effect impacted the eyewitness identification accuracy. These surprising results are discussed in terms of cross-race bias and recognition theory as well as applied implications.

Keywords: cross race effect, eyewitness identification, own-race bias, racial profiling

Procedia PDF Downloads 164

Authors: Martin Goubej, Tomas Popule, Alois Krejci

Abstract:

This paper deals with experimental identification of mechanical systems with nonlinear friction characteristics. Dynamic LuGre friction model is adopted and a systematic approach to parameter identification of both linear and nonlinear subsystems is given. The identification procedure consists of three subsequent experiments which deal with the individual parts of plant dynamics. The proposed method is experimentally verified on an industrial-grade robotic manipulator. Model fidelity is compared with the results achieved with a static friction model.

Keywords: mechanical friction, LuGre model, friction identification, motion control

Procedia PDF Downloads 413

Authors: Haythem H. Abdullah, Hesham Elkady

Abstract:

With the fast increase in radio frequency identification (RFID) applications such as medical recording, library management, etc., the limitation of active tags stems from its need to external batteries as well as passive or active chips. The chipless RFID tag reduces the cost to a large extent but at the expense of utilizing the spectrum. The reduction of the cost of chipless RFID is due to the absence of the chip itself. The identification is done by utilizing the spectrum in such a way that the frequency response of the tags consists of some resonance frequencies that represent the bits. The system capacity is decided by the number of resonators within the pre-specified band. It is important to find a solution to enhance the spectrum utilization when using chipless RFID. Target identification is a process that results in a decision that a specific target is present or not. Several target identification schemes are present, but one of the most successful techniques in radar target identification in the oscillatory region is the extinction pulse technique (E-Pulse). The E-Pulse technique is used to identify targets via its characteristics (natural) modes. By introducing an innovative solution for chipless RFID reader and tag designs, the spectrum utilization goes to the optimum case. In this paper, a novel capacity enhancement scheme based on the E-pulse technique is introduced to improve the performance of the chipless RFID system.

Keywords: chipless RFID, E-pulse, natural modes, resonators

Procedia PDF Downloads 80

Authors: A. A. M. A. S. S. Perera, L. A. Ranasinghe, T. K. H. Nimeshika, D. M. Dhanushka Dissanayake, Namalie Walgampaya

Abstract:

Nowadays, skin fungal diseases are mostly found in people of tropical countries like Sri Lanka. A skin fungal disease is a particular kind of illness caused by fungus. These diseases have various dangerous effects on the skin and keep on spreading over time. It becomes important to identify these diseases at their initial stage to control it from spreading. This paper presents an automated skin fungal disease identification system implemented to speed up the diagnosis process by identifying skin fungal infections in digital images. An image of the diseased skin lesion is acquired and a comprehensive computer vision and image processing scheme is used to process the image for the disease identification. This includes colour analysis using RGB and HSV colour models, texture classification using Grey Level Run Length Matrix, Grey Level Co-Occurrence Matrix and Local Binary Pattern, Object detection, Shape Identification and many more. This paper presents the approach and its outcome for identification of four most common skin fungal infections, namely, Tinea Corporis, Sporotrichosis, Malassezia and Onychomycosis. The main intention of this research is to provide an automated skin fungal disease identification system that increase the diagnostic quality, shorten the time-to-diagnosis and improve the efficiency of detection and successful treatment for skin fungal diseases.

Keywords: Circularity Index, Grey Level Run Length Matrix, Grey Level Co-Occurrence Matrix, Local Binary Pattern, Object detection, Ring Detection, Shape Identification

Procedia PDF Downloads 231

Authors: Kuo-Kai Lin, Po-Lun Chang

Abstract:

Research Background and Purpose: Following the development of the Internet and multimedia, the Internet and information technology have become crucial avenues of modern communication and knowledge acquisition. The advantages of using mobile devices for learning include making learning borderless and accessible. Mobile learning has become a trend in disease management and health promotion in recent years. End-stage renal disease (ESRD) is an irreversible chronic disease, and patients who do not receive kidney transplants can only rely on hemodialysis or peritoneal dialysis to survive. Due to the complexities in caregiving for patients with ESRD that stem from their advanced age and other comorbidities, the patients’ incapacity of self-care leads to an increase in the need to rely on their families or primary caregivers, although whether the primary caregivers adequately understand and implement patient care is a topic of concern. Therefore, this study explored whether primary caregivers’ health care provisions can be improved through the intervention of an automatic speech intelligent system, thereby improving the objective health outcomes of patients undergoing long-term dialysis. Method: This study developed an automatic speech intelligent system with healthcare functions such as health information voice prompt, two-way feedback, real-time push notification, and health information delivery. Convenience sampling was adopted to recruit eligible patients from a hemodialysis center at a regional teaching hospital as research participants. A one-group pretest-posttest design was adopted. Descriptive and inferential statistics were calculated from the demographic information collected from questionnaires answered by patients and primary caregivers, and from a medical record review, a health care scale (recorded six months before and after the implementation of intervention measures), a subjective health assessment, and a report of objective physiological indicators. The changes in health care behaviors, subjective health status, and physiological indicators before and after the intervention of the proposed automatic speech intelligent system were then compared. Conclusion and Discussion: The preliminary automatic speech intelligent system developed in this study was tested with 20 pretest patients at the recruitment location, and their health care capacity scores improved from 59.1 to 72.8; comparisons through a nonparametric test indicated a significant difference (p < .01). The average score for their subjective health assessment rose from 2.8 to 3.3. A survey of their objective physiological indicators discovered that the compliance rate for the blood potassium level was the most significant indicator; its average compliance rate increased from 81% to 94%. The results demonstrated that this automatic speech intelligent system yielded a higher efficacy for chronic disease care than did conventional health education delivered by nurses. Therefore, future efforts will continue to increase the number of recruited patients and to refine the intelligent system. Future improvements to the intelligent system can be expected to enhance its effectiveness even further.

Keywords: automatic speech intelligent system for health care, primary caregiver, long-term hemodialysis, health care capabilities, health outcomes

Procedia PDF Downloads 110

Authors: Agustinus Rudatyo Himamunanto, Anastasia Rita Widiarti

Abstract:

Transliteration using Javanese manuscripts is one of methods to preserve and legate the wealth of literature in the past for the present generation in Indonesia. The transliteration manual process commonly requires philologists and takes a relatively long time. The automatic transliteration process is expected to shorten the time so as to help the works of philologists. The preprocessing and segmentation stage firstly done is used to manage the document images, thus obtaining image script units that will compile input document images free from noise and have the similarity in properties in the thickness, size, and slope. The next stage of characteristic extraction is used to find unique characteristics that will distinguish each Javanese script image. One of characteristics that is used in this research is the number of black pixels in each image units. Each image of Java scripts contained in the data training will undergo the same process similar to the input characters. The system testing was performed with the data of the book Hamong Tani. The book Hamong Tani was selected due to its content, age and number of pages. Those were considered sufficient as a model experimental input. Based on the results of random page automatic transliteration process testing, it was determined that the maximum percentage correctness obtained was 81.53%. The percentage of success was obtained in 32x32 pixel input image size with the 5x5 image window. With regard to the results, it can be concluded that the automatic transliteration model offered is relatively good.

Keywords: Javanese script, character recognition, statistical, automatic transliteration

Procedia PDF Downloads 339

Authors: G. Rajeshwari, V. D. M. Jabez Daniel

Abstract:

Radio Frequency Identification systems are used for automated identification in various applications such as automobiles, health care and security. It is also called as the automated data collection technology. RFID readers are placed in any area to scan large number of tags to cover a wide distance. The placement of the RFID elements may result in several types of collisions. A major challenge in RFID system is collision avoidance. In the previous works the collision was avoided by using algorithms such as ALOHA and tree algorithm. This work proposes collision reduction and increased throughput through reading enhancement method with tree algorithm. The reading enhancement is done by improving interrogation procedure and increasing the data handling capacity of RFID reader with parallel processing. The work is simulated using Xilinx ISE 14.5 verilog language. By implementing this in the RFID system, we can able to achieve high throughput and avoid collision in the reader at a same instant of time. The overall system efficiency will be increased by implementing this.

Keywords: antenna, anti-collision protocols, data management system, reader, reading enhancement, tag

Procedia PDF Downloads 306

Authors: Leping Chen, Daoxiang An, Xiaotao Huang

Abstract:

Automatic vehicle detection using synthetic aperture radar (SAR) image has been widely researched, as well as using optical remote sensing images. However, most researches treat the detection as an independent problem, failing to make full use of SAR data information. In circular SAR (CSAR), the two long borders of vehicle will shrink if the imaging surface is set higher than the reference one. Based on above variance, an automatic vehicle detection using CSAR image is proposed to enhance detection ability under complex environment, such as vehicles’ closely packing, which confuses the detector. The detection method uses the multiple images generated by different height plane to obtain an energy-concentrated image for detecting and then uses the maximally stable extremal regions method (MSER) to detect vehicles. A result of vehicles’ detection is given to verify the effectiveness and correctness of proposed method.

Keywords: circular SAR, vehicle detection, automatic, imaging

Procedia PDF Downloads 367

Authors: Khaled Mohammed

Abstract:

This paper presents novel face recognition and identification approaches for the real-time attendance management problem in large companies/factories and government institutions. The proposed uses the Minimum Ratio (MR) approach for employee identification. Capturing the authentic face variability from a sequence of video frames has been considered for the recognition of faces and resulted in system robustness against the variability of facial features. Experimental results indicated an improvement in the performance of the proposed system compared to the Previous approaches at a rate between 2% to 5%. In addition, it decreased the time two times if compared with the Previous techniques, such as Extreme Learning Machine (ELM) & Multi-Scale Structural Similarity index (MS-SSIM). Finally, it achieved an accuracy of 99%.

Keywords: attendance management system, face detection and recognition, live face recognition, minimum ratio

Procedia PDF Downloads 155

Authors: Lotfi O. Gargab, Ruichong R. Zhang

Abstract:

A wave-based framework is presented for modeling seismic motion in multistory buildings and using measured response for system identification which can be utilized to extract important information regarding structure integrity. With one pair of building response at two locations, a generalized model response is formulated based on wave propagation features and expressed as frequency and time response functions denoted, respectively, as GFRF and GIRF. In particular, GIRF is fundamental in tracking arrival times of impulsive wave motion initiated at response level which is dependent on local model properties. Matching model and measured-structure responses can help in identifying model parameters and infer building properties. To show the effectiveness of this approach, the Millikan Library in Pasadena, California is identified with recordings of the Yorba Linda earthquake of September 3, 2002.

Keywords: system identification, continuous-discrete mass modeling, damage detection, post-earthquake

Procedia PDF Downloads 369

Authors: Mubashir Hussain, Mu Lv, Xiaohan Dong, Zhiyang Li, Bin Liu, Nongyue He

Abstract:

Detection and classification of microbes have a vast range of applications in biomedical engineering especially in detection, characterization, and quantification of bacterial contaminants. For identification of pathogens, different techniques are emerging in the field of biomedical engineering. Latest technology uses light scattering, capable of identifying different pathogens without any need for biochemical processing. Bacterial Pathogens Identification System (BPIS) which uses a laser beam, passes through the sample and light scatters off. An assembly of photodetectors surrounded by the sample at different angles to detect the scattering of light. The algorithm of the system consists of two parts: (a) Library files, and (b) Comparator. Library files contain data of known species of bacterial microbes in the form of binned plots, while comparator compares data of unknown sample with library files. Using collected data of unknown bacterial species, highest voltage values stored in the form of peaks and arranged in 3D histograms to find the frequency of occurrence. Resulting data compared with library files of known bacterial species. If sample data matching with any library file of known bacterial species, sample identified as a matched microbe. An experiment performed to identify three different bacteria particles: Enterococcus faecalis, Pseudomonas aeruginosa, and Escherichia coli. By applying algorithm using library files of given samples, results were compromising. This system is potentially applicable to several biomedical areas, especially those related to cell morphology.

Keywords: microbial identification, laser scattering, peak identification, binned plots classification

Procedia PDF Downloads 150

Authors: Maciej Zaręba, Sławomir Lasota

Abstract:

Understanding the dependencies between the input signal, that controls the production system and signals, that capture its output, is of a great importance in intelligent systems. The method for identification of the relationship between signals in continuous monitoring of production systems is described in the paper. The method discovers the correlation between changes in the states derived from input signals and resulting changes in the states of output signals of the production system. The method is able to handle system inertia, which determines the time shift of the relationship between the input and output.

Keywords: manufacturing operation management, signal relationship, continuous monitoring, production systems

Procedia PDF Downloads 92

Authors: J. Ritonja

Abstract:

Available commercial applications of power system stabilizers assure optimal damping of synchronous generator’s oscillations only in a small part of operating range. Parameters of the power system stabilizer are usually tuned for the selected operating point. Extensive variations of the synchronous generator’s operation result in changed dynamic characteristics. This is the reason that the power system stabilizer tuned for the nominal operating point does not satisfy preferred damping in the overall operation area. The small-signal stability and the transient stability of the synchronous generators have represented an attractive problem for testing different concepts of the modern control theory. Of all the methods, the adaptive control has proved to be the most suitable for the design of the power system stabilizers. The adaptive control has been used in order to assure the optimal damping through the entire synchronous generator’s operating range. The use of the adaptive control is possible because the loading variations and consequently the variations of the synchronous generator’s dynamic characteristics are, in most cases, essentially slower than the adaptation mechanism. The paper shows the development and the application of the self-tuning power system stabilizer based on recursive least square identification method and linear quadratic regulator. Identification method is used to calculate the parameters of the Heffron-Phillips model of the synchronous generator. On the basis of the calculated parameters of the synchronous generator’s mathematical model, the synthesis of the linear quadratic regulator is carried-out. The identification and the synthesis are implemented on-line. In this way, the self-tuning power system stabilizer adapts to the different operating conditions. A purpose of this paper is to contribute to development of the more effective power system stabilizers, which would replace currently used linear stabilizers. The presented self-tuning power system stabilizer makes the tuning of the controller parameters easier and assures damping improvement in the complete operating range. The results of simulations and experiments show essential improvement of the synchronous generator’s damping and power system stability.

Keywords: adaptive control, linear quadratic regulator, power system stabilizer, recursive least square identification

Procedia PDF Downloads 247

Authors: Xin Jiao, Xin Zhang, Jian Fan, Zhenwei Cai, Yiming Xu

Abstract:

Tower cranes play a crucial role in the construction industry, facilitating the vertical and horizontal movement of materials and aiding in building construction, especially for high-rise structures. However, tower crane accidents can lead to severe consequences, highlighting the importance of effective safety management and inspection. This paper presents an innovative approach to tower crane inspection utilizing Unmanned Aerial Vehicles (UAVs) and an Intelligent Inspection APP System. The system leverages UAVs equipped with high-definition cameras to conduct efficient and comprehensive inspections, reducing manual labor, inspection time, and risk. By integrating advanced technologies such as Real-Time Kinematic (RTK) positioning and digital image processing, the system enables precise route planning and collection of safety hazards images. A case study conducted on a construction site demonstrates the practicality and effectiveness of the proposed method, showcasing its potential to enhance tower crane safety. On-site testing of UAV intelligent inspections reveals key findings: efficient tower crane hazard inspection within 30 minutes, with a full-identification capability coverage rates of 76.3%, 64.8%, and 76.2% for major, significant, and general hazards respectively and a preliminary-identification capability coverage rates of 18.5%, 27.2%, and 19%, respectively. Notably, UAVs effectively identify various tower crane hazards, except for those requiring auditory detection. The limitations of this study primarily involve two aspects: Firstly, during the initial inspection, manual drone piloting is required for marking tower crane points, followed by automated flight inspections and reuse based on the marked route. Secondly, images captured by the drone necessitate manual identification and review, which can be time-consuming for equipment management personnel, particularly when dealing with a large volume of images. Subsequent research efforts will focus on AI training and recognition of safety hazard images, as well as the automatic generation of inspection reports and corrective management based on recognition results. The ongoing development in this area is currently in progress, and outcomes will be released at an appropriate time.

Keywords: tower crane, inspection, unmanned aerial vehicle (UAV), intelligent inspection app system, safety management

Procedia PDF Downloads 42

Authors: Nestor A. Garcia Fragoso, Tetyana Baydyk, Ernst Kussul

Abstract:

This article contains information from our investigation in the field of voice recognition. For this purpose, we created a voice database that contains different phrases in two languages, English and Spanish, for men and women. As a classifier, the LIRA (Limited Receptive Area) grayscale neural classifier was selected. The LIRA grayscale neural classifier was developed for image recognition tasks and demonstrated good results. Therefore, we decided to develop a recognition system using this classifier for voice recognition. From a specific set of speakers, we can recognize the speaker’s voice. For this purpose, the system uses spectrograms of the voice signals as input to the system, extracts the characteristics and identifies the speaker. The results are described and analyzed in this article. The classifier can be used for speaker identification in security system or smart buildings for different types of intelligent devices.

Keywords: extreme learning, LIRA neural classifier, speaker identification, voice recognition

Procedia PDF Downloads 177

Authors: Zehai Yu, Hui Zhu, Linglong Lin, Huawei Liang, Biao Yu, Weixin Huang

Abstract:

With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.

Keywords: curve fitting, lane-level road map, line recognition, multi-thresholding, two-stage clustering

Procedia PDF Downloads 128

Authors: Sihem Chaibeddra, Fattoum Kharchi, Fahim Kahlouche, Youcef Benna

Abstract:

In the recent years, a considerable level of interest has been developed on the use of earth in construction, led by its rediscovery as an environmentally building material. The Stabilized Earth Concrete (SEC) is a good alternative to the cement concrete, thanks to its thermal and moisture regulating features. Many parameters affect the behavior of stabilized earth concrete. This article presents research results related to the influence of the compacting nature on some SEC properties namely: The mechanical behavior, capillary absorption, shrinkage and sustainability to water erosion, and this, basing on two types of compacting: Manual and semi-automatic.

Keywords: behavior, compacting, manual, SEC, semi-automatic

Procedia PDF Downloads 360

Authors: Ke Lin, Steve Wu Qing Yang, Zhang Nan

Abstract:

The medicine and drugs has in the past been manufactured to the final products and then used laboratory analysis to verify their quality. However the industry needs crucially a monitoring technique for the final batch to batch quality check. The introduction of process analytical technology (PAT) provides an incentive to obtain real-time information about drugs on the production line, with the following optical techniques being considered: near-infrared (NIR) spectroscopy, Raman spectroscopy and imaging, mid-infrared spectroscopy with the use of chemometric techniques to quantify the final product. However, presents problems in that the spectra obtained will consist of many combination and overtone bands of the fundamental vibrations observed, making analysis difficult. In this work, we describe a non-destructive system and method for capsule and liquid medicine identification, more particularly, using terahertz time-domain spectroscopy and/or designed terahertz portable system for identifying different types of medicine in the package of capsule or in liquid medicine bottles. The target medicine can be detected directly, non-destructively and non-invasively.

Keywords: terahertz, non-destructive, non-invasive, chemical identification

Procedia PDF Downloads 131

Authors: Sidra Naeem, Ayesha Naeem, Sahar Rahim, Nadia Nawaz Qadri

Abstract:

Citrus greening is a bacterial disease that causes considerable damage to citrus fruits worldwide. Efficient method for this disease detection must be carried out to minimize the production loss. This paper presents a pattern recognition system that comprises three stages for the detection of citrus greening from Orange leaves: segmentation, feature extraction and classification. Image segmentation is accomplished by adaptive thresholding. The feature extraction stage comprises of three visual descriptors i.e. shape, color and texture. From shape feature we have used asymmetry index, from color feature we have used histogram of Cb component from YCbCr domain and from texture feature we have used local binary pattern. Classification was done using support vector machines and k nearest neighbors. The best performances of the system is Accuracy = 88.02% and AUROC = 90.1% was achieved by automatic segmented images. Our experiments validate that: (1). Segmentation is an imperative preprocessing step for computer assisted diagnosis of citrus greening, and (2). The combination of shape, color and texture features form a complementary set towards the identification of citrus greening disease.

Keywords: citrus greening, pattern recognition, feature extraction, classification

Procedia PDF Downloads 184

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: convolutional neural networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 123

Authors: Warinthorn Kiadtikornthaweeyot Evans, Nawattakorn Kaikaew

Abstract:

The communication system between the ground station and the satellite is very important to guarantee contact between both sides. Thailand, led by Geo-Informatics and Space Technology Development Agency (GISTDA), has received satellite images from other nation's satellites for a number of years. In 2008, Thailand Earth Observation Satellite (THEOS) was the first Earth observation satellite owned by Thailand. The mission was monitoring our country with affordable access to space-based Earth imagery. At this time, the control ground station was initially used to control the THEOS satellite by our Thai engineers. The Tele-commands were sent to the satellite according to requests from government and private sectors. Since then, GISTDA's engineers have gained their skill and experience to operate the satellite. Recently the desire to use satellite data is increasing rapidly due to space technology moving fast and giving us more benefits. It is essential to ensure that Thailand remains competitive in space technology. Thai Engineers have started to improve the performance of the control ground station in many different sections, also developing skills and knowledge in areas of satellite communication. Human resource skills are being enforced with development projects through capacity building. This paper focuses on the hands-on capacity building of GISTDA's engineers to develop a small automatic tracking antenna. The final achievement of the project is the first phase prototype of a small automatic tracking antenna to support the new technology of the satellites. There are two main subsystems that have been developed and tested; the tracking system and the monitoring and control software. The prototype first phase functions testing has been performed with Two Line Element (TLE) and the mission planning plan (MPP) file calculated from THEOS satellite by GISTDA.

Keywords: capacity building, small tracking antenna, automatic tracking system, project development procedure

Procedia PDF Downloads 75

Authors: Joseph C. Chen

Abstract:

Machine vision system provides automatic inspection to reduce manufacturing costs considerably. However, only a few principles have been found to optimize machine vision system and help it function more accurately in industrial practice. Mostly, there were complicated and impractical design techniques to improve the accuracy of machine vision system. This paper discusses implementing the Six Sigma Define, Measure, Analyze, Improve, and Control (DMAIC) approach to optimize the setup parameters of machine vision system when it is used as a direct measurement technique. This research follows a case study showing how Six Sigma DMAIC methodology has been put into use.

Keywords: DMAIC, machine vision system, process capability, Taguchi Parameter Design

Procedia PDF Downloads 437

Authors: Najib K. Dankadai, Ahmad 'Athif Mohd Faudzi, Khairuddin Osman, Muhammad Rusydi Muhammad Razif, IIi Najaa Aimi Mohd Nordin

Abstract:

Researches in soft actuators are now growing rapidly because of their adequacy to be applied in sectors like medical, agriculture, biological and welfare. This paper presents system identification (SI) and control of the force generated by a two chambers pneumatic soft actuator (PSA). A force mathematical model for the actuator was identified experimentally using data acquisition card and MATLAB SI toolbox. Two control techniques; a predictive functional control (PFC) and conventional proportional integral and derivative (PID) schemes are proposed and compared based on the identified model for the soft actuator flexible mechanism. Results of this study showed that both of the proposed controllers ensure accurate tracking when the closed loop system was tested with the step, sinusoidal and multi step reference input through MATLAB simulation although the PFC provides a better response than the PID.

Keywords: predictive functional control (PFC), proportional integral and derivative (PID), soft actuator, system identification

Procedia PDF Downloads 325

Authors: Michael Moeti, Khuliso Sigama, Thapelo Samuel Matlala

Abstract:

One of the principal challenges that the world is confronted with is insecurity. The crime rate is increasing exponentially, and protecting our physical assets especially in the motorist industry, is becoming impossible when applying our own strength. The need to develop technological solutions that detect and report theft without any human interference is inevitable. This is critical, especially for vehicle owners, to ensure theft detection and speedy identification towards recovery efforts in cases where a vehicle is missing or attempted theft is taking place. The vehicle theft detection system uses Convolutional Neural Network (CNN) to recognize the driver's face captured using an installed mobile phone device. The location identification function uses a Global Positioning System (GPS) to determine the real-time location of the vehicle. Upon identification of the location, Global System for Mobile Communications (GSM) technology is used to report or notify the vehicle owner about the whereabouts of the vehicle. The installed mobile app was implemented by making use of python as it is undoubtedly the best choice in machine learning. It allows easy access to machine learning algorithms through its widely developed library ecosystem. The graphical user interface was developed by making use of JAVA as it is better suited for mobile development. Google's online database (Firebase) was used as a means of storage for the application. The system integration test was performed using a simple percentage analysis. Sixty (60) vehicle owners participated in this study as a sample, and questionnaires were used in order to establish the acceptability of the system developed. The result indicates the efficiency of the proposed system, and consequently, the paper proposes the use of the system can effectively monitor the vehicle at any given place, even if it is driven outside its normal jurisdiction. More so, the system can be used as a database to detect, locate and report missing vehicles to different security agencies.

Keywords: CNN, location identification, tracking, GPS, GSM

Procedia PDF Downloads 166

Authors: M. Draman, S. Z. Muhamad Yassin, M. S. Alias, Z. Lambak, M. I. Zulkifli, S. N. Padhi, K. N. Baharim, F. Maskuriy, A. I. A. Rahim

Abstract:

The performance of Malay automatic speech recognition (ASR) system for the call centre environment is presented. The system utilizes Kaldi toolkit as the platform to the entire library and algorithm used in performing the ASR task. The acoustic model implemented in this system uses a deep neural network (DNN) method to model the acoustic signal and the standard (n-gram) model for language modelling. With 80 hours of training data from the call centre recordings, the ASR system can achieve 72% of accuracy that corresponds to 28% of word error rate (WER). The testing was done using 20 hours of audio data. Despite the implementation of DNN, the system shows a low accuracy owing to the varieties of noises, accent and dialect that typically occurs in Malaysian call centre environment. This significant variation of speakers is reflected by the large standard deviation of the average word error rate (WERav) (i.e., ~ 10%). It is observed that the lowest WER (13.8%) was obtained from recording sample with a standard Malay dialect (central Malaysia) of native speaker as compared to 49% of the sample with the highest WER that contains conversation of the speaker that uses non-standard Malay dialect.

Keywords: conversational speech recognition, deep neural network, Malay language, speech recognition

Procedia PDF Downloads 322

Authors: Fan Li, Chun-Hsien Chen, Li Pheng Khoo

Abstract:

Operators of vessel traffic service (VTS) center provides three different types of services; namely information service, navigational assistance and traffic organization to vessels. To provide these services, operators monitor vessel traffic through computer interface and provide navigational advice based on the information integrated from multiple sources, including automatic identification system (AIS), radar system, and closed circuit television (CCTV) system. Therefore, this information is crucial in VTS operation. However, what information the VTS operator actually need to efficiently and properly offer services is unclear. The aim of this study is to investigate into information requirements for VTS operation. To achieve this aim, field observation was carried out to elicit the information requirements for VTS operation. The study revealed that the most frequent and important tasks were handling arrival vessel report, potential conflict control and abeam vessel report. Current location and vessel name were used in all tasks. Hazard cargo information was particularly required when operators handle arrival vessel report. The speed, the course, and the distance of two or several vessels were only used in potential conflict control. The information requirements identified in this study can be utilized in designing a human-computer interface that takes into consideration what and when information should be displayed, and might be further used to build the foundation of a decision support system for VTS.

Keywords: vessel traffic service, information requirements, hierarchy task analysis, field observation

Procedia PDF Downloads 250

Authors: In-Geun Lim, Sung-Woong Ra

Abstract:

As high resolution satellite images can be used, lots of studies are carried out for exploiting these images in various fields. This paper proposes the method based on mathematical morphology for extracting the ‘horse's hoof shaped object’. This proposed method can make an automatic object detection system to track the meaningful object in a large satellite image rapidly. Mathematical morphology process can apply in binary image, so this method is very simple. Therefore this method can easily extract the ‘horse's hoof shaped object’ from any images which have indistinct edges of the tracking object and have different image qualities depending on filming location, filming time, and filming environment. Using the proposed method by which ‘horse's hoof shaped object’ can be rapidly extracted, the performance of the automatic object detection system can be improved dramatically.

Keywords: facility detection, satellite image, object, mathematical morphology

Procedia PDF Downloads 382