Search results for: discriminate accuracy

Authors: Gheida J. Shahrour, Martin J. Russell

Abstract:

The 3D body movement signals captured during human-human conversation include clues not only to the content of people’s communication but also to their culture and personality. This paper is concerned with automatic extraction of this information from body movement signals. For the purpose of this research, we collected a novel corpus from 27 subjects, arranged them into groups according to their culture. We arranged each group into pairs and each pair communicated with each other about different topics. A state-of-art recognition system is applied to the problems of person, culture, and topic recognition. We borrowed modeling, classification, and normalization techniques from speech recognition. We used Gaussian Mixture Modeling (GMM) as the main technique for building our three systems, obtaining 77.78%, 55.47%, and 39.06% from the person, culture, and topic recognition systems respectively. In addition, we combined the above GMM systems with Support Vector Machines (SVM) to obtain 85.42%, 62.50%, and 40.63% accuracy for person, culture, and topic recognition respectively. Although direct comparison among these three recognition systems is difficult, it seems that our person recognition system performs best for both GMM and GMM-SVM, suggesting that inter-subject differences (i.e. subject’s personality traits) are a major source of variation. When removing these traits from culture and topic recognition systems using the Nuisance Attribute Projection (NAP) and the Intersession Variability Compensation (ISVC) techniques, we obtained 73.44% and 46.09% accuracy from culture and topic recognition systems respectively.

Keywords: person recognition, topic recognition, culture recognition, 3D body movement signals, variability compensation

Procedia PDF Downloads 527

Authors: Suman Som, Abhijit Maity, Sunil B. Daschakraborty, Sujit Chaudhuri, Manik Pradhan

Abstract:

Background: Helicobacter pylori is a common and important human pathogen and the primary cause of peptic ulcer disease and gastric cancer. Currently H. pylori infection is detected by both invasive and non-invasive way but the diagnostic accuracy is not up to the mark. Aim: To set up an optimal diagnostic cut-off value of 13C-Urea Breath Test to detect H. pylori infection and evaluate a novel c-PDR methodology to overcome of inconclusive grey zone. Materials and Methods: All 83 subjects first underwent upper-gastrointestinal endoscopy followed by rapid urease test and histopathology and depending on these results; we classified 49 subjects as H. pylori positive and 34 negative. After an overnight, fast patients are taken 4 gm of citric acid in 200 ml water solution and 10 minute after ingestion of the test meal, a baseline exhaled breath sample was collected. Thereafter an oral dose of 75 mg 13C-Urea dissolved in 50 ml water was given and breath samples were collected upto 90 minute for 15 minute intervals and analysed by laser based high precisional cavity enhanced spectroscopy. Results: We studied the excretion kinetics of 13C isotope enrichment (expressed as δDOB13C ‰) of exhaled breath samples and found maximum enrichment around 30 minute of H. pylori positive patients, it is due to the acid mediated stimulated urease enzyme activity and maximum acidification happened within 30 minute but no such significant isotopic enrichment observed for H. pylori negative individuals. Using Receiver Operating Characteristic (ROC) curve an optimal diagnostic cut-off value, δDOB13C ‰ = 3.14 was determined at 30 minute exhibiting 89.16% accuracy. Now to overcome grey zone problem we explore percentage dose of 13C recovered per hour, i.e. 13C-PDR (%/hr) and cumulative percentage dose of 13C recovered, i.e. c-PDR (%) in exhaled breath samples for the present 13C-UBT. We further explored the diagnostic accuracy of 13C-UBT by constructing ROC curve using c-PDR (%) values and an optimal cut-off value was estimated to be c-PDR = 1.47 (%) at 60 minute, exhibiting 100 % diagnostic sensitivity , 100 % specificity and 100 % accuracy of 13C-UBT for detection of H. pylori infection. We also elucidate the gastric emptying process of present 13C-UBT for H. pylori positive patients. The maximal emptying rate found at 36 minute and half empting time of present 13C-UBT was found at 45 minute. Conclusions: The present study exhibiting the importance of c-PDR methodology to overcome of grey zone problem in 13C-UBT for accurate determination of infection without any risk of diagnostic errors and making it sufficiently robust and novel method for an accurate and fast non-invasive diagnosis of H. pylori infection for large scale screening purposes.

Keywords: 13C-Urea breath test, c-PDR methodology, grey zone, Helicobacter pylori

Procedia PDF Downloads 297

Authors: Tanwarat Kajsongkram, Saowalux Rotamporn, Sirinat Limbunruang, Sirinan Thubthimthed.

Abstract:

High-Performance Liquid Chromatography (HPLC) method was developed and validated for simultaneous estimation of 6-Gingerol(6G) and 6-Shogaol(6S) in joint pain relief gel containing ginger extract. The chromatographic separation was achieved by using C18 column, 150 x 4.6mm i.d., 5μ Luna, mobile phase containing acetonitrile and water (gradient elution). The flow rate was 1.0 ml/min and the absorbance was monitored at 282 nm. The proposed method was validated in terms of the analytical parameters such as specificity, accuracy, precision, linearity, range, limit of detection (LOD), limit of quantification (LOQ), and determined based on the International Conference on Harmonization (ICH) guidelines. The linearity ranges of 6G and 6S were obtained over 20-60 and 6-18 µg/ml respectively. Good linearity was observed over the above-mentioned range with linear regression equation Y= 11016x- 23778 for 6G and Y = 19276x-19604 for 6S (x is concentration of analytes in μg/ml and Y is peak area). The value of correlation coefficient was found to be 0.9994 for both markers. The limit of detection (LOD) and limit of quantification (LOQ) for 6G were 0.8567 and 2.8555 µg/ml and for 6S were 0.3672 and 1.2238 µg/ml respectively. The recovery range for 6G and 6S were found to be 91.57 to 102.36 % and 84.73 to 92.85 % for all three spiked levels. The RSD values from repeated extractions for 6G and 6S were 3.43 and 3.09% respectively. The validation of developed method on precision, accuracy, specificity, linearity, and range were also performed with well-accepted results.

Keywords: ginger, 6-gingerol, HPLC, 6-shogaol

Procedia PDF Downloads 428

Authors: Peter W. Woodruff, Georgios Ponirakis, Reem Ibrahim, Amani Ahmed, Hoda Gad, Ioannis N. Petropoulos, Adnan Khan, Ahmed Elsotouhy, Surjith Vattoth, Mahmoud K. M. Alshawwaf, Mohamed Adil Shah Khoodoruth, Marwan Ramadan, Anjushri Bhagat, James Currie, Ziyad Mahfoud, Hanadi Al Hamad, Ahmed Own, Peter Haddad, Majid Alabdulla, Rayaz A. Malik

Abstract:

Introduction:- We aimed to test the hypothesis that, using corneal confocal microscopy (a non-invasive method for assessing corneal nerve fibre integrity), patients with schizophrenia would show neuronal abnormalities compared with healthy participants. Schizophrenia is a neurodevelopmental and progressive neurodegenerative disease, for which there are no validated biomarkers. Corneal confocal microscopy (CCM) is a non-invasive ophthalmic imaging biomarker that can be used to detect neuronal abnormalities in neuropsychiatric syndromes. Methods:- Patients with schizophrenia (DSM-V criteria) without other causes of peripheral neuropathy and healthy controls underwent CCM, vibration perception threshold (VPT) and sudomotor function testing. The diagnostic accuracy of CCM in distinguishing patients from controls was assessed using the area under the curve (AUC) of the Receiver Operating Characterstics (ROC) curve. Findings:- Participants with schizophrenia (n=17) and controls (n=38) with comparable age (35.7±8.5 vs 35.6±12.2, P=0.96) were recruited. Patients with schizophrenia had significantly higher body weight (93.9±25.5 vs 77.1±10.1, P=0.02), lower Low Density Lipoproteins (2.6±1.0 vs 3.4±0.7, P=0.02), but comparable systolic and diastolic blood pressure, HbA1c, total cholesterol, triglycerides and High Density Lipoproteins were comparable with control participants. Patients with schizophrenia had significantly lower corneal nerve fiber density (CNFD, fibers/mm2) (23.5±7.8 vs 35.6±6.5, p<0.0001), branch density (CNBD, branches/mm2) (34.4±26.9 vs 98.1±30.6, p<0.0001), and fiber length (CNFL, mm/mm2) (14.3±4.7 vs 24.2±3.9, p<0.0001) but no difference in VPT (6.1±3.1 vs 4.5±2.8, p=0.12) and electrochemical skin conductance (61.0±24.0 vs 68.9±12.3, p=0.23) compared with controls. The diagnostic accuracy of CNFD, CNBD and CNFL to distinguish patients with schizophrenia from healthy controls were, according to the AUC, (95% CI): 87.0% (76.8-98.2), 93.2% (84.2-102.3), 93.2% (84.4-102.1), respectively. Conclusion:- In conclusion, CCM can be used to help identify neuronal changes and has a high diagnostic accuracy to distinguish subjects with schizophrenia from healthy controls.

Keywords:

Procedia PDF Downloads 262

Authors: N. R. N. Idris, S. Baharom

Abstract:

A meta-analysis may be performed using aggregate data (AD) or an individual patient data (IPD). In practice, studies may be available at both IPD and AD level. In this situation, both the IPD and AD should be utilised in order to maximize the available information. Statistical advantages of combining the studies from different level have not been fully explored. This study aims to quantify the statistical benefits of including available IPD when conducting a conventional summary-level meta-analysis. Simulated meta-analysis were used to assess the influence of the levels of data on overall meta-analysis estimates based on IPD-only, AD-only and the combination of IPD and AD (mixed data, MD), under different study scenario. The percentage relative bias (PRB), root mean-square-error (RMSE) and coverage probability were used to assess the efficiency of the overall estimates. The results demonstrate that available IPD should always be included in a conventional meta-analysis using summary level data as they would significantly increased the accuracy of the estimates. On the other hand, if more than 80% of the available data are at IPD level, including the AD does not provide significant differences in terms of accuracy of the estimates. Additionally, combining the IPD and AD has moderating effects on the biasness of the estimates of the treatment effects as the IPD tends to overestimate the treatment effects, while the AD has the tendency to produce underestimated effect estimates. These results may provide some guide in deciding if significant benefit is gained by pooling the two levels of data when conducting meta-analysis.

Keywords: aggregate data, combined-level data, individual patient data, meta-analysis

Procedia PDF Downloads 361

Authors: Dhurgham Al-Karawi, Nisreen Polus, Shakir Al-Zaidi, Sabah Jassim

Abstract:

The management of COVID-19 patients based on chest imaging is emerging as an essential tool for evaluating the spread of the pandemic which has gripped the global community. It has already been used to monitor the situation of COVID-19 patients who have issues in respiratory status. There has been increase to use chest imaging for medical triage of patients who are showing moderate-severe clinical COVID-19 features, this is due to the fast dispersal of the pandemic to all continents and communities. This article demonstrates the development of machine learning techniques for the test of COVID-19 patients using Chest X-Ray (CXR) images in nearly real-time, to distinguish the COVID-19 infection with a significantly high level of accuracy. The testing performance has covered a combination of different datasets of CXR images of positive COVID-19 patients, patients with viral and bacterial infections, also, people with a clear chest. The proposed AI scheme successfully distinguishes CXR scans of COVID-19 infected patients from CXR scans of viral and bacterial based pneumonia as well as normal cases with an average accuracy of 94.43%, sensitivity 95%, and specificity 93.86%. Predicted decisions would be supported by visual evidence to help clinicians speed up the initial assessment process of new suspected cases, especially in a resource-constrained environment.

Keywords: COVID-19, chest x-ray scan, artificial intelligence, texture analysis, local binary pattern transform, Gabor filter

Procedia PDF Downloads 136

Authors: T. Almutairi, K. Naudi, N. Nairn, X. Ju, B. Eng, J. Whitters, A. Ayoub

Abstract:

Purpose: At present Cone Beam Computed Tomography (CBCT) imaging does not record dental morphology accurately due to the scattering produced by metallic restorations and the reported magnification. The aim of this pilot study is the development and validation of a new method for the replacement of the distorted dentition of CBCT scans with the dental image captured by the digital intraoral camera. Materials and Method: Six dried skulls with orthodontics brackets on the teeth were used in this study. Three intra-oral markers made of dental stone were constructed which were attached to orthodontics brackets. The skulls were CBCT scanned, and occlusal surface was captured using TRIOS® 3D intraoral scanner. Marker based and surface based registrations were performed to fuse the digital intra-oral scan(IOS) into the CBCT models. This produced a new composite digital model of the skull and dentition. The skulls were scanned again using the commercially accurate Laser Faro® arm to produce the 'gold standard' model for the assessment of the accuracy of the developed method. The accuracy of the method was assessed by measuring the distance between the occlusal surfaces of the new composite model and the 'gold standard' 3D model of the skull and teeth. The procedure was repeated a week apart to measure the reproducibility of the method. Results: The results showed no statistically significant difference between the measurements on the first and second occasions. The absolute mean distance between the new composite model and the laser model ranged between 0.11 mm to 0.20 mm. Conclusion: The dentition of the CBCT can be accurately replaced with the dental image captured by the intra-oral scanner to create a composite model. This method will improve the accuracy of orthognathic surgical prediction planning, with the final goal of the fabrication of a physical occlusal wafer without to guide orthognathic surgery and eliminate the need for dental impression.

Keywords: orthognathic surgery, superimposition, models, cone beam computed tomography

Procedia PDF Downloads 179

Authors: Yousif Mohamed Y. Abdallah

Abstract:

This is an experimental study deals with detection, measurement and analysis of the periodic physiological organ motion during external beam radiotherapy; to improve the accuracy of the radiation field placement, and to reduce the exposure of healthy tissue during radiation treatments. The importance of this study is to detect the maximum path of the mobile structures during radiotherapy delivery, to define the planning target volume (PTV) and irradiated volume during both inspiration and expiration period and to verify the target volume. In addition to its role to highlight the importance of the application of Intense Guided Radiotherapy (IGRT) methods in the field of radiotherapy. The results showed (body contour was equally (3.17 + 0.23 mm), for left lung displacement reading (2.56 + 0.99 mm) and right lung is (2.42 + 0.77 mm) which the radiation oncologist to take suitable countermeasures in case of significant errors. In addition, the use of the image registration technique for automatic position control is predicted potential motion. The motion ranged between 2.13 mm and 12.2 mm (low and high). In conclusion, individualized assessment of tumor mobility can improve the accuracy of target areas definition in patients undergo Sterostatic RT for stage I, II and III lung cancer (NSCLC). Definition of the target volume based on a single CT scan with a margin of 10 mm is clearly inappropriate.

Keywords: respiratory motion, external beam radiotherapy, image processing, lung

Procedia PDF Downloads 525

Authors: Mohammad Saber Rohi, Saghar Heidari

Abstract:

In this paper, we studied the pricing problem of American options under a regime-switching model with the possibility of a non-optimal exercise policy (early or late exercise time) which is called an irrational strategy. For this, we consider a Markovmodulated model for the dynamic of the underlying asset as an alternative model to the classical Balck-Scholes-Merton model (BSM) and an intensity-based model for the irrational strategy, to provide more realistic results for American option prices under the irrational behavior in real financial markets. Applying a partial differential equation (PDE) approach, the pricing problem of American options under regime-switching models can be formulated as coupled PDEs. To solve the resulting systems of PDEs in this model, we apply a finite element method as the numerical solving procedure to the resulting variational inequality. Under some appropriate assumptions, we establish the stability of the method and compare its accuracy to some recent works to illustrate the suitability of the proposed model and the accuracy of the applied numerical method for the pricing problem of American options under the regime-switching model with irrational behaviors.

Keywords: irrational exercise strategy, rationality parameter, regime-switching model, American option, finite element method, variational inequality

Procedia PDF Downloads 63

Authors: Qian Liu, Steve Furber

Abstract:

To explore how the brain may recognize objects in its general,accurate and energy-efficient manner, this paper proposes the use of a neuromorphic hardware system formed from a Dynamic Video Sensor~(DVS) silicon retina in concert with the SpiNNaker real-time Spiking Neural Network~(SNN) simulator. As a first step in the exploration on this platform a recognition system for dynamic hand postures is developed, enabling the study of the methods used in the visual pathways of the brain. Inspired by the behaviours of the primary visual cortex, Convolutional Neural Networks (CNNs) are modeled using both linear perceptrons and spiking Leaky Integrate-and-Fire (LIF) neurons. In this study's largest configuration using these approaches, a network of 74,210 neurons and 15,216,512 synapses is created and operated in real-time using 290 SpiNNaker processor cores in parallel and with 93.0% accuracy. A smaller network using only 1/10th of the resources is also created, again operating in real-time, and it is able to recognize the postures with an accuracy of around 86.4% -only 6.6% lower than the much larger system. The recognition rate of the smaller network developed on this neuromorphic system is sufficient for a successful hand posture recognition system, and demonstrates a much-improved cost to performance trade-off in its approach.

Keywords: spiking neural network (SNN), convolutional neural network (CNN), posture recognition, neuromorphic system

Procedia PDF Downloads 455

Authors: Amit Kumar, Amanpreet Chander, Ashish Sahani

Abstract:

This paper presents our recent work on real-time human activity detection based on the media pipe pipeline and machine learning algorithms. The proposed system can detect human activities, including running, jumping, squatting, bending to the left or right, and standing still. This is a robust solution for developing a yoga, dance, metaverse, and fitness application that checks for the correction of the pose without having any additional monitor like a personal trainer. MediaPipe solution offers an open-source cross-platform which utilizes a two-step detector-tracker ML pipeline for live detection of key landmarks on our body which can be used for motion data collection. The prediction of real-time poses uses a variety of machine learning techniques and different types of analysis. Without primarily relying on powerful desktop environments for inference, our method achieves real-time performance on the majority of contemporary mobile phones, desktops/laptops, Python, or even the web. Experimental results show that our method outperforms the existing method in terms of accuracy and real-time capability, achieving an accuracy of 99.92% on testing datasets.

Keywords: human activity detection, media pipe, machine learning, metaverse applications

Procedia PDF Downloads 162

Authors: Bandar Alahmadi, Manohar Mareboyana, Lethia Jackson

Abstract:

Today, there are many applications that are using computer vision models, such as face recognition, image classification, and object detection. The accuracy of these models is very important for the performance of these applications. One challenge that facing the computer vision models is the adversarial examples attack. In computer vision, the adversarial example is an image that is intentionally designed to cause the machine learning model to misclassify it. One of very well-known method that is used to attack the Convolution Neural Network (CNN) is Fast Gradient Sign Method (FGSM). The goal of this method is to find the perturbation that can fool the CNN using the gradient of the cost function of CNN. In this paper, we introduce a novel model that can attack Regional-Convolution Neural Network (R-CNN) that use FGSM. We first extract the regions that are detected by R-CNN, and then we resize these regions into the size of regular images. Then, we find the best perturbation of the regions that can fool CNN using FGSM. Next, we add the resulted perturbation to the attacked region to get a new region image that looks similar to the original image to human eyes. Finally, we placed the regions back to the original image and test the R-CNN with the attacked images. Our model could drop the accuracy of the R-CNN when we tested with Pascal VOC 2012 dataset.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 180

Authors: Farhad Alizadeh, Alireza Faregh Gharamaleki, Mojtaba Jalilzadeh, Houshang Gholami, Ali Akhoundzadeh

Abstract:

This study presented hybrid pre-processing approach along with a conceptual model to enhance the accuracy of river discharge prediction. In order to achieve this goal, Ensemble Empirical Mode Decomposition algorithm (EEMD), Discrete Wavelet Transform (DWT) and Mutual Information (MI) were employed as a hybrid pre-processing approach conjugated to Least Square Support Vector Machine (LSSVM). A conceptual strategy namely multi-station model was developed to forecast the Souris River discharge more accurately. The strategy used herein was capable of covering uncertainties and complexities of river discharge modeling. DWT and EEMD was coupled, and the feature selection was performed for decomposed sub-series using MI to be employed in multi-station model. In the proposed feature selection method, some useless sub-series were omitted to achieve better performance. Results approved efficiency of the proposed DWT-EEMD-MI approach to improve accuracy of multi-station modeling strategies.

Keywords: river stage-discharge process, LSSVM, discrete wavelet transform, Ensemble Empirical Decomposition Mode, multi-station modeling

Procedia PDF Downloads 167

Authors: Joseph C. Chen, Venkata Mohan Kudapa

Abstract:

Development of two real-time surface roughness (Ra) prediction systems for milling operations was attempted. The systems used not only cutting parameters, such as feed rate and spindle speed, but also the cutting current generated and corrected by a clamp type energy sensor. Two different approaches were developed. First, a fuzzy inference system (FIS), in which the fuzzy logic rules are generated by experts in the milling processes, was used to conduct prediction modeling using current cutting data. Second, a neuro-fuzzy system (ANFIS) was explored. Neuro-fuzzy systems are adaptive techniques in which data are collected on the network, processed, and rules are generated by the system. The inference system then uses these rules to predict Ra as the output. Experimental results showed that the parameters of spindle speed, feed rate, depth of cut, and input current variation could predict Ra. These two systems enable the prediction of Ra during the milling operation with an average of 91.83% and 94.48% accuracy by FIS and ANFIS systems, respectively. Statistically, the ANFIS system provided better prediction accuracy than that of the FIS system.

Keywords: surface roughness, input current, fuzzy logic, neuro-fuzzy, milling operations

Procedia PDF Downloads 128

Authors: Juzhong Tan, William Kerr

Abstract:

Roasting is one critical procedure in chocolate processing, where special favors are developed, moisture content is decreased, and better processing properties are developed. Therefore, determination of roasting degree of cocoa bean is important for chocolate manufacturers to ensure the quality of chocolate products, and it also decides the commercial value of cocoa beans collected from cocoa farmers. The roasting degree of cocoa beans currently relies on human specialists, who sometimes are biased, and chemical analysis, which take long time and are inaccessible to many manufacturers and farmers. In this study, a self-made electronic nose system consists of gas sensors (TGS 800 and 2000 series) was used to detecting the gas generated by cocoa beans with a different roasting degree (0min, 20min, 30min, and 40min) and the signals collected by gas sensors were used to train a three-layers ANN. Chemical analysis of the graded beans was operated by traditional GC-MS system and the contents of volatile chemical compounds were used to train another ANN as a reference to electronic nosed signals trained ANN. Both trained ANN were used to predict cocoa beans with a different roasting degree for validation. The best accuracy of grading achieved by electronic nose signals trained ANN (using signals from TGS 813 826 820 880 830 2620 2602 2610) turned out to be 96.7%, however, the GC trained ANN got the accuracy of 83.8%.

Keywords: artificial neutron network, cocoa bean, electronic nose, roasting

Procedia PDF Downloads 219

Authors: Azita Ramezani, Atousa Ramezani

Abstract:

In the ever-escalating landscape of windows malware the necessity for pioneering defense strategies turns into undeniable this study introduces an avant-garde approach fusing the capabilities of clustering random forests and support vector machines SVM to combat the intricate web of cyber threats our fusion model triumphs with a staggering accuracy of 98.67 and an equally formidable f1 score of 98.68 a testament to its effectiveness in the realm of windows malware defense by deciphering the intricate patterns within malicious code our model not only raises the bar for detection precision but also redefines the paradigm of cybersecurity preparedness this breakthrough underscores the potential embedded in the fusion of diverse analytical methodologies and signals a paradigm shift in fortifying against the relentless evolution of windows malicious threats as we traverse through the dynamic cybersecurity terrain this research serves as a beacon illuminating the path toward a resilient future where innovative fusion models stand at the forefront of cyber threat defense.

Keywords: fusion models, cyber threat defense, windows malware, clustering, random forests, support vector machines (SVM), accuracy, f1-score, cybersecurity, malicious code detection

Procedia PDF Downloads 58

Authors: Gang Li, Ghulam Mubashar Hassan, Arcady Dyskin, Cara MacNish

Abstract:

Digital image correlation (DIC) is a contactless full-field displacement and strain reconstruction technique commonly used in the field of experimental mechanics. Comparing with physical measuring devices, such as strain gauges, which only provide very restricted coverage and are expensive to deploy widely, the DIC technique provides the result with full-field coverage and relative high accuracy using an inexpensive and simple experimental setup. It is very important to study the natural patterns effect on the DIC technique because the preparation of the artificial patterns is time consuming and hectic process. The objective of this research is to study the effect of using images having natural pattern on the performance of DIC. A systematical simulation method is used to build simulated deformed images used in DIC. A parameter (subset size) used in DIC can have an effect on the processing and accuracy of DIC and even cause DIC to failure. Regarding to the picture parameters (correlation coefficient), the higher similarity of two subset can lead the DIC process to fail and make the result more inaccurate. The pictures with good and bad quality for DIC methods have been presented and more importantly, it is a systematic way to evaluate the quality of the picture with natural patterns before they install the measurement devices.

Keywords: Digital Image Correlation (DIC), deformation simulation, natural pattern, subset size

Procedia PDF Downloads 407

Authors: Peter U. Eze, P. Udaya, Robin J. Evans

Abstract:

Data hiding can be achieved by Steganography or invisible digital watermarking. For digital watermarking, both accurate retrieval of the embedded watermark and the integrity of the cover image are important. Medical image security in Teleradiology is one of the applications where the embedded patient record needs to be extracted with accuracy as well as the medical image integrity verified. In this research paper, the Constant Correlation Spread Spectrum digital watermarking for medical image tamper detection and accurate embedded watermark retrieval is introduced. In the proposed method, a watermark bit from a patient record is spread in a medical image sub-block such that the correlation of all watermarked sub-blocks with a spreading code, W, would have a constant value, p. The constant correlation p, spreading code, W and the size of the sub-blocks constitute the secret key. Tamper detection is achieved by flagging any sub-block whose correlation value deviates by more than a small value, ℇ, from p. The major features of our new scheme include: (1) Improving watermark detection accuracy for high-pixel depth medical images by reducing the Bit Error Rate (BER) to Zero and (2) block-level tamper detection in a single computational process with simultaneous watermark detection, thereby increasing utility with the same computational cost.

Keywords: Constant Correlation, Medical Image, Spread Spectrum, Tamper Detection, Watermarking

Procedia PDF Downloads 178

Authors: Hendri Purwadi, Christine McCloud

Abstract:

Triage is a complex decision-making process that aims to categorize a victim’s level of acuity and the need for medical assistance. Two common triage systems have been widely used in Mass Casualty Incidents (MCIs) and disaster situation are START (Simple triage algorithm and rapid treatment) and SALT (sort, asses, lifesaving, intervention, and treatment/transport). There is currently controversy regarding the effectiveness of SALT over START triage system. This systematic review aims to investigate and compare the effectiveness between SALT and START triage system in disaster and MCIs setting. Literatures were searched via systematic search strategy from 2009 until 2019 in PubMed, Cochrane Library, CINAHL, Scopus, Science direct, Medlib, ProQuest. This review included simulated-based and medical record -based studies investigating the accuracy and applicability of SALT and START triage systems of adult and children population during MCIs and disaster. All type of studies were included. Joana Briggs institute critical appraisal tools were used to assess the quality of reviewed studies. As a result, 1450 articles identified in the search, 10 articles were included. Four themes were identified by review, they were accuracy, under-triage, over-triage and time to triage per individual victim. The START triage system has a wide range and inconsistent level of accuracy compared to SALT triage system (44% to 94. 2% of START compared to 70% to 83% of SALT). The under-triage error of START triage system ranged from 2.73% to 20%, slightly lower than SALT triage system (7.6 to 23.3%). The over-triage error of START triage system was slightly greater than SALT triage system (START ranged from 2% to 53% compared to 2% to 22% of SALT). The time for applying START triage system was faster than SALT triage system (START was 70-72.18 seconds compared to 78 second of SALT). Consequently; The START triage system has lower level of under-triage error and faster than SALT triage system in classifying victims of MCIs and disaster whereas SALT triage system is known slightly more accurate and lower level of over-triage. However, the magnitude of these differences is relatively small, and therefore the effect on the patient outcomes is not significance. Hence, regardless of the triage error, either START or SALT triage system is equally effective to triage victims of disaster and MCIs.

Keywords: disaster, effectiveness, mass casualty incidents, START triage system, SALT triage system

Procedia PDF Downloads 122

Authors: Christophe Spaas, Lies Pottel, Joke De Ceulaer, Johan Abeloos, Philippe Lamoral, Tom De Backer, Calix De Clercq

Abstract:

We aimed to evaluate the accuracy of an in-house developed low-cost computer-assisted surgery (CAS) protocol for osseous free flap mandibular reconstruction. All patients who underwent primary or secondary mandibular reconstruction with a free (solely or composite) osseous flap, either a fibula free flap or iliac crest free flap, between January 2014 and December 2017 were evaluated. The low-cost protocol consisted out of a virtual surgical planning, a prebend custom reconstruction plate and an individualized free flap positioning guide. The accuracy of the protocol was evaluated through comparison of the postoperative outcome with the 3D virtual planning, based on measurement of the following parameters: intercondylar distance, mandibular angle (axial and sagittal), inner angular distance, anterior-posterior distance, length of the fibular/iliac crest segments and osteotomy angles. A statistical analysis of the obtained values was done. Virtual 3D surgical planning and cutting guide design were performed with Proplan CMF® software (Materialise, Leuven, Belgium) and IPS Gate (KLS Martin, Tuttlingen, Germany). Segmentation of the DICOM data as well as outcome analysis were done with BrainLab iPlan® Software (Brainlab AG, Feldkirchen, Germany). A cost analysis of the protocol was done. Twenty-two patients (11 fibula /11 iliac crest) were included and analyzed. Based on voxel-based registration on the cranial base, 3D virtual planning landmark parameters did not significantly differ from those measured on the actual treatment outcome (p-values >0.05). A cost evaluation of the in-house developed CAS protocol revealed a 1750 euro cost reduction in comparison with a standard CAS protocol with a patient-specific reconstruction plate. Our results indicate that an accurate transfer of the planning with our in-house developed low-cost CAS protocol is feasible at a significant lower cost.

Keywords: CAD/CAM, computer-assisted surgery, low-cost, mandibular reconstruction

Procedia PDF Downloads 131

Authors: Ali J. Ghandour, Houssam A. Krayem, Abedelkarim A. Jezzini

Abstract:

High-resolution satellite images and remote sensing can provide global information in a fast way compared to traditional methods of data collection. Under such high resolution, a road is not a thin line anymore. Objects such as cars and trees are easily identifiable. Automatic vehicles enumeration can be considered one of the most important applications in traffic management. In this paper, autonomous vehicle detection and classification approach in highway environment is proposed. This approach consists mainly of three stages: (i) first, a set of preprocessing operations are applied including soil, vegetation, water suppression. (ii) Then, road networks detection and delineation is implemented using built-up area index, followed by several morphological operations. This step plays an important role in increasing the overall detection accuracy since vehicles candidates are objects contained within the road networks only. (iii) Multi-level Otsu segmentation is implemented in the last stage, resulting in vehicle detection and classification, where detected vehicles are classified into cars and trucks. Accuracy assessment analysis is conducted over different study areas to show the great efficiency of the proposed method, especially in highway environment.

Keywords: remote sensing, object identification, vehicle and road extraction, vehicle and road features-based classification

Procedia PDF Downloads 219

Authors: Rahmi Kafadar, Levent Genc

Abstract:

In present study, it was aimed to determine potential agricultural lands (PALs) in Gokceada (Imroz) Island of Canakkale province, Turkey. Seven-band Landsat 8 OLI images acquired on July 12 and August 13, 2013, and their 14-band combination image were used to identify current Land Use Land Cover (LULC) status. Principal Component Analysis (PCA) was applied to three Landsat datasets in order to reduce the correlation between the bands. A total of six Original and PCA images were classified using supervised classification method to obtain the LULC maps including 6 main classes (“Forest”, “Agriculture”, “Water Surface”, “Residential Area-Bare Soil”, “Reforestation” and “Other”). Accuracy assessment was performed by checking the accuracy of 120 randomized points for each LULC maps. The best overall accuracy and Kappa statistic values (90.83%, 0.8791% respectively) were found for PCA images which were generated from 14-bands combined images called 3-B/JA. Digital Elevation Model (DEM) with 15 m spatial resolution (ASTER) was used to consider topographical characteristics. Soil properties were obtained by digitizing 1:25000 scaled soil maps of rural services directorate general. Potential Agricultural Lands (PALs) were determined using Geographic information Systems (GIS). Procedure was applied considering that “Other” class of LULC map may be used for agricultural purposes in the future properties. Overlaying analysis was conducted using Slope (S), Land Use Capability Class (LUCC), Other Soil Properties (OSP) and Land Use Capability Sub-Class (SUBC) properties. A total of 901.62 ha areas within “Other” class (15798.2 ha) of LULC map were determined as PALs. These lands were ranked as “Very Suitable”, “Suitable”, “Moderate Suitable” and “Low Suitable”. It was determined that the 8.03 ha were classified as “Very Suitable” while 18.59 ha as suitable and 11.44 ha as “Moderate Suitable” for PALs. In addition, 756.56 ha were found to be “Low Suitable”. The results obtained from this preliminary study can serve as basis for further studies.

Keywords: digital elevation model (DEM), geographic information systems (GIS), gokceada (Imroz), lANDSAT 8 OLI-TIRS, land use land cover (LULC)

Procedia PDF Downloads 344

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 311

Authors: Nonlapun Meenil, Pisitpong Intarapong, Thitima Wongsheree, Pranchalee Samanpiboon

Abstract:

In Thailand, once pineapples are harvested, they must be classified into two classes based on their sweetness: sweet and unsweet. This paper has studied and developed the assessment of internal quality of pineapples using a low-cost compact spectroscopy sensor according to the Spectroscopy approach and Neural Network (NN). During the experiments, Batavia pineapples were utilized, generating 100 samples. The extracted pineapple juice of each sample was used to determine the Soluble Solid Content (SSC) labeling into sweet and unsweet classes. In terms of experimental equipment, the sensor cover was specifically designed to install the sensor and light source to read the reflectance at a five mm depth from pineapple flesh. By using a spectroscopy sensor, data on visible and near-infrared reflectance (Vis-NIR) were collected. The NN was used to classify the pineapple classes. Before the classification step, the preprocessing methods, which are Class balancing, Data shuffling, and Standardization were applied. The 510 nm and 900 nm reflectance values of the middle parts of pineapples were used as features of the NN. With the Sequential model and Relu activation function, 100% accuracy of the training set and 76.67% accuracy of the test set were achieved. According to the abovementioned information, using a low-cost compact spectroscopy sensor has achieved favorable results in classifying the sweetness of the two classes of pineapples.

Keywords: neural network, pineapple, soluble solid content, spectroscopy

Procedia PDF Downloads 59

Authors: Flavio Cordeiro Fontanella, Asla Medeiros e Sá, Moacyr Alvim Horta Barbosa da Silva

Abstract:

In the present work, we analyse the performance of football results forecasting models. In order to do so, we have performed the data collection from eight different forecasting models during the 2021 Brazilian football season. First, we guide the analysis through visual representations of the data, designed to highlight the most prominent features and enhance the interpretation of differences and similarities between the models. We propose using a 2-simplex triangle to investigate visual patterns from the results forecasting models. Next, we compute the expected points for every team playing in the championship and compare them to the final league standings, revealing interesting contrasts between actual to expected performances. Then, we evaluate forecasts’ accuracy using the Ranked Probability Score (RPS); models comparison accounts for tiny scale differences that may become consistent in time. Finally, we observe that the Wisdom of Crowds principle can be appropriately applied in the context, driving into a discussion of results forecasts usage in practice. This paper’s primary goal is to encourage football forecasts’ performance discussion. We hope to accomplish it by presenting appropriate criteria and easy-to-understand visual representations that can point out the relevant factors of the subject.

Keywords: accuracy evaluation, Brazilian championship, football results forecasts, forecasting models, visual analysis

Procedia PDF Downloads 85

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 76

Authors: Rudi Hartono, Bambang Purwanto

Abstract:

The translation quality of food and drink labels from Indonesian into English is poor because the translation is not accurate, less natural, and difficult to read. The label translation can be found in some cans packages of food and drink products produced and marketed by several companies in Indonesia. If this problem is left unchecked, it will lead to a misunderstanding on the translation results and make consumers confused. This study was conducted to analyze the translation errors on food and drink products labels and formulate the solution for the better translation quality. The research design was the evaluation research with a holistic criticism approach. The data used were words, phrases, and sentences translated from Indonesian to English language printed on food and drink product labels. The data were processed by using Interactive Model Analysis that carried out three main steps: collecting, classifying, and verifying data. Furthermore, the data were analyzed by using content analysis to view the accuracy, naturalness, and readability of translation. The results showed that the translation quality of food and drink product labels from Indonesian to English has the level of accuracy (60%), level of naturalness (50%), and level readability (60%). This fact needs a help to create an effective strategy for translating food and drink product labels later.

Keywords: translation quality, food and drink product labels, a holistic criticism approach, interactive model, content analysis

Procedia PDF Downloads 352

Authors: Jiaqi Dong, Qing-Hua Qin, Yi Xiao

Abstract:

Some of the most fundamental challenges of elastic metamaterials (EMMs) optimization can be attributed to the high consumption of computational power resulted from finite element analysis (FEA) simulations that render the optimization process inefficient. Furthermore, due to the inherent mesh dependence of FEA, minuscule geometry features, which often emerge during the later stages of optimization, induce very fine elements, resulting in enormously high time consumption, particularly when repetitive solutions are needed for computing the objective function. In this study, a surrogate modelling algorithm is developed to reduce computational time in structural optimization of EMMs. The surrogate model is constructed based on a multilayer feedforward artificial neural network (ANN) architecture, trained with prepopulated eigenfrequency data prepopulated from FEA simulation and optimized through regime selection with genetic algorithm (GA) to improve its accuracy in predicting the location and width of the primary elastic band gap. With the optimized ANN surrogate at the core, a Nelder-Mead (NM) algorithm is established and its performance inspected in comparison to the FEA solution. The ANNNM model shows remarkable accuracy in predicting the band gap width and a reduction of time consumption by 47%.

Keywords: artificial neural network, machine learning, mechanical metamaterials, Nelder-Mead optimization

Procedia PDF Downloads 119

Authors: Anjalika Fernando, Banuka Athuraliya

Abstract:

This paper presents a comprehensive approach for converting Sinhala Sign Language (SSL) into grammatically correct sentences using Natural Language Processing (NLP) techniques in real-time. While previous studies have explored various aspects of SSL translation, the research gap lies in the absence of grammar checking for SSL. This work aims to bridge this gap by proposing a two-stage methodology that leverages deep learning models to detect signs and translate them into coherent sentences, ensuring grammatical accuracy. The first stage of the approach involves the utilization of a Long Short-Term Memory (LSTM) deep learning model to recognize and interpret SSL signs. By training the LSTM model on a dataset of SSL gestures, it learns to accurately classify and translate these signs into textual representations. The LSTM model achieves a commendable accuracy rate of 94%, demonstrating its effectiveness in accurately recognizing and translating SSL gestures. Building upon the successful recognition and translation of SSL signs, the second stage of the methodology focuses on improving the grammatical correctness of the translated sentences. The project employs a Neural Machine Translation (NMT) architecture, consisting of an encoder and decoder with LSTM components, to enhance the syntactical structure of the generated sentences. By training the NMT model on a parallel corpus of Sinhala wrong sentences and their corresponding grammatically correct translations, it learns to generate coherent and grammatically accurate sentences. The NMT model achieves an impressive accuracy rate of 98%, affirming its capability to produce linguistically sound translations. The proposed approach offers significant contributions to the field of SSL translation and grammar correction. Addressing the critical issue of grammar checking, it enhances the usability and reliability of SSL translation systems, facilitating effective communication between hearing-impaired and non-sign language users. Furthermore, the integration of deep learning techniques, such as LSTM and NMT, ensures the accuracy and robustness of the translation process. This research holds great potential for practical applications, including educational platforms, accessibility tools, and communication aids for the hearing-impaired. Furthermore, it lays the foundation for future advancements in SSL translation systems, fostering inclusive and equal opportunities for the deaf community. Future work includes expanding the existing datasets to further improve the accuracy and generalization of the SSL translation system. Additionally, the development of a dedicated mobile application would enhance the accessibility and convenience of SSL translation on handheld devices. Furthermore, efforts will be made to enhance the current application for educational purposes, enabling individuals to learn and practice SSL more effectively. Another area of future exploration involves enabling two-way communication, allowing seamless interaction between sign-language users and non-sign-language users.In conclusion, this paper presents a novel approach for converting Sinhala Sign Language gestures into grammatically correct sentences using NLP techniques in real time. The two-stage methodology, comprising an LSTM model for sign detection and translation and an NMT model for grammar correction, achieves high accuracy rates of 94% and 98%, respectively. By addressing the lack of grammar checking in existing SSL translation research, this work contributes significantly to the development of more accurate and reliable SSL translation systems, thereby fostering effective communication and inclusivity for the hearing-impaired community

Keywords: Sinhala sign language, sign Language, NLP, LSTM, NMT

Procedia PDF Downloads 86

Authors: Burçin Saltık, Levent Genç

Abstract:

In this study, it was aimed to determine a route for identification of rice cultivation areas within Thrace and Marmara regions of Turkey using remote sensing and GIS. Landsat 8 (OLI-TIRS) imageries acquired in production season of 2013 with 181/32 Path/Row number were used. Four different seasonal images were generated utilizing original bands and different transformation techniques. All images were classified individually using supervised classification techniques and Land Use Land Cover Maps (LULC) were generated with 8 classes. Areas (ha, %) of each classes were calculated. In addition, district-based rice distribution maps were developed and results of these maps were compared with Turkish Statistical Institute (TurkSTAT; TSI)’s actual rice cultivation area records. Accuracy assessments were conducted, and most accurate map was selected depending on accuracy assessment and coherency with TSI results. Additionally, rice areas on over 4° slope values were considered as mis-classified pixels and they eliminated using slope map and GIS tools. Finally, randomized rice zones were selected to obtain maximum-minimum value ranges of each date (May, June, July, August, September images separately) NDVI, LSWI, and LST images to test whether they may be used for rice area determination via raster calculator tool of ArcGIS. The most accurate classification for rice determination was obtained from seasonal LSWI LULC map, and considering TSI data and accuracy assessment results and mis-classified pixels were eliminated from this map. According to results, 83151.5 ha of rice areas exist within study area. However, this result is higher than TSI records with an area of 12702.3 ha. Use of maximum-minimum range of rice area NDVI, LSWI, and LST was tested in Meric district. It was seen that using the value ranges obtained from July imagery, gave the closest results to TSI records, and the difference was only 206.4 ha. This difference is normal due to relatively low resolution of images. Thus, employment of images with higher spectral, spatial, temporal and radiometric resolutions may provide more reliable results.

Keywords: landsat 8 (OLI-TIRS), LST, LSWI, LULC, NDVI, rice

Procedia PDF Downloads 213