Automatic Classification of Biological Targets in a Tidal Channel Using a Multibeam Sonar

2020 ◽  
Vol 37 (8) ◽  
pp. 1437-1455 ◽  
Author(s):  
Emma Cotter ◽  
Brian Polagye
Keyword(s):  
Real Time ◽  
Automatic Classification ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Hill Climbing ◽  
Support Vector ◽  
Tidal Channel ◽  
Multibeam Sonar ◽  
Biological Targets

AbstractMultibeam sonars are widely used for environmental monitoring of fauna at marine renewable energy sites. However, they can rapidly accrue vast volumes of data, which poses a challenge for data processing. Here, using data from a deployment in a tidal channel with peak currents of 1–2 m s−1, we demonstrate the data-reduction benefits of real-time automatic classification of targets detected and tracked in multibeam sonar data. First, we evaluate classification capabilities for three machine learning algorithms: random forests, support vector machines, and k-nearest neighbors. For each algorithm, a hill-climbing search optimizes a set of hand-engineered attributes that describe tracked targets. The random forest algorithm is found to be most effective—in postprocessing, discriminating between biological and nonbiological targets with a recall rate of 0.97 and a precision of 0.60. In addition, 89% of biological targets are correctly classified as either seals, diving birds, fish schools, or small targets. Model dependence on the volume of training data is evaluated. Second, a real-time implementation of the model is shown to distinguish between biological targets and nonbiological targets with nearly the same performance as in postprocessing. From this, we make general recommendations for implementing real-time classification of biological targets in multibeam sonar data and the transferability of trained models.

A Comparison of Machine Learning Algorithms for the Segmentation and Classification of Snow Micro Penetrometer Profiles on Arctic Sea Ice

2021 ◽  
Author(s):  
Julia Kaltenborn ◽  
Viviane Clay ◽  
Amy R. Macfarlane ◽  
Joshua Michael Lloyd King ◽  
Martin Schneebeli
Keyword(s):  
Machine Learning ◽  
Sea Ice ◽  
Arctic Sea Ice ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Snow Layer ◽  
Arctic Sea ◽  
Execution Speed

<p>Snow-layer classification is an essential diagnostic task for a wide variety of cryospheric science and climate research applications. Traditionally, these measurements are made in snow pits, requiring trained operators and a substantial time commitment. The SnowMicroPen (SMP), a portable high-resolution snow penetrometer, has been demonstrated as a capable tool for rapid snow grain classification and layer type segmentation through statistical inversion of its mechanical signal. The manual classification of the SMP profiles requires time and training and becomes infeasible for large datasets.</p><p>Here, we introduce a novel set of SMP measurements collected during the MOSAiC expedition and apply Machine Learning (ML) algorithms to automatically classify and segment SMP profiles of snow on Arctic sea ice. To this end, different supervised and unsupervised ML methods, including Random Forests, Support Vector Machines, Artificial Neural Networks, and k-means Clustering, are compared. A subsequent segmentation of the classified data results in distinct layers and snow grain markers for the SMP profiles. The models are trained with the dataset by King et al. (2020) and the MOSAiC SMP dataset. The MOSAiC dataset is a unique and extensive dataset characterizing seasonal and spatial variation of snow on the central Arctic sea-ice.</p><p>We will test and compare the different algorithms and evaluate the algorithms’ effectiveness based on the need for initial dataset labeling, execution speed, and ease of implementation. In particular, we will compare supervised to unsupervised methods, which are distinguished by their need for labeled training data.</p><p>The implementation of different ML algorithms for SMP profile classification could provide a fast and automatic grain type classification and snow layer segmentation. Based on the gained knowledge from the algorithms’ comparison, a tool can be built to provide scientists from different fields with an immediate SMP profile classification and segmentation. </p><p> </p><p>King, J., Howell, S., Brady, M., Toose, P., Derksen, C., Haas, C., & Beckers, J. (2020). Local-scale variability of snow density on Arctic sea ice. <em>The Cryosphere</em>, <em>14</em>(12), 4323-4339, https://doi.org/10.5194/tc-14-4323-2020.</p>

Invisible experience to real-time assessment in elite tennis athlete training: Sport-specific movement classification based on wearable MEMS sensor data

2021 ◽  
pp. 175433712110503
Author(s):  
Mingyue Wu ◽  
Ran Wang ◽  
Yang Hu ◽  
Mengjiao Fan ◽  
Yufan Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Test Accuracy ◽  
Z Score ◽  
Mems Sensor ◽  
Score Normalization

This study examined the reliability of a tennis stroke classification and assessment platform consisting of a single low-cost MEMS sensor in a wrist-worn wearable device, smartphone, and computer. The data that was collected was transmitted via Bluetooth and analyzed by machine learning algorithms. Twelve right-handed male elite tennis athletes participated in the study, and each athlete performed 150 strokes. The results from three machine learning algorithms regarding their recognition and classification of the real-time data stream were compared. Stroke recognition and classification went through pre-processing, segmentation, feature extraction, and classification with Support Vector Machine (SVM), including SVM without normalization, SVM with Min–Max, SVM with Z-score normalization, K-nearest neighbor (K-NN), and Naive Bayes (NB) machine learning algorithms. During the data training process, 10-fold cross-validation was used to avoid overfitting and suitable parameters were found within the SVM classifiers. The best classifier was achieved when C = 1 using the RBF kernel function. Different machine learning algorithms’ classification of unique stroke types yielded highly reliable clusters within each stroke type with the highest test accuracy of 99% achieved by SVM with Min–Max normalization and 98.4% achieved using SVM with a Z-score normalization classifier.

scholarly journals Cumulant Features based Classification of Brain MR Images using ANN and LS-SVM Algorithm

2019 ◽  
Vol 8 (11) ◽  
pp. 4008-4012
Keyword(s):  
Brain Tumour ◽  
Automatic Classification ◽  
Machine Learning Algorithms ◽  
Least Square ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Mr Images ◽  
Mr Image ◽  
Linear Discriminant

Automatic classification of magnetic resonance (MR) brain images using machine learning algorithms has a significant role in clinical diagnosis of brain tumour. The higher order spectra cumulant features are powerful and competent tool for automatic classification. The study proposed an effective cumulant-based features to predict the severity of brain tumour. The study at first stage implicates the one-level classification of 2-D discrete wavelet transform (DWT) of taken brain MR image. The cumulants of every sub-bands are then determined to calculate the primary feature vector. Linear discriminant analysis is adopted to extract the discriminative features derived from the primary ones. A three layer feed-forward artificial neural network (ANN) and least square based support vector machine (LS-SVM) algorithms are considered to compute that the brain MR image is either belongs to normal or to one of seven other diseases (eight-class scenario). Furthermore, in one more classification problem, the input MR image is categorized as normal or abnormal (two-class scenario). The correct classification rate (CCR) of LS-SVM is superior than the ANN algorithm thereby the proposed study with LS-SVM attains higher accuracy rate in both classification scenarios of MR images.

scholarly journals Can Automatic Classification Help to Increase Accuracy in Data Collection?

2017 ◽  
Vol 1 (3) ◽  
pp. 42-58 ◽  
Author(s):  
Frederique Lang ◽  
Diego Chavarro ◽  
Yuxian Liu
Keyword(s):  
Data Collection ◽  
Linear Models ◽  
Data Cleaning ◽  
Automatic Classification ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Training Dataset ◽  
Support Vector ◽  
Classification Algorithms ◽  
Linear Discriminant

AbstractPurposeThe authors aim at testing the performance of a set of machine learning algorithms that could improve the process of data cleaning when building datasets.Design/methodology/approachThe paper is centered on cleaning datasets gathered from publishers and online resources by the use of specific keywords. In this case, we analyzed data from the Web of Science. The accuracy of various forms of automatic classification was tested here in comparison with manual coding in order to determine their usefulness for data collection and cleaning. We assessed the performance of seven supervised classification algorithms (Support Vector Machine (SVM), Scaled Linear Discriminant Analysis, Lasso and elastic-net regularized generalized linear models, Maximum Entropy, Regression Tree, Boosting, and Random Forest) and analyzed two properties: accuracy and recall. We assessed not only each algorithm individually, but also their combinations through a voting scheme. We also tested the performance of these algorithms with different sizes of training data. When assessing the performance of different combinations, we used an indicator of coverage to account for the agreement and disagreement on classification between algorithms.FindingsWe found that the performance of the algorithms used vary with the size of the sample for training. However, for the classification exercise in this paper the best performing algorithms were SVM and Boosting. The combination of these two algorithms achieved a high agreement on coverage and was highly accurate. This combination performs well with a small training dataset (10%), which may reduce the manual work needed for classification tasks.Research limitationsThe dataset gathered has significantly more records related to the topic of interest compared to unrelated topics. This may affect the performance of some algorithms, especially in their identification of unrelated papers.Practical implicationsAlthough the classification achieved by this means is not completely accurate, the amount of manual coding needed can be greatly reduced by using classification algorithms. This can be of great help when the dataset is big. With the help of accuracy, recall, and coverage measures, it is possible to have an estimation of the error involved in this classification, which could open the possibility of incorporating the use of these algorithms in software specifically designed for data cleaning and classification.Originality/valueWe analyzed the performance of seven algorithms and whether combinations of these algorithms improve accuracy in data collection. Use of these algorithms could reduce time needed for manual data cleaning.

scholarly journals Evaluation of Three Machine Learning Algorithms for the Automatic Classification of EMG Patterns in Gait Disorders

2021 ◽  
Vol 12 ◽  
Author(s):  
Christopher Fricke ◽  
Jalal Alizadeh ◽  
Nahrin Zakhary ◽  
Timo B. Woost ◽  
Martin Bogdan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Muscle Activity ◽  
Automatic Classification ◽  
Gait Disorders ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Female Age ◽  
Emg Patterns

Gait disorders are common in neurodegenerative diseases and distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge even for the experienced clinician. Ultimately, muscle activity underlies the generation of kinematic patterns. Therefore, one possible way to address this problem may be to differentiate gait disorders by analyzing intrinsic features of muscle activations patterns. Here, we examined whether it is possible to differentiate electromyography (EMG) gait patterns of healthy subjects and patients with different gait disorders using machine learning techniques. Nineteen healthy volunteers (9 male, 10 female, age 28.2 ± 6.2 years) and 18 patients with gait disorders (10 male, 8 female, age 66.2 ± 14.7 years) resulting from different neurological diseases walked down a hallway 10 times at a convenient pace while their muscle activity was recorded via surface EMG electrodes attached to 5 muscles of each leg (10 channels in total). Gait disorders were classified as predominantly hypokinetic (n = 12) or ataxic (n = 6) gait by two experienced raters based on video recordings. Three different classification methods (Convolutional Neural Network—CNN, Support Vector Machine—SVM, K-Nearest Neighbors—KNN) were used to automatically classify EMG patterns according to the underlying gait disorder and differentiate patients and healthy participants. Using a leave-one-out approach for training and evaluating the classifiers, the automatic classification of normal and abnormal EMG patterns during gait (2 classes: “healthy” and “patient”) was possible with a high degree of accuracy using CNN (accuracy 91.9%), but not SVM (accuracy 67.6%) or KNN (accuracy 48.7%). For classification of hypokinetic vs. ataxic vs. normal gait (3 classes) best results were again obtained for CNN (accuracy 83.8%) while SVM and KNN performed worse (accuracy SVM 51.4%, KNN 32.4%). These results suggest that machine learning methods are useful for distinguishing individuals with gait disorders from healthy controls and may help classification with respect to the underlying disorder even when classifiers are trained on comparably small cohorts. In our study, CNN achieved higher accuracy than SVM and KNN and may constitute a promising method for further investigation.

scholarly journals NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2503
Author(s):  
Taro Suzuki ◽  
Yoshiharu Amano
Keyword(s):  
Machine Learning ◽  
Satellite System ◽  
Training Data ◽  
Support Vector ◽  
Positioning Errors ◽  
Automated Method ◽  
Global Navigation Satellite ◽  
Better Than ◽  
Signal Correlation

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

scholarly journals Delineating Smallholder Maize Farms from Sentinel-1 Coupled with Sentinel-2 Data Using Machine Learning

2021 ◽  
Vol 13 (9) ◽  
pp. 4728
Author(s):  
Zinhle Mashaba-Munghemezulu ◽  
George Johannes Chirima ◽  
Cilence Munghemezulu
Keyword(s):  
Machine Learning ◽  
Food Security ◽  
Rural Communities ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Subsistence Agriculture ◽  
Smallholder Farms ◽  
Main Driver ◽  
Sentinel 2

Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores the use of Sentinel-1 and Sentinel-2 data to map smallholder maize farms. The random forest (RF), support vector (SVM) machine learning algorithms and model stacking (ST) were applied. Results show that the classification of combined Sentinel-1 and Sentinel-2 data improved the RF, SVM and ST algorithms by 24.2%, 8.7%, and 9.1%, respectively, compared to the classification of Sentinel-1 data individually. Similarities in the estimated areas (7001.35 ± 1.2 ha for RF, 7926.03 ± 0.7 ha for SVM and 7099.59 ± 0.8 ha for ST) show that machine learning can estimate smallholder maize areas with high accuracies. The study concludes that the single-date Sentinel-1 data were insufficient to map smallholder maize farms. However, single-date Sentinel-1 combined with Sentinel-2 data were sufficient in mapping smallholder farms. These results can be used to support the generation and validation of national crop statistics, thus contributing to food security.

scholarly journals Classification of Daily Irradiance Profiles and the Behaviour of Photovoltaic Plant Elements: The Effects of Cloud Enhancement

2021 ◽  
Vol 11 (11) ◽  
pp. 5230
Author(s):  
Isabel Santiago ◽  
Jorge Luis Esquivel-Martin ◽  
David Trillo-Montero ◽  
Rafael Jesús Real-Calvo ◽  
Víctor Pallarés-López
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Automatic Classification ◽  
Sampling Frequency ◽  
Machine Learning Algorithms ◽  
Unsupervised Machine Learning ◽  
Average Efficiency ◽  
Clear Sky ◽  
Photovoltaic Plant

In this work, the automatic classification of daily irradiance profiles registered in a photovoltaic installation located in the south of Spain was carried out for a period of nine years, with a sampling frequency of 5 min, and the subsequent analysis of the operation of the elements of the installation on each type of day was also performed. The classification was based on the total daily irradiance values and the fluctuations of this parameter throughout the day. The irradiance profiles were grouped into nine different categories using unsupervised machine learning algorithms for clustering, implemented in Python. It was found that the behaviour of the modules and the inverter of the installation was influenced by the type of day obtained, such that the latter worked with a better average efficiency on days with higher irradiance and lower fluctuations. However, the modules worked with better average efficiency on days with irradiance fluctuations than on clear sky days. This behaviour of the modules may be due to the presence, on days with passing clouds, of the phenomenon known as cloud enhancement, in which, due to reflections of radiation on the edges of the clouds, irradiance values can be higher at certain moments than those that occur on clear sky days, without passing clouds. This is due to the higher energy generated during these irradiance peaks and to the lower temperatures that the module reaches due to the shaded areas created by the clouds, resulting in a reduction in its temperature losses.

scholarly journals Drill-Core Mineral Abundance Estimation Using Hyperspectral and High-Resolution Mineralogical Data

2020 ◽  
Vol 12 (7) ◽  
pp. 1218
Author(s):  
Laura Tuşa ◽  
Mahdi Khodadadzadeh ◽  
Cecilia Contreras ◽  
Kasra Rafiezadeh Shahi ◽  
Margret Fuchs ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Ore Deposits ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Drill Core ◽  
Data Types ◽  
Mineralogical Characterization ◽  
Core Samples

Due to the extensive drilling performed every year in exploration campaigns for the discovery and evaluation of ore deposits, drill-core mapping is becoming an essential step. While valuable mineralogical information is extracted during core logging by on-site geologists, the process is time consuming and dependent on the observer and individual background. Hyperspectral short-wave infrared (SWIR) data is used in the mining industry as a tool to complement traditional logging techniques and to provide a rapid and non-invasive analytical method for mineralogical characterization. Additionally, Scanning Electron Microscopy-based image analyses using a Mineral Liberation Analyser (SEM-MLA) provide exhaustive high-resolution mineralogical maps, but can only be performed on small areas of the drill-cores. We propose to use machine learning algorithms to combine the two data types and upscale the quantitative SEM-MLA mineralogical data to drill-core scale. This way, quasi-quantitative maps over entire drill-core samples are obtained. Our upscaling approach increases result transparency and reproducibility by employing physical-based data acquisition (hyperspectral imaging) combined with mathematical models (machine learning). The procedure is tested on 5 drill-core samples with varying training data using random forests, support vector machines and neural network regression models. The obtained mineral abundance maps are further used for the extraction of mineralogical parameters such as mineral association.

Sign in / Sign up

Export Citation Format

Share Document