scholarly journals 3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification

2021 ◽  
Vol 13 (4) ◽  
pp. 729
Author(s):  
Pedro J. Navarro ◽  
Leanne Miller ◽  
Alberto Gila-Navarro ◽  
María Victoria Díaz-Galián ◽  
Diego J. Aguila ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ad Hoc ◽  
Vision System ◽  
Classification Performance ◽  
Unmanned Vehicles ◽  
Table Grape ◽  
Classification Systems ◽  
Multispectral Images ◽  
Training Time ◽  
Grape Varieties

Current predefined architectures for deep learning are computationally very heavy and use tens of millions of parameters. Thus, computational costs may be prohibitive for many experimental or technological setups. We developed an ad hoc architecture for the classification of multispectral images using deep learning techniques. The architecture, called 3DeepM, is composed of 3D filter banks especially designed for the extraction of spatial-spectral features in multichannel images. The new architecture has been tested on a sample of 12210 multispectral images of seedless table grape varieties: Autumn Royal, Crimson Seedless, Itum4, Itum5 and Itum9. 3DeepM was able to classify 100% of the images and obtained the best overall results in terms of accuracy, number of classes, number of parameters and training time compared to similar work. In addition, this paper presents a flexible and reconfigurable computer vision system designed for the acquisition of multispectral images in the range of 400 nm to 1000 nm. The vision system enabled the creation of the first dataset consisting of 12210 37-channel multispectral images (12 VIS + 25 IR) of five seedless table grape varieties that have been used to validate the 3DeepM architecture. Compared to predefined classification architectures such as AlexNet, ResNet or ad hoc architectures with a very high number of parameters, 3DeepM shows the best classification performance despite using 130-fold fewer parameters than the architecture to which it was compared. 3DeepM can be used in a multitude of applications that use multispectral images, such as remote sensing or medical diagnosis. In addition, the small number of parameters of 3DeepM make it ideal for application in online classification systems aboard autonomous robots or unmanned vehicles.

scholarly journals Combining CNN and LSTM for activity of daily living recognition with a 3D matrix skeleton representation

2021 ◽  
Author(s):  
Giovanni Ercolano ◽  
Silvia Rossi
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Daily Living ◽  
Ad Hoc ◽  
Extraction Process ◽  
Classification Performance ◽  
Features Extraction ◽  
Assistive Robotics ◽  
Periodic Pattern ◽  
Time Activity

AbstractIn socially assistive robotics, human activity recognition plays a central role when the adaptation of the robot behavior to the human one is required. In this paper, we present an activity recognition approach for activities of daily living based on deep learning and skeleton data. In the literature, ad hoc features extraction/selection algorithms with supervised classification methods have been deployed, reaching an excellent classification performance. Here, we propose a deep learning approach, combining CNN and LSTM, that exploits both the learning of spatial dependencies correlating the limbs in a skeleton 3D grid representation and the learning of temporal dependencies from instances with a periodic pattern that works on raw data and so without requiring an explicit feature extraction process. These models are proposed for real-time activity recognition, and they are tested on the CAD-60 dataset. Results show that the proposed model behaves better than an LSTM model thanks to the automatic features extraction of the limbs’ correlation. “New Person” results show that the CNN-LSTM model achieves $$95.4\%$$ 95.4 % of precision and $$94.4\%$$ 94.4 % of recall, while the “Have Seen” results are $$96.1\%$$ 96.1 % of precision and $$94.7\%$$ 94.7 % of recall.

SVM-based global vision system of sports competition and action recognition

2020 ◽  
pp. 1-12
Author(s):  
Changxin Sun ◽  
Di Ma
Keyword(s):  
Target Recognition ◽  
Vision System ◽  
Task Assignment ◽  
Recognition Algorithm ◽  
Control Factor ◽  
Training Time ◽  
Adaboost Algorithm ◽  
Advantages And Disadvantages ◽  
Time Control ◽  
Correlation Degree

In the research of intelligent sports vision systems, the stability and accuracy of vision system target recognition, the reasonable effectiveness of task assignment, and the advantages and disadvantages of path planning are the key factors for the vision system to successfully perform tasks. Aiming at the problem of target recognition errors caused by uneven brightness and mutations in sports competition, a dynamic template mechanism is proposed. In the target recognition algorithm, the correlation degree of data feature changes is fully considered, and the time control factor is introduced when using SVM for classification,At the same time, this study uses an unsupervised clustering method to design a classification strategy to achieve rapid target discrimination when the environmental brightness changes, which improves the accuracy of recognition. In addition, the Adaboost algorithm is selected as the machine learning method, and the algorithm is optimized from the aspects of fast feature selection and double threshold decision, which effectively improves the training time of the classifier. Finally, for complex human poses and partially occluded human targets, this paper proposes to express the entire human body through multiple parts. The experimental results show that this method can be used to detect sports players with multiple poses and partial occlusions in complex backgrounds and provides an effective technical means for detecting sports competition action characteristics in complex backgrounds.

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

scholarly journals Vulnerability in Deep Transfer Learning Models to Adversarial Fast Gradient Sign Attack for COVID-19 Prediction from Chest Radiography Images

2021 ◽  
Vol 11 (9) ◽  
pp. 4233
Author(s):  
Biprodip Pal ◽  
Debashis Gupta ◽  
Md. Rashed-Al-Mahfuz ◽  
Salem A. Alyami ◽  
Mohammad Ali Moni
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Chest Radiography ◽  
High Sensitivity ◽  
Ct Images ◽  
Classification Performance ◽  
Learning Models ◽  
X Ray ◽  
Image Capturing ◽  
Fast Gradient

The COVID-19 pandemic requires the rapid isolation of infected patients. Thus, high-sensitivity radiology images could be a key technique to diagnose patients besides the polymerase chain reaction approach. Deep learning algorithms are proposed in several studies to detect COVID-19 symptoms due to the success in chest radiography image classification, cost efficiency, lack of expert radiologists, and the need for faster processing in the pandemic area. Most of the promising algorithms proposed in different studies are based on pre-trained deep learning models. Such open-source models and lack of variation in the radiology image-capturing environment make the diagnosis system vulnerable to adversarial attacks such as fast gradient sign method (FGSM) attack. This study therefore explored the potential vulnerability of pre-trained convolutional neural network algorithms to the FGSM attack in terms of two frequently used models, VGG16 and Inception-v3. Firstly, we developed two transfer learning models for X-ray and CT image-based COVID-19 classification and analyzed the performance extensively in terms of accuracy, precision, recall, and AUC. Secondly, our study illustrates that misclassification can occur with a very minor perturbation magnitude, such as 0.009 and 0.003 for the FGSM attack in these models for X-ray and CT images, respectively, without any effect on the visual perceptibility of the perturbation. In addition, we demonstrated that successful FGSM attack can decrease the classification performance to 16.67% and 55.56% for X-ray images, as well as 36% and 40% in the case of CT images for VGG16 and Inception-v3, respectively, without any human-recognizable perturbation effects in the adversarial images. Finally, we analyzed that correct class probability of any test image which is supposed to be 1, can drop for both considered models and with increased perturbation; it can drop to 0.24 and 0.17 for the VGG16 model in cases of X-ray and CT images, respectively. Thus, despite the need for data sharing and automated diagnosis, practical deployment of such program requires more robustness.

scholarly journals An Automated Light Trap to Monitor Moths (Lepidoptera) Using Computer Vision-Based Tracking and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 343
Author(s):  
Kim Bjerge ◽  
Jakob Bonde Nielsen ◽  
Martin Videbæk Sepstrup ◽  
Flemming Helsing-Nielsen ◽  
Toke Thomas Høye
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Vision System ◽  
Low Cost ◽  
Light Trap ◽  
Automatic Monitoring ◽  
Light Sources ◽  
Monitoring Methods ◽  
Computer Vision System ◽  
Substantial Investment

Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.

scholarly journals Genetic Improvement of Routing Protocols for Delay Tolerant Networks

2021 ◽  
Vol 1 (1) ◽  
pp. 1-37
Author(s):  
Michela Lorandi ◽  
Leonardo Lucio Custode ◽  
Giovanni Iacca
Keyword(s):  
Routing Protocols ◽  
Genetic Improvement ◽  
Ad Hoc ◽  
Delay Tolerant Networks ◽  
Unmanned Vehicles ◽  
Test Cases ◽  
Urban Networks ◽  
Delivery Probability ◽  
Apply Genetic ◽  
Delay Tolerant

Routing plays a fundamental role in network applications, but it is especially challenging in Delay Tolerant Networks (DTNs). These are a kind of mobile ad hoc networks made of, e.g., (possibly, unmanned) vehicles and humans where, despite a lack of continuous connectivity, data must be transmitted while the network conditions change due to the nodes’ mobility. In these contexts, routing is NP-hard and is usually solved by heuristic “store and forward” replication-based approaches, where multiple copies of the same message are moved and stored across nodes in the hope that at least one will reach its destination. Still, the existing routing protocols produce relatively low delivery probabilities. Here, we genetically improve two routing protocols widely adopted in DTNs, namely, Epidemic and PRoPHET, in the attempt to optimize their delivery probability. First, we dissect them into their fundamental components, i.e., functionalities such as checking if a node can transfer data, or sending messages to all connections. Then, we apply Genetic Improvement (GI) to manipulate these components as terminal nodes of evolving trees. We apply this methodology, in silico, to six test cases of urban networks made of hundreds of nodes and find that GI produces consistent gains in delivery probability in four cases. We then verify if this improvement entails a worsening of other relevant network metrics, such as latency and buffer time. Finally, we compare the logics of the best evolved protocols with those of the baseline protocols, and we discuss the generalizability of the results across test cases.

scholarly journals Train Fast While Reducing False Positives: Improving Animal Classification Performance Using Convolutional Neural Networks

Geomatics ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 34-49
Author(s):  
Mael Moreni ◽  
Jerome Theau ◽  
Samuel Foucher
Keyword(s):  
False Positive ◽  
Classification Performance ◽  
Large Datasets ◽  
False Positives ◽  
Fine Tuning ◽  
Training Time ◽  
In The Wild ◽  
Test Sets ◽  
High Level ◽  
Time Decrease

The combination of unmanned aerial vehicles (UAV) with deep learning models has the capacity to replace manned aircrafts for wildlife surveys. However, the scarcity of animals in the wild often leads to highly unbalanced, large datasets for which even a good detection method can return a large amount of false detections. Our objectives in this paper were to design a training method that would reduce training time, decrease the number of false positives and alleviate the fine-tuning effort of an image classifier in a context of animal surveys. We acquired two highly unbalanced datasets of deer images with a UAV and trained a Resnet-18 classifier using hard-negative mining and a series of recent techniques. Our method achieved sub-decimal false positive rates on two test sets (1 false positive per 19,162 and 213,312 negatives respectively), while training on small but relevant fractions of the data. The resulting training times were therefore significantly shorter than they would have been using the whole datasets. This high level of efficiency was achieved with little tuning effort and using simple techniques. We believe this parsimonious approach to dealing with highly unbalanced, large datasets could be particularly useful to projects with either limited resources or extremely large datasets.

Deep Learning Associated with Laser-Induced Breakdown Spectroscopy (LIBS) for the Prediction of Lead in Soil

2019 ◽  
Vol 73 (5) ◽  
pp. 565-573 ◽  
Author(s):  
Yun Zhao ◽  
Mahamed Lamine Guindo ◽  
Xing Xu ◽  
Miao Sun ◽  
Jiyu Peng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Confusion Matrix ◽  
Principal Component ◽  
Classification Performance ◽  
Soil Samples ◽  
Laser Induced Breakdown Spectroscopy ◽  
Support Vector ◽  
Breakdown Spectroscopy ◽  
Laser Induced Breakdown ◽  
Different Levels

In this study, a method based on laser-induced breakdown spectroscopy (LIBS) was developed to detect soil contaminated with Pb. Different levels of Pb were added to soil samples in which tobacco was planted over a period of two to four weeks. Principal component analysis and deep learning with a deep belief network (DBN) were implemented to classify the LIBS data. The robustness of the method was verified through a comparison with the results of a support vector machine and partial least squares discriminant analysis. A confusion matrix of the different algorithms shows that the DBN achieved satisfactory classification performance on all samples of contaminated soil. In terms of classification, the proposed method performed better on samples contaminated for four weeks than on those contaminated for two weeks. The results show that LIBS can be used with deep learning for the detection of heavy metals in soil.

scholarly journals Validating Deep Neural Networks for Online Decoding of Motor Imagery Movements from EEG Signals

Sensors ◽  
2019 ◽  
Vol 19 (1) ◽  
pp. 210 ◽  
Author(s):  
Zied Tayeb ◽  
Juri Fedjaev ◽  
Nejla Ghaboosi ◽  
Christoph Richter ◽  
Lukas Everding ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Classification Performance ◽  
Feature Engineering ◽  
Learning Models ◽  
Eeg Signals ◽  
Learning Methods

Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject’s motor intention into control signals through classifying the EEG patterns caused by different imagination tasks, e.g., hand movements. This type of BCI has been widely studied and used as an alternative mode of communication and environmental control for disabled patients, such as those suffering from a brainstem stroke or a spinal cord injury (SCI). Notwithstanding the success of traditional machine learning methods in classifying EEG signals, these methods still rely on hand-crafted features. The extraction of such features is a difficult task due to the high non-stationarity of EEG signals, which is a major cause by the stagnating progress in classification performance. Remarkable advances in deep learning methods allow end-to-end learning without any feature engineering, which could benefit BCI motor imagery applications. We developed three deep learning models: (1) A long short-term memory (LSTM); (2) a spectrogram-based convolutional neural network model (CNN); and (3) a recurrent convolutional neural network (RCNN), for decoding motor imagery movements directly from raw EEG signals without (any manual) feature engineering. Results were evaluated on our own publicly available, EEG data collected from 20 subjects and on an existing dataset known as 2b EEG dataset from “BCI Competition IV”. Overall, better classification performance was achieved with deep learning models compared to state-of-the art machine learning techniques, which could chart a route ahead for developing new robust techniques for EEG signal decoding. We underpin this point by demonstrating the successful real-time control of a robotic arm using our CNN based BCI.

Sign in / Sign up

Export Citation Format

Share Document