Search results for: convolutional coding

Authors: Hechmi Saidi, Noureddine Hamdi

Abstract:

The performance of decode and forward (DF) multihop free space optical (FSO) scheme deploying multiple input multiple output (MIMO) configuration under gamma-gamma (GG) statistical distribution, that adopts M-ary pulse position modulation (MPPM) coding, is investigated. We have extracted exact and estimated values of symbol-error rates (SERs) respectively. The probability density function (PDF)’s closed-form formula is expressed for our designed system. Thanks to the use of DF multihop MIMO FSO configuration and MPPM signaling, atmospheric turbulence is combatted; hence the transmitted signal quality is improved.

Keywords: free space optical, gamma gamma channel, radio frequency, decode and forward, multiple-input multiple-output, M-ary pulse position modulation, symbol error rate

Procedia PDF Downloads 225

Authors: Sandra Rigot, Samira Demaria, Frederic Lemaire

Abstract:

The starting point of this research is the contemporary capitalist paradox: there is a real scarcity of long term investment despite the boom of potential long term investors. This gap represents a major challenge: there are important needs for long term financing in developed and emerging countries in strategic sectors such as energy, transport infrastructure, information and communication networks. Moreover, the recent financial and sovereign debt crises, which have respectively reduced the ability of financial banking intermediaries and governments to provide long term financing, questions the identity of the actors able to provide long term financing, their methods of financing and the most appropriate forms of intermediation. The issue of long term financing is deemed to be very important by the EU Commission, as it issued a 2013 Green Paper (GP) on long-term financing of the EU economy. Among other topics, the paper discusses the impact of the recent regulatory reforms on long-term investment, both in terms of accounting (in particular fair value) and prudential standards for banks. For banks, prudential and accounting standards are also crucial. Fair value is indeed well adapted to the trading book in a short term view, but this method hardly suits for a medium and long term portfolio. Banks’ ability to finance the economy and long term projects depends on their ability to distribute credit and the way credit is valued (fair value or amortised cost) leads to different banking strategies. Furthermore, in the banking industry, accounting standards are directly connected to the prudential standards, as the regulatory requirements of Basel III use accounting figures with prudential filter to define the needs for capital and to compute regulatory ratios. The objective of these regulatory requirements is to prevent insolvency and financial instability. In the same time, they can represent regulatory constraints to long term investing. The balance between financial stability and the need to stimulate long term financing is a key question raised by the EU GP. Does fair value accounting contributes to short-termism in the investment behaviour? Should prudential rules be “appropriately calibrated” and “progressively implemented” not to prevent banks from providing long-term financing? These issues raised by the EU GP lead us to question to what extent the main regulatory requirements incite or constrain banks to finance long term projects. To that purpose, we study the 292 responses received by the EU Commission during the public consultation. We analyze these contributions focusing on particular questions related to fair value accounting and prudential norms. We conduct a two stage content analysis of the responses. First, we proceed to a qualitative coding to identify arguments of respondents and subsequently we run a quantitative coding in order to conduct statistical analyses. This paper provides a better understanding of the position that a large panel of European stakeholders have on these issues. Moreover, it adds to the debate on fair value accounting and its effects on prudential requirements for banks. This analysis allows us to identify some short term bias in banking regulation.

Keywords: basel 3, fair value, securitization, long term investment, banks, insurers

Procedia PDF Downloads 267

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 233

Authors: Nathenal Thomas Lambamo

Abstract:

Based on the fact that more than 85% of the labor force and 90% of the export earnings are taken by agriculture in Ethiopia and it can be said that it is the backbone of the overall socio-economic activities in the country. Among the cereal crops that the agriculture sector provides for the country, wheat is the third-ranking one preceding teff and maize. In the present day, wheat is in higher demand related to the expansion of industries that use them as the main ingredient for their products. The local supply of wheat for these companies covers only 35 to 40% and the rest 60 to 65% percent is imported on behalf of potential customers that exhaust the country’s foreign currency reserves. The above facts show that the need for this crop in the country is too high and in reverse, the productivity of the crop is very less because of these reasons. Wheat disease is the most devastating disease that contributes a lot to this unbalance in the demand and supply status of the crop. It reduces both the yield and quality of the crop by 27% on average and up to 37% when it is severe. This study aims to detect the most frequent and degrading wheat diseases, Septoria and Leaf rust, using the most efficiently used subset of machine learning technology, deep learning. As a state of the art, a deep learning class classification technique called Convolutional Neural Network (CNN) has been used to detect diseases and has an accuracy of 99.01% is achieved.

Keywords: septoria, leaf rust, deep learning, CNN

Procedia PDF Downloads 51

Authors: Juan Pablo Botero Torres, Alba Avila, Luis Felipe Giraldo

Abstract:

Independent navigation and mobility through unknown spaces pose a challenge for the autonomy of visually impaired people (VIP), who have relied on the use of traditional assistive tools like the white cane and trained dogs. However, emerging visually assistive technologies (VAT) have proposed several human-machine interfaces (HMIs) that could improve VIP’s ability for self-guidance. Hereby, we introduce the design and implementation of a visually assistive device, Anajaa – Visual Substitution System (AVSS). This system integrates ultrasonic sensors with custom electronics, and computer vision models (convolutional neural networks), in order to achieve a robust system that acquires information of the surrounding space and transmits it to the user in an intuitive and efficient manner. AVSS consists of two modules: the sensing and the actuation module, which are fitted to a chest mount and belt that communicate via Bluetooth. The sensing module was designed for the acquisition and processing of proximity signals provided by an array of ultrasonic sensors. The distribution of these within the chest mount allows an accurate representation of the surrounding space, discretized in three different levels of proximity, ranging from 0 to 6 meters. Additionally, this module is fitted with an RGB-D camera used to detect potentially threatening obstacles, like staircases, using a convolutional neural network specifically trained for this purpose. Posteriorly, the depth data is used to estimate the distance between the stairs and the user. The information gathered from this module is then sent to the actuation module that creates an HMI, by the means of a 3x2 array of vibration motors that make up the tactile display and allow the system to deliver haptic feedback. The actuation module uses vibrational messages (tactones); changing both in amplitude and frequency to deliver different awareness levels according to the proximity of the obstacle. This enables the system to deliver an intuitive interface. Both modules were tested under lab conditions, and the HMI was additionally tested with a focal group of VIP. The lab testing was conducted in order to establish the processing speed of the computer vision algorithms. This experimentation determined that the model can process 0.59 frames per second (FPS); this is considered as an adequate processing speed taking into account that the walking speed of VIP is 1.439 m/s. In order to test the HMI, we conducted a focal group composed of two females and two males between the ages of 35-65 years. The subject selection was aided by the Colombian Cooperative of Work and Services for the Sightless (COOTRASIN). We analyzed the learning process of the haptic messages throughout five experimentation sessions using two metrics: message discrimination and localization success. These correspond to the ability of the subjects to recognize different tactones and locate them within the tactile display. Both were calculated as the mean across all subjects. Results show that the focal group achieved message discrimination of 70% and a localization success of 80%, demonstrating how the proposed HMI leads to the appropriation and understanding of the feedback messages, enabling the user’s awareness of its surrounding space.

Keywords: computer vision on embedded systems, electronic trave aids, human-machine interface, haptic feedback, visual assistive technologies, vision substitution systems

Procedia PDF Downloads 53

Authors: Yuntao Liu, Lei Wang, Haoran Xia

Abstract:

Machine learning has shown extensive applications in the development of classification models for autism spectrum disorder (ASD) using neural image data. This paper proposes a fusion multi-modal classification network based on a graph neural network. First, the brain is segmented into 116 regions of interest using a medical segmentation template (AAL, Anatomical Automatic Labeling). The image features of sMRI and the signal features of fMRI are extracted, which build the node and edge embedding representations of the brain map. Then, we construct a dynamically updated brain map neural network and propose a method based on a dynamic brain map adjacency matrix update mechanism and learnable graph to further improve the accuracy of autism diagnosis and recognition results. Based on the Autism Brain Imaging Data Exchange I dataset(ABIDE I), we reached a prediction accuracy of 74% between ASD and TD subjects. Besides, to study the biomarkers that can help doctors analyze diseases and interpretability, we used the features by extracting the top five maximum and minimum ROI weights. This work provides a meaningful way for brain disorder identification.

Keywords: autism spectrum disorder, brain map, supervised machine learning, graph network, multimodal data, model interpretability

Procedia PDF Downloads 29

Authors: Alina Trifan, António J. R. Neves

Abstract:

Although most digital cameras acquire images in a raw format, based on a Color Filter Array that arranges RGB color filters on a square grid of photosensors, most image compression techniques do not use the raw data; instead, they use the rgb result of an interpolation algorithm of the raw data. This approach is inefficient and by performing a lossless compression of the raw data, followed by pixel interpolation, digital cameras could be more power efficient and provide images with increased resolution given that the interpolation step could be shifted to an external processing unit. In this paper, we conduct a survey on the use of lossless compression algorithms with raw Bayer images. Moreover, in order to reduce the effect of the transition between colors that increase the entropy of the raw Bayer image, we split the image into three new images corresponding to each channel (red, green and blue) and we study the same compression algorithms applied to each one individually. This simple pre-processing stage allows an improvement of more than 15% in predictive based methods.

Keywords: bayer image, CFA, lossless compression, image coding standards

Procedia PDF Downloads 298

Authors: Jovina Concepcion Bachynski, Lenora Duhn, Idevania G. Costa, Pilar Camargo-Plazas

Abstract:

Kidney failure is a life-limiting condition for which treatment, such as dialysis (hemodialysis and peritoneal dialysis), can exact a tremendously high physical and psychosocial symptom burden. Kidney failure can be severe enough to require a palliative approach to care. The term supportive care can be used in lieu of palliative care to avoid the misunderstanding that palliative care is synonymous with end-of-life or hospice care. Kidney supportive care, encompassing advance care planning, is an approach to care that improves the quality of life for people receiving dialysis through early identification and treatment of symptoms throughout the disease trajectory. Advanced care planning involves ongoing conversations about the values, goals, and preferences for future care between individuals and their healthcare teams. Kidney supportive care is underutilized and often initiated late in this population. There is evidence to indicate nurses are not providing the necessary elements of supportive kidney care. Dialysis nurses’ delay or lack of engagement in supportive care until close to the end of life may result in people dying without receiving optimal palliative care services. Using Charmaz’s constructivist grounded theory, the purpose of this doctoral study is to develop a substantive theory that explains the process of engagement in supportive care by nurses working in dialysis settings in Canada. Through initial purposeful and subsequent theoretical sampling, 23 nurses with current or recent work experience in outpatient hemodialysis, home hemodialysis, and peritoneal dialysis settings drawn from across Canada were recruited to participate in two intensive interviews using the Zoom© teleconferencing platform. Concurrent data collection and data analysis, constant comparative analysis of initial and focused codes until the attainment of theoretical saturation, and memo-writing, as well as researcher reflexivity, have been undertaken to aid the emergence of concepts, categories, and, ultimately, the constructed theory. At the time of abstract submission, data analysis is currently at the second level of coding (i.e., focused coding stage) of the research study. Preliminary categories include: (a) focusing on biomedical care; (b) multi-dimensional challenges to having the conversation; (c) connecting and setting boundaries with patients; (d) difficulty articulating kidney-supportive care; and (e) unwittingly practising kidney-supportive care. For the conference, the resulting theory will be presented. Nurses working in dialysis are well-positioned to ensure the delivery of quality kidney-supportive care. This study will help to determine the process and the factors enabling and impeding nurse engagement in supportive care in dialysis to effect change for normalizing advance care planning conversations in the clinical setting. This improved practice will have substantive beneficial implications for the many individuals living with kidney failure and their supporting loved ones.

Keywords: dialysis, kidney failure, nursing, supportive care

Procedia PDF Downloads 82

Authors: Teja Koduru

Abstract:

Untreated Lyme disease can lead to neurological, cardiac, and dermatological complications. Rapid diagnosis of the erythema migrans (EM) rash, a characteristic symptom of Lyme disease is therefore crucial to early diagnosis and treatment. In this study, we aim to utilize deep learning frameworks including Tensorflow and Keras to create deep convolutional neural networks (DCNN) to detect images of acute Lyme Disease from images of erythema migrans. This study uses a custom database of erythema migrans images of varying quality to train a DCNN capable of classifying images of EM rashes vs. non-EM rashes. Images from publicly available sources were mined to create an initial database. Machine-based removal of duplicate images was then performed, followed by a thorough examination of all images by a clinician. The resulting database was combined with images of confounding rashes and regular skin, resulting in a total of 683 images. This database was then used to create a DCNN with an accuracy of 93% when classifying images of rashes as EM vs. non EM. Finally, this model was converted into a web and mobile application to allow for rapid diagnosis of EM rashes by both patients and clinicians. This tool could be used for patient prescreening prior to treatment and lead to a lower mortality rate from Lyme disease.

Keywords: Lyme, untreated Lyme, erythema migrans rash, EM rash

Procedia PDF Downloads 208

Authors: Ali Reza Sattarzadeh, Ronny J. Kutadinata, Pubudu N. Pathirana, Van Thanh Huynh

Abstract:

Traffic congestion has become a severe worldwide problem, affecting everyday life, fuel consumption, time, and air pollution. The primary causes of these issues are inadequate transportation infrastructure, poor traffic signal management, and rising population. Traffic flow forecasting is one of the essential and effective methods in urban congestion and traffic management, which has attracted the attention of researchers. With the development of technology, undeniable progress has been achieved in existing methods. However, there is a possibility of improvement in the extraction of temporal and spatial features to determine the importance of traffic flow sequences and extraction features. In the proposed model, we implement the convolutional neural network (CNN) and long short-term memory (LSTM) deep learning models for mining nonlinear correlations and their effectiveness in increasing the accuracy of traffic flow prediction in the real dataset. According to the experiments, the results indicate that implementing Conv-LSTM networks increases the productivity and accuracy of deep learning models for traffic flow prediction.

Keywords: deep learning algorithms, intelligent transportation systems, spatiotemporal features, traffic flow prediction

Procedia PDF Downloads 138

Authors: Amjad Nusayr

Abstract:

Software security is a general term used to any type of software architecture or model in which security aspects are incorporated in this architecture. These aspects are not part of the main logic of the underlying program. Software security can be achieved using a combination of approaches, including but not limited to secure software designs, third part component validation, and secure coding practices. Memory safety is one feature in software security where we ensure that any object in memory has a valid pointer or a reference with a valid type. Aspect-Oriented Programming (AOP) is a paradigm that is concerned with capturing the cross-cutting concerns in code development. AOP is generally used for common cross-cutting concerns like logging and DB transaction managing. In this paper, we introduce the concepts that enable AOP to be used for the purpose of memory and type safety. We also present ideas for extending AOP in software security practices.

Keywords: aspect oriented programming, programming languages, software security, memory and type safety

Procedia PDF Downloads 105

Authors: Soniya Takshak, R. K. Sharma

Abstract:

Let q and n be positive integers, then Fᵩ denotes the finite field of q elements, and Fqn denotes the extension of Fᵩ of degree n. Also, Fᵩ* represents the multiplicative group of non-zero elements of Fᵩ, and the generators of Fᵩ* are called primitive elements. A normal element α of a finite field Fᵩⁿ is such that {α, αᵠ, . . . , αᵠⁿ⁻¹} forms a basis for Fᵩⁿ over Fᵩ. Primitive normal elements have several applications in coding theory and cryptography. So, establishing the existence of primitive normal elements under certain conditions is both theoretically important and a natural issue. In this article, we provide a sufficient condition for the existence of a primitive normal element α in Fᵩⁿ of a prescribed primitive norm and non-zero trace over Fᵩ such that f(α) is also primitive, where f(x) ∈ Fᵩⁿ(x) is a rational function of degree sum m. Particularly, we investigated the rational functions of degree sum 4 over Fᵩⁿ, where q = 11ᵏ and demonstrated that there are only 3 exceptional pairs (q, n), n ≥ 7 for which such kind of primitive normal elements may not exist. In general, we show that such elements always exist except for finitely many choices of (q, n). To arrive to our conclusion, we used additive and multiplicative character sums.

Keywords: finite field, primitive element, normal element, norm, trace, character

Procedia PDF Downloads 72

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 79

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs –Sigmoid, ReLU, and Tanh–have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment with multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLUReLU) combination. Our results show that using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: activation function, universal approximation function, neural networks, convergence

Procedia PDF Downloads 130

Authors: Maslin Masrom, Nik Hasnaa Nik Mahmood, Wan Normeza Wan Zakaria, Azizul Azizan, Norshaliza Kamaruddin

Abstract:

Traditionally, in science education, the teacher provides facts and the students learn them. It is outmoded for today’s students to equip them with real-life situations, mainly because knowledge and life skills are acquired passively from the instructors. Inquiry-Based Science Education (IBSE) is an approach that allows students to experiment, ask questions, and develop responses based on reasoning. It has provided students and teachers with opportunities to actively engage in collaborative learning via inquiry. This approach inspires the students to become active thinkers, research for solutions, and gain life-long experience and self-confidence. Therefore, the research aims to investigate how the primary-school teacher supports students or pupils through an inquiry-based science education approach for computer science, specifically coding skills. The results are presented and described.

Keywords: inquiry-based science education, student-centered learning, computer science, primary school

Procedia PDF Downloads 127

Authors: Ali Berkan Ural

Abstract:

This paper presents the analysis, evaluation, and pre-diagnosis of early stage breast based diagnostic problems (breast cancer, nodulesorlumps) by Computer Aided Diagnosing (CAD) system from mammogram radiological images. According to the statistics, the time factor is crucial to discover the disease in the patient (especially in women) as possible as early and fast. In the study, a new algorithm is developed using advanced image processing and deep learning method to detect and classify the problem at earlystagewithmoreaccuracy. This system first works with image processing methods (Image acquisition, Noiseremoval, Region Growing Segmentation, Morphological Operations, Breast BorderExtraction, Advanced Segmentation, ObtainingRegion Of Interests (ROIs), etc.) and segments the area of interest of the breast and then analyzes these partly obtained area for cancer detection/lumps in order to diagnosis the disease. After segmentation, with using the Spectrogramimages, 5 different deep learning based methods (specified Convolutional Neural Network (CNN) basedAlexNet, ResNet50, VGG16, DenseNet, Xception) are applied to classify the breast based problems.

Keywords: computer aided diagnosis, breast cancer, region growing, segmentation, deep learning

Procedia PDF Downloads 67

Authors: Parisa Golbayani, Dan Wang, Ionut¸ Florescu

Abstract:

In this work we implement machine learning techniques to financial statement reports in order to asses company’s credit rating. Specifically, the work analyzes the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating as issued by Standard and Poor’s. The paper focuses on companies from the energy, financial, and healthcare sectors in the US. The goal of this analysis is to improve application of machine learning algorithms to credit assessment. To accomplish this, the study investigates three questions. First, we investigate if the algorithms perform better when using a selected subset of important features or whether better performance is obtained by allowing the algorithms to select features themselves. Second, we address the temporal aspect inherent in financial data and study whether it is important for the results obtained by a machine learning algorithm. Third, we aim to answer if one of the four particular neural network architectures considered consistently outperforms the others, and if so under which conditions. This work frames the problem as several case studies to answer these questions and analyze the results using ANOVA and multiple comparison testing procedures.

Keywords: convolutional neural network, long short term memory, multilayer perceptron, credit rating

Procedia PDF Downloads 209

Authors: Lianzhong Zhang, Chao Huang

Abstract:

Sea-land segmentation is a basic step in many tasks such as sea surface monitoring and ship detection. The existing sea-land segmentation algorithms have poor segmentation accuracy, and the parameter adjustments are cumbersome and difficult to meet actual needs. Also, the current sea-land segmentation adopts traditional deep learning models that use Convolutional Neural Networks (CNN). At present, the transformer architecture has achieved great success in the field of natural images, but its application in the field of radar images is less studied. Therefore, this paper proposes a sea-land segmentation method based on the transformer architecture to strengthen edge supervision. It uses a self-attention mechanism with a gating strategy to better learn relative position bias. Meanwhile, an additional edge supervision branch is introduced. The decoder stage allows the feature information of the two branches to interact, thereby improving the edge precision of the sea-land segmentation. Based on the Gaofen-3 satellite image dataset, the experimental results show that the method proposed in this paper can effectively improve the accuracy of sea-land segmentation, especially the accuracy of sea-land edges. The mean IoU (Intersection over Union), edge precision, overall precision, and F1 scores respectively reach 96.36%, 84.54%, 99.74%, and 98.05%, which are superior to those of the mainstream segmentation models and have high practical application values.

Keywords: SAR, sea-land segmentation, deep learning, transformer

Procedia PDF Downloads 140

Authors: Brian J. Biroscak

Abstract:

In the United States (US), “sex trafficking” is defined at the federal level in the Trafficking Victims Protection Act of 2000 as encompassing a number of processes such as recruitment, transportation, and provision of a person for the purpose of a commercial sex act. It involves the use of force, fraud, or coercion, or in which the person induced to perform such act has not attained 18 years of age. Accumulating evidence suggests that sex trafficking is exacerbated by social and environmental stressors (e.g., pandemics). Given that “provision” is a key part of the definition, “provisioning systems” may offer a useful lens through which to study sex trafficking dynamics. Provisioning systems are the social systems connecting individuals, small groups, entities, and embedded communities as they seek to satisfy their needs and wants for goods, services, experiences and ideas through value-based exchange in communities. This project presents a conceptual framework for understanding sex trafficking dynamics in the context of the COVID pandemic. The framework is developed as a system dynamics simulation model based on published evidence, social and behavioral science theory, and key informant interviews with stakeholders from the Protection, Prevention, Prosecution, and Partnership sectors in one US state. This “4 P Paradigm” has been described as fundamental to the US government’s anti-trafficking strategy. The present research question is: “How do sex trafficking systems (e.g., supply, demand and price) interact with other provisioning systems (e.g., networks of organizations that help sexually exploited persons) to influence trafficking over time vis-à-vis the COVID pandemic?” Semi-structured interviews with stakeholders (n = 19) were analyzed based on grounded theory and combined for computer simulation. The first step (Problem Definition) was completed by open coding video-recorded interviews, supplemented by a literature review. The model depicts provision of sex trafficking services for victims and survivors as declining in March 2020, coincidental with COVID, but eventually rebounding. The second modeling step (Dynamic Hypothesis Formulation) was completed by open- and axial coding of interview segments, as well as consulting peer-reviewed literature. Part of the hypothesized explanation for changes over time is that the sex trafficking system behaves somewhat like a commodities market, with each of the other subsystems exhibiting delayed responses but collectively keeping trafficking levels below what they would be otherwise. Next steps (Model Building & Testing) led to a ‘proof of concept’ model that can be used to conduct simulation experiments and test various action ideas, by taking model users outside the entire system and seeing it whole. If sex trafficking dynamics unfold as hypothesized, e.g., oscillated post-COVID, then one potential leverage point is to address the lack of information feedback loops between the actual occurrence and consequences of sex trafficking and those who seek to prevent its occurrence, prosecute the traffickers, protect the victims and survivors, and partner with the other anti-trafficking advocates. Implications for researchers, administrators, and other stakeholders are discussed.

Keywords: pandemics, provisioning systems, sex trafficking, system dynamics modeling

Procedia PDF Downloads 56

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular diseases caused by hypertension are extremely threatening to human health, and early diagnosis of hypertension can save a large number of lives. Traditional hypertension detection methods require special equipment and are difficult to detect continuous blood pressure changes. In this regard, this paper first analyzes the principle of heart rate variability (HRV) and introduces sliding window and power spectral density (PSD) to analyze the time domain features and frequency domain features of HRV, and secondly, designs an HRV-based hypertension prediction network by combining Resnet, attention mechanism, and multilayer perceptron, which extracts the frequency domain through the improved ResNet18 features through a modified ResNet18, its fusion with time-domain features through an attention mechanism, and the auxiliary prediction of hypertension through a multilayer perceptron. Finally, the network was trained and tested using the publicly available SHAREE dataset on PhysioNet, and the test results showed that this network achieved 92.06% prediction accuracy for hypertension and outperformed K Near Neighbor(KNN), Bayes, Logistic, and traditional Convolutional Neural Network(CNN) models in prediction performance.

Keywords: feature extraction, heart rate variability, hypertension, residual networks

Procedia PDF Downloads 71

Authors: Cheng Fang, Lingwei Quan, Cunyue Lu

Abstract:

Human pose estimation and tracking are to accurately identify and locate the positions of human joints in the video. It is a computer vision task which is of great significance for human motion recognition, behavior understanding and scene analysis. There has been remarkable progress on human pose estimation in recent years. However, more researches are needed for human pose tracking especially for online tracking. In this paper, a framework, called PoseSRPN, is proposed for online single-person pose estimation and tracking. We use Siamese network attaching a pose estimation branch to incorporate Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) into one framework. The pose estimation branch has a simple network structure that replaces the complex upsampling and convolution network structure with deconvolution. By augmenting the loss of fully convolutional Siamese network with the pose estimation task, pose estimation and tracking can be trained in one stage. Once trained, PoseSRPN only relies on a single bounding box initialization and producing human joints location. The experimental results show that while maintaining the good accuracy of pose estimation on COCO and PoseTrack datasets, the proposed method achieves a speed of 59 frame/s, which is superior to other pose tracking frameworks.

Keywords: computer vision, pose estimation, pose tracking, Siamese network

Procedia PDF Downloads 128

Authors: Zikiou Nadia, Lahdir Mourad, Ameur Soltane

Abstract:

In this paper, we propose an effective method for image compression based on SVM Regression (SVR), with three different kernels, and biorthogonal 2D Discrete Wavelet Transform. SVM regression could learn dependency from training data and compressed using fewer training points (support vectors) to represent the original data and eliminate the redundancy. Biorthogonal wavelet has been used to transform the image and the coefficients acquired are then trained with different kernels SVM (Gaussian, Polynomial, and Linear). Run-length and Arithmetic coders are used to encode the support vectors and its corresponding weights, obtained from the SVM regression. The peak signal noise ratio (PSNR) and their compression ratios of several test images, compressed with our algorithm, with different kernels are presented. Compared with other kernels, Gaussian kernel achieves better image quality. Experimental results show that the compression performance of our method gains much improvement.

Keywords: image compression, 2D discrete wavelet transform (DWT-2D), support vector regression (SVR), SVM Kernels, run-length, arithmetic coding

Procedia PDF Downloads 357

Authors: Bandar Alahmadi, Lethia Jackson

Abstract:

Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.

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

Procedia PDF Downloads 312

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation

Procedia PDF Downloads 154

Authors: Kaomud Tyagi, Rajasree Chakraborty, Shantanu Kundu, Devkant Singha, Kailash Chandra, Vikas Kumar

Abstract:

The melon thrips, Thrips palmi is a serious pest of a wide range of agriculture crops and also act as vectors for plant viruses (genus Tospovirus, family Bunyaviridae). More molecular data on this species is required to understand the cryptic speciation and evolutionary affiliations. Mitochondrial genomes have been widely used in phylogenetic and evolutionary studies in insect. So far, mitogenomes of five thrips species (Anaphothrips obscurus, Frankliniella intonsa, Frankliniella occidentalis, Scirtothrips dorsalis and Thrips imaginis) is available in the GenBank database. In this study, we sequenced the first complete mitogenome T. palmi and compared it with available thrips mitogenomes. We assembled the mitogenome from the whole genome sequencing data generated using Illumina Hiseq2500. Annotation was performed using MITOS web-server to estimate the location of protein coding genes (PCGs), transfer RNA (tRNAs), ribosomal RNAs (rRNAs) and their secondary structures. The boundaries of PCGs and rRNAs was confirmed manually in NCBI. Phylogenetic analyses were performed using the 13 PCGs data using maximum likelihood (ML) in PAUP, and Bayesian inference (BI) in MrBayes 3.2. The complete mitogenome of T. palmi was 15,333 base pairs (bp), which was greater than the genomes of A. obscurus (14,890bp), F. intonsa (15,215 bp), F. occidentalis (14,889 bp) and S. dorsalis South Asia strain (SA1) (14,283 bp), but smaller than the genomes of T. imaginis (15,407 bp) and S. dorsalis East Asia strain (EA1) (15,343bp). Like in other thrips species, the mitochondrial genome of T. palmi was represented by 37 genes, including 13 PCGs, large and small ribosomal RNA (rrnL and rrnS) genes, 22 transfer RNA (tRNAs) genes (with one extra gene for trn-Serine) and two A+T-rich control regions (CR1 and CR2). Thirty one genes were observed on heavy (H) strand and six genes on the light (L) strand. The six tRNA genes (trnG,trnK, trnY, trnW, trnF, and trnH) were found to be conserved in all thrips species mitogenomes in their locations relative to a protein-coding or rRNA gene upstream or downstream. The gene arrangements of T. palmi is very close to T. imaginis except the rearrangements in tRNAs genes: trnR (arginine), and trnE (glutamic acid) were found to be located between cox3 and CR2 in T. imaginis which were translocated between atp6 and CR1 in T. palmi; trnL1 (Leucine) and trnS1(Serine) were located between atp6 and CR1 in T. imaginis which were translocated between cox3 and CR2 in T. palmi. The location of CR1 upstream of nad5 gene was suggested to be ancestral condition of the thrips species in subfamily Thripinae, was also observed in T. palmi. Both the Maximum likelihood (ML) and Bayesian Inference (BI) phylogenetic trees generated resulted in similar topologies. The T. palmi was clustered with T. imaginis. We concluded that more molecular data on the diverse thrips species from different hierarchical level is needed, to understand the phylogenetic and evolutionary relationships among them.

Keywords: thrips, comparative mitogenomics, gene rearrangements, phylogenetic analysis

Procedia PDF Downloads 144

Authors: Leen Al Kassab, Sarah Johns, Helen Noble, Nawal Nour, Elizabeth Janiak, Sarrah Shahawy

Abstract:

Introduction: Immigrant and refugee women experience disparities in sexual and reproductive health (SRH) outcomes, partially as a result of barriers to SRH literacy and to regular healthcare access and engagement. Despite the existing data highlighting growing needs for culturally relevant and structurally competent care, interventions are scarce and not well-documented. Methods: In this IRB-approved study, we used a community-based participatory research approach, with the assistance of a community advisory board, to conduct a qualitative needs assessment of SRH knowledge and service engagement with immigrant and refugee women from Africa or the Middle East and currently residing in Boston. We conducted a total of nine focus group discussions (FGDs) in partnership with medical, community, and religious centers, in six languages: Arabic, English, French, Somali, Pashtu, and Dari. A total of 44 individuals participated. We explored migrant and refugee women’s current and evolving SRH care needs and gaps, specifically related to the development of interventions and clinical best practices targeting SRH literacy, healthcare engagement, and informed decision-making. Recordings of the FGDs were transcribed verbatim and translated by interpreter services. We used open coding with multiple coders who resolved discrepancies through consensus and iteratively refined our codebook while coding data in batches using Dedoose software. Results: Participants reported immigrant adaptation experiences, discrimination, and feelings of trust, autonomy, privacy, and connectedness to family, community, and the healthcare system as factors surrounding SRH knowledge and needs. The context of previously learned SRH knowledge was commonly noted to be in schools, at menstruation, before marriage, from family members, partners, friends, and online search engines. Common themes included empowering strength drawn from religious and cultural communities, difficulties bridging educational gaps with their US- born daughters, and a desire for more SRH education from multiple sources, including family, health care providers, and religious experts & communities. Regarding further SRH education, participants’ preferences varied regarding ideal platform (virtual vs. in-person), location (in religious and community centers or not), smaller group sizes, and the involvement of men. Conclusions: Based on these results, empowering SRH initiatives should include both community and religious center-based, as well as clinic-based, interventions. Interventions should be composed of frequent educational workshops in small groups involving age-grouped women, daughters, and (sometimes) men, tailored SRH messaging, and the promotion of culturally, religiously, and linguistically competent care.

Keywords: community, immigrant, religion, sexual & reproductive health, women's health

Procedia PDF Downloads 101

Authors: Issa Hussein Manita

Abstract:

This paper presents an example of industrial information system design and implementation (IIDC), the most common software engineering design steps that are applied to the different design stages. We are going through the life cycle of software system development. We start by a study of system requirement and end with testing and delivering system, going by system design and coding, program integration and system integration step. The most modern software design tools available used in the design this includes, but not limited to, Unified Modeling Language (UML), system modeling, SQL server side application, uses case analysis, design and testing as applied to information processing systems. The system is designed to perform tasks specified by the client with real data. By the end of the implementation of the system, default or user defined acceptance policy to provide an overall score as an indication of the system performance is used. To test the reliability of he designed system, it is tested in different environment and different work burden such as multi-user environment.

Keywords: software engineering, design, system requirement, integration, unified modeling language

Procedia PDF Downloads 549

Authors: Xiang Yu, Chuntao Feng, Lu Yang, Meiyang Song, Wenhao Zhou

Abstract:

The existing two-dimensional micro-Doppler features extraction ignores the correlation information between the spatial and temporal dimension features. For the range-Doppler map, the time dimension is introduced, and a frequency modulation continuous wave (FMCW) radar human fall detection algorithm based on time-varying range-Doppler features is proposed. Firstly, the range-Doppler sequence maps are generated from the echo signals of the continuous motion of the human body collected by the radar. Then the three-dimensional data cube composed of multiple frames of range-Doppler maps is input into the three-dimensional Convolutional Neural Network (3D CNN). The spatial and temporal features of time-varying range-Doppler are extracted by the convolution layer and pool layer at the same time. Finally, the extracted spatial and temporal features are input into the fully connected layer for classification. The experimental results show that the proposed fall detection algorithm has a detection accuracy of 95.66%.

Keywords: FMCW radar, fall detection, 3D CNN, time-varying range-doppler features

Procedia PDF Downloads 94

Authors: Masood Monjezi

Abstract:

The English teachers’ pedagogical identity construction is the way teachers go through the process of becoming teachers and how they maintain their teaching selves. The pedagogical identity of teachers is influenced by several factors within the individual and the society. The purpose of this study was to compare the imagined social world of the pre-service teachers with the real experiences the in-service teachers had in the context of Iran to see how prepared the pre-service teachers are with a view to their identity being. This study used a qualitative approach to collection and analysis of the data. Structured and semi-structured interviews, focus groups and process logs were used to collect the data. Then, using open coding, the data were analyzed. The findings showed that the imagined world of the pre-service teachers partly corresponded with the real world experiences of the in-service teachers leaving the pre-service teachers unprepared for their real world teaching profession. The findings suggest that the current approaches to English teacher training are in need of modification to better prepare the pre-service teachers for the future that expects them.

Keywords: imagined professional world, in-service teachers, pre-service teachers, real experiences, community of practice, identity

Procedia PDF Downloads 311

Authors: Louis Okon Akpan

Abstract:

National Open University of Nigeria (NOUN) is an open and distance learning institution whose aim is to provide education for all and also promote lifelong learning in Nigeria. Before now, student-centred learning was adopted. In recent times, online facilitation has been introduced. Therefore, the study explores ways in which students are satisfied with online facilitation provided by NOUN lecturers. A qualitative approach was adopted. The interpretive paradigm was employed as a lens to interpret narratives from the participants. In order to gather information for the study, a semi-structured interview was developed for sixteen participants who were purposively selected from eight facilities of the university. After data gathering from the field, it was subjected to transcription and coding. The emergence of themes from the coded data was analysed using thematic analysis. Findings indicated that students found online learning, recently introduced by the university management, extremely fulfilling and rewarding.

Keywords: online facilitation, lecturer, students’ satisfaction, National Open University of Nigeria

Procedia PDF Downloads 58