Feature Engineering Approach Research Articles

Lung and colon cancer classification using medical imaging: a feature engineering approach.

Lung and colon cancers lead to a significant portion of deaths. Their simultaneous occurrence is uncommon, however, in the absence of early diagnosis, the metastasis of cancer cells is very high between these two organs. Currently, histopathological diagnosis and appropriate treatment are the only way to improve the chances of survival and reduce cancer mortality. Using artificial intelligence in the histopathological diagnosis of colon and lung cancer can provide significant help to specialists in identifying cases of colon and lung cancers with less effort, time and cost. The objective of this study is to set up a computer-aided diagnostic system that can accurately classify five types of colon and lung tissues (two classes for colon cancer and three classes for lung cancer) by analyzing their histopathological images. Using machine learning, features engineering and image processing techniques, the six models XGBoost, SVM, RF, LDA, MLP and LightGBM were used to perform the classification of histopathological images of lung and colon cancers that were acquired from the LC25000 dataset. The main advantage of using machine learning models is that they allow a better interpretability of the classification model since they are based on feature engineering; however, deep learning models are black box networks whose working is very difficult to understand due to the complex network design. The acquired experimental results show that machine learning models give satisfactory results and are very precise in identifying classes of lung and colon cancer subtypes. The XGBoost model gave the best performance with an accuracy of 99% and a F1-score of 98.8%. The implementation and the development of this model will help healthcare specialists identify types of colon and lung cancers. The code will be available upon request.

Ablation Study On Feature Group Importance For Automated Essay Scoring

Grading of written academic essays by humans requires significant effort. It is a time-consuming task and is vulnerable to human biases. Ever since the introduction of modern computing, this has been one of the many automations being explored. Researches in automated essay scoring have been on-going, where the majority of the researches in recent years are based on extracting multiple linguistic features and using them to build a classification model for automated essay scoring. The 3 main types of features used are lexical, grammatical, and semantic. In our work, we conducted an ablation study to discover the engineered features that has the weakest influence. We did this using a generic feature engineering and classification approach that was used by the winners of the Automated Student Assessment Prize (ASAP). This is to mitigate biases that may have addressed specific feature engineering or models. Our results show that a semantic feature called the prompt has been the weakest feature in influencing the models. From further investigations, this was due to it being over-fitted in the classification model.

An Accurate Multiple Sclerosis Detection Model Based on Exemplar Multiple Parameters Local Phase Quantization: ExMPLPQ

Multiple sclerosis (MS) is a chronic demyelinating condition characterized by plaques in the white matter of the central nervous system that can be detected using magnetic resonance imaging (MRI). Many deep learning models for automated MS detection based on MRI have been presented in the literature. We developed a computationally lightweight machine learning model for MS diagnosis using a novel handcrafted feature engineering approach. The study dataset comprised axial and sagittal brain MRI images that were prospectively acquired from 72 MS and 59 healthy subjects who attended the Ozal University Medical Faculty in 2021. The dataset was divided into three study subsets: axial images only (n = 1652), sagittal images only (n = 1775), and combined axial and sagittal images (n = 3427) of both MS and healthy classes. All images were resized to 224 × 224. Subsequently, the features were generated with a fixed-size patch-based (exemplar) feature extraction model based on local phase quantization (LPQ) with three-parameter settings. The resulting exemplar multiple parameters LPQ (ExMPLPQ) features were concatenated to form a large final feature vector. The top discriminative features were selected using iterative neighborhood component analysis (INCA). Finally, a k-nearest neighbor (kNN) algorithm, Fine kNN, was deployed to perform binary classification of the brain images into MS vs. healthy classes. The ExMPLPQ-based model attained 98.37%, 97.75%, and 98.22% binary classification accuracy rates for axial, sagittal, and hybrid datasets, respectively, using Fine kNN with 10-fold cross-validation. Furthermore, our model outperformed 19 established pre-trained deep learning models that were trained and tested with the same data. Unlike deep models, the ExMPLPQ-based model is computationally lightweight yet highly accurate. It has the potential to be implemented as an automated diagnostic tool to screen brain MRIs for white matter lesions in suspected MS patients.

A Machine Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars.

Identifying accident patterns is one of the most vital research foci of driving analysis. Environmental or safety applications and the growing area of fleet management all benefit from accident detection contributions by minimizing the risk vehicles and drivers are subject to, improving their service and reducing overhead costs. Some solutions have been proposed in the past literature for automated accident detection that are mainly based on traffic data or external sensors. However, traffic data can be difficult to access, while external sensors can end up being difficult to set up and unreliable, depending on how they are used. Additionally, the scarcity of accident detection data has limited the type of approaches used in the past, leaving in particular, machine learning (ML) relatively unexplored. Thus, in this paper, we propose a ML framework for automated car accident detection based on mutimodal in-car sensors. Our work is a unique and innovative study on detecting real-world driving accidents by applying state-of-the-art feature extraction methods using basic sensors in cars. In total, five different feature extraction approaches, including techniques based on feature engineering and feature learning with deep learning are evaluated on the strategic highway research program (SHRP2) naturalistic driving study (NDS) crash data set. The main observations of this study are as follows: (1) CNN features with a SVM classifier obtain very promising results, outperforming all other tested approaches. (2) Feature engineering and feature learning approaches were finding different best performing features. Therefore, our fusion experiment indicates that these two feature sets can be efficiently combined. (3) Unsupervised feature extraction remarkably achieves a notable performance score.

Multi-Perspective Content Delivery Networks Security Framework Using Optimized Unsupervised Anomaly Detection

Content delivery networks (CDNs) provide efficient content distribution over the Internet. CDNs improve the connectivity and efficiency of global communications, but their caching mechanisms may be breached by cyber-attackers. Among the security mechanisms, effective anomaly detection forms an important part of CDN security enhancement. In this work, we propose a multi-perspective unsupervised learning framework for anomaly detection in CDNs. In the proposed framework, a multi-perspective feature engineering approach, an optimized unsupervised anomaly detection model that utilizes an isolation forest and a Gaussian mixture model, and a multi-perspective validation method, are developed to detect abnormal behaviors in CDNs mainly from the client Internet Protocol (IP) and node perspectives, therefore to identify the denial of service (DoS) and cache pollution attack (CPA) patterns. Experimental results are presented based on the analytics of eight days of real-world CDN log data provided by a major CDN operator. Through experiments, the abnormal contents, compromised nodes, malicious IPs, as well as their corresponding attack types, are identified effectively by the proposed framework and validated by multiple cybersecurity experts. This shows the effectiveness of the proposed method when applied to real-world CDN data.

Feature engineering solution with structured query language analytic functions in detecting electricity frauds using machine learning

Detecting fraud related to electricity consumption is usually a difficult challenge as the input datasets are sometimes unreliable due to missing and inconsistent records, faults, misinterpretation of meter reading remarks, status, etc. In this paper, we obtain meaningful insights from fraud detection using real datasets of Tunisian electricity consumption metered by conventional meters. We propose an extensive feature engineering approach using the structured query language (SQL) analytic functions. Furthermore, double merging of datasets reveals more dimensions of the data allowing better detection of irregularities in consumption. We analyze the results of several machine learning (ML) algorithms that manage cases of weakly correlated features and highly unbalanced datasets. The skewness of the target is approached as a regular characteristic of the input data because most of consumers are fair and only a small portion attempt to mislead the utility companies by tampering with metering devices. Our fraud detection solutions consist of combining classifiers with an anomaly detection feature obtained with an unsupervised ML algorithm—Isolation Forest, and extensive feature engineering using SQL analytic functions on large datasets. Several techniques for feature processing enhanced the Area Under the Curve score for Decision Tree algorithm from 0.68 to 0.99.

Sentiment analysis and spam filtering using the YAC2 clustering algorithm with transferability

Two notable applications of text classification are sentiment analysis and spam filtering. Traditional machine learning approaches to text classification are often complex, non-transferrable, and require supervision. This paper introduces an unsupervised approach to text classification which is relatively simple and transfers between problem domains, while providing accuracy comparable or better than established alternatives. We present an integrated solution which combines a new clustering algorithm, Yet Another Clustering Algorithm (YAC2), with a domain transferrable feature engineering approach for Twitter sentiment analysis and spam filtering of YouTube comments. We evaluate the effectiveness of this integrated solution for Twitter sentiment analysis using three datasets: Starbucks, Verizon, and Southwest Airlines. YouTube spam filtering is evaluated using four datasets: Psy, LMFAO, Shakira,and Katy Perry. We compare the results with established clusteringsolutions: KNN, Spectral, and DBSCAN. Our integrated solution performs better than all the alternatives for sentiment analysis. For spam filtering, YAC2 and KNN perform within 1% of each other and far better than Spectral and DBSCAN for all datasets. Additionally, our feature engineering approach improves accuracy compared to using a traditional method, while significantly reducing model dimensionality, matrix sparsity and providing transferability across the datasets tested.

Fraudulent review detection model focusing on emotional expressions and explicit aspects: investigating the potential of feature engineering

Reading customer reviews before purchasing items online has become a common practice; however, some companies use machine learning (ML) algorithms to generate false reviews in order to create positive brand images of their own products and negative images of competitors' offerings. Existing techniques use review content to identify fraudulent reviewers; however, spammers become more intelligent, started to learn from their mistakes, and changed their tactics in order to avoid detection techniques. Thus, investigating fraudulent accounts' behaviour of generating fake negative or positive reviews for competitors or themselves and the necessity of ML classifiers to identify fraudulent reviews, is more important than ever. In this research, we present a novel feature engineering approach in which we (1) extract several “review-centric” and “reviewer-centric” features from a dataset; (2) combine the cumulative effects of features distributions into a unified model that represents overall behavior of the fraudulent reviewers; (3) investigate the role of effective data pre-processing to improve detection accuracy; and (4) develop a probabilistic approach to detect fraudulent reviewers by learning a novel M-SMOTE model over a derived balanced dataset and feature distributions, which outperforms other ML models. Our study contributes to the literature on digital platforms and fraudulent review detection with significant managerial and theoretical implications through these novel findings.

Diabetes Prediction Using Derived Features and Ensembling of燘oosting燙lassifiers

Diabetes is increasing commonly in people’s daily life and represents an extraordinary threat to human well-being. Machine Learning (ML) in the healthcare industry has recently made headlines. Several ML models are developed around different datasets for diabetic prediction. It is essential for ML models to predict diabetes accurately. Highly informative features of the dataset are vital to determine the capability factors of the model in the prediction of diabetes. Feature engineering (FE) is the way of taking forward in yielding highly informative features. Pima Indian Diabetes Dataset (PIDD) is used in this work, and the impact of informative features in ML models is experimented with and analyzed for the prediction of diabetes. Missing values (MV) and the effect of the imputation process in the data distribution of each feature are analyzed. Permutation importance and partial dependence are carried out extensively and the results revealed that Glucose (GLUC), Body Mass Index (BMI), and Insulin (INS) are highly informative features. Derived features are obtained for BMI and INS to add more information with its raw form. The ensemble classifier with an ensemble of AdaBoost (AB) and XGBoost (XB) is considered for the impact analysis of the proposed FE approach. The ensemble model performs well for the inclusion of derived features provided the high Diagnostics Odds Ratio (DOR) of 117.694. This shows a high margin of 8.2% when compared with the ensemble model with no derived features (DOR = 96.306) included in the experiment. The inclusion of derived features with the FE approach of the current state-of-the-art made the ensemble model performs well with Sensitivity (0.793), Specificity (0.945), DOR (79.517), and False Omission Rate (0.090) which further improves the state-of-the-art results.

Feature Engineering and Artificial Intelligence-Supported Approaches Used for Electric Powertrain Fault Diagnosis: A Review

Electric powertrain is constituted by electric machine transmission unit, inverter and battery packs, etc., is a highly-integrated system. Its reliability and safety are not only related to industrial costs, but more importantly to the safety of human life. This review is the first contribution to comprehensively summarize both the feature engineering methods and artificial intelligence (AI) algorithms (including machine learning, neural networks and deep learning) in electric powertrain condition monitoring and fault diagnosis approaches. Specifically, this paper systematically divides the AI-supported method into two main steps: feature engineering and AI approach. On the one hand, it introduces the data and feature processing in AI-supported methods, and on the other hand it summarizes input signals, feature methods and AI algorithms included in the AI method in cases. Therefore, firstly this review is to guide how to choose the appropriate feature engineering method in further research. Secondly, the up-to-date AI algorithms adopted for powertrain health monitoring are presented in detail. Finally, such current approaches are discussed and future trends are proposed.

Functional coding haplotypes and machine-learning feature elimination identifies predictors of Methotrexate Response in Rheumatoid Arthritis patients.

SummaryBackgroundMajor challenges in large scale genetic association studies include not only the identification of causative single nucleotide polymorphisms (SNPs), but also accounting for SNP-SNP interactions. This study thus proposes a novel feature engineering approach integrating potentially functional coding haplotypes (pfcHap) with machine-learning (ML) feature selection to identify biologically meaningful, possibly causative genetic factors, that take into consideration potential SNP-SNP interactions within the pfcHap, to best predict for methotrexate (MTX) response in rheumatoid arthritis (RA) patients.MethodsExome sequencing from 349 RA patients were analysed, of which they were split into training and unseen test set. Inferred pfcHaps were combined with 30 non-genetic features to undergo ML recursive feature elimination with cross-validation using the training set. Predictive capacity and robustness of the selected features were assessed using six popular machine learning models through a train set cross-validation and evaluated in an unseen test set.FindingsSignificantly, 100 features (95 pfcHaps, 5 non-genetic factors) were identified to have good predictive performance (AUC: 0.776-0.828; Sensitivity: 0.656-0.813; Specificity: 0.684-0.868) across all six ML models in an unseen test dataset for the prediction of MTX response in RA patients.InterpretationMajority of the predictive pfcHap SNPs were predicted to be potentially functional and some of the genes in which the pfcHap resides in were identified to be associated with previously reported MTX/RA pathways.FundingSingapore Ministry of Health's National Medical Research Council (NMRC) [NMRC/CBRG/0095/2015; CG12Aug17; CGAug16M012; NMRC/CG/017/2013]; National Cancer Center Research Fund and block funding Duke-NUS Medical School.; Singapore Ministry of Education Academic Research Fund Tier 2 grant MOE2019-T2-1-138.

Inquest of Current Situation in Afghanistan Under Taliban Rule Using Sentiment Analysis and Volume Analysis

Microblogging websites and social media platforms serve as a potential source for mining public opinions and sentiments on a variety of subjects including the prevailing situations in war-afflicted countries. In particular, Twitter has a large number of geotagged tweets that make the analysis of sentiments across time and space possible. This study performs volume analysis and sentiment analysis using LDA (Latent Dirichlet Allocation) and text mining over two datasets collected for different periods. To increase the adequacy and efficacy of the sentiment analysis, a hybrid feature engineering approach is proposed that elevates the performance of machine learning models. Geotagged tweets are used for volume analysis indicating that the highest number of tweets is originated from India, the US, the UK, Pakistan, and Afghanistan. Analysis of positive and negative tweets reveals that negative tweets are mostly originated from India and the US. On the contrary, positive tweets belong to Pakistan and Afghanistan. LDA is used for topic modeling on two datasets containing tweets about the current situation after the Taliban take control of Afghanistan. Topics extracted through LDA suggest that majority of the Afghanistan people seem satisfied with the Taliban’s takeover while the topics from negative tweets reveal that issues discussed in negative tweets are related to the US concerns in Afghanistan. Sentiment analysis over two different datasets indicates that the trend of the sentiments has been shifted positively over three weeks.

Week Ahead Electricity Power and Price Forecasting Using Improved DenseNet-121 Method

In the Smart Grid (SG) residential environment, consumers change their power consumption routine according to the price and incentives announced by the utility, which causes the prices to deviate from the initial pattern. Thereby, electricity demand and price forecasting play a significant role and can help in terms of reliability and sustainability. Due to the massive amount of data, big data analytics for forecasting becomes a hot topic in the SG domain. In this paper, the changing and non-linearity of consumer consumption pattern complex data is taken as input. To minimize the computational cost and complexity of the data, the average of the feature engineering approaches includes: Recursive Feature Eliminator (RFE), Extreme Gradient Boosting (XGboost), Random Forest (RF), and are upgraded to extract the most relevant and significant features. To this end, we have proposed the DensetNet-121 network and Support Vector Machine (SVM) ensemble with Aquila Optimizer (AO) to ensure adaptability and handle the complexity of data in the classification. Further, the AO method helps to tune the parameters of DensNet (121 layers) and SVM, which achieves less training loss, computational time, minimized overfitting problems and more training/test accuracy. Performance evaluation metrics and statistical analysis validate the proposed model results are better than the benchmark schemes. Our proposed method has achieved a minimal value of the Mean Average Percentage Error (MAPE) rate i.e., 8% by DenseNet-AO and 6% by SVM-AO and the maximum accurateness rate of 92% and 95%, respectively.

Brain tumor magnetic resonance images classification based machine learning paradigms

Cancer of the nervous system is one of the most common types of cancer in the world and mostly due to presence of a tumour in the brain. The symptoms and severity of the brain tumour depend on its location. The tumour within the brain may develop from nerves, dura (meningioma), pituitary gland (pituitary adenoma), or from the brain tissue itself (glioma). In this study we proposed a feature engineering approach for classification magnetic resonance imaging (MRI) of 3 kinds of most common brain tumour, i.e. glioma, meningioma, pituitary, and no-tumour. Here 5 machine learning classifiers were used, i.e. support vector machine, K-nearest neighbour (KNN), Naive Bayes, Decision Tree, and Ensemble classifier with their paradigms. The handcrafted features such as histogram of oriented gradients, local binary pattern features, and grey level co-occurrence matrix are extracted from the MRI, and the feature fusion technique is adopted to enhance the dimension of feature vector. The Fine KNN outperforms among the classifiers for recognition of 4 kinds of MRI: glioma, meningioma, pituitary, and no tumour, and achieved 91.1% accuracy and 0.95 area under the curve (AUC). The proposed method, i.e. Fine KNN, achieved 91.1% accuracy and 0.96 AUC. Furthermore, this model has the possibility to integrate in low-end devices unlike deep learning, which required a complex system.

Pushing the Boundaries of Molecular Property Prediction for Drug Discovery with Multitask Learning BERT Enhanced by SMILES Enumeration.

Accurate prediction of pharmacological properties of small molecules is becoming increasingly important in drug discovery. Traditional feature-engineering approaches heavily rely on handcrafted descriptors and/or fingerprints, which need extensive human expert knowledge. With the rapid progress of artificial intelligence technology, data-driven deep learning methods have shown unparalleled advantages over feature-engineering-based methods. However, existing deep learning methods usually suffer from the scarcity of labeled data and the inability to share information between different tasks when applied to predicting molecular properties, thus resulting in poor generalization capability. Here, we proposed a novel multitask learning BERT (Bidirectional Encoder Representations from Transformer) framework, named MTL-BERT, which leverages large-scale pre-training, multitask learning, and SMILES (simplified molecular input line entry specification) enumeration to alleviate the data scarcity problem. MTL-BERT first exploits a large amount of unlabeled data through self-supervised pretraining to mine the rich contextual information in SMILES strings and then fine-tunes the pretrained model for multiple downstream tasks simultaneously by leveraging their shared information. Meanwhile, SMILES enumeration is used as a data enhancement strategy during the pretraining, fine-tuning, and test phases to substantially increase data diversity and help to learn the key relevant patterns from complex SMILES strings. The experimental results showed that the pretrained MTL-BERT model with few additional fine-tuning can achieve much better performance than the state-of-the-art methods on most of the 60 practical molecular datasets. Additionally, the MTL-BERT model leverages attention mechanisms to focus on SMILES character features essential to target properties for model interpretability.

Efficient Kinect Sensor-based Kurdish Sign Language Recognition Using Echo System Network

Sign language assists in building communication and bridging gaps in understanding. Automatic sign language recognition (ASLR) is a field that has recently been studied for various sign languages. However, Kurdish sign language (KuSL) is relatively new and therefore researches and designed datasets on it are limited. This paper has proposed a model to translate KuSL into text and has designed a dataset using Kinect V2 sensor. The computation complexity of feature extraction and classification steps, which are serious problems for ASLR, has been investigated in this paper. The paper proposed a feature engineering approach on the skeleton position alone to provide a better representation of the features and avoid the use of all of the image information. In addition, the paper proposed model makes use of recurrent neural networks (RNNs)-based models. Training RNNs is inherently difficult, and consequently, motivates to investigate alternatives. Besides the trainable long short-term memory (LSTM), this study has proposed the untrained low complexity echo system network (ESN) classifier. The accuracy of both LSTM and ESN indicates they can outperform those in state-of-the-art studies. In addition, ESN which has not been proposed thus far for ASLT exhibits comparable accuracy to the LSTM with a significantly lower training time.

Design of an Intelligent Approach on Capsule Networks to Detect Forged Images

Forgeries have recently become more prevalent in the society as a result of recent improvements in media generation technologies. In real-time, modern technology allows for the creation of a forged version of a single image obtained from a social network. Forgery detection algorithms have been created for a variety of areas; however they quickly become obsolete as new attack types exist. This paper presents a unique image forgery detection strategy based on deep learning algorithms. The proposed approach employs a convolutional neural network (CNN) to produce histogram representations from input RGB color images, which are then utilized to detect image forgeries. With the image separation method and copy-move detection applications in mind, the proposed CNN is combined with an intelligent approach and histogram mapping. It is used to detect fake or true images at the initial stage of our proposed work. Besides, it is specially designed for performing feature extraction in image layer separation with the help of CNN model. To capture both geographical and histogram information and the likelihood of presence at the same time, we use vectors in our dynamic capsule networks to detect the forgery kernels from reference images. The proposed research work integrates the intelligence with a feature engineering approach in an efficient manner. They are well-known and efficient in the identification of forged images. The performance metrics such as accuracy, recall, precision, and half total error rate (HTER) are computed and tabulated with the graph plot.

Data-Driven Method for the Prediction of Estimated Time of Arrival

Predicting the estimated time of arrival (ETA) plays an essential role in decision support (conflict detection, arrival sequencing, or trajectory optimization) for air traffic controllers. In this paper, a new multiple stages strategy for ETA prediction is proposed based on radar trajectories, including arrival pattern identification, arrival pattern classification, and flight time estimation. First, an intention-oriented trajectory clustering method is developed based on a new trajectory representation technique. Such a proposed trajectory clustering method can group trajectories into different arrival patterns in an efficient way. Second, an arrival pattern classification model is constructed based on random forest and XGBoost algorithms. Then, a flight time regression model is trained for each arrival pattern by using the XGBoost algorithm. Information on current states, historical states, and traffic situations is considered to build the feature set during these processes. Finally, the arrival operation toward Guangzhou International Airport is chosen as a case study. The results illustrate that the proposed method and feature engineering approach could improve the performance of ETA prediction. The proposed multiple stages strategy is superior to the single-model-based ETA prediction.

Feature investigation on the ROP machine learning model using realtime drilling data

To meet the demand for reducing drilling costs in petroleum engineering, improving drilling efficiency is one of the main objectives in field operations. Highly accurate prediction of ROP is an essential basis for improving drilling efficiency and reducing development cycle time. However, realtime prediction of the Rate of Penetration (ROP) is not straightforward, affected by a number of operational and mechanical parameters. The interactions between these parameters also complicated the analysis and modeling ROP. In the presented study, we apply the Feature Engineering approach to analyze the features affecting ROP according to their relevance and relative importance. In addition, the input features are reduced from 14, manually selected based on physical relevance, to optimized 8. Then the model is retrained again for comparing the accuracy of the two prediction models. As a result, it is concluded that by reducing the input of low impact features, the model is substantially simplified, while there are only insignificant accuracy changes.

Convolutional feature extraction for process monitoring using ultrasonic sensors

Ultrasonic sensors are a low-cost and in-line technique and can be combined with machine learning for industrial process monitoring. However, training accurate machine learning models for process monitoring using sensor data is dependant on the feature selection methodology. This paper compares a convolutional feature extraction method to a traditional, coarse feature engineering approach. The convolutional method uses filter weights pre-trained on an auxiliary task to classify ultrasonic waveform dataset membership using previously obtained sensor data. The filter weights are used to extract features from the ultrasonic waveform. Principal component analysis is then applied to produce five principal components to be input into long short-term memory neural networks. The two approaches are compared on fermentation, mixing and cleaning datasets monitored using ultrasonic sensors. Overall, the convolutional feature method produced more informative waveform features than the coarse feature engineering approach, achieving higher model accuracy for datasets requiring substantial waveform information and for 65% of tasks overall. Multi-task learning also improved feature trajectory learning but led to reduced model accuracy for data points far from the classification decision boundaries. This can be overcome by further optimisation of neural network hyperparameters, though at increased model development time. Once trained, the convolutional feature extraction approach is a fast and convenient way of producing high quality features from ultrasonic waveforms using convolutional neural networks with little training data.