Search results for: convolutional architectures

Authors: Thilina Ranaweera, Enes Makalic, John L. Hopper, Adrian Bickerstaffe

Abstract:

Data are the primary asset of biomedical researchers, and the engine for both discovery and research translation. As the volume and complexity of research datasets increase, especially with new technologies such as large single nucleotide polymorphism (SNP) chips, so too does the requirement for software to manage, process and analyze the data. Researchers often need to execute complicated queries and conduct complex analyzes of large-scale datasets. Existing tools to analyze such data, and other types of high-dimensional data, unfortunately suffer from one or more major problems. They typically require a high level of computing expertise, are too simplistic (i.e., do not fit realistic models that allow for complex interactions), are limited by computing power, do not exploit the computing power of large-scale parallel architectures (e.g. supercomputers, GPU clusters etc.), or are limited in the types of analysis available, compounded by the fact that integrating new analysis methods is not straightforward. Solutions to these problems, such as those developed and implemented on parallel architectures, are currently available to only a relatively small portion of medical researchers with access and know-how. The past decade has seen a rapid expansion of data management systems for the medical domain. Much attention has been given to systems that manage phenotype datasets generated by medical studies. The introduction of heterogeneous genomic data for research subjects that reside in these systems has highlighted the need for substantial improvements in software architecture. To address this problem, we have developed SPARK, an enabling and translational system for medical research, leveraging existing high performance computing resources, and analysis techniques currently available or being developed. It builds these into The Ark, an open-source web-based system designed to manage medical data. SPARK provides a next-generation biomedical data management solution that is based upon a novel Micro-Service architecture and Big Data technologies. The system serves to demonstrate the applicability of Micro-Service architectures for the development of high performance computing applications. When applied to high-dimensional medical datasets such as genomic data, relational data management approaches with normalized data structures suffer from unfeasibly high execution times for basic operations such as insert (i.e. importing a GWAS dataset) and the queries that are typical of the genomics research domain. SPARK resolves these problems by incorporating non-relational NoSQL databases that have been driven by the emergence of Big Data. SPARK provides researchers across the world with user-friendly access to state-of-the-art data management and analysis tools while eliminating the need for high-level informatics and programming skills. The system will benefit health and medical research by eliminating the burden of large-scale data management, querying, cleaning, and analysis. SPARK represents a major advancement in genome research technologies, vastly reducing the burden of working with genomic datasets, and enabling cutting edge analysis approaches that have previously been out of reach for many medical researchers.

Keywords: biomedical research, genomics, information systems, software

Procedia PDF Downloads 232

Authors: Ahmed Madian, Muaz Aljarhi

Abstract:

Coordinate Rotation Digital Computer (CORDIC) is a unique digital computing unit intended for the computation of mathematical operations and functions. This paper presents a multi-CORDIC processor that integrates different CORDIC architectures on a single FPGA chip and allows the user to select the CORDIC architecture to proceed with based on what he wants to calculate and his/her needs. Synthesis show that radix 2 CORDIC has the lowest clock delay, radix 8 CORDIC has the highest LUT usage and lowest register usage while Hybrid Radix 4 CORDIC had the highest clock delay.

Keywords: multi, CORDIC, FPGA, processor

Procedia PDF Downloads 438

Authors: Tesfaye Alamirew Dessie

Abstract:

Our study focuses on developing a Model Predictive Controller (MPC) and evaluating it against a traditional PID for a pasteurization process. Utilizing system identification from the experimental data, the dynamics of the pasteurization process were calculated. Using best fit with data validation, residual, and stability analysis, the quality of several model architectures was evaluated. The validation data fit the auto-regressive with exogenous input (ARX322) model of the pasteurization process by roughly 80.37 percent. The ARX322 model structure was used to create MPC and PID control techniques. After comparing controller performance based on settling time, overshoot percentage, and stability analysis, it was found that MPC controllers outperform PID for those parameters.

Keywords: MPC, PID, ARX, pasteurization

Procedia PDF Downloads 118

Authors: Donatella R. Fiorino, Marzia Loddo

Abstract:

The practice of freeing monuments from subsequent additions crosses the entire history of conservation and it is traditionally connected to the aim of valorisation, both for cultural and educational purpose and recently even for touristic exploitation. Defence heritage has been widely interested by these cultural and technical moods from philological restoration to critic innovations. A renovated critical analysis of Italian episodes and in particular the Sardinian case of the area of San Pancrazio in Cagliari, constitute an important lesson about the limits of this practice and the uncertainty in terms of results, towards the definition of a sustainable good practice in the restoration of military architectures.

Keywords: defensive architecture, liberation, Valorisation for tourism, historical restoration

Procedia PDF Downloads 298

Authors: C. J. Rossouw, T. I. van Niekerk

Abstract:

The global manufacturing industry is utilizing the internet and cloud-based services to further explore the anatomy and optimize manufacturing processes in support of the movement into the Fourth Industrial Revolution (4IR). The 4IR from a third world and African perspective is hindered by the fact that many manufacturing systems that were developed in the third industrial revolution are not inherently equipped to utilize the internet and services of the 4IR, hindering the progression of third world manufacturing industries into the 4IR. This research focuses on the development of a non-invasive and cost-effective cyber-physical IoT system that will exploit a machine’s vibration to expose semantic characteristics in the manufacturing process and utilize these results through a real-time cloud-based machine condition monitoring system with the intention to optimize the system. A microcontroller-based IoT sensor was designed to acquire a machine’s mechanical vibration data, process it in real-time, and transmit it to a cloud-based platform via Wi-Fi and the internet. Time-frequency Fourier analysis was applied to the vibration data to form an image representation of the machine’s behaviour. This data was used to train a Convolutional Neural Network (CNN) to learn semantic characteristics in the machine’s behaviour and relate them to a state of operation. The same data was also used to train a Convolutional Autoencoder (CAE) to detect anomalies in the data. Real-time edge-based artificial intelligence was achieved by deploying the CNN and CAE on the sensor to analyse the vibration. A cloud platform was deployed to visualize the vibration data and the results of the CNN and CAE in real-time. The cyber-physical IoT system was deployed on a semi-automated metal granulation machine with a set of trained machine learning models. Using a single sensor, the system was able to accurately visualize three states of the machine’s operation in real-time. The system was also able to detect a variance in the material being granulated. The research demonstrates how non-IoT manufacturing systems can be equipped with edge-based artificial intelligence to establish a remote machine condition monitoring system.

Keywords: IoT, cyber-physical systems, artificial intelligence, manufacturing, vibration analytics, continuous machine condition monitoring

Procedia PDF Downloads 57

Authors: Himanshu Sharma, Karthik Kumar, Harish Kumar

Abstract:

The major problem in crop cultivation is the occurrence of multiple crop diseases. During the growth stage, timely identification of crop diseases is paramount to ensure the high yield of crops, lower production costs, and minimize pesticide usage. In most cases, crop diseases produce observable characteristics and symptoms. The Surveyors usually diagnose crop diseases when they walk through the fields. However, surveyor inspections tend to be biased and error-prone due to the nature of the monotonous task and the subjectivity of individuals. In addition, visual inspection of each leaf or plant is costly, time-consuming, and labour-intensive. Furthermore, the plant pathologists and experts who can often identify the disease within the plant according to their symptoms in early stages are not readily available in remote regions. Therefore, this study specifically addressed early detection of leaf scald, red rot, and eyespot types of diseases within sugarcane plants. The study proposes a computer vision-based approach using a convolutional neural network (CNN) for automatic identification of crop diseases. To facilitate this, firstly, images of sugarcane diseases were taken from google without modifying the scene, background, or controlling the illumination to build the training dataset. Then, the testing dataset was developed based on the real-time collected images from the sugarcane field from India. Then, the image dataset is pre-processed for feature extraction and selection. Finally, the CNN-based Visual Geometry Group (VGG) model was deployed on the training and testing dataset to classify the images into diseased and healthy sugarcane plants and measure the model's performance using various parameters, i.e., accuracy, sensitivity, specificity, and F1-score. The promising result of the proposed model lays the groundwork for the automatic early detection of sugarcane disease. The proposed research directly sustains an increase in crop yield.

Keywords: automatic classification, computer vision, convolutional neural network, image processing, sugarcane disease, visual geometry group

Procedia PDF Downloads 84

Authors: Xiaobo Liu, Rakesh Mishra, Yun Zhang

Abstract:

Continuous monitoring of forest canopy height with large coverage is essential for obtaining forest carbon stocks and emissions, quantifying biomass estimation, analyzing vegetation coverage, and determining biodiversity. LiDAR can be used to collect accurate woody vegetation structure such as canopy height. However, LiDAR’s coverage is usually limited because of its high cost and limited maneuverability, which constrains its use for dynamic and large area forest canopy monitoring. On the other hand, optical satellite images, like Sentinel-2, have the ability to cover large forest areas with a high repeat rate, but they do not have height information. Hence, exploring the solution of integrating LiDAR data and Sentinel-2 images to enlarge the coverage of forest canopy height prediction and increase the prediction repeat rate has been an active research topic in the environmental remote sensing community. In this study, we explore the potential of training a Random Forest Regression (RFR) model and a Convolutional Neural Network (CNN) model, respectively, to develop two predictive models for predicting and validating the forest canopy height of the Acadia Forest in New Brunswick, Canada, with a 10m ground sampling distance (GSD), for the year 2018 and 2021. Two 10m airborne LiDAR-derived canopy height models, one for 2018 and one for 2021, are used as ground truth to train and validate the RFR and CNN predictive models. To evaluate the prediction performance of the trained RFR and CNN models, two new predicted canopy height maps (CHMs), one for 2018 and one for 2021, are generated using the trained RFR and CNN models and 10m Sentinel-2 images of 2018 and 2021, respectively. The two 10m predicted CHMs from Sentinel-2 images are then compared with the two 10m airborne LiDAR-derived canopy height models for accuracy assessment. The validation results show that the mean absolute error (MAE) for year 2018 of the RFR model is 2.93m, CNN model is 1.71m; while the MAE for year 2021 of the RFR model is 3.35m, and the CNN model is 3.78m. These demonstrate the feasibility of using the RFR and CNN models developed in this research for predicting large-coverage forest canopy height at 10m spatial resolution and a high revisit rate.

Keywords: remote sensing, forest canopy height, LiDAR, Sentinel-2, artificial intelligence, random forest regression, convolutional neural network

Procedia PDF Downloads 48

Authors: Marcos Valdez Alexander Junior, Igor Aguilar-Alonso

Abstract:

Malnutrition is the root of different diseases that universally affect everyone, diseases such as obesity and malnutrition. The objective of this research is to predict the calories of the food to be eaten, developing a smart mobile application to show the user if a meal is balanced. Due to the large percentage of obesity and malnutrition in Peru, the present work is carried out. The development of the intelligent application is proposed with a three-layer architecture, and for the prediction of the nutritional value of the food, the use of pre-trained models based on convolutional neural networks is proposed.

Keywords: volume estimation, calorie estimation, artificial vision, food nutrition

Procedia PDF Downloads 63

Authors: Ananya Gangavarapu

Abstract:

Convolutional Neural Networks (CNN) based models are providing diagnostic capabilities on par with the medical specialists in many specialty areas. However, collecting the medical data for training purposes is very challenging because of the increased regulations around data collections and privacy concerns around personal health data. The gathering of the data becomes even more difficult if the capture devices are edge-based mobile devices (like smartphones) with feeble wireless connectivity in rural/remote areas. In this paper, I would like to highlight Federated Learning approach to mitigate data privacy and security issues.

Keywords: deep learning in healthcare, data privacy, federated learning, training in distributed environment

Procedia PDF Downloads 106

Authors: Soner Guler, Fuat Korkut

Abstract:

Recently, the using of lightweights concretes in construction sector is rapidly increasing all over the world. Faster construction, low density and thermal transmitting coefficient and high fire resistance are the remarkable characteristics of the lightweight concretes. Lightweight concrete can be described as a type of concrete which enhance the volume of the mixture while giving additional advantages such as to reduce the dead weight of the structures. It is lighter than the conventional concrete. The use of lightweight concrete has been widely spread across countries such as USA, United Kingdom, and Sweden. In this study, the necessity of the using of lightweights concretes in the construction sector is emphasized and evaluated briefly for the architectures and civil engineers.

Keywords: lightweights concretes, low density, low thermal coefficient, construction sector

Procedia PDF Downloads 480

Authors: Snehal G. Teli, R. J. Shelke

Abstract:

CNN and MultiUNet models are the framework for the proposed method for enhancing and reconstructing underwater images. Multiscale merging of features and regeneration are both performed by the MultiUNet. CNN collects relevant features. Extensive tests on benchmark datasets show that the proposed strategy performs better than the latest methods. As a result of this work, underwater images can be represented and interpreted in a number of underwater applications with greater clarity. This strategy will advance underwater exploration and marine research by enhancing real-time underwater image processing systems, underwater robotic vision, and underwater surveillance.

Keywords: convolutional neural network, image enhancement, machine learning, multiunet, underwater images

Procedia PDF Downloads 38

Authors: Ali Hamza

Abstract:

Accurate segmentation of breast ultrasound images is of paramount importance in enhancing the diagnostic capabilities of breast cancer detection. This study presents an approach utilizing the U-Net architecture for segmenting breast ultrasound images aimed at improving the accuracy and reliability of mass identification within the breast tissue. The proposed method encompasses a multi-stage process. Initially, preprocessing techniques are employed to refine image quality and diminish noise interference. Subsequently, the U-Net architecture, a deep learning convolutional neural network (CNN), is employed for pixel-wise segmentation of regions of interest corresponding to potential breast masses. The U-Net's distinctive architecture, characterized by a contracting and expansive pathway, enables accurate boundary delineation and detailed feature extraction. To evaluate the effectiveness of the proposed approach, an extensive dataset of breast ultrasound images is employed, encompassing diverse cases. Quantitative performance metrics such as the Dice coefficient, Jaccard index, sensitivity, specificity, and Hausdorff distance are employed to comprehensively assess the segmentation accuracy. Comparative analyses against traditional segmentation methods showcase the superiority of the U-Net architecture in capturing intricate details and accurately segmenting breast masses. The outcomes of this study emphasize the potential of the U-Net-based segmentation approach in bolstering breast ultrasound image analysis. The method's ability to reliably pinpoint mass boundaries holds promise for aiding radiologists in precise diagnosis and treatment planning. However, further validation and integration within clinical workflows are necessary to ascertain their practical clinical utility and facilitate seamless adoption by healthcare professionals. In conclusion, leveraging the U-Net architecture for breast ultrasound image segmentation showcases a robust framework that can significantly enhance diagnostic accuracy and advance the field of breast cancer detection. This approach represents a pivotal step towards empowering medical professionals with a more potent tool for early and accurate breast cancer diagnosis.

Keywords: mage segmentation, U-Net, deep learning, breast cancer detection, diagnostic accuracy, mass identification, convolutional neural network

Procedia PDF Downloads 45

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 91

Authors: C. Jameke

Abstract:

During the cognitivist era in cognitive psychology, a theory of internal rules and symbolic representations was posited as an account of human cognition. This type of cognitive architecture had its heyday during the 1970s and 80s, but it has now been largely abandoned in favour of subsymbolic architectures (e.g. connectionism), non-representational frameworks (e.g. dynamical systems theory), and statistical approaches such as Bayesian theory. In this presentation I describe this changing landscape of research, and comment on the increasing influence of neuroscience on cognitive psychology. I then briefly review a few recent developments in connectionism, and neurocomputation relevant to cognitive psychology, and critically discuss the assumption made by some researchers in these frameworks that higher-level aspects of human cognition are simply emergent properties of massively large distributed neural networks

Keywords: connectionism, emergentism, postocgnitivist, representations, subsymbolic archiitecture

Procedia PDF Downloads 539

Authors: Daniel P. Clayton, Edward A. Ball

Abstract:

This paper describes an investigation into the isolation characteristics and bandwidth performance of RF combiners that are used as part of Chireix PA architectures, designed for use in the X-Band range of frequencies. Combiner designs investigated are the typical Chireix and Wilkinson configurations which also include simulation of the Wilkinson using manufacturer’s data for the isolation resistor. Another simulation was the less common approach of using a Branchline coupler to form the combiner, as well as simulation results from adding an additional stage. This paper presents the findings of this investigation and compares the bandwidth performance and isolation characteristics to determine suitability.

Keywords: bandwidth, Chireix, couplers, outphasing, power amplifiers, Wilkinson, X-Band

Procedia PDF Downloads 223

Authors: Guezouli Larbi, Belkacem Soundes

Abstract:

The automation of the text detection process can help the human in his driving task. Its application can be very useful to help drivers to have more information about their environment by facilitating the reading of road signs such as directional signs, events, stores, etc. In this paper, a system consisting of two stages has been proposed. In the first one, we used pseudo-Zernike moments to pinpoint areas of the image that may contain text. The architecture of this part is based on three main steps, region of interest (ROI) detection, text localization, and non-text region filtering. Then, in the second step, we present a convolutional neural network architecture (On-Road Text Detection Network - ORTDN) which is considered a classification phase. The results show that the proposed framework achieved ≈ 35 fps and an mAP of ≈ 90%, thus a low computational time with competitive accuracy.

Keywords: text detection, CNN, PZM, deep learning

Procedia PDF Downloads 54

Authors: Yiwei Li, Mingyu Gao

Abstract:

Integrating hybrid memories with heterogeneous processors could leverage heterogeneity in both compute and memory domains for better system efficiency. To ensure performance isolation, we introduce Hydrogen, a hardware architecture to optimize the allocation of hybrid memory resources to heterogeneous CPU-GPU systems. Hydrogen supports efficient capacity and bandwidth partitioning between CPUs and GPUs in both memory tiers. We propose decoupled memory channel mapping and token-based data migration throttling to enable flexible partitioning. We also support epoch-based online search for optimized configurations and lightweight reconfiguration with reduced data movements. Hydrogen significantly outperforms existing designs by 1.21x on average and up to 1.31x.

Keywords: hybrid memory, heterogeneous systems, dram cache, graphics processing units

Procedia PDF Downloads 18

Authors: Tamara Trček Pečak, Andrej Mohar, Denis Trček

Abstract:

This article investigates the latest technological means, which deploy smart structures that are based on (advanced) wireless sensors technologies and ubiquitous computing in general in order to support the above mentioned decision making. Based on two years of in-field research experiences it gives their analysis for these kinds of purposes and provides appropriate architectures and architectural solutions. Moreover, the directions for future research are stated, because these technologies are currently the most promising ones to enable cost-effective preservation of cultural heritage not only in uncontrolled places, but also in general.

Keywords: smart structures, wireless sensors, sensors networks, green computing, cultural heritage preservation, monitoring, cost effectiveness

Procedia PDF Downloads 412

Authors: Sundus Ayyaz, Saad Rehman, Usman Qamar

Abstract:

Software Architecture is the basic structure of software that states the development and advancement of a software system. Software architecture is also considered as a significant tool for the construction of high quality software systems. A clean design leads to the control, value and beauty of software resulting in its longer life while a bad design is the cause of architectural erosion where a software evolution completely fails. This paper discusses the occurrence of software architecture erosion and presents a set of methods for the detection, declaration and prevention of architecture erosion. The causes and symptoms of architecture erosion are observed with the examples of prescriptive and descriptive architectures and the practices used to stop this erosion are also discussed by considering different types of software erosion and their affects. Consequently finding and devising the most suitable approach for fighting software architecture erosion and in some way reducing its affect is evaluated and tested on different scenarios.

Keywords: software architecture, architecture erosion, prescriptive architecture, descriptive architecture

Procedia PDF Downloads 464

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 19

Authors: Sharjeel Aslam, Vassil Vassilev, Karim Ouazzane

Abstract:

Ontologies and various semantic repositories became a convenient approach for implementing model-driven architectures of distributed systems on the Web. SPARQL is the standard query language for querying such. However, although SPARQL is well-established standard for querying semantic repositories in RDF and OWL format and there are commonly used APIs which supports it, like Jena for Java, its parallel option is not incorporated in them. This article presents a complete framework consisting of an object algebra for parallel RDF and an index-based implementation of the parallel query engine capable of dealing with the distributed RDF ontologies which share common vocabulary. It has been implemented in Java, and for validation of the algorithms has been applied to the problem of organizing virtual exhibitions on the Web.

Keywords: distributed ontologies, parallel querying, semantic indexing, shared vocabulary, SPARQL

Procedia PDF Downloads 161

Authors: Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

Abstract:

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.

Keywords: machine learning, pattern clustering, pooling, classification

Procedia PDF Downloads 419

Authors: Predrag Simović, Katarina Stojanović, Milena Radenković, Dimitrija Savić Zdravković, Aleksandar Milosavljević, Bratislav Predić, Milenka Božanić, Ana Petrović, Djuradj Milošević

Abstract:

Mayflies (Ephemeroptera), stoneflies (Plecoptera), and caddisflies (Trichoptera) (collectively referred to as EPT) are key participants in most freshwater habitats and often exhibit high diversity. Moreover, their presence and relative abundance are used in freshwater ecological and biomonitoring studies. Current methods for freshwater ecosystem biomonitoring follow a traditional approach of taxa monitoring based on morphological characters, which is time-consuming, and often generates data sets with low taxonomic resolution and unverifiable identification precision. To assist in solving identification problems and contribute to the knowledge of the distribution of many species, there was a need to develop alternative approaches in macroinvertebrate sample identification. Here, we establish an automatic machine-based identification approach for EPT taxa (Insect) using deep Convolutional Neural Networks (CNNs) and computer vision to increase the efficiency and taxonomic resolution in biomonitoring. The 5 550 specimens were collected from freshwater ecosystems of Serbia, and the deep model was built upon 90 EPT taxa. The protocol for obtaining images included the following stages: taxonomic identification by human experts and DNA barcoding validation, mounting the larvae, and photographing the dorsal side using a stereomicroscope and camera (16 650 individuals). The most informative image regions (the dorsal segments of individuals) for the decision-making process in the deep learning model were visualized using Gradient Weighted Class Activation Mapping (Grad-CAM). After training the artificial neural network, a CNN model was then built that was able to classify the 90 EPT taxa into their respective taxonomic categories automatically with 98.7%. Our approach offers a straightforward and efficient solution for routine monitoring programs, focusing on key biotic descriptors, such as EPT taxa. In addition, this application provides a streamlined solution that not only saves time, reduces equipment and expert requirements but also significantly enhances reliability and information content. The identification of the EPT larvae is difficult because of the variation of morphological features even within a single genus or the close resemblance of several species, and therefore, future research should focus on increasing the number of entities (species) in the model.

Keywords: convolutional neural networks, DNA barcoding, EPT taxa, biomonitoring

Procedia PDF Downloads 42

Authors: Ashutosh Mishra, Nikhil Goyal

Abstract:

A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.

Keywords: facial recognition, computational intelligence, convolutional neural network, depth map

Procedia PDF Downloads 193

Authors: Huayuan Lu, Chunfang Yang, Ma Zhu, Baojun Qi, Yaqiong Qiao, Jiangqian Xu

Abstract:

Image geolocalization has great application prospects in fields such as autonomous driving and virtual/augmented reality. In practical application scenarios, the size of the image to be located is not fixed; it is impractical to train different networks for all possible sizes. When its size does not match the size of the input of the descriptor extraction model, existing image geolocalization methods usually directly scale or crop the image in some common ways. This will result in the loss of some information important to the geolocalization task, thus affecting the performance of the image geolocalization method. For example, excessive down-sampling can lead to blurred building contour, and inappropriate cropping can lead to the loss of key semantic elements, resulting in incorrect geolocation results. To address this problem, this paper designs a learnable image resizer and proposes an arbitrary-sized image geolocation method. (1) The designed learnable image resizer employs the self-attention mechanism to enhance the geometric features of the resized image. Firstly, it applies bilinear interpolation to the input image and its feature maps to obtain the initial resized image and the resized feature maps. Then, SKNet (selective kernel net) is used to approximate the best receptive field, thus keeping the geometric shapes as the original image. And SENet (squeeze and extraction net) is used to automatically select the feature maps with strong contour information, enhancing the geometric features. Finally, the enhanced geometric features are fused with the initial resized image, to obtain the final resized images. (2) The proposed image geolocalization method embeds the above image resizer as a fronting layer of the descriptor extraction network. It not only enables the network to be compatible with arbitrary-sized input images but also enhances the geometric features that are crucial to the image geolocalization task. Moreover, the triplet attention mechanism is added after the first convolutional layer of the backbone network to optimize the utilization of geometric elements extracted by the first convolutional layer. Finally, the local features extracted by the backbone network are aggregated to form image descriptors for image geolocalization. The proposed method was evaluated on several mainstream datasets, such as Pittsburgh30K, Tokyo24/7, and Places365. The results show that the proposed method has excellent size compatibility and compares favorably to recently mainstream geolocalization methods.

Keywords: image geolocalization, self-attention mechanism, image resizer, geometric feature

Procedia PDF Downloads 170

Authors: Ersan Aktas, Eren Turanoğuz

Abstract:

In this study, the quad-electrical rotor driven unmanned aerial vehicle system is designed and modeled using fundamental dynamic equations. After that, mechanical, electronical and control system of the air vehicle are designed and implemented. Brushless motor speeds are altered via electronic speed controllers in order to achieve desired controllability. The vehicle's fundamental Euler angles (i.e., roll angle, pitch angle, and yaw angle) are obtained via AHRS sensor. These angles are provided as an input to the control algorithm that run on soft the processor on the electronic card. The vehicle control algorithm is implemented in the electronic card. Controller is designed and improved for each Euler angles. Finally, flight tests have been performed to observe and improve the flight characteristics.

Keywords: quadrotor, UAS applications, control architectures, PID

Procedia PDF Downloads 331

Authors: Vidhi Jain

Abstract:

Communication between speakers and non-speakers of American Sign Language (ASL) can be problematic, inconvenient, and expensive. This project attempts to bridge the communication gap by designing a portable glove that captures the user’s ASL gestures and outputs the translated text on a smartphone. The glove is equipped with flex sensors, contact sensors, and a gyroscope to measure the flexion of the fingers, the contact between fingers, and the rotation of the hand. The glove’s Arduino UNO microcontroller analyzes the sensor readings to identify the gesture from a library of learned gestures. The Bluetooth module transmits the gesture to a smartphone. Using this device, one day speakers of ASL may be able to communicate with others in an affordable and convenient way.

Keywords: sign language, morse code, convolutional neural network, American sign language, gesture recognition

Procedia PDF Downloads 19

Authors: C. Mayr, J. Periya, A. Kariminezhad

Abstract:

In this paper, we developed a learning framework for the classification of vulnerable road users (VRU) by their range-Doppler signatures. The frequency-modulated continuous-wave (FMCW) radar raw data is first pre-processed to obtain robust object range-Doppler maps per coherent time interval. The complex-valued range-Doppler maps captured from our outdoor measurements are further fed into a convolutional neural network (CNN) to learn the classification. This CNN has gone through a hyperparameter optimization process for improved learning. By learning VRU range-Doppler signatures, the three classes 'pedestrian', 'dog', and 'noise' are classified with an average accuracy of almost 95%. Interestingly, this classification accuracy holds for a combined longitudinal and lateral object trajectories.

Keywords: machine learning, radar, signal processing, autonomous driving

Procedia PDF Downloads 206

Authors: Susan E Orlovich

Abstract:

Ongoing, effective teacher professional learning is acknowledged as a critical influence on teacher practice. However, it is unclear whether the elements of effective professional learning result in transformed teacher practice in the classroom. This research project is interested in 4C teacher professional learning. The professional learning practices to assist teachers in transforming their practice to integrate the 4C capabilities seldom feature in the academic literature. The 4Cs are a shorthand way of representing the concepts of communication, collaboration, creativity, and critical reflection and refer to the capabilities needed for deeper learning, personal growth, and effective participation in society. The New South Wales curriculum review (2020) acknowledges that identifying, teaching, and assessing the 4C capabilities are areas of challenge for teachers. However, it also recognises that it is essential for teachers to build the confidence and capacity to understand, teach and assess the capabilities necessary for learners to thrive in the 21st century. This qualitative research project explores the professional learning experiences of sixteen teachers in four different primaries (K-6) settings in Sydney, Australia, who are learning to integrate, teach and assess the 4Cs. The project draws on the Theory of Practice Architecture as a framework to analyse and interpret teachers' experiences in each site. The sixteen participants in the study are teachers from four primary settings and include early career, experienced, and teachers in leadership roles (including the principal). In addition, some of the participants are also teachers who are learning within a Community of Practice (CoP) as their school setting is engaged in a 4C professional learning, Community of Practice. Qualitative and arts-informed research methods are utilised to examine the cultural-discursive, social-political, and material-economic practice arrangements of the site, explore how these arrangements may have shaped the professional learning experiences of teachers, and in turn, influence the teaching practices of the 4Cs in the setting. The research is in the data analysis stage (October 2022), with preliminary findings pending. The research objective is to investigate the elements of the professional learning experiences undertaken by teachers to teach the 4Cs in the primary setting. The lens of practice architectures theory is used to identify the influence of the practice architectures on critical praxis in each site and examine how the practice arrangements enable or constrain the teaching of 4C capabilities. This research aims to offer deep insight into the practice arrangements which may enable or constrain teacher professional learning in the 4Cs. Such insight from this study may contribute to a better understanding of the practices that enable teachers to transform their practice to achieve the integration, teaching, and assessment of the 4C capabilities.

Keywords: 4Cs, communication, collaboration, creativity, critical reflection, teacher professional learning

Procedia PDF Downloads 72

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN

Procedia PDF Downloads 91