Search results for: object based classification

Authors: Silvia Portarena, Chiara Anselmi, Chiara Baldacchini, Enrico Brugnoli

Abstract:

Extra virgin olive oil (EVOO) is a complex matrix mainly composed by fatty acid and other minor compounds, among which carotenoids are well known for their antioxidative function that is a key mechanism of protection against cancer, cardiovascular diseases, and macular degeneration in humans. EVOO composition in terms of such constituents is generally the result of a complex combination of genetic, agronomical and environmental factors. To selectively improve the quality of EVOOs, the role of each factor on its biochemical composition need to be investigated. By selecting fruits from four different cultivars similarly grown and harvested, it was demonstrated that Raman spectroscopy, combined with chemometric analysis, is able to discriminate the different cultivars, also as a function of the harvest date, based on the relative content and composition of fatty acid and carotenoids. In particular, a correct classification up to 94.4% of samples, according to the cultivar and the maturation stage, was obtained. Moreover, by using gas chromatography and high-performance liquid chromatography as reference techniques, the Raman spectral features further allowed to build models, based on partial least squares regression, that were able to predict the relative amount of the main fatty acids and the main carotenoids in EVOO, with high coefficients of determination. Besides genetic factors, climatic parameters, such as light exposition, distance from the sea, temperature, and amount of precipitations could have a strong influence on EVOO composition of both major and minor compounds. This suggests that the Raman spectra could act as a specific fingerprint for the geographical discrimination and authentication of EVOO. To understand the influence of environment on EVOO Raman spectra, samples from seven regions along the Italian coasts were selected and analyzed. In particular, it was used a dual approach combining Raman spectroscopy and isotope ratio mass spectrometry (IRMS) with principal component and linear discriminant analysis. A correct classification of 82% EVOO based on their regional geographical origin was obtained. Raman spectra were obtained by Super Labram spectrometer equipped with an Argon laser (514.5 nm wavelenght). Analyses of stable isotope content ratio were performed using an isotope ratio mass spectrometer connected to an elemental analyzer and to a pyrolysis system. These studies demonstrate that RR spectroscopy is a valuable and useful technique for the analysis of EVOO. In combination with statistical analysis, it makes possible the assessment of specific samples’ content and allows for classifying oils according to their geographical and varietal origin.

Keywords: authentication, chemometrics, olive oil, raman spectroscopy

Procedia PDF Downloads 332

Authors: Mohammed Salahat, Steve Wade

Abstract:

This paper presents and compares the SSDDD “Systematic Soft Domain Driven Design Framework” to DDD “Domain Driven Design Framework” as a soft system approach of information systems development. The framework use SSM as a guiding methodology within which we have embedded a sequence of design tasks based on the UML leading to the implementation of a software system using the Naked Objects framework. This framework has been used in action research projects that have involved the investigation and modelling of business processes using object-oriented domain models and the implementation of software systems based on those domain models. Within this framework, Soft Systems Methodology (SSM) is used as a guiding methodology to explore the problem situation and to develop the domain model using UML for the given business domain. The framework is proposed and evaluated in our previous works, a comparison between SSDDD and DDD is presented in this paper, to show how SSDDD improved DDD as an approach to modelling and implementing business domain perspectives for Information Systems Development. The comparison process, the results, and the improvements are presented in the following sections of this paper.

Keywords: domain-driven design, soft domain-driven design, naked objects, soft language

Procedia PDF Downloads 298

Authors: Guenther Schuh, Michael Riesener, Jan Kantelberg

Abstract:

Due to the fugacity of markets and the reduction of product lifecycles, manufacturing companies from high-wage countries are nowadays faced with the challenge to place more innovative products within even shorter development time on the market. At the same time, volatile customer requirements have to be satisfied in order to successfully differentiate from market competitors. One potential approach to address the explained challenges is provided by agile values and principles. These agile values and principles already proofed their success within software development projects in the form of management frameworks like Scrum or concrete procedure models such as Extreme Programming or Crystal Clear. Those models lead to significant improvements regarding quality, costs and development time and are therefore used within most software development projects. Motivated by the success within the software industry, manufacturing companies have tried to transfer agile mechanisms of action to the development of hardware products ever since. Though first empirical studies show similar effects in the agile development of hardware products, no comprehensive procedure model for the design of development iterations has been developed for hardware development yet due to different constraints of the domains. For this reason, this paper focusses on the design of agile product development processes by transferring mechanisms of action used in agile software development towards product development. This is conducted by decomposing the individual systems 'product development' and 'agile software development' into relevant elements and symbiotically composing the elements of both systems in respect of the design of agile product development processes afterwards. In a first step, existing product development processes are described following existing approaches of the system theory. By analyzing existing case studies from industrial companies as well as academic approaches, characteristic objectives, activities and artefacts are identified within a target-, action- and object-system. In partial model two, mechanisms of action are derived from existing procedure models of agile software development. These mechanisms of action are classified in a superior strategy level, in a system level comprising characteristic, domain-independent activities and their cause-effect relationships as well as in an activity-based element level. Within partial model three, the influence of the identified agile mechanism of action towards the characteristic system elements of product development processes is analyzed. For this reason, target-, action- and object-system of the product development are compared with the strategy-, system- and element-level of agile mechanism of action by using the graph theory. Furthermore, the necessity of existence of activities within iteration can be determined by defining activity-specific degrees of freedom. Based on this analysis, agile product development processes are designed in form of different types of iterations within a last step. By defining iteration-differentiating characteristics and their interdependencies, a logic for the configuration of activities, their form of execution as well as relevant artefacts for the specific iteration is developed. Furthermore, characteristic types of iteration for the agile product development are identified.

Keywords: activity-based process model, agile mechanisms of action, agile product development, degrees of freedom

Procedia PDF Downloads 207

Authors: Yuanqing Li, Changyi Lei, Zhaopeng Xue, Zhuo Zheng, Yanbo Long

Abstract:

In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.

Keywords: agricultural object detection, deep learning, machine vision, YOLO family

Procedia PDF Downloads 198

Authors: Jia-Chao Wang

Abstract:

A model of the universe without invoking space expansion is proposed to explain the observed redshift-distance relation and the cosmic microwave background radiation (CMB). The main hypothesized feature of the model is that photons traveling in space interact with the CMB photon gas. This interaction causes the photons to gradually lose energy through dissipation and, therefore, experience redshift. The interaction also causes some of the photons to be scattered off their track toward an observer and, therefore, results in beam intensity attenuation. As observed, the CMB exists everywhere in space and its photon density is relatively high (about 410 per cm³). The small average energy of the CMB photons (about 6.3×10⁻⁴ eV) can reduce the energies of traveling photons gradually and will not alter their momenta drastically as in, for example, Compton scattering, to totally blur the images of distant objects. An object moving through a thermalized photon gas, such as the CMB, experiences a drag. The cause is that the object sees a blue shifted photon gas along the direction of motion and a redshifted one in the opposite direction. An example of this effect can be the observed CMB dipole: The earth travels at about 368 km/s (600 km/s) relative to the CMB. In the all-sky map from the COBE satellite, radiation in the Earth's direction of motion appears 0.35 mK hotter than the average temperature, 2.725 K, while radiation on the opposite side of the sky is 0.35 mK colder. The pressure of a thermalized photon gas is given by Pγ = Eγ/3 = αT⁴/3, where Eγ is the energy density of the photon gas and α is the Stefan-Boltzmann constant. The observed CMB dipole, therefore, implies a pressure difference between the two sides of the earth and results in a CMB drag on the earth. By plugging in suitable estimates of quantities involved, such as the cross section of the earth and the temperatures on the two sides, this drag can be estimated to be tiny. But for a photon traveling at the speed of light, 300,000 km/s, the drag can be significant. In the present model, for the dissipation part, it is assumed that a photon traveling from a distant object toward an observer has an effective interaction cross section pushing against the pressure of the CMB photon gas. For the attenuation part, the coefficient of the typical attenuation equation is used as a parameter. The values of these two parameters are determined by fitting the 748 µ vs. z data points compiled from 643 supernova and 105 γ-ray burst observations with z values up to 8.1. The fit is as good as that obtained from the lambda cold dark matter (ΛCDM) model using online cosmological calculators and Planck 2015 results. The model can be used to interpret Hubble's constant, Olbers' paradox, the origin and blackbody nature of the CMB radiation, the broadening of supernova light curves, and the size of the observable universe.

Keywords: CMB as the lowest energy state, model of the universe, origin of CMB in a static universe, photon-CMB photon gas interaction

Procedia PDF Downloads 134

Authors: Sofia Matoug, Amr Abdel-Dayem

Abstract:

This paper presents a comprehensive survey of recent research studies to segment and classify brain MR (magnetic resonance) images in order to detect significant changes to brain ventricles. The paper also presents a general framework for detecting regions that atrophy, which can help neurologists in detecting and staging Alzheimer. Furthermore, a prototype was implemented to segment brain MR images in order to extract the region of interest (ROI) and then, a classifier was employed to differentiate between normal and abnormal brain tissues. Experimental results show that the proposed scheme can provide a reliable second opinion that neurologists can benefit from.

Keywords: Alzheimer, brain images, classification techniques, Magnetic Resonance Images MRI

Procedia PDF Downloads 302

Authors: Petr Šimek

Abstract:

This work deals with the problem of synchronization of bus frames during transmission using USB (Universal Serial Bus). The principles for synchronization between USB and the non-deterministic CAN (Controller Area Network) bus will be described here. Furthermore, the work deals with ensuring the time sequence of communication frames when receiving from multiple communication bus channels. The structure of a general object for storing frames from different types of communication buses, such as CAN and LIN (Local Interconnect Network), will be described here. Finally, an evaluation of the communication throughput of bus frames for USB High speed will be performed. The creation of this architecture was based on the analysis of the communication of control units with a large number of communication buses. For the design of the architecture, a test HW with a USB-HS interface was used, which received previously known messages, which were compared with the received result. The result of this investigation is the block architecture of the control program for test HW ensuring correct data transmission via the USB bus.

Keywords: analysis, CAN, interface, LIN, synchronization, USB

Procedia PDF Downloads 63

Authors: Lian Yang

Abstract:

Object-oriented programming (OOP) is the dominant programming paradigm in today’s software industry and it has literally enabled average software developers to develop millions of commercial strength software applications in the era of INTERNET revolution over the past three decades. On the other hand, the lack of strict mathematical model and domain constraint features at the language level has long perplexed the computer science academia and OOP engineering community. This situation resulted in inconsistent system qualities and hard-to-understand designs in some OOP projects. The difficulties with regards to fix the current situation are also well known. Although the power of OOP lies in its unbridled flexibility and enormously rich data modeling capability, we argue that the ambiguity and the implicit facade surrounding the conceptual model of a class and an object should be eliminated as much as possible. We listed the five major usage of class and propose to separate them by proposing new language constructs. By using well-established theories of set and FSM, we propose to apply certain simple, generic, and yet effective constraints at OOP language level in an attempt to find a possible solution to the above-mentioned issues regarding OOP. The goal is to make OOP more theoretically sound as well as to aid programmers uncover warning signs of irregularities and domain-specific issues in applications early on the development stage and catch semantic mistakes at runtime, improving correctness verifiability of software programs. On the other hand, the aim of this paper is more practical than theoretical.

Keywords: new language constructs, set theory, FSM theory, user defined value type, function groups, membership qualification attribute (MQA), check-constraint (CC)

Procedia PDF Downloads 240

Authors: Vineetha Bettaiah, Heggere S. Ranganath

Abstract:

This paper presents a Hierarchical Piecewise Linear Approximation (HPLA) for the representation of time series data in which the time series is treated as a curve in the time-amplitude image space. The curve is partitioned into segments by choosing perceptually important points as break points. Each segment between adjacent break points is recursively partitioned into two segments at the best point or midpoint until the error between the approximating line and the original curve becomes less than a pre-specified threshold. The HPLA representation achieves dimensionality reduction while preserving prominent local features and general shape of time series. The representation permits course-fine processing at different levels of details, allows flexible definition of similarity based on mathematical measures or general time series shape, and supports time series data mining operations including query by content, clustering and classification based on whole or subsequence similarity.

Keywords: data mining, dimensionality reduction, piecewise linear representation, time series representation

Procedia PDF Downloads 275

Authors: Zbigniew Czyz, Krzysztof Skiba, Miroslaw Wendeker

Abstract:

This paper discusses the results of aerodynamic investigation of the Tajfun gyroplane body designed by a Polish company, Aviation Artur Trendak. This gyroplane has been studied as a 1:8 scale model. Scaling objects for aerodynamic investigation is an inherent procedure in any kind of designing. If scaling, the criteria of similarity need to be satisfied. The basic criteria of similarity are geometric, kinematic and dynamic. Despite the results of aerodynamic research are often reduced to aerodynamic coefficients, one should pay attention to how values of coefficients behave if certain criteria are to be satisfied. To satisfy the dynamic criterion, for example, the Reynolds number should be focused on. This is the correlation of inertial to viscous forces. With the multiplied flow speed by the specific dimension as a numerator (with a constant kinematic viscosity coefficient), flow speed in a wind tunnel research should be increased as many times as an object is decreased. The aerodynamic coefficients specified in this research depend on the real forces that act on an object, its specific dimension, medium speed and variations in its density. Rapid prototyping with a 3D printer was applied to create the research object. The research was performed with a T-1 low-speed wind tunnel (its diameter of the measurement volume is 1.5 m) and a six-element aerodynamic internal scales, WDP1, at the Institute of Aviation in Warsaw. This T-1 wind tunnel is low-speed continuous operation with open space measurement. The research covered a number of the selected speeds of undisturbed flow, i.e. V = 20, 30 and 40 m/s, corresponding to the Reynolds numbers (as referred to 1 m) Re = 1.31∙106, 1.96∙106, 2.62∙106 for the angles of attack ranging -15° ≤ α ≤ 20°. Our research resulted in basic aerodynamic characteristics and observing the impact of undisturbed flow speed on the correlation of aerodynamic coefficients as a function of the angle of attack of the gyroplane body. If the speed of undisturbed flow in the wind tunnel changes, the aerodynamic coefficients are significantly impacted. At speed from 20 m/s to 30 m/s, drag coefficient, Cx, changes by 2.4% up to 9.9%, whereas lift coefficient, Cz, changes by -25.5% up to 15.7% if the angle of attack of 0° excluded or by -25.5% up to 236.9% if the angle of attack of 0° included. Within the same speed range, the coefficient of a pitching moment, Cmy, changes by -21.1% up to 7.3% if the angles of attack -15° and -10° excluded or by -142.8% up to 618.4% if the angle of attack -15° and -10° included. These discrepancies in the coefficients of aerodynamic forces definitely need to consider while designing the aircraft. For example, if load of certain aircraft surfaces is calculated, additional correction factors definitely need to be applied. This study allows us to estimate the discrepancies in the aerodynamic forces while scaling the aircraft. This work has been financed by the Polish Ministry of Science and Higher Education.

Keywords: aerodynamics, criteria of similarity, gyroplane, research tunnel

Procedia PDF Downloads 393

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 96

Authors: Subham Ghosh, Arnab Nandi

Abstract:

Background: The proliferation of Wireless Body Area Networks (WBAN) and Internet of Things (IoT) applications demonstrates the potential for continuous monitoring of physical changes in the body. These technologies are vital for health monitoring tasks, such as identifying coughing and breathing activities, which are necessary for disease diagnosis and management. Monitoring activities such as coughing and deep breathing can provide valuable insights into a variety of medical issues. Wearable radio-based antenna sensors, which are lightweight and easy to incorporate into clothing or portable goods, provide continuous monitoring. This mobility gives it a substantial advantage over stationary environmental sensors like as cameras and radar, which are constrained to certain places. Furthermore, using compressive techniques provides benefits such as reduced data transmission speeds and memory needs. These wearable sensors offer more advanced and diverse health monitoring capabilities. Methodology: This study analyzes the feasibility of using a semi-flexible antenna operating at 2.4 GHz (ISM band) and positioned around the neck and near the mouth to identify three activities: coughing, deep breathing, and idleness. Vector network analyzer (VNA) is used to collect time-varying complex reflection coefficient data from perturbed antenna nearfield. The reflection coefficient (S11) conveys nuanced information caused by simultaneous variations in the nearfield radiation of three activities across time. The signatures are sparsely represented with gaussian windowed Gabor spectrograms. The Gabor spectrogram is used as a sparse representation approach, which reassigns the ridges of the spectrogram images to improve their resolution and focus on essential components. The antenna is biocompatible in terms of specific absorption rate (SAR). The sparsely represented Gabor spectrogram pictures are fed into a lightweight deep learning (DL) model for feature extraction and classification. Two antenna locations are investigated in order to determine the most effective localization for three different activities. Findings: Cross-validation techniques were used on data from both locations. Due to the complex form of the recorded S11, separate analyzes and assessments were performed on the magnitude, phase, and their combination. The combination of magnitude and phase fared better than the separate analyses. Various sliding window sizes, ranging from 1 to 5 seconds, were tested to find the best window for activity classification. It was discovered that a neck-mounted design was effective at detecting the three unique behaviors.

Keywords: activity recognition, antenna, deep-learning, time-frequency

Procedia PDF Downloads 10

Authors: Dan Kanmegne

Abstract:

Africa will become the most populated continent by the end of the century, with around 4 billion inhabitants. Food security and climate changes will become continental issues since agricultural practices depend on climate but also contribute to global emissions and land degradation. Agroforestry has been identified as a cost-efficient and reliable strategy to address these two issues. It is defined as the integrated management of trees and crops/animals in the same land unit. Agroforestry provides benefits in terms of goods (fruits, medicine, wood, etc.) and services (windbreaks, fertility, etc.), and is acknowledged to have a great potential for carbon sequestration; therefore it can be integrated into reduction mechanisms of carbon emissions. Particularly in sub-Saharan Africa, the constraint stands in the lack of information about both areas under agroforestry and the characterization (composition, structure, and management) of each agroforestry system at the country level. This study describes and quantifies “what is where?”, earliest to the quantification of carbon stock in different systems. Remote sensing (RS) is the most efficient approach to map such a dynamic technology as agroforestry since it gives relatively adequate and consistent information over a large area at nearly no cost. RS data fulfill the good practice guidelines of the Intergovernmental Panel On Climate Change (IPCC) that is to be used in carbon estimation. Satellite data are getting more and more accessible, and the archives are growing exponentially. To retrieve useful information to support decision-making out of this large amount of data, satellite data needs to be organized so to ensure fast processing, quick accessibility, and ease of use. A new solution is a data cube, which can be understood as a multi-dimensional stack (space, time, data type) of spatially aligned pixels and used for efficient access and analysis. A data cube for Burkina Faso has been set up from the cooperation project between the international service provider WASCAL and Germany, which provides an accessible exploitation architecture of multi-temporal satellite data. The aim of this study is to map and characterize agroforestry systems using the Burkina Faso earth observation data cube. The approach in its initial stage is based on an unsupervised image classification of a normalized difference vegetation index (NDVI) time series from 2010 to 2018, to stratify the country based on the vegetation. Fifteen strata were identified, and four samples per location were randomly assigned to define the sampling units. For safety reasons, the northern part will not be part of the fieldwork. A total of 52 locations will be visited by the end of the dry season in February-March 2020. The field campaigns will consist of identifying and describing different agroforestry systems and qualitative interviews. A multi-temporal supervised image classification will be done with a random forest algorithm, and the field data will be used for both training the algorithm and accuracy assessment. The expected outputs are (i) map(s) of agroforestry dynamics, (ii) characteristics of different systems (main species, management, area, etc.); (iii) assessment report of Burkina Faso data cube.

Keywords: agroforestry systems, Burkina Faso, earth observation data cube, multi-temporal image classification

Procedia PDF Downloads 145

Authors: Rifaldy, Misbahudin, Khalid Rizky, Ricky Aryanto, M. Alfiyan Bagus, Fahri Septianto, Firman Najib Wibisana, Excobar Arman

Abstract:

Indonesia is a country that has a high level of disaster because it is on the ring of fire, and there are several regions with three major plates meeting in the world. So that disaster analysis must always be done to see the potential disasters that might always occur, especially in this research are landslides and liquefaction. This research was conducted to analyze areas that are vulnerable to landslides and liquefaction hazards and their relationship with the assessment of the issue of moving the new capital of the Republic of Indonesia to the island of Kalimantan with a total area of 612,267.22 km². The method in this analysis uses the Analytical Hierarchy Process and consistency ratio testing as a complex and unstructured problem-solving process into several parameters by providing values. The parameters used in this analysis are the slope, land cover, lithology distribution, wetness index, earthquake data, peak ground acceleration. Weighted overlay was carried out from all these parameters using the percentage value obtained from the Analytical Hierarchy Process and confirmed its accuracy with a consistency ratio so that a percentage of the area obtained with different vulnerability classification values was obtained. Based on the analysis results obtained vulnerability classification from very high to low vulnerability. There are (0.15%) 918.40083 km² of highly vulnerable, medium (20.75%) 127,045,44815 km², low (56.54%) 346,175.886188 km², very low (22.56%) 138,127.484832 km². This research is expected to be able to map landslides and liquefaction disasters on the island of Kalimantan and provide consideration of the suitability of regional development of the new capital of the Republic of Indonesia. Also, this research is expected to provide input or can be applied to all regions that are analyzing the vulnerability of landslides and liquefaction or the suitability of the development of certain regions.

Keywords: analytic hierarchy process, Borneo Island, landslide and liquefaction, vulnerability analysis

Procedia PDF Downloads 177

Authors: J. Fernandez, R. Fernandez de Canete, J. Perea-Paizal, J. C. Ramos-Diaz

Abstract:

The high prevalence of cardiovascular diseases has provoked a raising interest in the development of mathematical models in order to evaluate the cardiovascular function both under physiological and pathological conditions. In this paper, a physical model of the cardiovascular system with intrinsic regulation is presented and implemented by using the object-oriented Modelica simulation software tools.  For this task, a multi-compartmental system previously validated with physiological data has been built, based on the interconnection of cardiovascular elements such as resistances, capacitances and pumping among others, by following an electrohydraulic analogy. The results obtained under both physiological and pathological scenarios provide an easy interpretative key to analyze the hemodynamic behavior of the patient. The described approach represents a valuable tool in the teaching of physiology for graduate medical and nursing students among others.

Keywords: cardiovascular system, MODELICA simulation software, physical modelling, teaching tool

Procedia PDF Downloads 301

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 73

Authors: Adriana Aparecida Rodrigues Leite

Abstract:

Linguistics and grammar conceptions are necessary to comprehend the structure of a language. On one hand, grammar depicts structural rules and instructions. On the other hand, linguistcs is a science which intends to understand the changes that occur in a language. Ferdinand de Saussure throughout his book called: Cours de linguistique générale (Course of general Linguistics) developed theories that portray explanations which defines linguistics as a real object of study of a language. It differs from grammar which is seen by Saussure as an element without scientific pattern. By that means, this research plans to decipher whether Ferdinand de Saussure would be against these conceptions and rules proposed by grammar. Besides that, this paper was based on the exploratory approach to pose concrete principles and facts to provide a response for the problem. This research is divided in the following sections: Introduction, Ferdinand de Saussure, Linguistics Conceptions, Linguistics for Saussure, Grammar Conceptions, and Grammar for Saussure. The result obtained from the analysis of the problem is highlighted in the section: Final Considerations.

Keywords: linguistics, grammar, ferdinand de saussure, language

Procedia PDF Downloads 28

Authors: Jerzy Merkisz, Pawel Fuc, Piotr Lijewski, Andrzej Ziolkowski, Pawel Czarkowski

Abstract:

The paper presents preliminary results of the development of an automotive exhaust gas energy recovery module. The aim of the performed analyses was to select the geometry of the heat exchanger that would ensure the highest possible transfer of heat at minimum heat flow losses. The starting point for the analyses was a straight portion of a pipe, from which the exhaust system of the tested vehicle was made. The design of the heat exchanger had a cylindrical cross-section, was 300 mm long and was fitted with a diffuser and a confusor. The model works were performed for the mentioned geometry utilizing the finite volume method based on the Ansys CFX v12.1 and v14 software. This method consisted in dividing of the system into small control volumes for which the exhaust gas velocity and pressure calculations were performed using the Navier-Stockes equations. The heat exchange in the system was modeled based on the enthalpy balance. The temperature growth resulting from the acting viscosity was not taken into account. The heat transfer on the fluid/solid boundary in the wall layer with the turbulent flow was done based on an arbitrarily adopted dimensionless temperature. The boundary conditions adopted in the analyses included the convective condition of heat transfer on the outer surface of the heat exchanger and the mass flow and temperature of the exhaust gas at the inlet. The mass flow and temperature of the exhaust gas were assumed based on the measurements performed in actual traffic using portable PEMS analyzers. The research object was a passenger vehicle fitted with a 1.9 dm3 85 kW diesel engine. The tests were performed in city traffic conditions.

Keywords: waste heat recovery, heat exchanger, CFD simulation, pems

Procedia PDF Downloads 574

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

In the precision agriculture area, one of the main tasks is the automated detection of diseases in crops. Machine Learning algorithms have been studied in recent decades for such tasks in view of their potential for improving economic outcomes that automated disease detection may attain over crop fields. The latest generation of deep learning convolution neural networks has presented significant results in the area of image classification. In this way, this work has tested the implementation of an architecture of deep learning convolution neural network for the detection of diseases in different types of crops. A data augmentation strategy was used to meet the requirements of the algorithm implemented with a deep learning framework. Two test scenarios were deployed. The first scenario implemented a neural network under images extracted from a controlled environment while the second one took images both from the field and the controlled environment. The results evaluated the generalisation capacity of the neural networks in relation to the two types of images presented. Results yielded a general classification accuracy of 59% in scenario 1 and 96% in scenario 2.

Keywords: convolutional neural networks, deep learning, disease detection, precision agriculture

Procedia PDF Downloads 259

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 199

Authors: Arth J. Shah, Madhu R. Kamble

Abstract:

Voice biometric liveness detection is customized to certify an authentication process of the voice data presented is genuine and not a recording or synthetic voice. With the rise of deepfakes and other equivalently sophisticated spoofing generation techniques, it’s becoming challenging to ensure that the person on the other end is a live speaker or not. Voice Liveness Detection (VLD) system is a group of security measures which detect and prevent voice spoofing attacks. Motivated by the recent development of the Kolmogorov-Arnold Network (KAN) based on the Kolmogorov-Arnold theorem, we proposed KAN for the VLD task. To date, multilayer perceptron (MLP) based classifiers have been used for the classification tasks. We aim to capture not only the compositional structure of the model but also to optimize the values of univariate functions. This study explains the mathematical as well as experimental analysis of KAN for VLD tasks, thereby opening a new perspective for scientists to work on speech and signal processing-based tasks. This study emerges as a combination of traditional signal processing tasks and new deep learning models, which further proved to be a better combination for VLD tasks. The experiments are performed on the POCO and ASVSpoof 2017 V2 database. We used Constant Q-transform, Mel, and short-time Fourier transform (STFT) based front-end features and used CNN, BiLSTM, and KAN as back-end classifiers. The best accuracy is 91.26 % on the POCO database using STFT features with the KAN classifier. In the ASVSpoof 2017 V2 database, the lowest EER we obtained was 26.42 %, using CQT features and KAN as a classifier.

Keywords: Kolmogorov Arnold networks, multilayer perceptron, pop noise, voice liveness detection

Procedia PDF Downloads 41

Authors: Chika Catherine Ayogu

Abstract:

Rehabilitation plays an important and integral part in the life of roadway rehabilitation management system. It is a systematic method for inspection and rating the roadway condition in a given area. The system performs a cost effective analysis of various maintenance and rehabilitation strategies. Finally the system prioritize and recommend roadway rehabilitation and maintenance to maximize results within a given budget amount. During execution of maintenance activity, the system also tracks labour, materials, equipment and cost for activities performed. The system implements physical assessment field inspection and rating of each street segment which is then entered into a database. The information is analyzed using a software, and provide recommendations and project future conditions. The roadway management system provides a deterioration curve for each segment based on input then assigns the most cost-effective maintenance strategy based on conditions, surface type and functional classification, and available budget. This paper investigates the roadway management system and its capabilities to assist in applying the right treatment to the right roadway at the right time so that expected service life of the roadway is extended as long as possible with acceptable cost.

Keywords: effectiveness, rehabilitation, roadway, software system

Procedia PDF Downloads 152

Authors: B. H. Aitchanov, Sh. K. Aitchanova, O. A. Baimuratov

Abstract:

This paper is focused on dynamic pulse-frequency modulation (DPFM) control systems. Currently, the control law based on DPFM control signals is widely used in direct digital control subsystems introduced in the automated control systems of technological processes. Statistical analysis of automatic control systems is reduced to its construction of functional relationships between the statistical characteristics of the errors processes and input processes. Structural and dynamic Volterra models of digital pulse-frequency control systems can be used to develop methods for generating the dependencies, differing accuracy, requiring the amount of information about the statistical characteristics of input processes and computing labor intensity of their use.

Keywords: digital dynamic pulse-frequency control systems, dynamic pulse-frequency modulation, control object, discrete filter, impulse device, microcontroller

Procedia PDF Downloads 495

Authors: Joseph Wolff, Jeffrey Eilbott

Abstract:

Autism Spectrum Disorders (ASD) are a spectrum of social disorders characterized by deficits in social communication, verbal ability, and interaction that can vary in severity. In recent years, researchers have used magnetic resonance imaging (MRI) to help detect how neural patterns in individuals with ASD differ from those of neurotypical (NT) controls for classification purposes. This study analyzed the classification of ASD within males and females using functional MRI data. Functional connectivity (FC) correlations among brain regions were used as feature inputs for machine learning algorithms. Analysis was performed on 558 cases from the Autism Brain Imaging Data Exchange (ABIDE) I dataset. When trained specifically on females, the algorithm underperformed in classifying the ASD subset of our testing population. Although the subject size was relatively smaller in the female group, the manual matching of both male and female training groups helps explain the algorithm’s bias, indicating the altered sex abnormalities in functional brain networks compared to typically developing peers. These results highlight the importance of taking sex into account when considering how generalizations of findings on males with ASD apply to females.

Keywords: autism spectrum disorder, machine learning, neuroimaging, sex differences

Procedia PDF Downloads 209

Authors: Amin Derakhshan, Mohammad Mikaili, Mohammad Ali Khalilzadeh, Amin Mohammadian

Abstract:

This paper proposes a stress recognition system from multi-modal bio-potential signals. For stress recognition, Support Vector Machines (SVM) and LDA are applied to design the stress classifiers and its characteristics are investigated. Using gathered data under psychological polygraph experiments, the classifiers are trained and tested. The pattern recognition method classifies stressful from non-stressful subjects based on labels which come from polygraph data. The successful classification rate is 96% for 12 subjects. It means that facial thermal imaging due to its non-contact advantage could be a remarkable alternative for psycho-physiological methods.

Keywords: stress, thermal imaging, face, SVM, polygraph

Procedia PDF Downloads 487

Authors: Tegan H. Emerson, Colin C. Olson, George Stantchev, Jason A. Edelberg, Michael Wilson

Abstract:

Detecting small targets at range is difficult because there is not enough spatial information present in an image sub-region containing the target to use correlation-based methods to differentiate it from dynamic confusers present in the scene. Moreover, this lack of spatial information also disqualifies the use of most state-of-the-art deep learning image-based classifiers. Here, we use characteristics of target tracks extracted from video sequences as data from which to derive distinguishing topological features that help robustly differentiate targets of interest from confusers. In particular, we calculate persistent homology from time-delayed embeddings of dynamic statistics calculated from motion tracks extracted from a wide field-of-view video stream. In short, we use topological methods to extract features related to target motion dynamics that are useful for classification and disambiguation and show that small targets can be detected at range with high probability.

Keywords: motion tracks, persistence images, time-delay embedding, topological data analysis

Procedia PDF Downloads 114

Authors: Nadjoua Bourmatte, Hacène Houari

Abstract:

Glass has been indispensable to men’s life due to its properties, including pliability to take any shape with ease, bright surface, resistance to abrasion, reasonable safety and durability. Waste glass creates serious environmental problems, mainly due to the inconsistency of waste glass streams. With increasing environmental pressure to reduce solid waste and to recycle as much as possible, the concrete industry has adopted a number of methods to achieve this goal. The object of this research work is to study the effect of using recycled glass waste, as a partial replacement of fine aggregate, on the fresh and hardened properties of concrete. Recycled glass was used to replace fine aggregate in proportions of 0%, 25% and 50%. We could observe that the Glass waste aggregates are lighter than natural aggregates and they show a very low water absorption. The experimental results showed that the slump flow increased with the increase of recycled glass content. On the other hand, the compressive strength and tensile strength of recycled glass mixtures decreased with the increase in the recycled glass content. The results showed that recycled glass aggregate can successfully be used with limited level for producing concrete. The standard sand was substituted with aggregates based on glass waste for manufacturing mortars, Mortar based on glass shows a compressive strength and low bending with a 1/2 ratio with control mortar strength.

Keywords: concrete, environment, glass waste, recycling

Procedia PDF Downloads 232

Authors: Francisca Margarita Ocran

Abstract:

Underwear, and more particularly bras and panties, are defined as intimate clothing. Strictly speaking, they enhance the place of women in the public or private satchel. Therefore, women's lingerie is a complex garment with a high involvement profile, motivating consumers to buy it not only by its functional utility but also by the multisensory experience it provides them. Customer behavior models are generally based on customer data mining, and each model is designed to answer questions at a specific time. Predicting the customer experience is uncertain and difficult. Thus, knowledge of consumers' tastes in lingerie deserves to be treated as an experiential product, where the dimensions of the experience motivating consumers to buy a lingerie product and to remain faithful to it must be analyzed in detail by the manufacturers and retailers to engage and retain consumers, which is why this research aims to identify the variables that push consumers to choose their lingerie product, based on an in-depth analysis of the types of fabrics used to make lingerie. The data used in this study comes from online purchases. Machine learning approach with the use of Python programming language and Pycaret gives us a precision of 86.34%, 85.98%, and 84.55% for the three algorithms to use concerning the preference of a buyer in front of a range of lingerie. Gradient Boosting, random forest, and K Neighbors were used in this study; they are very promising and rich in the classification of preference in the textile industry.

Keywords: consumer behavior, data mining, lingerie, machine learning, preference

Procedia PDF Downloads 90

Authors: Kishor Chandra Kandpal, Amit Kumar

Abstract:

The Indian Himalaya region harbours approximately 1748 plants of medicinal importance, and as per International Union for Conservation of Nature (IUCN), the 112 plant species among these are threatened and endangered. To ease the pressure on these plants, the government of India is encouraging its in-situ cultivation. The Saussurea costus, Valeriana jatamansi, and Picrorhiza kurroa have also been prioritized for large scale cultivation owing to their market demand, conservation value and medicinal properties. These species are found from 1000 m to 4000 m elevation ranges in the Indian Himalaya. Identification of these plants in the field requires taxonomic skills, which is one of the major bottleneck in the conservation and management of these plants. In recent years, Hyperspectral remote sensing techniques have been precisely used for the discrimination of plant species with the help of their unique spectral signatures. In this background, a spectral library of the above 03 medicinal plants was prepared by collecting the spectral data using a handheld spectroradiometer (325 to 1075 nm) from farmer’s fields of Himachal Pradesh and Uttarakhand states of Indian Himalaya. The Random forest (RF) model was implied on the spectral data for the classification of the medicinal plants. The 80:20 standard split ratio was followed for training and validation of the RF model, which resulted in training accuracy of 84.39 % (kappa coefficient = 0.72) and testing accuracy of 85.29 % (kappa coefficient = 0.77). This RF classifier has identified green (555 to 598 nm), red (605 nm), and near-infrared (725 to 840 nm) wavelength regions suitable for the discrimination of these species. The findings of this study have provided a technique for rapid and onsite identification of the above medicinal plants in the field. This will also be a key input for the classification of hyperspectral remote sensing images for mapping of these species in farmer’s field on a regional scale. This is a pioneer study in the Indian Himalaya region for medicinal plants in which the applicability of hyperspectral remote sensing has been explored.

Keywords: himalaya, hyperspectral remote sensing, machine learning; medicinal plants, random forests

Procedia PDF Downloads 204

Authors: Mohd Ridzwan Yaakub, Muhammad Iqbal Abu Latiffi

Abstract:

Online business has become popular recently due to the massive amount of information and medium available on the Internet. This has resulted in the huge number of reviews where the consumers share their opinion, criticisms, and satisfaction on the products they have purchased on the websites or the social media such as Facebook and Twitter. However, to analyze customer’s behavior has become very important for organizations to find new market trends and insights. The reviews from the websites or the social media are in structured and unstructured data that need a sentiment analysis approach in analyzing customer’s review. In this article, techniques used in will be defined. Definition of the ontology and description of its possible usage in sentiment analysis will be defined. It will lead to empirical research that related to mobile phones used in research and the ontology used in the experiment. The researcher also will explore the role of preprocessing data and feature selection methodology. As the result, ontology-based approach in sentiment analysis can help in achieving high accuracy for the classification task.

Keywords: feature selection, ontology, opinion, preprocessing data, sentiment analysis

Procedia PDF Downloads 200