Search results for: convolutional coding

Authors: Po-Hao Huang, Pei-Ju Chiang

Abstract:

The structured light 3D scanner is commonly used for measuring the 3D shape of an object. Through projecting designed light patterns on the object, deformed patterns can be obtained and used for the geometric shape reconstruction. At present, Gray code is the most reliable and commonly used light pattern in the structured light 3D scanner. However, the trade-off between scanning efficiency and accuracy is a long-standing and challenging problem. The design of light patterns plays a significant role in the scanning efficiency and accuracy. Thereby, we proposed a novel encoding method integrating color information and Gray-code to improve the scanning efficiency. We will demonstrate that with the proposed method, the scanning time can be reduced to approximate half of the one needed by Gray-code without reduction of precision.

Keywords: gray-code, structured light scanner, 3D shape acquisition, 3D reconstruction

Procedia PDF Downloads 457

Authors: Haozhe Xiang

Abstract:

With the rise of the Internet of Things era, intelligent products are gradually integrating into people's lives. Pedestrian trajectory prediction has become a key issue, which is crucial for the motion path planning of intelligent agents such as autonomous vehicles, robots, and drones. In the current technological context, deep learning technology is becoming increasingly sophisticated and gradually replacing traditional models. The pedestrian trajectory prediction algorithm combining neural networks and attention mechanisms has significantly improved prediction accuracy. Based on in-depth research on deep learning and pedestrian trajectory prediction algorithms, this article focuses on physical environment modeling and learning of historical trajectory time dependence. At the same time, social interaction between pedestrians and scene interaction between pedestrians and the environment were handled. An improved pedestrian trajectory prediction algorithm is proposed by analyzing the existing model architecture. With the help of these improvements, acceptable predicted trajectories were successfully obtained. Experiments on public datasets have demonstrated the algorithm's effectiveness and achieved acceptable results.

Keywords: deep learning, graph convolutional network, attention mechanism, LSTM

Procedia PDF Downloads 70

Authors: Güzi̇n Ti̇rkeş, Özge Teki̇n, Kerem Kurtuluş, Y. Yekta Yurtseven, Murat Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: convolutional neural networks, deep learning, image classification, scanning electron microscope

Procedia PDF Downloads 125

Authors: Avinash Malladhi

Abstract:

Forensic accounting is a specialized field that involves the application of accounting principles, investigative skills, and legal knowledge to detect and prevent fraud. With the rise of big data and technological advancements, artificial intelligence (AI) and machine learning (ML) algorithms have emerged as powerful tools for forensic accountants to enhance their fraud detection capabilities. In this paper, we review and analyze various AI/ML algorithms that are commonly used in forensic accounting, including supervised and unsupervised learning, deep learning, natural language processing Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Support Vector Machines (SVMs), Decision Trees, and Random Forests. We discuss their underlying principles, strengths, and limitations and provide empirical evidence from existing research studies demonstrating their effectiveness in detecting financial fraud. We also highlight potential ethical considerations and challenges associated with using AI/ML in forensic accounting. Furthermore, we highlight the benefits of these technologies in improving fraud detection and prevention in forensic accounting.

Keywords: AI, machine learning, forensic accounting & fraud detection, anti money laundering, Benford's law, fraud triangle theory

Procedia PDF Downloads 93

Authors: Jeong-Hyun Park, Young-Sik Park, Hyo-Teag Jung

Abstract:

This paper presents static analysis deployment model for code quality on R&D Projects of SW Development. The proposed model includes the scope of R&D projects and index for static analysis of source code, operation model and execution process, environments and infrastructure system for R&D projects of SW development. There is the static analysis result of pilot project as case study based on the proposed deployment model and environment, and strategic considerations for success operation of the proposed static analysis deployment model for R&D Projects of SW Development. The proposed static analysis deployment model in this paper will be adapted and improved continuously for quality upgrade of R&D projects, and customer satisfaction of developed source codes and products.

Keywords: static analysis, code quality, coding rules, automation tool

Procedia PDF Downloads 520

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Blaise Fyama, Elie Museng, Grace Mukoma

Abstract:

In this article we present a java implementation of video telephony using the SIP protocol (Session Initiation Protocol). After a functional analysis of the SIP protocol, we relied on the work of Italian researchers of University of Parma-Italy to acquire adequate libraries for the development of our own communication tool. In order to optimize the code and improve the prototype, we used, in an incremental approach, test techniques based on a static analysis based on the evaluation of the complexity of the software with the application of metrics and the number cyclomatic of Mccabe. The objective is to promote the emergence of local start-ups producing IP video in a well understood local context. We have arrived at the creation of a video telephony tool whose code is optimized.

Keywords: static analysis, coding complexity metric mccabe, Sip, uml

Procedia PDF Downloads 119

Authors: Meruert Serik, Nassipzhan Duisegaliyeva, Danara Tleumagambetova

Abstract:

The article highlights and describes the characteristic features of real-time face detection in images and videos using machine learning algorithms. Students of educational programs reviewed the research work "6B01511-Computer Science", "7M01511-Computer Science", "7M01525- STEM Education," and "8D01511-Computer Science" of Eurasian National University named after L.N. Gumilyov. As a result, the advantages and disadvantages of Haar Cascade (Haar Cascade OpenCV), HoG SVM (Histogram of Oriented Gradients, Support Vector Machine), and MMOD CNN Dlib (Max-Margin Object Detection, convolutional neural network) detectors used for face detection were determined. Dlib is a general-purpose cross-platform software library written in the programming language C++. It includes detectors used for determining face detection. The Cascade OpenCV algorithm is efficient for fast face detection. The considered work forms the basis for the development of machine learning methods by future computer science teachers.

Keywords: algorithm, artificial intelligence, education, machine learning

Procedia PDF Downloads 73

Authors: Pawan Kumar Mishra, Ganesh Singh Bisht

Abstract:

Super-resolution is the technique that is being used in computer vision to construct high-resolution images from a single low-resolution image. It is used to increase the frequency component, recover the lost details and removing the down sampling and noises that caused by camera during image acquisition process. High-resolution images or videos are desired part of all image processing tasks and its analysis in most of digital imaging application. The target behind super-resolution is to combine non-repetition information inside single or multiple low-resolution frames to generate a high-resolution image. Many methods have been proposed where multiple images are used as low-resolution images of same scene with different variation in transformation. This is called multi-image super resolution. And another family of methods is single image super-resolution that tries to learn redundancy that presents in image and reconstruction the lost information from a single low-resolution image. Use of deep learning is one of state of art method at present for solving reconstruction high-resolution image. In this research, we proposed Deep Denoising Super Resolution (DDSR) that is a deep neural network for effectively reconstruct the high-resolution image from low-resolution image.

Keywords: resolution, deep-learning, neural network, de-blurring

Procedia PDF Downloads 517

Authors: Kate Jonathan

Abstract:

This article presents the findings of a qualitative study into parenting practices in families of Pakistani origin in the North of England. It focuses on the involvement of fathers in childrearing within the Pakistani community. Data was generated from thirty parents’ in-depth interviews and ethnographic observation of parent-child relationships. The data was analyzed by an initial coding, identifying themes, a grouping of patterns, and arriving at a meaningful understanding. The study shows that the traditional role of fathers as breadwinners, providing discipline and protection, was still prominent in most of the Pakistani families who took part in the study. However, few men were becoming pragmatic and would engage in more childrearing chores, as their wives. The findings indicate that previous general portrayal of fatherhood as the primary, and sometimes, only, breadwinner is changing to encompass a lot more in Pakistani communities. Nowadays, some fathers are more involved in caregiving and are increasingly become co-contributors in the development of their children. However, the change is slower in some families than others and varied within this community.

Keywords: caregiving, childrearing, fathers, Pakistani families

Procedia PDF Downloads 296

Authors: S. C. Sharma, Ankit Gambhir, Rajeev Arya

Abstract:

In today’s era data security is an important concern and most demanding issues because it is essential for people using online banking, e-shopping, reservations etc. The two major techniques that are used for secure communication are Cryptography and Steganography. Cryptographic algorithms scramble the data so that intruder will not able to retrieve it; however steganography covers that data in some cover file so that presence of communication is hidden. This paper presents the implementation of Ron Rivest, Adi Shamir, and Leonard Adleman (RSA) Algorithm with Image and Audio Steganography and Data Encryption Standard (DES) Algorithm with Image and Audio Steganography. The coding for both the algorithms have been done using MATLAB and its observed that these techniques performed better than individual techniques. The risk of unauthorized access is alleviated up to a certain extent by using these techniques. These techniques could be used in Banks, RAW agencies etc, where highly confidential data is transferred. Finally, the comparisons of such two techniques are also given in tabular forms.

Keywords: audio steganography, data security, DES, image steganography, intruder, RSA, steganography

Procedia PDF Downloads 290

Authors: Mohammad Saleh Vahdatpour, Yanqing Zhang

Abstract:

Understanding the neural mechanisms underlying motion detection in the human visual system has long been a fascinating challenge in neuroscience and artificial intelligence. This paper presents a spiking neural network model inspired by the processing of motion information in the primate visual system, particularly focusing on the Middle Temporal (MT) area. In our study, we propose a multi-layer spiking neural network model to perform motion detection tasks, leveraging the idea that synaptic delays in neuronal communication are pivotal in motion perception. Synaptic delay, determined by factors like axon length and myelin insulation, affects the temporal order of input spikes, thereby encoding motion direction and speed. Overall, our spiking neural network model demonstrates the feasibility of capturing motion detection principles observed in the primate visual system. The combination of synaptic delays, learning mechanisms, and shared weights and delays in SMD provides a promising framework for motion perception in artificial systems, with potential applications in computer vision and robotics.

Keywords: neural network, motion detection, signature detection, convolutional neural network

Procedia PDF Downloads 87

Authors: Almostafa Abdelaziz, Liang Guozhu, Anwer Elsayed

Abstract:

The determination of grain geometry is an important and critical step in the design of solid propellant rocket motor. In this study, the design process involved parametric geometry modeling in CAD, MATLAB coding of performance prediction and 2D star grain ignition experiment. The 2D star grain burnback achieved by creating new surface via each web increment and calculating geometrical properties at each step. The 2D star grain is further modified to burn as a tapered 3D star grain. Zero dimensional method used to calculate the internal ballistic performance. Experimental and theoretical results were compared in order to validate the performance prediction of the solid rocket motor. The results show that the usage of 3D grain geometry will decrease the pressure inside the combustion chamber and enhance the volumetric loading ratio.

Keywords: burnback analysis, rocket motor, star grain, three dimensional grains

Procedia PDF Downloads 244

Authors: J. L. Liu, L. Wang, B. Zhu, J. Zhou, W. D. Gao

Abstract:

Fabric textures are very common in our daily life. However, we never explore the representation of fabric textures from neuroscience view. Theoretical studies suggest that primary visual cortex (V1) uses a sparse code to efficiently represent natural images. However, how the simple cells in V1 encode the artificial textures is still a mystery. So, here we will take fabric texture as stimulus to study the response of independent component analysis that is established to model the receptive field of simple cells in V1. Experimental results based on 140 classical fabric images indicate that the receptive fields of simple cells have obvious selectivity in orientation, frequency, and phase when drifting gratings are used to determine their tuning properties. Additionally, the distribution of optimal orientation and frequency shows that the patch size selected from each original fabric image has a significant effect on the frequency selectivity.

Keywords: fabric texture, receptive filed, simple cell, spare coding

Procedia PDF Downloads 475

Authors: William Whiteley, Jens Gregor

Abstract:

In recent developments of direct neural network based positron emission tomography (PET) reconstruction, two prominent architectures have emerged for converting measurement data into images: 1) networks that contain fully-connected layers; and 2) networks that primarily use a convolutional encoder-decoder architecture. In this paper, we present a multi-modal direct PET reconstruction method called MDPET, which is a hybrid approach that combines the advantages of both types of networks. MDPET processes raw data in the form of sinograms and histo-images in concert with attenuation maps to produce high quality multi-slice PET images (e.g., 8x440x440). MDPET is trained on a large whole-body patient data set and evaluated both quantitatively and qualitatively against target images reconstructed with the standard PET reconstruction benchmark of iterative ordered subsets expectation maximization. The results show that MDPET outperforms the best previously published direct neural network methods in measures of bias, signal-to-noise ratio, mean absolute error, and structural similarity.

Keywords: deep learning, image reconstruction, machine learning, neural network, positron emission tomography

Procedia PDF Downloads 110

Authors: Septimia Sarbu

Abstract:

The entropy rate of a stochastic process is a fundamental concept in information theory. It provides a limit to the amount of information that can be transmitted reliably over a communication channel, as stated by Shannon's coding theorems. Recently, researchers have focused on developing new measures of information that generalize Shannon's classical theory. The aim is to design more efficient information encoding and transmission schemes. This paper continues the study of generalized entropy rates, by deriving a closed-form solution to the Sharma-Mittal entropy rate for Gaussian processes. Using the squeeze theorem, we solve the limit in the definition of the entropy rate, for different values of alpha and beta, which are the parameters of the Sharma-Mittal entropy. In the end, we compare it with Shannon and Rényi's entropy rates for Gaussian processes.

Keywords: generalized entropies, Sharma-Mittal entropy rate, Gaussian processes, eigenvalues of the covariance matrix, squeeze theorem

Procedia PDF Downloads 519

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 90

Authors: Oke Oktavianty, Tadayuki Kyoutani, Shigeyuki Haruyama, Junji Kaneko, Ken Kaminishi

Abstract:

Modelica has many advantages and it is very useful in modeling and simulation especially for the multi-domain with a complex technical system. However, the big obstacle for a beginner is to understand the basic concept and to build a new system model for a real system. In order to understand how to solve the simple circuit model by hand translation and to get a better understanding of how modelica works, we provide a detailed explanation about solver ordering system in horizontal and vertical sorting and make some proposals for improvement. In this study, some difficulties in using modelica software with the original concept and the comparison with Finite Element Method (FEM) approach is discussed. We also present our textual modeling approach using FEM concept for acausal and causal model construction. Furthermore, simulation results are provided that demonstrate the comparison between using textual modeling with original coding in modelica and FEM concept.

Keywords: FEM, a causal model, modelica, horizontal and vertical sorting

Procedia PDF Downloads 308

Authors: Edward Schwalb, Matthias Dehmer, Michael Schlenkrich, Farzaneh Taslimi, Ketron Mitchell-Wynne, Horen Kuecuekyan

Abstract:

We present a generalized feature extraction approach for supporting Machine Learning (ML) algorithms which perform tasks similar to Finite-Element Analysis (FEA). We report results for estimating the Head Injury Categorization (HIC) of vehicle engine compartments across various impact scenarios. Our experiments demonstrate that models learned using features derived with a simple discretization approach provide a reasonable approximation of a full simulation. We observe that Decision Trees could be as effective as Neural Networks for the HIC task. The simplicity and performance of the learned Decision Trees could offer a trade-off of a multiple order of magnitude increase in speed and cost improvement over full simulation for a reasonable approximation. When used as a complement to full simulation, the approach enables rapid approximate feedback to engineering teams before submission for full analysis. The approach produces mesh independent features and is further agnostic of the assembly structure.

Keywords: mechanical design validation, FEA, supervised decision tree, convolutional neural network.

Procedia PDF Downloads 139

Authors: Tolulope Aremu

Abstract:

The key process steps to produce liquid detergent products will introduce potential defects, such as formulation, mixing, filling, and packaging, which might compromise product quality, consumer safety, and operational efficiency. Real-time identification and characterization of such defects are of prime importance for maintaining high standards and reducing waste and costs. Usually, defect detection is performed by human inspection or rule-based systems, which is very time-consuming, inconsistent, and error-prone. The present study overcomes these limitations in dealing with optimization in defect characterization within the process for making liquid detergents using Machine Learning algorithms. Performance testing of various machine learning models was carried out: Support Vector Machine, Decision Trees, Random Forest, and Convolutional Neural Network on defect detection and classification of those defects like wrong viscosity, color deviations, improper filling of a bottle, packaging anomalies. These algorithms have significantly benefited from a variety of optimization techniques, including hyperparameter tuning and ensemble learning, in order to greatly improve detection accuracy while minimizing false positives. Equipped with a rich dataset of defect types and production parameters consisting of more than 100,000 samples, our study further includes information from real-time sensor data, imaging technologies, and historic production records. The results are that optimized machine learning models significantly improve defect detection compared to traditional methods. Take, for instance, the CNNs, which run at 98% and 96% accuracy in detecting packaging anomaly detection and bottle filling inconsistency, respectively, by fine-tuning the model with real-time imaging data, through which there was a reduction in false positives of about 30%. The optimized SVM model on detecting formulation defects gave 94% in viscosity variation detection and color variation. These values of performance metrics correspond to a giant leap in defect detection accuracy compared to the usual 80% level achieved up to now by rule-based systems. Moreover, this optimization with models can hasten defect characterization, allowing for detection time to be below 15 seconds from an average of 3 minutes using manual inspections with real-time processing of data. With this, the reduction in time will be combined with a 25% reduction in production downtime because of proactive defect identification, which can save millions annually in recall and rework costs. Integrating real-time machine learning-driven monitoring drives predictive maintenance and corrective measures for a 20% improvement in overall production efficiency. Therefore, the optimization of machine learning algorithms in defect characterization optimum scalability and efficiency for liquid detergent companies gives improved operational performance to higher levels of product quality. In general, this method could be conducted in several industries within the Fast moving consumer Goods industry, which would lead to an improved quality control process.

Keywords: liquid detergent manufacturing, defect detection, machine learning, support vector machines, convolutional neural networks, defect characterization, predictive maintenance, quality control, fast-moving consumer goods

Procedia PDF Downloads 18

Authors: Belayneh Matebie, Michael Melese

Abstract:

The study focuses on addressing the challenges in classifying and ensuring the quality of Eragrostis Teff, a small and round grain that is the smallest cereal grain. Employing a traditional classification method is challenging because of its small size and the similarity of its environmental characteristics. To overcome this, this study employs a machine learning approach to develop a source and quality classification system for Teff cereal. Data is collected from various production areas in the Amhara regions, considering two types of cereal (high and low quality) across eight classes. A total of 5,920 images are collected, with 740 images for each class. Image enhancement techniques, including scaling, data augmentation, histogram equalization, and noise removal, are applied to preprocess the data. Convolutional Neural Network (CNN) is then used to extract relevant features and reduce dimensionality. The dataset is split into 80% for training and 20% for testing. Different classifiers, including FVGG16, FINCV3, QSCTC, EMQSCTC, SVM, and RF, are employed for classification, achieving accuracy rates ranging from 86.91% to 97.72%. The ensemble of FVGG16, FINCV3, and QSCTC using the Max-Voting approach outperforms individual algorithms.

Keywords: Teff, ensemble learning, max-voting, CNN, SVM, RF

Procedia PDF Downloads 53

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 250

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 291

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 63

Authors: Ramzi Rihane, Yassine Benayed

Abstract:

Epilepsy is a chronic neurological disorder characterized by recurrent, unprovoked seizures resulting from abnormal electrical activity in the brain. Timely and accurate detection of these seizures is essential for improving patient care. In this study, we leverage the UK Bonn University open-source EEG dataset and employ advanced deep-learning techniques to automate the detection of epileptic seizures. By extracting key features from both time and frequency domains, as well as Spectrogram features, we enhance the performance of various deep learning models. Our investigation includes architectures such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), 1D Convolutional Neural Networks (1D-CNN), and hybrid CNN-LSTM and CNN-BiLSTM models. The models achieved impressive accuracies: LSTM (98.52%), Bi-LSTM (98.61%), CNN-LSTM (98.91%), CNN-BiLSTM (98.83%), and CNN (98.73%). Additionally, we utilized a data augmentation technique called SMOTE, which yielded the following results: CNN (97.36%), LSTM (97.01%), Bi-LSTM (97.23%), CNN-LSTM (97.45%), and CNN-BiLSTM (97.34%). These findings demonstrate the effectiveness of deep learning in capturing complex patterns in EEG signals, providing a reliable and scalable solution for real-time seizure detection in clinical environments.

Keywords: electroencephalogram, epileptic seizure, deep learning, LSTM, CNN, BI-LSTM, seizure detection

Procedia PDF Downloads 12

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 320

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 102

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

Abstract:

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

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

Procedia PDF Downloads 259

Authors: 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 76

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 32