Search results for: scene classification

Authors: Muhammad Tayyab Afzal, Muhammad Arslan, Mirza Muhammad Waqar

Abstract:

Snow constitutes an important component of the cryosphere, characterized by high temporal and spatial variability. Because of the contribution of snow melt to water availability, snow is an important focus for research on climate change and adaptation. MODIS satellite data have been used to identify spatial-temporal trends in snow cover in the upper Indus basin. For this research MODIS satellite 8 day composite data of medium resolution (250m) have been analysed from 2001-2005.Pixel based supervised classification have been performed and extent of snow have been calculated of all the images. Results show large variation in snow cover between years while an increasing trend from west to east is observed. Temperature data for the Upper Indus Basin (UIB) have been analysed for seasonal and annual trends over the period 2001-2005 and calibrated with the results acquired by the research. From the analysis it is concluded that there are indications that regional warming is one of the factor that is affecting the hydrology of the upper Indus basin due to accelerated glacial melting during the simulation period, stream flow in the upper Indus basin can be predicted with a high degree of accuracy. This conclusion is also supported by the research of ICIMOD in which there is an observation that the average annual precipitation over a five year period is less than the observed stream flow and supported by positive temperature trends in all seasons.

Keywords: indus basin, MODIS, remote sensing, snow cover

Procedia PDF Downloads 362

Authors: Hui Zhang, Ye Tian, Fang Ye, Ziming Guo

Abstract:

Communication signal modulation recognition technology is one of the key technologies in the field of modern information warfare. At present, communication signal automatic modulation recognition methods are mainly divided into two major categories. One is the maximum likelihood hypothesis testing method based on decision theory, the other is a statistical pattern recognition method based on feature extraction. Now, the most commonly used is a statistical pattern recognition method, which includes feature extraction and classifier design. With the increasingly complex electromagnetic environment of communications, how to effectively extract the features of various signals at low signal-to-noise ratio (SNR) is a hot topic for scholars in various countries. To solve this problem, this paper proposes a feature extraction algorithm for the communication signal based on the improved Holder cloud feature. And the extreme learning machine (ELM) is used which aims at the problem of the real-time in the modern warfare to classify the extracted features. The algorithm extracts the digital features of the improved cloud model without deterministic information in a low SNR environment, and uses the improved cloud model to obtain more stable Holder cloud features and the performance of the algorithm is improved. This algorithm addresses the problem that a simple feature extraction algorithm based on Holder coefficient feature is difficult to recognize at low SNR, and it also has a better recognition accuracy. The results of simulations show that the approach in this paper still has a good classification result at low SNR, even when the SNR is -15dB, the recognition accuracy still reaches 76%.

Keywords: communication signal, feature extraction, Holder coefficient, improved cloud model

Procedia PDF Downloads 122

Authors: Soumya Sajjan

Abstract:

Liver cancer is the most common cancer disease worldwide in men and women, and is one of the few cancers still on the rise. Liver disease is the 4th leading cause of death. According to new NHS (National Health Service) figures, deaths from liver diseases have reached record levels, rising by 25% in less than a decade; heavy drinking, obesity, and hepatitis are believed to be behind the rise. In this study, we focus on Development of Diagnostic Classifier for Ultrasound liver lesion. Ultrasound (US) Sonography is an easy-to-use and widely popular imaging modality because of its ability to visualize many human soft tissues/organs without any harmful effect. This paper will provide an overview of underlying concepts, along with algorithms for processing of liver ultrasound images Naturaly, Ultrasound liver lesion images are having more spackle noise. Developing classifier for ultrasound liver lesion image is a challenging task. We approach fully automatic machine learning system for developing this classifier. First, we segment the liver image by calculating the textural features from co-occurrence matrix and run length method. For classification, Support Vector Machine is used based on the risk bounds of statistical learning theory. The textural features for different features methods are given as input to the SVM individually. Performance analysis train and test datasets carried out separately using SVM Model. Whenever an ultrasonic liver lesion image is given to the SVM classifier system, the features are calculated, classified, as normal and diseased liver lesion. We hope the result will be helpful to the physician to identify the liver cancer in non-invasive method.

Keywords: segmentation, Support Vector Machine, ultrasound liver lesion, co-occurance Matrix

Procedia PDF Downloads 385

Authors: Phan Minh Trang, Joacim Rocklöv, Kim Bao Giang, Gunnar Kullgren, Maria Nilsson

Abstract:

There are recent studies from high income countries reporting an association between heat waves and hospital admissions for mental health disorders. It is not previously studied if such relations exist in sub-tropical and tropical low- and middle-income countries. In this study from Vietnam, the assumption was that hospital admissions for mental disorders may be triggered, or exacerbated, by heat exposure and heat waves. A database from Hanoi Mental Hospital with mental disorders diagnosed by the International Classification of Diseases 10, spanning over five years, was used to estimate the heatwave-related impacts on admissions for mental disorders. The relationship was analysed by a Negative Binomial regression model accounting for year, month, and days of week. The focus of the study was heat-wave events with periods of three or seven consecutive days above the threshold of 35oC daily maximum temperature. The preliminary study results indicated that heat-waves increased the risks for hospital admission for mental disorders (F00-79) from heat-waves of three and seven days with relative risks (RRs) of 1.16 (1.01–1.33) and 1.42 (1.02–1.99) respectively, when compared with non-heat-wave periods. Heatwave-related admissions for mental disorders increased statistically significantly among men, among residents in rural communities and in elderly. Moreover, cases for organic mental disorders including symptomatic illnesses (F0-9) and mental retardation (F70-79) raised in high risks during heat waves. The findings are novel studying a sub-tropical middle-income city, facing rapid urbanisation and epidemiological and demographic transitions.

Keywords: mental disorders, admissions for F0-9 or F70-79, maximum temperature, heat waves

Procedia PDF Downloads 216

Authors: Sujata Upgupta, Prasoon Kumar Singh

Abstract:

The expansion of large scale coal mining into forest areas is a potential hazard for the local biodiversity and wildlife. The objective of this study is to provide a picture of the threat that coal mining poses to the forests of the East Bokaro landscape. The vulnerable forest areas at risk have been assessed and the priority areas for conservation have been presented. The forested areas at risk in the current scenario have been assessed and compared with the past conditions using classification and buffer based overlay approach. Forest vulnerability has been assessed using an analytical framework based on systematic indicators and composite vulnerability index values. The results indicate that more than 4 km² of forests have been lost from 1973 to 2016. Large patches of forests have been diverted for coal mining projects. Forests in the northern part of the coal field within 1-3 km radius around the coal mines are at immediate risk. The original contiguous forests have been converted into fragmented and degraded forest patches. Most of the collieries are located within or very close to the forests thus threatening the biodiversity and hydrology of the surrounding regions. Based on the vulnerability values estimated, it was concluded that more than 90% of the forested grids in East Bokaro are highly vulnerable to mining. The forests in the sub-districts of Bermo and Chandrapura have been identified as the most vulnerable to coal mining activities. This case study would add to the capacity of the forest managers and mine managers to address the risk and vulnerability of forests at a small landscape level in order to achieve sustainable development.

Keywords: forest, coal mining, indicators, vulnerability

Procedia PDF Downloads 370

Authors: Michael Kho Lim

Abstract:

This paper examines the status of the film industry as an industry in the Philippines—where or how it is classified in the Philippine industrial classification system and how this positioning gives the film industry an identity (or not) and affects (film) policy development and impacts the larger national economy. It is important to look at how the national government recognises Philippine cinema officially, as this will have a direct and indirect impact on the industry in terms of its representation, conduct of business, international relations, and most especially its implications on policy development and implementation. Therefore, it is imperative that the ‘identity’ of Philippine cinema be clearly established and defined in the overall industrial landscape. Having a clear understanding of Philippine cinema’s industry status provides a better view of the bigger picture and helps us determine cinema’s position in the national agenda in terms of priority setting, future direction and how the state perceives and thereby values the film industry as an industry. This will then serve as a frame of reference that will anchor the succeeding discussion. Once the Philippine film industry status is identified, the paper will then clarify how cultural policy is defined, understood, and applied in the Philippines in relation to Philippine cinema by reviewing and analyzing existing policy documents and pending bills in the Philippine Congress and Senate. Lastly, the paper delves into the roles that (national) cultural institutions and industry organisations play as primary drivers or support mechanisms and how they become platforms (or not) for the upliftment of the independent film sector and towards the sustainability of the film industry. The paper concludes by arguing that the role of the government and how government officials perceive and treats culture is far more important than cultural policy itself, as these policies emanate from them.

Keywords: cultural and creative industries, cultural policy, film industry, Philippine cinema

Procedia PDF Downloads 390

Authors: Milton Ayoki, Edward Bbaale

Abstract:

This paper analyses the relationship between innovation and employment at firm level with the objective of understanding the contribution of the different innovation strategies in fostering employment growth in Uganda. We use National Innovation Survey (micro-data of 705 Ugandan firms) for the period 2011-2014 and follow closely Harrison et al. (2014) structured approach, and relate employment growth to process innovations and to the growth of sales separately due to innovative and unchanged products. We find positive effects of product innovation on employment at firm level, while process innovation has no discernable impact on employment. Although there is evidence to suggest displacement of labour in some cases where firms only introduce new process, this effect is compensated by growth in employment from new products, which for most firms are introduced simultaneously with new process. Results suggest that source of innovation as well as size of innovating firms or end users of innovation matter for job growth. Innovation that develops from within the firm itself (user) and involving larger firms has greater impact on employment than that developed from outside or coming from within smaller firms. In addition, innovative firms are one and half times more likely to survive in the innovation driven economy environment than those that do not innovate. These results have important implications for policymakers and stakeholders in innovation ecosystem. Supporting policies need to be correctly tailored since the impacts depend on the innovation strategy (type) and characteristics and sector of the innovative firms (small, large, industry, etc.). Policies to spur investment, particularly in innovative sectors and firms with high growth potential would have long lasting effects on job creation. JEL Classification: D24, J0, J20, L20, O30.

Keywords: employment, process innovation, product innovation, Sub-Saharan Africa

Procedia PDF Downloads 141

Authors: Junbeom Lee, Jaehyuck Cho, Wookyeong Jeong, Jonghan Won, Jungmin Hwang, Youngseok Song, Taikyeong Jeong

Abstract:

This paper investigates and analyzes meta-learning technologies that use multiple-cameras to monitor and check abnormal behavior in people in real-time in the area of healthcare fields. Advances in artificial intelligence and computer vision technologies have confirmed that cameras can be useful for individual health monitoring and abnormal behavior detection. Through this, it is possible to establish a system that can respond early by automatically detecting abnormal behavior of the elderly, such as patients and the elderly. In this paper, we use a technique called meta-learning to analyze image data collected from cameras and develop a commercial product to determine abnormal behavior. Meta-learning applies machine learning algorithms to help systems learn and adapt quickly to new real data. Through this, the accuracy and reliability of the abnormal behavior discrimination system can be improved. In addition, this study proposes a meta-learning-based abnormal behavior detection system that includes steps such as data collection and preprocessing, feature extraction and selection, and classification model development. Various healthcare scenarios and experiments analyze the performance of the proposed system and demonstrate excellence compared to other existing methods. Through this study, we present the possibility that camera-based meta-learning technology can be useful for monitoring and testing abnormal behavior in the healthcare area.

Keywords: artificial intelligence, abnormal behavior, early detection, health monitoring

Procedia PDF Downloads 59

Authors: Hamed Yousefi, Farnaz Mohammadi, Niloufar Mirian, Navid Amini

Abstract:

Investigating possible capacities of visual functions where adapted mechanisms can enhance the capability of sports trainees is a promising area of research, not only from the cognitive viewpoint but also in terms of unlimited applications in sports training. In this paper, the visual evoked potential (VEP) and event-related potential (ERP) signals of amateur and trained volleyball players in a pilot study were processed. Two groups of amateur and trained subjects are asked to imagine themselves in the state of receiving a ball while they are shown a simulated volleyball field. The proposed method is based on a set of time-frequency features using algorithms such as Gabor filter, continuous wavelet transform, and a multi-stage wavelet decomposition that are extracted from VEP signals that can be indicative of being amateur or trained. The linear discriminant classifier achieves the accuracy, sensitivity, and specificity of 100% when the average of the repetitions of the signal corresponding to the task is used. The main purpose of this study is to investigate the feasibility of a fast, robust, and reliable feature/model determination as a neurofeedback parameter to be utilized for improving the volleyball players’ performance. The proposed measure has potential applications in brain-computer interface technology where a real-time biomarker is needed.

Keywords: visual evoked potential, time-frequency feature extraction, short-time Fourier transform, event-related spectrum potential classification, linear discriminant analysis

Procedia PDF Downloads 112

Authors: Jyoti Brahma

Abstract:

Folk epics of India are found in various Indian languages. The study of folk epics and its importance in folkloristic study in India came into prominence only during the nineteenth century. The British administrators and missionaries collected and documented folk epics from various parts of the country. The paper is an attempt to investigate how colonial outpost appears to penetrate the interiors of Indian land and society and triggered off the Indian Renaissance. It takes into account the compositions of the epics of India and the attention it received during the nineteenth century, which in turn gave, rise to the national consciousness shaping the culture of India. Composed as oral traditions these folk epics are now seen as repositories of historical consciousness whereas in earlier times societies without literacy were said to be without history. So, there is an urgent need to re-examine the British impact on Indian literary traditions. The Bhakti poets through their nuanced responses in their efforts to change the behavior of Indian society gives us the perfect example of deferment in the clear cut distinction between the folk and the classical in the context of India. It evades a pure categorization and classification of the classical and constitutes part of the folk traditions of the cultural heritage of India. Therefore, the ethical question of what is ontologically known as ordinary discourse in the case of the “folk” forms metaphors and folk language gains importance once more. The paper also thus seeks simultaneously to outline the significant factors responsible for shaping the destiny of folklore in South India particularly the four political states of the Indian Union: Andhra Pradesh, Karnataka, Kerala and Tamil Nadu, what could be termed as South Indian “cultural zones”.

Keywords: colonial, folk, folklore, tradition

Procedia PDF Downloads 291

Authors: Arwa Alzughaibi

Abstract:

Human Motion detection is a challenging task due to a number of factors including variable appearance, posture and a wide range of illumination conditions and background. So, the first need of such a model is a reliable feature set that can discriminate between a human and a non-human form with a fair amount of confidence even under difficult conditions. By having richer representations, the classification task becomes easier and improved results can be achieved. The Aim of this paper is to investigate the reliable and accurate human motion detection models that are able to detect the human motions accurately under varying illumination levels and backgrounds. Different sets of features are tried and tested including Histogram of Oriented Gradients (HOG), Deformable Parts Model (DPM), Local Decorrelated Channel Feature (LDCF) and Aggregate Channel Feature (ACF). However, we propose an efficient and reliable human motion detection approach by combining Histogram of oriented gradients (HOG) and local phase quantization (LPQ) as the feature set, and implementing search pruning algorithm based on optical flow to reduce the number of false positive. Experimental results show the effectiveness of combining local phase quantization descriptor and the histogram of gradient to perform perfectly well for a large range of illumination conditions and backgrounds than the state-of-the-art human detectors. Areaunder th ROC Curve (AUC) of the proposed method achieved 0.781 for UCF dataset and 0.826 for CDW dataset which indicates that it performs comparably better than HOG, DPM, LDCF and ACF methods.

Keywords: human motion detection, histograms of oriented gradient, local phase quantization, local phase quantization

Procedia PDF Downloads 233

Authors: Adamu Abdullahi, On Francisca, Saidu Isah Rambo, G. N. Obunadike, D. T. Chinyio

Abstract:

The paper discusses the potential threat of Denial of Service (DoS) attacks in the Internet of Things (IoT) networks on constrained application protocols (CoAP). As billions of IoT devices are expected to be connected to the internet in the coming years, the security of these devices is vulnerable to attacks, disrupting their functioning. This research aims to tackle this issue by applying mixed methods of qualitative and quantitative for feature selection, extraction, and cluster algorithms to detect DoS attacks in the Constrained Application Protocol (CoAP) using the Machine Learning Algorithm (MLA). The main objective of the research is to enhance the security scheme for CoAP in the IoT environment by analyzing the nature of DoS attacks and identifying a new set of features for detecting them in the IoT network environment. The aim is to demonstrate the effectiveness of the MLA in detecting DoS attacks and compare it with conventional intrusion detection systems for securing the CoAP in the IoT environment. Findings: The research identifies the appropriate node to detect DoS attacks in the IoT network environment and demonstrates how to detect the attacks through the MLA. The accuracy detection in both classification and network simulation environments shows that the k-means algorithm scored the highest percentage in the training and testing of the evaluation. The network simulation platform also achieved the highest percentage of 99.93% in overall accuracy. This work reviews conventional intrusion detection systems for securing the CoAP in the IoT environment. The DoS security issues associated with the CoAP are discussed.

Keywords: algorithm, CoAP, DoS, IoT, machine learning

Procedia PDF Downloads 45

Authors: Jacob J. Shila, Xiaoyu O. Wu

Abstract:

As the applications of unmanned aerial vehicles (UAV) continue to increase across the world, it is critical to understand the factors that contribute to incidents and accidents associated with these systems. Given the variety of daily applications that could utilize the operations of the UAV (e.g., medical, security operations, construction activities, landscape activities), the main discussion has been how to safely incorporate the UAV into the national airspace system. The types of UAV incidents being reported range from near sightings by other pilots to actual collisions with aircraft or UAV. These incidents have the potential to impact the rest of aviation operations in a variety of ways, including human lives, liability costs, and delay costs. One of the largest causes of these incidents cited is the human factor; other causes cited include maintenance, aircraft, and others. This work investigates the key human factors associated with UAV incidents. To that end, the data related to UAV incidents that have occurred in the United States is both reviewed and analyzed to identify key human factors related to UAV incidents. The data utilized in this work is gathered from the Federal Aviation Administration (FAA) drone database. This study adopts the human factor analysis and classification system (HFACS) to identify key human factors that have contributed to some of the UAV failures to date. The uniqueness of this work is the incorporation of UAV incident data from a variety of applications and not just military data. In addition, identifying the specific human factors is crucial towards developing safety operational models and human factor guidelines for the UAV. The findings of these common human factors are also compared to similar studies in other countries to determine whether these factors are common internationally.

Keywords: human factors, incidents and accidents, safety, UAS, UAV

Procedia PDF Downloads 214

Authors: Kasidis Chomrat, Nopasit Chakpitak, Anukul Tamprasirt, Annop Thananchana

Abstract:

Internet of Things devices or IoT and Edge Computing has become one of the biggest things happening in innovations and one of the most discussed of the potential to improve and disrupt traditional business and industry alike. With rises of new hang cliff challenges like COVID-19 pandemic that posed a danger to workforce and business process of the system. Along with drastically changing landscape in business that left ruined aftermath of global COVID-19 pandemic, looming with the threat of global energy crisis, global warming, more heating global politic that posed a threat to become new Cold War. How emerging technology like edge computing and usage of specialized design visual processing units will be great opportunities for business. The literature reviewed on how the internet of things and disruptive wave will affect business, which explains is how all these new events is an effect on the current business and how would the business need to be adapting to change in the market and world, and example test benchmarking for consumer marketed of newer devices like the internet of things devices equipped with new edge computing devices will be increase efficiency and reducing posing a risk from a current and looming crisis. Throughout the whole paper, we will explain the technologies that lead the present technologies and the current situation why these technologies will be innovations that change the traditional practice through brief introductions to the technologies such as cloud computing, edge computing, Internet of Things and how it will be leading into future.

Keywords: internet of things, edge computing, machine learning, pattern recognition, image classification

Procedia PDF Downloads 128

Authors: Lise Paesen, Marielle Leijten

Abstract:

People diagnosed with probable Alzheimer disease suffer from an impairment of their language capacities; a gradual impairment which affects both their spoken and written communication. Our study aims at characterising the language decline in DAT patients with the use of congeneric elicited writing tasks. Within these tasks, a descriptive text has to be written based upon images with which the participants are confronted. A randomised set of images allows us to present the participants with a different task on every encounter, thus allowing us to avoid a recognition effect in this iterative study. This method is a revision from previous studies, in which participants were presented with a larger picture depicting an entire scene. In order to create the randomised set of images, existing pictures were adapted following strict criteria (e.g. frequency, AoA, colour, ...). The resulting data set contained 50 images, belonging to several categories (vehicles, animals, humans, and objects). A pre-test was constructed to validate the created picture set; most images had been used before in spoken picture naming tasks. Hence the same reaction times ought to be triggered in the typed picture naming task. Once validated, the effectiveness of the descriptive tasks was assessed. First, the participants (n=60 students, n=40 healthy elderly) performed a typing task, which provided information about the typing speed of each individual. Secondly, two descriptive writing tasks were carried out, one simple and one complex. The simple task contains 4 images (1 animal, 2 objects, 1 vehicle) and only contains elements with high frequency, a young AoA (<6 years), and fast reaction times. Slow reaction times, a later AoA (≥ 6 years) and low frequency were criteria for the complex task. This task uses 6 images (2 animals, 1 human, 2 objects and 1 vehicle). The data were collected with the keystroke logging programme Inputlog. Keystroke logging tools log and time stamp keystroke activity to reconstruct and describe text production processes. The data were analysed using a selection of writing process and product variables, such as general writing process measures, detailed pause analysis, linguistic analysis, and text length. As a covariate, the intrapersonal interkey transition times from the typing task were taken into account. The pre-test indicated that the new images lead to similar or even faster reaction times compared to the original images. All the images were therefore used in the main study. The produced texts of the description tasks were significantly longer compared to previous studies, providing sufficient text and process data for analyses. Preliminary analysis shows that the amount of words produced differed significantly between the healthy elderly and the students, as did the mean length of production bursts, even though both groups needed the same time to produce their texts. However, the elderly took significantly more time to produce the complex task than the simple task. Nevertheless, the amount of words per minute remained comparable between simple and complex. The pauses within and before words varied, even when taking personal typing abilities (obtained by the typing task) into account.

Keywords: Alzheimer's disease, experimental design, language decline, writing process

Procedia PDF Downloads 252

Authors: D. Jayalakshmi, S. S. Bhosale

Abstract:

This paper, in its first part, presents the state-of-the-art literature of design approaches for geosynthetic reinforced unpaved roads. The literature starting since 1970 and the critical appraisal of flexible pavement design by Giroud and Han (2004) and Jonathan Fannin (2006) is presented. The design example is illustrated for Indian conditions. The example emphasizes the results computed by Giroud and Han's (2004) design method with the Indian road congress guidelines by IRC SP 72 -2015. The input data considered are related to the subgrade soil condition of Maharashtra State in India. The unified soil classification of the subgrade soil is inorganic clay with high plasticity (CH), which is expansive with a California bearing ratio (CBR) of 2% to 3%. The example exhibits the unreinforced case and geotextile as reinforcement by varying the rut depth from 25 mm to 100 mm. The present result reveals the base thickness for the unreinforced case from the IRC design catalogs is in good agreement with Giroud and Han (2004) approach for a range of 75 mm to 100 mm rut depth. Since Giroud and Han (2004) method is applicable for both reinforced and unreinforced cases, for the same data with appropriate Nc factor, for the same rut depth, the base thickness for the reinforced case has arrived for the Indian condition. From this trial, for the CBR of 2%, the base thickness reduction due to geotextile inclusion is 35%. For the CBR range of 2% to 5% with different stiffness in geosynthetics, the reduction in base course thickness will be evaluated, and the validation will be executed by the full-scale accelerated pavement testing set up at the College of Engineering Pune (COE), India.

Keywords: base thickness, design approach, equation, full scale accelerated pavement set up, Indian condition

Procedia PDF Downloads 163

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network

Procedia PDF Downloads 45

Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung

Abstract:

Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.

Keywords: medical technology, artificial intelligence, radiology, lung cancer

Procedia PDF Downloads 42

Authors: Saba Gachpaz, Hamid Reza Heidari

Abstract:

The sharp increase in population growth leads to more pressure on agricultural areas to satisfy the food supply. To achieve this, more resources should be consumed and, besides other environmental concerns, highlight sustainable agricultural development. Land-use management is a crucial factor in obtaining optimum productivity. Machine learning is a widely used technique in the agricultural sector, from yield prediction to customer behavior. This method focuses on learning and provides patterns and correlations from our data set. In this study, nine physical control factors, namely, soil classification, electrical conductivity, normalized difference water index (NDWI), groundwater level, elevation, annual precipitation, pH of water, annual mean temperature, and slope in the alluvial plain in Khuzestan (an agricultural hotspot in Iran) are used to decide the best agricultural land use for both rainfed and irrigated agriculture for ten different crops. For this purpose, each variable was imported into Arc GIS, and a raster layer was obtained. In the next level, by using training samples, all layers were imported into the python environment. A random forest model was applied, and the weight of each variable was specified. In the final step, results were visualized using a digital elevation model, and the importance of all factors for each one of the crops was obtained. Our results show that despite 62% of the study area being allocated to agricultural purposes, only 42.9% of these areas can be defined as a suitable class for cultivation purposes.

Keywords: land suitability, machine learning, random forest, sustainable agriculture

Procedia PDF Downloads 55

Authors: Iva Zdrilić, Petra Došenović Bonča, Darija Aleksić

Abstract:

Since the boundaryless career, with its emphasis on cross-employer movements, was introduced as a new paradigm of career development, inter-organizational employee mobility has been increasing. Although this phenomenon may have positive implications for individual careers and destination organizations, the consequences for the source organizations losing workers are less clear. The aim of this paper is thus to develop a comprehensive typology of possible inter-organizational employee mobility determinants. Since the most common classification differentiates between mobility determinants at different levels (i.e., economic, organizational, and individual), this paper focuses on building a comprehensive multi-level typology of inter-organizational mobility determinants across diverse sectors and industries. By using a structured literature review approach and bibliometric analysis, the paper reveals both intricate relationships between different mobility determinants and the complexity of inter-organizational networks and social ties. The latter appears as both a mobility determinant (at the organizational and individual level) and a mobility effect. Indeed, inter-organizational employee mobility leads to the formation of networks between source and destination organizations. These networks are practically based on the social ties between mobile employees and their colleagues and, in this way, they close the "inter-organizational employee mobility - inter-organizational network/ties" circle. The paper contributes to the career development literature by uncovering hitherto underexplored diverse determinants of intra- and inter-sectoral mobility as well as the conflicting results of the existing studies on some factors (e.g., inter-organizational networks and/or social ties) that appear both as a mobility determinant and a mobility effect.

Keywords: inter-organizational mobility, social ties, inter-organizational network, knowledge transfer

Procedia PDF Downloads 78

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

Abstract:

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

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

Procedia PDF Downloads 207

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 52

Authors: Xizhen Zhou, Yanjie Ji

Abstract:

In advancing the management of integrated electric vehicle (EV) parking-charging behaviors, this study uses Changshu City in Suzhou as a case study to establish a data association mechanism for parking-charging platforms and to develop a database for EV parking-charging behaviors. Key indicators, such as charging start time, initial state of charge, final state of charge, and parking-charging time difference, are considered. Utilizing the K-S test method, the paper examines the heterogeneity of parking-charging behavior preferences among pure EV and non-pure EV users. The K-means clustering method is employed to analyze the characteristics of parking-charging behaviors for both user groups, thereby enhancing the overall understanding of these behaviors. The findings of this study reveal that using a classification model, the parking-charging behaviors of pure EVs can be classified into five distinct groups, while those of non-pure EVs can be separated into four groups. Among them, both types of EV users exhibit groups with low range anxiety for complete charging with special journeys, complete charging at destination, and partial charging. Additionally, both types have a group with high range anxiety, characterized by pure EV users displaying a preference for complete charging with specific journeys, while non-pure EV users exhibit a preference for complete charging. Notably, pure EV users also display a significant group engaging in nocturnal complete charging. The findings of this study can provide technical support for the scientific and rational layout and management of integrated parking and charging facilities for EVs.

Keywords: traffic engineering, potential preferences, cluster analysis, EV, parking-charging behavior

Procedia PDF Downloads 53

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 292

Authors: Ishita Singh

Abstract:

Social-dimension of Climate Change is no longer peripheral to Science, Technology and Innovation (STI). Indeed, STI is being mobilized to address small farmers’ vulnerability and adaptation to Climate Change. The experiences from the cold desert of Leh (Ladakh) in North-West Himalaya illustrate the potential of STI to address the challenges of Climate Change and the needs of small farmers through the use of Artificial Glacier Techniques. Small farmers have a unique technique of water harvesting to augment irrigation, called “Artificial Glaciers” - an intricate network of water channels and dams along the upper slope of a valley that are located closer to villages and at lower altitudes than natural glaciers. It starts to melt much earlier and supplements additional irrigation to small farmers’ improving their livelihoods. Therefore, the issue of vulnerability, adaptive capacity and adaptation strategy needs to be analyzed in a local context and the communities as well as regions where people live. Leh (Ladakh) in North-West Himalaya provides a Case Study for exploring the ways in which adaptation to Climate Change is taking place at a community scale using Artificial Glacier Technology. With the above backdrop, an attempt has been made to analyze the rural poor households' vulnerability and adaptation practices to Climate Change using this technology, thereby drawing lessons on vulnerability-livelihood interactions in the cold desert of Leh (Ladakh) in North-West Himalaya, India. The study is based on primary data and information collected from 675 households confined to 27 villages of Leh (Ladakh) in North-West Himalaya, India. It reveals that 61.18% of the population is driving livelihoods from agriculture and allied activities. With increased irrigation potential due to the use of Artificial Glaciers, food security has been assured to 77.56% of households and health vulnerability has been reduced in 31% of households. Seasonal migration as a livelihood diversification mechanism has declined in nearly two-thirds of households, thereby improving livelihood strategies. Use of tactical adaptations by small farmers in response to persistent droughts, such as selling livestock, expanding agriculture lands, and use of relief cash and foods, have declined to 20.44%, 24.74% and 63% of households. However, these measures are unsustainable on a long-term basis. The role of policymakers and societal stakeholders becomes important in this context. To address livelihood challenges, the role of technology is critical in a multidisciplinary approach involving multilateral collaboration among different stakeholders. The presence of social entrepreneurs and new actors on the adaptation scene is necessary to bring forth adaptation measures. Better linkage between Science and Technology policies, together with other policies, should be encouraged. Better health care, access to safe drinking water, better sanitary conditions, and improved standards of education and infrastructure are effective measures to enhance a community’s adaptive capacity. However, social transfers for supporting climate adaptive capacity require significant amounts of additional investment. Developing institutional mechanisms for specific adaptation interventions can be one of the most effective ways of implementing a plan to enhance adaptation and build resilience.

Keywords: climate change, adaptation, livelihood, stakeholders

Procedia PDF Downloads 37

Authors: Cam Nguyen

Abstract:

Rapid, accurate, and safe sensing and imaging of physical quantities or structures finds many applications and is of significant interest to society. Sensing and imaging using radio-frequency (RF) techniques, particularly, has gone through significant development and subsequently established itself as a unique territory in the sensing world. RF sensing and imaging has played a critical role in providing us many sensing and imaging abilities beyond our human capabilities, benefiting both civilian and military applications - for example, from sensing abnormal conditions underneath some structures’ surfaces to detection and classification of concealed items, hidden activities, and buried objects. We present the developments of several sensing and imaging systems implementing RF technologies like ultra-wide band (UWB), synthetic-pulse, and interferometry. These systems are fabricated completely using RF integrated circuits. The UWB impulse system operates over multiple pulse durations from 450 to 1170 ps with 5.5-GHz RF bandwidth. It performs well through tests of various samples, demonstrating its usefulness for subsurface sensing. The synthetic-pulse system operating from 0.6 to 5.6 GHz can assess accurately subsurface structures. The synthetic-pulse system operating from 29.72-37.7 GHz demonstrates abilities for various surface and near-surface sensing such as profile mapping, liquid-level monitoring, and anti-personnel mine locating. The interferometric system operating at 35.6 GHz demonstrates its multi-functional capability for measurement of displacements and slow velocities. These RF sensors are attractive and useful for various surface and subsurface sensing applications. This paper was made possible by NPRP grant # 6-241-2-102 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors.

Keywords: RF sensors, radars, surface sensing, subsurface sensing

Procedia PDF Downloads 291

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 131

Authors: Abdullah Saeidi, Aydin Gülses, Christan Flörke

Abstract:

Skin cancer of the face region is the most common type of malignancy and surgical excision is the preferred approach. However, the clinical long term results reported in the literature are still controversial. Objectives: To describe; 1. Demographical characteristics 2. Affected site, distribution and TNM classification regarding tumor type 3. Surgical aspects • Surgical removal: excision principles, safety margins, the need for secondary resection, primary reconstruction/ defect closure, anesthesia protocol, duration of hospital stay (if any) • Secondary intervention for defect closure/reconstruction: Flap technique, anesthesia protocol, duration of hospital stay (if any), postoperative wound management etc. 4. Tumor recurrences 5. Clinical outcomes 6. Studying the possible therapy approach throw Biostatistical relation and correlation between multiple Histological, diagnostics and clinical Faktors. following surgical ablation of the skin cancer of the head and neck region. Methods: Selection and statistical analysis of medical records of patients who had admitted to the Department of Oral and Maxillofacial Surgery, Universitätsklinikum Schleswig Holstein, Campus Kiel during the period of 2015-2019 will be retrospectively evaluated. Data will be collected via ORBIS Information-Management-System (ORBIS AG, Saarbrücken, Germany).

Keywords: non melanoma skin cancer, face skin cancer, skin reconstruction, non melanoma skin cancer recurrence, non melanoma skin cancer metastases

Procedia PDF Downloads 87

Authors: Chi Wu, Dean Wu, Wen-Te Liu, Cheng-Yu Tsai, Shin-Mei Hsu, Yin-Tzu Lin, Ru-Yin Yang

Abstract:

Background: The results of previous studies compared the benefits and risks of receiving insomnia medication. However, the effects between hypnotic drugs used and enhancement of sleep quality were still unclear. Objective: The aim of this study is to establish a prediction model for hypnotic drugs' dosage used for insomnia subjects and associated the relationship between sleep stage ratio change and drug types. Methodologies: According to American Academy of Sleep Medicine (AASM) guideline, sleep stages were classified and transformed to hypnogram via the polysomnography (PSG) in a hospital in New Taipei City (Taiwan). The subjects with diagnosis for insomnia without receiving hypnotic drugs treatment were be set as the comparison group. Conversely, hypnotic drugs dosage within the past three months was obtained from the clinical registration for each subject. Furthermore, the collecting subjects were divided into two groups for training and testing. After training convolution neuron network (CNN) to predict types of hypnotics used and dosages are taken, the test group was used to evaluate the accuracy of classification. Results: We recruited 76 subjects in this study, who had been done PSG for transforming hypnogram from their sleep stages. The accuracy of dosages obtained from confusion matrix on the test group by CNN is 81.94%, and accuracy of hypnotic drug types used is 74.22%. Moreover, the subjects with high ratio of wake stage were correctly classified as requiring medical treatment. Conclusion: CNN with hypnogram was potentially used for adjusting the dosage of hypnotic drugs and providing subjects to pre-screening the types of hypnotic drugs taken.

Keywords: convolution neuron network, hypnotic drugs, insomnia, polysomnography

Procedia PDF Downloads 163

Authors: H. El-Messiry, M. El-Zainy, D. Abdelkhalek

Abstract:

Cone-beam computed tomography (CBCT) provides high-quality 3-dimensional images of dental structures because of its high spatial resolution. The study of dental morphology is important in research as it provides information about diversities within a population. Many studies have shown different shapes and numbers of roots canals among different races, especially in molars. The aim of this study was to determine the morphology of root canals of mandibular first and third molars in a sample of Egyptian population using CBCT scanning. Fifty mandibular first Molars (M1) and fifty mandibular third (M3) extracted molars were collected. Thick rectangular molds were made using pink wax to hold the samples. Molars were embedded in the wax mold by aligning them in rows leaving arbitrary 0.5cm space between them. The molds with the samples in were submitted for CBCT scan. The number and morphology of root canals were assessed and classified according to Vertucci's classification. The mesial and the distal roots were examined separately. Finally, data was analyzed using Fisher exact test. The most prevalent mesial root canal frequency in M1 was type IV (60%) and type II (40 %), while M3 showed prevalence of type I (40%) and II (40%). Distal root canal morphology showed prevalence of type I in both M1 (66%) and M3 (86%). So, it can be concluded that CBCT scanning provides supplemental information about the root canal configurations of mandibular molars in a sample of Egyptian population. This study may help clinicians in the root canal treatment of mandibular molars.

Keywords: cone beam computed tomography, mandibular first molar, mandibular third molar, root canal morphology

Procedia PDF Downloads 292