Search results for: deep learning image model

Authors: Yong Wee Foo, Lai Meng Tang

Abstract:

Artificial Intelligence (AI), particularly the usage of deep neural networks for hierarchical representations from data, has found numerous complex applications across various domains, including computer vision, robotics, autonomous vehicles, and other scientific fields. However, their inherent “black box” nature can sometimes make it challenging for early researchers or school students of various levels to comprehend and trust the results they produce. Consequently, there has been a growing demand for reliable visualization tools in engineering and science education to help learners understand, trust, and explain a deep learning network. This has led to a notable emphasis on the visualization of AI in the research community in recent years. AI visualization tools are increasingly being adopted to significantly improve the comprehension of complex topics in deep learning. This paper proposes a novel approach to empower students to actively explore the inner workings of deep neural networks by combining the student-centered learning approach of flipped classroom models with the investigative power of AI visualization tools, namely, the TensorFlow Playground, the Local Interpretable Model-agnostic Explanations (LIME), and the SHapley Additive exPlanations (SHAP), for delivering an AI education curriculum. Combining the two factors is vital in fostering ownership, responsibility, and critical thinking skills in the age of AI.

Keywords: deep learning, explainable AI, AI visualization, representation learning

Procedia PDF Downloads 41

Authors: Sonia Perez-Gamboa, Qingquan Sun, Yan Zhang

Abstract:

Non-intrusive sensor-based human activity recognition (HAR) is utilized in a spectrum of applications, including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short term memory (LSTM) recurrent neural networks (RNNs) provide a way to achieve HAR accurately and effectively. In this paper, we design a multi-layer hybrid architecture with CNN and LSTM and explore a variety of multi-layer combinations. Based on the exploration, we present a lightweight, hybrid, and multi-layer model, which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model, which can achieve a 94.7% activity recognition rate on a benchmark human activity dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between recognition rate and training time consumption.

Keywords: deep learning, LSTM, CNN, human activity recognition, inertial sensor

Procedia PDF Downloads 124

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 21

Authors: Avatharam Ganivada, Krishna Shah

Abstract:

The Mask R-CNN is recently introduced by the team of Facebook AI Research (FAIR), which is mainly concerned with instance segmentation in images. Here, the Mask R-CNN is based on ResNet and feature pyramid network (FPN), where a single dropout method is employed. This paper provides a modified Mask R-CNN by adding multiple dropout methods into the Mask R-CNN. The proposed model has also utilized the concepts of Resnet and FPN to extract stage-wise network feature maps, wherein a top-down network path having lateral connections is used to obtain semantically strong features. The proposed model produces three outputs for each object in the image: class label, bounding box coordinates, and object mask. The performance of the proposed network is evaluated in the segmentation of every instance in images using COCO and cityscape datasets. The proposed model achieves better performance than the state-of-the-networks for the datasets.

Keywords: instance segmentation, object detection, convolutional neural networks, deep learning, computer vision

Procedia PDF Downloads 53

Authors: Anas H. Aljemely, Jianping Xuan

Abstract:

Rolling bearing fault diagnosis plays a pivotal issue in the rotating machinery of modern manufacturing. In this research, a raw vibration signal and improved deep learning method for bearing fault diagnosis are proposed. The multi-dimensional scales of raw vibration signals are selected for evaluation condition monitoring system, and the deep learning process has shown its effectiveness in fault diagnosis. In the proposed method, employing an Exponential linear unit (ELU) layer in a convolutional neural network (CNN) that conducts the identical function on positive data, an exponential nonlinearity on negative inputs, and a particular convolutional operation to extract valuable features. The identification results show the improved method has achieved the highest accuracy with a 100-dimensional scale and increase the training and testing speed.

Keywords: bearing fault prognostics, developed CNN model, multiple-scale evaluation, deep learning features

Procedia PDF Downloads 179

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 77

Authors: Prachi Desai, Ankita Gandhi, Mitali Acharya

Abstract:

Rainfall forecast is mainly used for predictions of rainfall in a specified area and determining their future rainfall conditions. Rainfall is always a global issue as it affects all major aspects of one's life. Agricultural, fisheries, forestry, tourism industry and other industries are widely affected by these conditions. The studies have resulted in insufficient availability of water resources and an increase in water demand in the near future. We already have a new forecast system that uses the deep Convolutional Neural Network (CNN) to forecast monthly rainfall and climate changes. We have also compared CNN against Artificial Neural Networks (ANN). Machine Learning techniques that are used in rainfall predictions include ARIMA Model, ANN, LR, SVM etc. The dataset on which we are experimenting is gathered online over the year 1901 to 20118. Test results have suggested more realistic improvements than conventional rainfall forecasts.

Keywords: ANN, CNN, supervised learning, machine learning, deep learning

Procedia PDF Downloads 165

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 105

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 27

Authors: Edgardo V. Gubatanga Jr., Mark Joshua Salvacion

Abstract:

Most aerial LiDAR systems have accompanying aerial cameras in order to capture not only the terrain of the surveyed area but also its true-color appearance. However, the presence of atmospheric clouds, poor lighting conditions, and aerial camera problems during an aerial survey may cause absence of aerial photographs. These leave areas having terrain information but lacking aerial photographs. Intensity images can be derived from LiDAR data but they are only grayscale images. A deep learning model is developed to create a complex function in a form of a deep neural network relating the pixel values of LiDAR-derived intensity images and true-color images. This complex function can then be used to predict the true-color images of a certain area using intensity images from LiDAR data. The predicted true-color images do not necessarily need to be accurate compared to the real world. They are only intended to look realistic so that they can be used as base maps.

Keywords: aerial LiDAR, colorization, deep learning, intensity images

Procedia PDF Downloads 140

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 76

Authors: Aragorn Joaquin Pineda Dela Cruz

Abstract:

Road traffic congestion is continually deteriorating in Hong Kong. The largest contributing factor is the increase in vehicle fleet size, resulting in higher competition over the utilisation of road space. This study proposes a project that can process closed-circuit television images and videos to provide real-time traffic detection and prediction capabilities. Specifically, a deep-learning model involving computer vision techniques for video and image-based vehicle counting, then a separate model to detect and predict traffic congestion levels based on said data. State-of-the-art object detection models such as You Only Look Once and Faster Region-based Convolutional Neural Networks are tested and compared on closed-circuit television data from various major roads in Hong Kong. It is then used for training in long short-term memory networks to be able to predict traffic conditions in the near future, in an effort to provide more precise and quicker overviews of current and future traffic conditions relative to current solutions such as navigation apps.

Keywords: intelligent transportation system, vehicle detection, traffic analysis, deep learning, machine learning, computer vision, traffic prediction

Procedia PDF Downloads 76

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 78

Authors: Xiaoheng Tan, Xianfang Li, Tan Guo, Yuchuan Liu, Zhijun Yang, Hongye Li, Kai Fu, Yufang Wu, Heling Gong

Abstract:

The image data collected in reality often have high dimensions, and it contains noise and redundant information. Therefore, it is necessary to extract the compact feature expression of the original perceived image. In this process, effective use of prior knowledge such as data structure distribution and sample label is the key to enhance image feature discrimination and robustness. Based on the above considerations, this paper proposes a local preserving discriminant feature learning model based on graph optimization. The model has the following characteristics: (1) Locality preserving constraint can effectively excavate and preserve the local structural relationship between data. (2) The flexibility of graph learning can be improved by constructing a new local geometric structure graph using label information and the nearest neighbor threshold. (3) The L₂,₁ norm is used to redefine LDA, and the diagonal matrix is introduced as the scale factor of LDA, and the samples are selected, which improves the robustness of feature learning. The validity and robustness of the proposed algorithm are verified by experiments in two public image datasets.

Keywords: feature extraction, graph optimization local preserving projection, linear discriminant analysis, L₂, ₁ norm

Procedia PDF Downloads 128

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

Abstract:

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

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

Procedia PDF Downloads 134

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 216

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 235

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 82

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 52

Authors: Yuanqing Li, Changyi Lei, Zhaopeng Xue, Zhuo Zheng, Yanbo Long

Abstract:

In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.

Keywords: agricultural object detection, deep learning, machine vision, YOLO family

Procedia PDF Downloads 174

Authors: Shady Adib, Vladimir Vinogradov, Peter Gosling

Abstract:

Digital Twin (DT) technology is a new technology that appeared in the early 21st century. The DT is defined as the digital representation of living and non-living physical assets. By connecting the physical and virtual assets, data are transmitted smoothly, allowing the virtual asset to fully represent the physical asset. Although there are lots of studies conducted on the DT concept, there is still limited information about the ability of the DT models for monitoring and detecting unexpected changes in structural behaviour in real time. This is due to the large computational efforts required for the analysis and an excessively large amount of data transferred from sensors. This paper aims to develop the DT concept to be able to detect the abnormal changes in structural behaviour in real time using advanced modelling techniques, deep learning algorithms, and data acquisition systems, taking into consideration model uncertainties. finite element (FE) models were first developed offline to be used with a reduced basis (RB) model order reduction technique for the construction of low-dimensional space to speed the analysis during the online stage. The RB model was validated against experimental test results for the establishment of a DT model of a two-dimensional truss. The established DT model and deep learning algorithms were used to identify the location of damage once it has appeared during the online stage. Finally, the RB model was used again to identify the damage severity. It was found that using the RB model, constructed offline, speeds the FE analysis during the online stage. The constructed RB model showed higher accuracy for predicting the damage severity, while deep learning algorithms were found to be useful for estimating the location of damage with small severity.

Keywords: data acquisition system, deep learning, digital twin, model uncertainties, reduced basis, reduced order model

Procedia PDF Downloads 77

Authors: Shervin Alaei, Reza Moradi

Abstract:

Trading in financial markets is subject to risks due to their high volatilities. Here, using an LSTM neural network, and by doing some risk-based feature engineering tasks, we developed a method that can accurately predict trends of the Tehran stock exchange market index from a few days ago. Our test results have shown that the proposed method with an average prediction accuracy of more than 94% is superior to the other common machine learning algorithms. To the best of our knowledge, this is the first work incorporating deep learning and risk factors to accurately predict market trends.

Keywords: deep learning, LSTM, trend prediction, risk management, artificial neural networks

Procedia PDF Downloads 128

Authors: Jiaqi Huang, Yuheng Wang

Abstract:

Premises selection, the task of selecting a set of axioms for proving a given conjecture, is a major bottleneck in automated theorem proving. An array of deep-learning-based methods has been established for premises selection, but a perfect performance remains challenging. Our study examines the inaccuracy of deep neural networks in premises selection. Through training network models using encoded conjecture and axiom pairs from the Mizar Mathematical Library, two potential biases are found: the network models classify more premises as necessary than unnecessary, referred to as the ‘positive bias’, and the network models perform better in proving conjectures that paired with more axioms, referred to as ‘length bias’. The ‘positive bias’ and ‘length bias’ discovered could inform the limitation of existing deep neural networks.

Keywords: automated theorem proving, premises selection, deep learning, interpreting deep learning

Procedia PDF Downloads 163

Authors: Uvais Qidwai, Amor Moursi, Mohamed Tahar, Malek Hamad, Hamad Alansi

Abstract:

This paper focuses on the development and implementation of an advanced plant health monitoring system with an AI backbone and IoT sensory network. Our approach involves addressing the critical environmental factors essential for preserving a plant’s well-being, including air temperature, soil moisture, soil temperature, soil conductivity, pH, water levels, and humidity, as well as the presence of essential nutrients like nitrogen, phosphorus, and potassium. Central to our methodology is the utilization of computer vision technology, particularly a night vision camera. The captured data is then compared against a reference database containing different health statuses. This comparative analysis is implemented using an AI deep learning model, which enables us to generate accurate assessments of plant health status. By combining the AI-based decision-making approach, our system aims to provide precise and timely insights into the overall health and well-being of plants, offering a valuable tool for effective plant care and management.

Keywords: deep learning image model, IoT sensing, cloud-based analysis, remote monitoring app, computer vision, fuzzy control

Procedia PDF Downloads 20

Authors: Lin Li, Farshad Amini

Abstract:

The flipped classroom has been introduced to promote collaborative learning and higher-order learning objectives. In contrast to the traditional classroom, the flipped classroom has students watch prerecorded lecture videos before coming to class and then “class becomes the place to work through problems, advance concepts, and engage in collaborative learning”. In this paper, the active flipped learning combines flipped classroom with active learning that is to establish an active flipped learning (AFL) model, aiming to promote active learning, stress deep learning, encourage student engagement and highlight data-driven personalized learning. Because students have watched the lecture prior to class, contact hours can be devoted to problem-solving and gain a deeper understanding of the subject matter. The instructor is able to provide students with a wide range of learner-centered opportunities in class for greater mentoring and collaboration, increasing the possibility to engage students. Currently, little is known about the extent to which AFL improves engineering students’ performance. This paper presents the preliminary study on the core course of sophomore students in Engineering Mechanics. A series of survey and interviews have been conducted to compare students’ learning engagement, empowerment, self-efficacy, and satisfaction with the AFL. It was found that the AFL model taking advantage of advanced technology is a convenient and professional avenue for engineering students to strengthen their academic confidence and self-efficacy in the Engineering Mechanics by actively participating in learning and fostering their deep understanding of engineering statics and dynamics

Keywords: active learning, engineering mechanics, flipped classroom, performance

Procedia PDF Downloads 272

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 99

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 102

Authors: Yijun Shao, Yan Cheng, Rashmee U. Shah, Charlene R. Weir, Bruce E. Bray, Qing Zeng-Treitler

Abstract:

Deep neural network (DNN) models are being explored in the clinical domain, following the recent success in other domains such as image recognition. For clinical adoption, outcome prediction models require explanation, but due to the multiple non-linear inner transformations, DNN models are viewed by many as a black box. In this study, we developed a deep neural network model for predicting 1-year mortality of patients who underwent major cardio vascular procedures (MCVPs), using temporal image representation of past medical history as input. The dataset was obtained from the electronic medical data warehouse administered by Veteran Affairs Information and Computing Infrastructure (VINCI). We identified 21,355 veterans who had their first MCVP in 2014. Features for prediction included demographics, diagnoses, procedures, medication orders, hospitalizations, and frailty measures extracted from clinical notes. Temporal variables were created based on the patient history data in the 2-year window prior to the index MCVP. A temporal image was created based on these variables for each individual patient. To generate the explanation for the DNN model, we defined a new concept called impact score, based on the presence/value of clinical conditions’ impact on the predicted outcome. Like (log) odds ratio reported by the logistic regression (LR) model, impact scores are continuous variables intended to shed light on the black box model. For comparison, a logistic regression model was fitted on the same dataset. In our cohort, about 6.8% of patients died within one year. The prediction of the DNN model achieved an area under the curve (AUC) of 78.5% while the LR model achieved an AUC of 74.6%. A strong but not perfect correlation was found between the aggregated impact scores and the log odds ratios (Spearman’s rho = 0.74), which helped validate our explanation.

Keywords: deep neural network, temporal data, prediction, frailty, logistic regression model

Procedia PDF Downloads 136

Authors: Omar Elharrouss, Youssef Hmamouche, Assia Kamal Idrissi, Btissam El Khamlichi, Amal El Fallah-Seghrouchni

Abstract:

Edge detection is represented as one of the most challenging tasks in computer vision, due to the complexity of detecting the edges or boundaries in real-world images that contains objects of different types and scales like trees, building as well as various backgrounds. Edge detection is represented also as a key task for many computer vision applications. Using a set of backbones as well as attention modules, deep-learning-based methods improved the detection of edges compared with the traditional methods like Sobel and Canny. However, images of complex scenes still represent a challenge for these methods. Also, the detected edges using the existing approaches suffer from non-refined results while the image output contains many erroneous edges. To overcome this, n this paper, by using the mechanism of residual learning, a refined edge detection network is proposed (RED-Net). By maintaining the high resolution of edges during the training process, and conserving the resolution of the edge image during the network stage, we make the pooling outputs at each stage connected with the output of the previous layer. Also, after each layer, we use an affined batch normalization layer as an erosion operation for the homogeneous region in the image. The proposed methods are evaluated using the most challenging datasets including BSDS500, NYUD, and Multicue. The obtained results outperform the designed edge detection networks in terms of performance metrics and quality of output images.

Keywords: edge detection, convolutional neural networks, deep learning, scale-representation, backbone

Procedia PDF Downloads 79

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 195