Search results for: Deep learning

Authors: Nicholas Milburn, Yu Liang, Dalei Wu

Abstract:

Athlete performance scoring within the climbing do-main presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill levels within any sport is valuable as it can be used to mark progress while training, and it can help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. The investigated solutions to the classification problem included light weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Keywords: classification, climbing, data imbalance, data scarcity, machine learning, time sequence

Procedia PDF Downloads 143

Authors: Xiaoqi Jia, Qing Zhu, Hao Zhang, Su Yang

Abstract:

A gender recognition system is able to tell the gender of the given person through a few of frontal facial images. An effective gender recognition approach enables to improve the performance of many other applications, including security monitoring, human-computer interaction, image or video retrieval and so on. In this paper, we present an effective method for gender classification task in frontal facial images based on deep belief networks (DBNs), which can pre-train model and improve accuracy a little bit. Our experiments have shown that the pre-training method with DBNs for gender classification task is feasible and achieves a little improvement of accuracy on FERET and CAS-PEAL-R1 facial datasets.

Keywords: gender recognition, beep belief net-works, semi-supervised learning, greedy-layer wise RBMs

Procedia PDF Downloads 453

Authors: Sirapop Nuannimnoi, Hojjat Baghban, Ching-Yao Huang

Abstract:

Over the past decade, with the fast development of blockchain technology since the birth of Bitcoin, there has been a massive increase in the usage of Cryptocurrencies. Cryptocurrencies are not seen as an investment opportunity due to the market’s erratic behavior and high price volatility. With the recent success of deep reinforcement learning (DRL), portfolio management can be modeled and automated. In this paper, we propose a novel DRL-based multi-agent system to automatically make proper trading decisions on multiple cryptocurrencies and gain profits in the highly volatile cryptocurrency market. We also extend this multi-agent system with horizontal federated transfer learning for better adapting to the inclusion of new cryptocurrencies in our portfolio; therefore, we can, through the concept of diversification, maximize our profits and minimize the trading risks. Experimental results through multiple simulation scenarios reveal that this proposed algorithmic trading system can offer three promising key advantages over other systems, including maximized profits, minimized risks, and adaptability.

Keywords: cryptocurrency portfolio management, algorithmic trading, federated learning, multi-agent reinforcement learning

Procedia PDF Downloads 119

Authors: Gong Zhilin, Jing Yang, Jian Yin

Abstract:

The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data using hybrid deep learning models. The projected model encapsulates five major phases are pre-processing, imbalance-data handling, feature extraction, optimal feature selection, and fraud detection with an ensemble classifier. The collected raw data (input) is pre-processed to enhance the quality of the data through alleviation of the missing data, noisy data as well as null values. The pre-processed data are class imbalanced in nature, and therefore they are handled effectively with the K-means clustering-based SMOTE model. From the balanced class data, the most relevant features like improved Principal Component Analysis (PCA), statistical features (mean, median, standard deviation) and higher-order statistical features (skewness and kurtosis). Among the extracted features, the most optimal features are selected with the Self-improved Arithmetic Optimization Algorithm (SI-AOA). This SI-AOA model is the conceptual improvement of the standard Arithmetic Optimization Algorithm. The deep learning models like Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and optimized Quantum Deep Neural Network (QDNN). The LSTM and CNN are trained with the extracted optimal features. The outcomes from LSTM and CNN will enter as input to optimized QDNN that provides the final detection outcome. Since the QDNN is the ultimate detector, its weight function is fine-tuned with the Self-improved Arithmetic Optimization Algorithm (SI-AOA).

Keywords: credit card, data mining, fraud detection, money transactions

Procedia PDF Downloads 131

Authors: Jihan Albayati, Kim Abdullah

Abstract:

This poster focuses on the significance of active learning strategies and their usage in the ESL classroom. Active learning is a big shift from traditional lecturing to active student engagement which can enhance and enrich student learning; therefore, engaging students is the core of this approach. Students learn more when they participate in the process of learning such as discussions, debates, analysis, synthesis, or any form of activity that requires student involvement. In order to achieve active learning, teachers can use different instructional strategies that are conducive to learning and the selection of these strategies depends on student learning outcomes. Active learning techniques must be carefully designed and integrated into the classroom to increase critical thinking and student participation. This poster provides a concise definition of active learning and its importance, instructional strategies, active learning techniques and their impact on student engagement. Also, it demonstrates the differences between passive and active learners.

Keywords: active learning, learner engagement, student-centered, teaching strategies

Procedia PDF Downloads 494

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 102

Authors: Ashish James, Anusha James

Abstract:

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Ensemble of NNs typically produce good predictions but uncertainty estimates tend to be inconsistent. Inspired by these, this paper presents a framework that can quantitatively estimate the uncertainties by leveraging the advances in transfer learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments with known and unknown distributions show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Keywords: uncertainty estimation, neural networks, transfer learning, regression

Procedia PDF Downloads 135

Authors: Francisco A. Ribeiro Da Costa

Abstract:

Who is responsible for teaching architecture; consider various ways to participate in learning, manipulating various pedagogical tools to streamline the creative process. The Architectural Design Studio (ADS) should become a holistic, systemic process responding to the complexity of our world. This essay corresponds to a deep reflection developed by the author on the teaching of architecture. The outcomes achieved are the corollary of experimentation; discussion and application of pedagogical methods that allowed consolidate the creativity applied by students. The purpose is to show the conjectures that have been considered effective in creating an intellectual environment that nurtures the subject of Architectural Design Studio (ADS), as an operational synthesis in the final stage of the degree. These assumptions, which are part of the proposed model, displaying theories and teaching methodologies that try to respect the learning process based on student learning styles Kolb, ensuring their latent specificities and formulating the structure of the ASD discipline. In addition, the assessing methods are proposed, which consider the architectural Design Studio as an operational synthesis in the teaching of architecture.

Keywords: teaching-learning, architectural design studio, architecture, education

Procedia PDF Downloads 390

Authors: Mahmut Yildirim

Abstract:

This paper proposed the bidirectional long short-term memory (Bi-LSTM) network-aided deep learning (DL)-based signal detection for Orthogonal frequency division multiplexing with all index modulation (OFDM-AIM), namely Bi-DeepAIM. OFDM-AIM is developed to increase the spectral efficiency of OFDM with index modulation (OFDM-IM), a promising multi-carrier technique for communication systems beyond 5G. In this paper, due to its strong classification ability, Bi-LSTM is considered an alternative to the maximum likelihood (ML) algorithm, which is used for signal detection in the classical OFDM-AIM scheme. The performance of the Bi-DeepAIM is compared with LSTM network-aided DL-based OFDM-AIM (DeepAIM) and classic OFDM-AIM that uses (ML)-based signal detection via BER performance and computational time criteria. Simulation results show that Bi-DeepAIM obtains better bit error rate (BER) performance than DeepAIM and lower computation time in signal detection than ML-AIM.

Keywords: bidirectional long short-term memory, deep learning, maximum likelihood, OFDM with all index modulation, signal detection

Procedia PDF Downloads 72

Authors: Konstantinos Sofianos, Michail Stefanidakis

Abstract:

Nowadays, despite the great advances in technology, most educational frameworks lack a strong educational design basis. E-learning has become prevalent, but it faces various challenges such as student isolation and lack of quality in the learning process. An intelligent learning system provides a student with educational material according to their learning background and learning preferences. It records full information about the student, such as demographic information, learning styles, and academic performance. This information allows the system to be fully adapted to the student’s needs. In this paper, we propose a framework and an ontology for music education, consisting of the learner model and all elements of the learning process (learning objects, teaching methods, learning activities, assessment). This framework can be integrated into an intelligent learning system and used for music education in schools for the development of professional skills and beyond.

Keywords: intelligent learning systems, e-learning, music education, ontology, semantic web

Procedia PDF Downloads 140

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 181

Authors: Parsa Mahdavi, M. Amin Hariri-Ardebili

Abstract:

The development of accurate machine learning and deep learning models traditionally demands hands-on expertise and a solid background to fine-tune hyperparameters. With the continuous expansion of datasets in various scientific and engineering domains, researchers increasingly turn to machine learning methods to unveil hidden insights that may elude classic regression techniques. This surge in adoption raises concerns about the adequacy of the resultant meta-models and, consequently, the interpretation of the findings. In response to these challenges, automated machine learning (AutoML) emerges as a promising solution, aiming to construct machine learning models with minimal intervention or guidance from human experts. AutoML encompasses crucial stages such as data preparation, feature engineering, hyperparameter optimization, and neural architecture search. This paper provides a comprehensive overview of the principles underpinning AutoML, surveying several widely-used AutoML platforms. Additionally, the paper offers a glimpse into the application of AutoML on various engineering datasets. By comparing these results with those obtained through classical machine learning methods, the paper quantifies the uncertainties inherent in the application of a single ML model versus the holistic approach provided by AutoML. These examples showcase the efficacy of AutoML in extracting meaningful patterns and insights, emphasizing its potential to revolutionize the way we approach and analyze complex datasets.

Keywords: automated machine learning, uncertainty, engineering dataset, regression

Procedia PDF Downloads 61

Authors: Thomas Yeboah, Gifty Akouko Sarpong

Abstract:

Every learner has a specific learning style that helps him/her to study best. This means that any learning method (e-learning method or traditional face-to-face method) a learner chooses should address the learning style of the learner. Therefore, the main purpose of this research is to investigate whether learners’ grade achievement in e-learning environment is improved for learners with a particular learning style. In this research, purposive sampling technique was employed for selecting the sample size of three hundred and twenty (320) students studying a course UGRC 140 Science and Technology in our Lives at Christian Service University College. Data were analyzed by using, percentages, T -test, and one-way ANOVA. A thorough analysis was done on the data collected and the results revealed that learners with the Assimilator learning style and the converger learning style obtained higher grade achievement than both diverger learning style and accommodative learning style. Again, the results also revealed that accommodative learning style was not good enough for e-learning method.

Keywords: e-learning, learning style, grade achievement, accomodative, divergent, convergent, assimilative

Procedia PDF Downloads 432

Authors: Jawairia Rasheed

Abstract:

Modern robots are often used for search and rescue purpose. One of the key areas of interest in such cases is learning complex environments. One of the key methodologies for robots in such cases is reinforcement learning. In reinforcement learning robots learn to move the path to reach the goal while avoiding obstacles. Q-learning, one of the most advancement of reinforcement learning is used for making the robots to learn the path. Robots learn by interacting with the environment to reach the goal. In this paper simulation model of bee-like robots is implemented in NETLOGO. In the start the learning rate was less and it increased with the passage of time. The bees successfully learned to reach the goal while avoiding obstacles through Q-learning technique.

Keywords: reinforlearning of bee like robots for reaching the goalcement learning for randomly placed obstacles, obstacle avoidance through q-learning, q-learning for obstacle avoidance,

Procedia PDF Downloads 101

Authors: Kritiyaporn Kunsook

Abstract:

Machine learning algorithms (MLAs) such us artificial neural networks (ANNs), decision tree, support vector machines (SVMs), Naïve Bayes, and ensemble classifier by voting are powerful data driven methods that are relatively less widely used in the mapping of technique of system, and thus have not been comparatively evaluated together thoroughly in this field. The performances of a series of MLAs, ANNs, decision tree, SVMs, Naïve Bayes, and ensemble classifier by voting in technique of hydroponic systems prospectively modeling are compared based on the accuracy of each model. Classification of hydroponic systems only covers the test samples from vegetables grown with Nutrient film technique (NFT) and Deep flow technique (DFT). The feature, which are the characteristics of vegetables compose harvesting height width, temperature, require light and color. The results indicate that the classification performance of the ANNs is 98%, decision tree is 98%, SVMs is 97.33%, Naïve Bayes is 96.67%, and ensemble classifier by voting is 98.96% algorithm respectively.

Keywords: artificial neural networks, decision tree, support vector machines, naïve Bayes, ensemble classifier by voting

Procedia PDF Downloads 372

Authors: Oluwafunmibi Omotayo Fasanya, Augustine Kena Adjei

Abstract:

Diabetic nephropathy (DN) is a major complication of diabetes, with fibrosis and propionate metabolism playing critical roles in its progression. Identifying biomarkers linked to these pathways may provide novel insights into DN diagnosis and treatment. This study aims to identify biomarkers associated with fibrosis and propionate metabolism in DN. Analyze the biological pathways and regulatory mechanisms of these biomarkers. Develop a machine learning model to predict DN-related biomarkers and validate their functional roles. Publicly available transcriptome datasets related to DN (GSE96804 and GSE104948) were obtained from the GEO database (https://www.ncbi.nlm.nih.gov/gds), and 924 propionate metabolism-related genes (PMRGs) and 656 fibrosis-related genes (FRGs) were identified. The analysis began with the extraction of DN-differentially expressed genes (DN-DEGs) and propionate metabolism-related DEGs (PM-DEGs), followed by the intersection of these with fibrosis-related genes to identify key intersected genes. Instead of relying on traditional models, we employed a combination of deep neural networks (DNNs) and ensemble methods such as Gradient Boosting Machines (GBM) and XGBoost to enhance feature selection and biomarker discovery. Recursive feature elimination (RFE) was coupled with these advanced algorithms to refine the selection of the most critical biomarkers. Functional validation was conducted using convolutional neural networks (CNN) for gene set enrichment and immunoinfiltration analysis, revealing seven significant biomarkers—SLC37A4, ACOX2, GPD1, ACE2, SLC9A3, AGT, and PLG. These biomarkers are involved in critical biological processes such as fatty acid metabolism and glomerular development, providing a mechanistic link to DN progression. Furthermore, a TF–miRNA–mRNA regulatory network was constructed using natural language processing models to identify 8 transcription factors and 60 miRNAs that regulate these biomarkers, while a drug–gene interaction network revealed potential therapeutic targets such as UROKINASE–PLG and ATENOLOL–AGT. This integrative approach, leveraging deep learning and ensemble models, not only enhances the accuracy of biomarker discovery but also offers new perspectives on DN diagnosis and treatment, specifically targeting fibrosis and propionate metabolism pathways.

Keywords: diabetic nephropathy, deep neural networks, gradient boosting machines (GBM), XGBoost

Procedia PDF Downloads 9

Authors: Shahbaz Ahmed

Abstract:

This study is conducted to demonstrate the knowledge of intentional learning and incidental learning. Hypothesis of this experiment is intentional learning is better than incidental learning, participants were demonstrated and were asked to learn the 10 nonsense syllables in a specific sequence from the colored cards in the end they were asked to recall the background color of each card instead of nonsense syllables. Independent variables of the experiment are the colored cards containing nonsense syllables which are to be memorized by the participants, dependent variables are the number of correct responses made by the participant. The findings of the experiment concluded that intentional learning is better than incidental learning, hence hypothesis is proved.

Keywords: intentional learning, incidental learning, non-sense syllable cards, score sheets

Procedia PDF Downloads 534

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 316

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 446

Authors: Rachael Olubukola Afolabi

Abstract:

Immersive technologies known as X Reality or Cross Reality that include virtual reality augmented reality, and mixed reality have pervaded into the education system at different levels from elementary school to adult learning. Instructors, instructional designers, and learning experience specialists continue to find new ways to engage students in the learning process using technology. While the progression of web technologies has enhanced digital learning experiences, analytics on learning outcomes continue to be explored to determine the relevance of these technologies in learning. Digital learning has evolved from web 1.0 (static) to 4.0 (dynamic and interactive), and this evolution of technologies has also advanced teaching methods and approaches. This paper explores how these technologies are being utilized in learning and the results that educators and learners have identified as effective learning opportunities and approaches.

Keywords: immersive technologoes, virtual reality, augmented reality, technology in learning

Procedia PDF Downloads 145

Authors: Teerada Apibunyopas, Nithinant Thammakoranonta

Abstract:

Many organizations bring e-Learning to use as a tool in their training and human development department. It is getting more popular because it is easy to access to get knowledge all the time and also it provides a rich content, which can develop the employees skill efficiently. This study focused on the factors that affect using e-Learning efficiently, so it will make job satisfaction increased. The questionnaires were sent to employees in large commercial banks, which use e-Learning located in Bangkok, the results from multiple linear regression analysis showed that employee’s characteristics, characteristics of e-Learning, learning and growth have influence on job satisfaction.

Keywords: e-Learning, job satisfaction, learning and growth, Bangkok

Procedia PDF Downloads 491

Authors: Farouk Lawan Gambo, Hamada Mohammad

Abstract:

Data compression shrinks files into fewer bits than their original presentation. It has more advantage on the internet because the smaller a file, the faster it can be transferred but learning most of the concepts in data compression are abstract in nature, therefore, making them difficult to digest by some students (engineers in particular). This paper studies the learning preference of engineering students who tend to have strong, active, sensing, visual and sequential learning preferences, the paper also studies the three shift of technology-aided that learning has experienced, which mobile learning has been considered to be the feature of learning that will integrate other form of the education process. Lastly, we propose a design and implementation of mobile learning application using software engineering methodology that will enhance the traditional teaching and learning of data compression techniques.

Keywords: data compression, learning preference, mobile learning, multimedia

Procedia PDF Downloads 447

Authors: Manaranjan Pradhan, Shailaja Grover, U. Dinesh Kumar

Abstract:

Farming community in India, as well as other parts of the world, is one of the highly stressed communities due to reasons such as increasing input costs (cost of seeds, fertilizers, pesticide), droughts, reduced revenue leading to farmer suicides. Lack of integrated farm advisory system in India adds to the farmers problems. Farmers need right information during the early stages of crop’s lifecycle to prevent damage and loss in revenue. In this paper, we use deep learning techniques to develop an early warning system for detection of crop diseases using images taken by farmers using their smart phone. The research work leads to building a smart assistant using analytics and big data which could help the farmers with early diagnosis of the crop diseases and corrective actions. The classical approach for crop disease management has been to identify diseases at crop level. Recently, ImageNet Classification using the convolutional neural network (CNN) has been successfully used to identify diseases at individual plant level. Our model uses convolution filters, max pooling, dense layers and dropouts (to avoid overfitting). The models are built for binary classification (healthy or not healthy) and multi class classification (identifying which disease). Transfer learning is used to modify the weights of parameters learnt through ImageNet dataset and apply them on crop diseases, which reduces number of epochs to learn. One shot learning is used to learn from very few images, while data augmentation techniques are used to improve accuracy with images taken from farms by using techniques such as rotation, zoom, shift and blurred images. Models built using combination of these techniques are more robust for deploying in the real world. Our model is validated using tomato crop. In India, tomato is affected by 10 different diseases. Our model achieves an accuracy of more than 95% in correctly classifying the diseases. The main contribution of our research is to create a personal assistant for farmers for managing plant disease, although the model was validated using tomato crop, it can be easily extended to other crops. The advancement of technology in computing and availability of large data has made possible the success of deep learning applications in computer vision, natural language processing, image recognition, etc. With these robust models and huge smartphone penetration, feasibility of implementation of these models is high resulting in timely advise to the farmers and thus increasing the farmers' income and reducing the input costs.

Keywords: analytics in agriculture, CNN, crop disease detection, data augmentation, image recognition, one shot learning, transfer learning

Procedia PDF Downloads 119

Authors: Subham Ghosh, Banani Basu, Marami Das

Abstract:

Background: The development of compact, low-power antenna sensors has resulted in hardware restructuring, allowing for wireless ubiquitous sensing. The antenna sensors can create wireless body-area networks (WBAN) by linking various wireless nodes across the human body. WBAN and IoT applications, such as remote health and fitness monitoring and rehabilitation, are becoming increasingly important. In particular, Parkinson’s disease (PD), a common neurodegenerative disorder, presents clinical features that can be easily misdiagnosed. As a mobility disease, it may greatly benefit from the antenna’s nearfield approach with a variety of activities that can use WBAN and IoT technologies to increase diagnosis accuracy and patient monitoring. Methodology: This study investigates the feasibility of leveraging a single patch antenna mounted (using cloth) on the wrist dorsal to differentiate actual Parkinson's disease (PD) from false PD using a small hardware platform. The semi-flexible antenna operates at the 2.4 GHz ISM band and collects reflection coefficient (Γ) data from patients performing five exercises designed for the classification of PD and other disorders such as essential tremor (ET) or those physiological disorders caused by anxiety or stress. The obtained data is normalized and converted into 2-D representations using the Gabor wavelet transform (GWT). Data augmentation is then used to expand the dataset size. A lightweight deep-learning (DL) model is developed to run on the GPU-enabled NVIDIA Jetson Nano platform. The DL model processes the 2-D images for feature extraction and classification. Findings: The DL model was trained and tested on both the original and augmented datasets, thus doubling the dataset size. To ensure robustness, a 5-fold stratified cross-validation (5-FSCV) method was used. The proposed framework, utilizing a DL model with 1.356 million parameters on the NVIDIA Jetson Nano, achieved optimal performance in terms of accuracy of 88.64%, F1-score of 88.54, and recall of 90.46%, with a latency of 33 seconds per epoch.

Keywords: antenna, deep-learning, GPU-hardware, Parkinson’s disease

Procedia PDF Downloads 7

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 396

Authors: Pedro Paulo Galindo Francisco, Eli Dhadad Junior

Abstract:

This study addresses the Meese-Rogoff Puzzle by introducing the latest machine learning techniques as alternatives for predicting the exchange rates. Using RMSE as a comparison metric, Meese and Rogoff discovered that economic models are unable to outperform the random walk model as short-term exchange rate predictors. Decades after this study, no statistical prediction technique has proven effective in overcoming this obstacle; although there were positive results, they did not apply to all currencies and defined periods. Recent advancements in artificial intelligence technologies have paved the way for a new approach to exchange rate prediction. Leveraging this technology, we applied five machine learning techniques to attempt to overcome the Meese-Rogoff puzzle. We considered daily data for the real, yen, British pound, euro, and Chinese yuan against the US dollar over a time horizon from 2010 to 2023. Our results showed that none of the presented techniques were able to produce an RMSE lower than the Random Walk model. However, the performance of some models, particularly LSTM and N-BEATS were able to outperform the ARIMA model. The results also suggest that machine learning models have untapped potential and could represent an effective long-term possibility for overcoming the Meese-Rogoff puzzle.

Keywords: exchage rate, prediction, machine learning, deep learning

Procedia PDF Downloads 31

Authors: Marcos Silva Tavares, Jamile Raquel Regazzo, Edson José de Souza Sardinha, Murilo Mesquita Baesso

Abstract:

Common beans are a widely cultivated and consumed legume globally, serving as a staple food for humans, especially in developing countries, due to their nutritional characteristics. Nitrogen (N) is the most limiting nutrient for productivity, and foliar analysis is crucial to ensure balanced nitrogen fertilization. Excessive N applications can cause, either isolated or cumulatively, soil and water contamination, plant toxicity, and increase their susceptibility to diseases and pests. However, the quantification of N using conventional methods is time-consuming and costly, demanding new technologies to optimize the adequate supply of N to plants. Thus, it becomes necessary to establish constant monitoring of the foliar content of this macronutrient in plants, mainly at the V4 stage, aiming at precision management of nitrogen fertilization. In this work, the objective was to evaluate the performance of a deep learning model, Resnet-50, in the classification of foliar nitrogen in common beans using RGB images. The BRS Estilo cultivar was sown in a greenhouse in a completely randomized design with four nitrogen doses (T1 = 0 kg N ha-1, T2 = 25 kg N ha-1, T3 = 75 kg N ha-1, and T4 = 100 kg N ha-1) and 12 replications. Pots with 5L capacity were used with a substrate composed of 43% soil (Neossolo Quartzarênico), 28.5% crushed sugarcane bagasse, and 28.5% cured bovine manure. The water supply of the plants was done with 5mm of water per day. The application of urea (45% N) and the acquisition of images occurred 14 and 32 days after sowing, respectively. A code developed in Matlab© R2022b was used to cut the original images into smaller blocks, originating an image bank composed of 4 folders representing the four classes and labeled as T1, T2, T3, and T4, each containing 500 images of 224x224 pixels obtained from plants cultivated under different N doses. The Matlab© R2022b software was used for the implementation and performance analysis of the model. The evaluation of the efficiency was done by a set of metrics, including accuracy (AC), F1-score (F1), specificity (SP), area under the curve (AUC), and precision (P). The ResNet-50 showed high performance in the classification of foliar N levels in common beans, with AC values of 85.6%. The F1 for classes T1, T2, T3, and T4 was 76, 72, 74, and 77%, respectively. This study revealed that the use of RGB images combined with deep learning can be a promising alternative to slow laboratory analyses, capable of optimizing the estimation of foliar N. This can allow rapid intervention by the producer to achieve higher productivity and less fertilizer waste. Future approaches are encouraged to develop mobile devices capable of handling images using deep learning for the classification of the nutritional status of plants in situ.

Keywords: convolutional neural network, residual network 50, nutritional status, artificial intelligence

Procedia PDF Downloads 19

Authors: Jeongim Kang, Moon Hee Kim, Seong Baeg Kim

Abstract:

This paper proposes a novel e-learning model that is based on a dynamic formative evaluation. On evaluating the existing format of e-learning, conditions regarding repetitive learning to achieve mastery, causes issues for learners to lose tension and become neglectful of learning. The dynamic formative evaluation proposed is able to supplement limitation of the existing approaches. Since a repetitive learning method does not provide a perfect feedback, this paper puts an emphasis on the dynamic formative evaluation that is able to maximize learning achievement. Through the dynamic formative evaluation, the instructor is able to refer to the evaluation result when making estimation about the learner. To show the flow chart of learning, based on the dynamic formative evaluation, the model proves its effectiveness and validity.

Keywords: online learning, dynamic formative evaluation, mastery learning, repetitive learning method, learning achievement

Procedia PDF Downloads 511

Authors: Simon Espigolé, Igor Shalyminov, Helen Hastie

Abstract:

Deep machine learning techniques including deep neural networks (DNN) have been used to model language and dialogue for conversational agents to perform tasks, such as giving technical support and also for general chit-chat. They have been shown to be capable of generating long, diverse and coherent sentences in end-to-end dialogue systems and natural language generation. However, these systems tend to imitate the training data and will only generate the concepts and language within the scope of what they have been trained on. This work explores how deep neural networks can be used in a task that would normally require human creativity, whereby the human would read the movie description and/or watch the movie and come up with a compelling, interesting movie title. This task differs from simple summarization in that the movie title may not necessarily be derivable from the content or semantics of the movie description. Here, we train a type of DNN called a sequence-to-sequence model (seq2seq) that takes as input a short textual movie description and some information on e.g. genre of the movie. It then learns to output a movie title. The idea is that the DNN will learn certain techniques and approaches that the human movie titler may deploy that may not be immediately obvious to the human-eye. To give an example of a generated movie title, for the movie synopsis: ‘A hitman concludes his legacy with one more job, only to discover he may be the one getting hit.’; the original, true title is ‘The Driver’ and the one generated by the model is ‘The Masquerade’. A human evaluation was conducted where the DNN output was compared to the true human-generated title, as well as a number of baselines, on three 5-point Likert scales: ‘creativity’, ‘naturalness’ and ‘suitability’. Subjects were also asked which of the two systems they preferred. The scores of the DNN model were comparable to the scores of the human-generated movie title, with means m=3.11, m=3.12, respectively. There is room for improvement in these models as they were rated significantly less ‘natural’ and ‘suitable’ when compared to the human title. In addition, the human-generated title was preferred overall 58% of the time when pitted against the DNN model. These results, however, are encouraging given the comparison with a highly-considered, well-crafted human-generated movie title. Movie titles go through a rigorous process of assessment by experts and focus groups, who have watched the movie. This process is in place due to the large amount of money at stake and the importance of creating an effective title that captures the audiences’ attention. Our work shows progress towards automating this process, which in turn may lead to a better understanding of creativity itself.

Keywords: creativity, deep machine learning, natural language generation, movies

Procedia PDF Downloads 326

Authors: Ashkan Shafee, Ahmad Fahimifar

Abstract:

There is a growing demand for construction of high-rise buildings and infrastructures in large cities, which sometimes require deep excavations in the vicinity of pile foundations. In this study, a two-dimensional finite element analysis is used to gain insight into the response of pile groups adjacent to deep excavations in sand. The numerical code was verified by available experimental works, and a parametric study was performed on different working load combinations, excavation depth and supporting system. The results show that the simple two-dimensional plane strain model can accurately simulate the excavation induced changes on adjacent pile groups. It was found that further excavation than pile toe level and also inclined loading on adjacent pile group can severely affect the serviceability of the foundation.

Keywords: deep excavation, inclined loading, lateral deformation, pile group

Procedia PDF Downloads 274