Search results for: Recognition accuracy.

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, capsule network, capacity optimization, character recognition, data augmentation; semantic segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 655

Authors: El Sayed A. Sharara, A. Tsuji, K. Terada

Abstract:

Call centers have been expanding and they have influence on activation in various markets increasingly. A call center’s work is known as one of the most demanding and stressful jobs. In this paper, we propose the fatigue detection system in order to detect burnout of call center agents in the case of a neck pain and upper back pain. Our proposed system is based on the computer vision technique combined skin color detection with the Viola-Jones object detector. To recognize the gesture of hand poses caused by stress sign, the YCbCr color space is used to detect the skin color region including face and hand poses around the area related to neck ache and upper back pain. A cascade of clarifiers by Viola-Jones is used for face recognition to extract from the skin color region. The detection of hand poses is given by the evaluation of neck pain and upper back pain by using skin color detection and face recognition method. The system performance is evaluated using two groups of dataset created in the laboratory to simulate call center environment. Our call center agent burnout detection system has been implemented by using a web camera and has been processed by MATLAB. From the experimental results, our system achieved 96.3% for upper back pain detection and 94.2% for neck pain detection.

Keywords: Call center agents, fatigue, skin color detection, face recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 994

Authors: B. Q. Huang, Tarik Rashid, M-T. Kechadi

Abstract:

this paper presents a multi-context recurrent network for time series analysis. While simple recurrent network (SRN) are very popular among recurrent neural networks, they still have some shortcomings in terms of learning speed and accuracy that need to be addressed. To solve these problems, we proposed a multi-context recurrent network (MCRN) with three different learning algorithms. The performance of this network is evaluated on some real-world application such as handwriting recognition and energy load forecasting. We study the performance of this network and we compared it to a very well established SRN. The experimental results showed that MCRN is very efficient and very well suited to time series analysis and its applications.

Keywords: Gradient descent method, recurrent neural network, learning algorithms, time series, BP

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3001

Authors: Yehjune Heo

Abstract:

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Keywords: Anti-spoofing, CNN, fingerprint recognition, GAN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 544

Authors: Hisham A. Elfergani, Ayad A. Abdalla, Ahmed R. Ballil

Abstract:

Acoustic Emission (AE) is one of the most effective non-destructive tests that can be used to detect the defect process as it is occurring. AE techniques can be used to monitor a wide range of structures and materials such as metals, non-metals and combinations of these when load is applied. The current work investigates the effectiveness and accuracy of TOA method in AE tests involving reinforced composite concrete-mortar structures. A series of experimental tests were performed using the Hsu-Neilson (H-N) source to study 2-D location accuracy using this method on concrete-mortar (400×400 mm) specimens. Four AE sensors (R3I – resonant frequency 30 kHz) were mounted to the mortar surface and six sources were performed at each point of preselected locations on the upper surface of the mortar. Results show that the TOA method can be used effectively to locate signals on composite concrete/mortar specimen and has high accuracy.

Keywords: Acoustic emission, time of arrival, composite materials, reinforced concrete.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 588

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125 Hz to 8000 Hz. The data contain patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R2 values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R2 values for the best models for KNN ranges from .89 to .95. The best imputation models received R2 between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our imputation models versus constant imputations by a two percent increase.

Keywords: Machine Learning, audiograms, data imputations, single imputations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 61

Authors: K. Diwakar, N. Vasudevan, C. Senthilpari

Abstract:

This paper presents MOSFET based analog to digital converter which is simple in design, has high resolution, and conversion rate better than dual slope ADC. It has no DAC which will limit the performance, no error in conversion, can operate for wide range of inputs and never become unstable. One of the industrial applications, where the proposed high resolution MOSFET ADC can be used is, for the positioning of control valves in a multi channel data acquisition and control system (DACS), using stepper motors as actuators of control valves. It is observed that in a DACS having ten control valves, 0.02% of positional accuracy of control valves can be achieved with the data update period of 250ms and with stepper motors of maximum pulse rate 20 Kpulses per sec. and minimum pulse width of 2.5 μsec. The reported accuracy so far by other authors is 0.2%, with update period of 255 ms and with 8 bit DAC. The accuracy in the proposed configuration is limited by the available precision stepper motor and not by the MOSFET based ADC.

Keywords: MOSFET based ADC, Actuators, Positional accuracy, Stepper Motors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2563

Authors: Ali Gholami

Abstract:

In this research the Preparation of Land use map of scanner LISS III satellite data, belonging to the IRS in the Aghche region in Isfahan province, is studied carefully. For this purpose, the IRS satellite images of August 2008 and various land preparation uses in region including rangelands, irrigation farming, dry farming, gardens and urban areas were separated and identified. Therefore, the GPS and Erdas Imaging software were used and three methods of Maximum Likelihood, Mahalanobis Distance and Minimum Distance were analyzed. In each of these methods, matrix error and Kappa index were calculated and accuracy of each method, based on percentages: 53.13, 56.64 and 48.44, were obtained respectively. Considering the low accuracy of these methods in separation of land preparation use, the visual interpretation of the map was used. Finally, regional visits of 150 points were noted at random and no error was observed. It shows that the map prepared by visual interpretation is in high accuracy. Although the probable errors due to visual interpretation and geometric correction might happen but the desired accuracy of the map which is more than 85 percent is reliable.

Keywords: Land use map, Aghche Region, Erdas Imagine, satellite images

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1524

Authors: Ravneet Kaur, Joydeep Acharya, Sudhanshu Gaur

Abstract:

Artificial Intelligence (AI) has the potential to transform manufacturing by improving shop floor processes such as production, maintenance and quality. However, industrial datasets are notoriously difficult to extract in a real-time, streaming fashion thus, negating potential AI benefits. The main example is some specialized industrial controllers that are operated by custom software which complicates the process of connecting them to an Information Technology (IT) based data acquisition network. Security concerns may also limit direct physical access to these controllers for data acquisition. To connect the Operational Technology (OT) data stored in these controllers to an AI application in a secure, reliable and available way, we propose a novel Industrial IoT (IIoT) solution in this paper. In this solution, we demonstrate how video cameras can be installed in a factory shop floor to continuously obtain images of the controller HMIs. We propose image pre-processing to segment the HMI into regions of streaming data and regions of fixed meta-data. We then evaluate the performance of multiple Optical Character Recognition (OCR) technologies such as Tesseract and Google vision to recognize the streaming data and test it for typical factory HMIs and realistic lighting conditions. Finally, we use the meta-data to match the OCR output with the temporal, domain-dependent context of the data to improve the accuracy of the output. Our IIoT solution enables reliable and efficient data extraction which will improve the performance of subsequent AI applications.

Keywords: Human machine interface, industrial internet of things, internet of things, optical character recognition, video analytic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 688

Authors: Paulo S. Caparelli, Eduardo Costa, Alexsandro S. Soares, Hipolito Barbosa

Abstract:

This paper presents an evolutionary method for designing electronic circuits and numerical methods associated with monitoring systems. The instruments described here have been used in studies of weather and climate changes due to global warming, and also in medical patient supervision. Genetic Programming systems have been used both for designing circuits and sensors, and also for determining sensor parameters. The authors advance the thesis that the software side of such a system should be written in computer languages with a strong mathematical and logic background in order to prevent software obsolescence, and achieve program correctness.

Keywords: Pattern recognition, evolutionary computation, biological signal, functional programming.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1704

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: Automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 739

Authors: Jing Wu, Wei Lv, Yibing Li, Yuanfan You

Abstract:

The separation of speech signals has become a research hotspot in the field of signal processing in recent years. It has many applications and influences in teleconferencing, hearing aids, speech recognition of machines and so on. The sounds received are usually noisy. The issue of identifying the sounds of interest and obtaining clear sounds in such an environment becomes a problem worth exploring, that is, the problem of blind source separation. This paper focuses on the under-determined blind source separation (UBSS). Sparse component analysis is generally used for the problem of under-determined blind source separation. The method is mainly divided into two parts. Firstly, the clustering algorithm is used to estimate the mixing matrix according to the observed signals. Then the signal is separated based on the known mixing matrix. In this paper, the problem of mixing matrix estimation is studied. This paper proposes an improved algorithm to estimate the mixing matrix for speech signals in the UBSS model. The traditional potential algorithm is not accurate for the mixing matrix estimation, especially for low signal-to noise ratio (SNR).In response to this problem, this paper considers the idea of an improved potential function method to estimate the mixing matrix. The algorithm not only avoids the inuence of insufficient prior information in traditional clustering algorithm, but also improves the estimation accuracy of mixing matrix. This paper takes the mixing of four speech signals into two channels as an example. The results of simulations show that the approach in this paper not only improves the accuracy of estimation, but also applies to any mixing matrix.

Keywords: Clustering algorithm, potential function, speech signal, the UBSS model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 629

Authors: Mohd Hasmadi Ismail, Kamaruzaman Jusoff

Abstract:

In order to develop forest management strategies in tropical forest in Malaysia, surveying the forest resources and monitoring the forest area affected by logging activities is essential. There are tremendous effort has been done in classification of land cover related to forest resource management in this country as it is a priority in all aspects of forest mapping using remote sensing and related technology such as GIS. In fact classification process is a compulsory step in any remote sensing research. Therefore, the main objective of this paper is to assess classification accuracy of classified forest map on Landsat TM data from difference number of reference data (200 and 388 reference data). This comparison was made through observation (200 reference data), and interpretation and observation approaches (388 reference data). Five land cover classes namely primary forest, logged over forest, water bodies, bare land and agricultural crop/mixed horticultural can be identified by the differences in spectral wavelength. Result showed that an overall accuracy from 200 reference data was 83.5 % (kappa value 0.7502459; kappa variance 0.002871), which was considered acceptable or good for optical data. However, when 200 reference data was increased to 388 in the confusion matrix, the accuracy slightly improved from 83.5% to 89.17%, with Kappa statistic increased from 0.7502459 to 0.8026135, respectively. The accuracy in this classification suggested that this strategy for the selection of training area, interpretation approaches and number of reference data used were importance to perform better classification result.

Keywords: Image Classification, Reference Data, Accuracy Assessment, Kappa Statistic, Forest Land Cover

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3101

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars, and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: Remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2019

Authors: Danni Cong, Meiping Wu, Hua Mu, Xiaofeng He, Junxiang Lian, Juliang Cao, Shaokun Cai, Hao Qin

Abstract:

Gravity field is of great significance in geoscience, national economy and national security, and gravitational gradient measurement has been extensively studied due to its higher accuracy than gravity measurement. Gravity gradient sensor, being one of core devices of the gravity gradient instrument, plays a key role in measuring accuracy. Therefore, this paper starts from analyzing the working principle of the gravity gradient sensor by Newton’s law, and then considers the relative motion between inertial and non-inertial systems to build a relatively adequate mathematical model, laying a foundation for the measurement error calibration, measurement accuracy improvement.

Keywords: Gravity gradient, accelerometer, gravity gradient sensor, single-axis rotation modulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1005

Authors: Ching-Tsan Chiang, Sheng-Jie Yang, Jing-Kai Huang

Abstract:

The purpose of this research is to develop and apply the RSCMAC to enhance the dynamic accuracy of Global Positioning System (GPS). GPS devices provide services of accurate positioning, speed detection and highly precise time standard for over 98% area on the earth. The overall operation of Global Positioning System includes 24 GPS satellites in space; signal transmission that includes 2 frequency carrier waves (Link 1 and Link 2) and 2 sets random telegraphic codes (C/A code and P code), on-earth monitoring stations or client GPS receivers. Only 4 satellites utilization, the client position and its elevation can be detected rapidly. The more receivable satellites, the more accurate position can be decoded. Currently, the standard positioning accuracy of the simplified GPS receiver is greatly increased, but due to affected by the error of satellite clock, the troposphere delay and the ionosphere delay, current measurement accuracy is in the level of 5~15m. In increasing the dynamic GPS positioning accuracy, most researchers mainly use inertial navigation system (INS) and installation of other sensors or maps for the assistance. This research utilizes the RSCMAC advantages of fast learning, learning convergence assurance, solving capability of time-related dynamic system problems with the static positioning calibration structure to improve and increase the GPS dynamic accuracy. The increasing of GPS dynamic positioning accuracy can be achieved by using RSCMAC system with GPS receivers collecting dynamic error data for the error prediction and follows by using the predicted error to correct the GPS dynamic positioning data. The ultimate purpose of this research is to improve the dynamic positioning error of cheap GPS receivers and the economic benefits will be enhanced while the accuracy is increased.

Keywords: Dynamic Error, GPS, Prediction, RSCMAC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1640

Authors: Amr Almaddah, Sadi Vural, Yasushi Mae, Kenichi Ohara, Tatsuo Arai

Abstract:

In this paper, we propose a robust face relighting technique by using spherical space properties. The proposed method is done for reducing the illumination effects on face recognition. Given a single 2D face image, we relight the face object by extracting the nine spherical harmonic bases and the face spherical illumination coefficients. First, an internal training illumination database is generated by computing face albedo and face normal from 2D images under different lighting conditions. Based on the generated database, we analyze the target face pixels and compare them with the training bootstrap by using pre-generated tiles. In this work, practical real time processing speed and small image size were considered when designing the framework. In contrast to other works, our technique requires no 3D face models for the training process and takes a single 2D image as an input. Experimental results on publicly available databases show that the proposed technique works well under severe lighting conditions with significant improvements on the face recognition rates.

Keywords: Face synthesis and recognition, Face illumination recovery, 2D spherical spaces, Vision for graphics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1725

Authors: Semeh Ben Salem, Sami Naouali, Moetez Sallami

Abstract:

The increasing amount of collected data has limited the performance of the current analyzing algorithms. Thus, developing new cost-effective algorithms in terms of complexity, scalability, and accuracy raised significant interests. In this paper, a modified effective k-means based algorithm is developed and experimented. The new algorithm aims to reduce the computational load without significantly affecting the quality of the clusterings. The algorithm uses the City Block distance and a new stop criterion to guarantee the convergence. Conducted experiments on a real data set show its high performance when compared with the original k-means version.

Keywords: Pattern recognition, partitional clustering, K-means clustering, Manhattan distance, terrorism data analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1321

Authors: Mahesh Pal

Abstract:

In recent years, a number of works proposing the combination of multiple classifiers to produce a single classification have been reported in remote sensing literature. The resulting classifier, referred to as an ensemble classifier, is generally found to be more accurate than any of the individual classifiers making up the ensemble. As accuracy is the primary concern, much of the research in the field of land cover classification is focused on improving classification accuracy. This study compares the performance of four ensemble approaches (boosting, bagging, DECORATE and random subspace) with a univariate decision tree as base classifier. Two training datasets, one without ant noise and other with 20 percent noise was used to judge the performance of different ensemble approaches. Results with noise free data set suggest an improvement of about 4% in classification accuracy with all ensemble approaches in comparison to the results provided by univariate decision tree classifier. Highest classification accuracy of 87.43% was achieved by boosted decision tree. A comparison of results with noisy data set suggests that bagging, DECORATE and random subspace approaches works well with this data whereas the performance of boosted decision tree degrades and a classification accuracy of 79.7% is achieved which is even lower than that is achieved (i.e. 80.02%) by using unboosted decision tree classifier.

Keywords: Ensemble learning, decision tree, remote sensingclassification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2541

Authors: Sanja Seljan, Ivan Dunđer

Abstract:

The paper presents combined automatic speech recognition (ASR) of English and machine translation (MT) for English and Croatian and Croatian-English language pairs in the domain of business correspondence. The first part presents results of training the ASR commercial system on English data sets, enriched by error analysis. The second part presents results of machine translation performed by free online tool for English and Croatian and Croatian-English language pairs. Human evaluation in terms of usability is conducted and internal consistency calculated by Cronbach's alpha coefficient, enriched by error analysis. Automatic evaluation is performed by WER (Word Error Rate) and PER (Position-independent word Error Rate) metrics, followed by investigation of Pearson’s correlation with human evaluation.

Keywords: Automatic machine translation, integrated language technologies, quality evaluation, speech recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2873

Authors: M. K. Jindal, G. S. Lehal, R. K. Sharma

Abstract:

Character segmentation is an important preprocessing step for text recognition. In degraded documents, existence of touching characters decreases recognition rate drastically, for any optical character recognition (OCR) system. In this paper we have proposed a complete solution for segmenting touching characters in all the three zones of printed Gurmukhi script. A study of touching Gurmukhi characters is carried out and these characters have been divided into various categories after a careful analysis. Structural properties of the Gurmukhi characters are used for defining the categories. New algorithms have been proposed to segment the touching characters in middle zone, upper zone and lower zone. These algorithms have shown a reasonable improvement in segmenting the touching characters in degraded printed Gurmukhi script. The algorithms proposed in this paper are applicable only to machine printed text. We have also discussed a new and useful technique to segment the horizontally overlapping lines.

Keywords: Character Segmentation, Middle Zone, Upper Zone, Lower Zone, Touching Characters, Horizontally Overlapping Lines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1661

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, Speech Emotion Recognition, longitudinal biomarker, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 190

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: Convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1349

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: Visual search, deep learning, convolutional neural network, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 784

Authors: H. El Ayech, A. Trabelsi

Abstract:

In this article we are going to discuss the improvement of the multi classes- classification problem using multi layer Perceptron. The considered approach consists in breaking down the n-class problem into two-classes- subproblems. The training of each two-class subproblem is made independently; as for the phase of test, we are going to confront a vector that we want to classify to all two classes- models, the elected class will be the strongest one that won-t lose any competition with the other classes. Rates of recognition gotten with the multi class-s approach by two-class-s decomposition are clearly better that those gotten by the simple multi class-s approach.

Keywords: Artificial neural network, letter-recognition, Multi class Classification, Multi Layer Perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1537

Authors: Jung-hoon Lee, Eung Tai Kim, Byung-hee Chang, In-hee Hwang, Dae-sung Lee

Abstract:

The accuracy of estimated stability and control derivatives of a light aircraft from flight test data were evaluated. The light aircraft, named ChangGong-91, is the first certified aircraft from the Korean government. The output error method, which is a maximum likelihood estimation technique and considers measurement noise only, was used to analyze the aircraft responses measures. The multi-step control inputs were applied in order to excite the short period mode for the longitudinal and Dutch-roll mode for the lateral-directional motion. The estimated stability/control derivatives of Chan Gong-91 were analyzed for the assessment of handling qualities comparing them with those of similar aircraft. The accuracy of the flight derivative estimates derived from flight test measurement was examined in engineering judgment, scatter and Cramer-Rao bound, which turned out to be satisfactory with minor defects..

Keywords: Light Aircraft, Flight Test, Accuracy, Engineering Judgment, Scatter, Cramer-Rao Bound

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1920

Authors: Supattra Aomumpai, Chutima Prommak

Abstract:

This paper presents a studyof the impact of reference node locations on the accuracy of the indoor positioning systems. In particular, we analyze the localization accuracy of the RSSI database mapping techniques, deploying on the IEEE 802.15.4 wireless networks. The results show that the locations of the reference nodes used in the positioning systems affect the signal propagation characteristics in the service area. Thisin turn affects the accuracy of the wireless indoor positioning system. We found that suitable location of reference nodes could reduce the positioning error upto 35 %.

Keywords: Indoor positioning systems, IEEE 802.15.4 wireless networks, Signal propagation characteristics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1447

Authors: Neeta Awasthy, J.P.Saini, D.S.Chauhan

Abstract:

ICA which is generally used for blind source separation problem has been tested for feature extraction in Speech recognition system to replace the phoneme based approach of MFCC. Applying the Cepstral coefficients generated to ICA as preprocessing has developed a new signal processing approach. This gives much better results against MFCC and ICA separately, both for word and speaker recognition. The mixing matrix A is different before and after MFCC as expected. As Mel is a nonlinear scale. However, cepstrals generated from Linear Predictive Coefficient being independent prove to be the right candidate for ICA. Matlab is the tool used for all comparisons. The database used is samples of ISOLET.

Keywords: Cepstral Coefficient, Distance measures, Independent Component Analysis, Linear Predictive Coefficients.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1917

Authors: Raymond Xu, Ashley Hua, Andrew Wang, Yuru Lin

Abstract:

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Keywords: Artificial intelligence, depression detection, facial emotion recognition, natural language processing, mental disorder.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1101

Authors: T. Anbu, K. Aravind Kumar

Abstract:

The road environment information is needed accurately for applications such as road maintenance and virtual 3D city modeling. Mobile laser scanning (MLS) produces dense point clouds from huge areas efficiently from which the road and its environment can be modeled in detail. Objects such as buildings, cars and trees are an important part of road environments. Different methods have been developed for detection of above such objects, but still there is a lack of accuracy due to the problems of illumination, environmental changes, and multiple objects with same features. In this work the comparison between different classifiers such as Multiclass SVM, kNN and Multiclass LDA for the road environment detection is analyzed. Finally the classification accuracy for kNN with LBP feature improved the classification accuracy as 93.3% than the other classifiers.

Keywords: Classifiers, feature extraction, mobile-based laser scanning, object location estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 745