Multi-feature Datasets Research Articles

A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost

AbstractThe success of machine learning in real-world use cases has increased its demand in mission-critical applications such as autonomous vehicles, healthcare and medical diagnosis, aviation and flight safety, natural disaster prediction, early warning systems, etc. Adaptive Boosting (AdaBoost) is an ensemble learning method that has gained much traction in such applications. Inherently being a non-interpretable model, the interpretability of the AdaBoost algorithm has been a research topic for many years. Furthermore, most of the research being conducted till now is aimed at explaining AdaBoost using perturbation-based techniques. The paper presents a technique to interpret the AdaBoost algorithm from a data perspective using deletion diagnostics and Cook’s distance. The technique achieves interpretability by detecting the most influential data instances and their impact on the feature importance of the model. This interpretability enables domain experts to accurately modify the significance of specific features in a trained AdaBoost model depending on the data instances. Unlike explaining AdaBoost using perturbation-based techniques, interpreting from a data perspective will enable it to debug data-related biases, errors and to impart the knowledge of the domain experts into the model through domain aware fine-tuning. Experimental studies were conducted with diverse real-world multi-feature datasets to demonstrate interpretability and knowledge integration through domain-aware fine-tuning.

TVGCN: Time-varying graph convolutional networks for multivariate and multifeature spatiotemporal series prediction.

Spatiotemporal (ST) graph modeling has garnered increasing attention recently. Most existing methods rely on a predefined graph structure or construct a single learnable graph throughout training. However, it is challenging to use a predefined graph structure to capture dynamic ST changes effectively due to evolving node relationships over time. Furthermore, these methods typically utilize only the original data, neglecting external temporal factors. Therefore, we put forward a novel time-varying graph convolutional network model that integrates external factors for multifeature ST series prediction. Firstly, we construct a time-varying adjacency matrix using attention to capture dynamic spatial relationships among nodes. The graph structure adapts over time during training, validation, and testing phases. Then, we model temporal dependence by dilated causal convolution, leveraging gated activation unit and residual connection. Notably, the prediction accuracy is enhanced through the incorporation of embedding absolute time and the fusion of multifeature. This model has been applied to three real-world multifeature datasets, achieving state-of-the-art performance in all cases. Experiments show that the method has high accuracy and robustness when applied to multifeature and multivariate ST series problems.

Garlic Crops’ Mapping and Change Analysis in the Erhai Lake Basin Based on Google Earth Engine

Garlic (Allium sativum) is an important economic crop in China. In terms of using remote sensing technology to identify it, there is still room for improvement, and the high-precision classification of garlic has become an important issue. However, to the best of our knowledge, few studies have focused on garlic area mapping. Here, we propose a method for identifying garlic crops using samples and a multi-feature dataset under limited conditions. The results indicate the following: (1) In the land-use classification of the Erhai Lake Basin, the importance ranking of the characteristic bands, from high to low, is as follows: spectral features, vegetation features, texture features, and terrain features. (2) The random forest method based on feature selection demonstrates high accuracy in land-use classification within the Erhai Lake Basin in Yunnan Province. The overall classification accuracy reached 95.79%, with a Kappa coefficient of 0.95. (3) From 1999 to 2023, the expansion of garlic cultivation in the Erhai Lake Basin showed a trend of initially strengthening from north to south, which was followed by weakening. The vertical development of garlic cultivation reached saturation, showing a slow trend toward horizontal expansion between 2005 and 2018. The planting distributions in various townships in the Erhai Lake Basin gradually shifted from relatively uniform distributions to upstream development. This study utilized the Google Earth Engine (GEE) cloud computing platform and machine learning algorithms to compensate for the lack of statistical data on garlic cultivation in the Erhai Lake Basin. Moreover, it accurately, rapidly, and efficiently extracted planting information, demonstrating significant potential for practical applications.

Distinguishing Ulva prolifera and Sargassum horneri by using multi-feature-based ResUnet algorithm

In recent years, two types of macroalgae, namely, Ulva prolifera and Sargassum horneri, have appeared occasionally together in the Yellow Sea and the East China Sea. Remote sensing enables timely and cost-effective observation of macroalgae across large areas. In the available studies, the recognition and classification of the two macroalgae are primarily based on spectral difference analysis. In this study, the spectral features, indices and textural feature parameters of the macroalgae targets were extracted and a preliminary multi-feature dataset was constructed based on Sentinel-2 images. Feature selection was performed using SHAP-based importance analysis and Bhattacharyya distance. From this, a multi-feature dataset was created and used as an input to a deep semantic segmentation network of improved ResUnet. The experiments of intelligent recognition and classification of U. prolifera and S. horneri were carried out using the proposed multi-feature-based ResUnet algorithm, with specific F1-scores of 96.7% and 96.8%, respectively. The proposed multi-feature-based ResUnet algorithm can obtain efficient and high-accuracy results for the recognition and classification of marine floating macroalgae. It achieves accurate remote sensing monitoring of the two types of marine floating macroalgae and has significant theoretical research significance and practical application value.

A data-driven matching algorithm for ride pooling problem

This paper proposes a data-driven matching algorithm for the problem of ride pooling, which is a transportation mode enabling people to share a vehicle for a trip. The problem is considered as a variant of matching problem, since it aims to find a matching between drivers and riders. Proposed algorithm is a machine learning algorithm based on rank aggregation idea, where every feature in a multi-feature dataset provides a ranking of candidate drivers and weight for each feature is learned from past data through an optimization model. Once weight learning and candidate ranking problems are considered simultaneously, resulting optimization model becomes a nonlinear bilevel optimization model, which is reformulated as a single level mixed-integer nonlinear optimization model. To demonstrate the performance of the proposed algorithm, a real-life dataset from a mobile application of a ride pooling start-up company is used and company’s current approach is considered as benchmark. Results reveal that proposed algorithm correctly predicts the first choice of riders 17% to 28% better compared to the benchmark in different scenarios. Similarly, proposed algorithm offers recommendation lists in which the preferred driver is ranked 0.38 to 1.12 person closer (to the rider’s actual choice) compared to the benchmark.

Automated Corn Seed Fusarium Disease Classification System Using Hybrid Feature Space and Conventional Machine Learning Techniques

The purpose of this learning is to detect the Corn Seed Fusarium Disease using Hybrid Feature Space and Conventional machine learning (ML) approaches. A novel machine learning approach is employed for the classification of a total of six types of corn seed are collected which contain Infected Fusarium (moniliforme, graminearum, gibberella, verticillioides, kernel) as well as healthy corn seed, based on a multi-feature dataset, which is the grouping of geometric, texture and histogram features extracted from digital images. For each corn seed image, a total of twenty-five multi-features have been developed on every area of interest (AOI), sizes (50 × 50), (100 × 100), (150 × 150), and (200 × 200). A total of seven optimized features were selected by using a machine learning-based algorithm named “Correlation-based Feature Selection”. For experimentation, “Random forest”, “BayesNet” and “LogitBoost” have been employed using an optimized multi-feature user-supplied dataset divided with 70% training and 30 % testing. A comparative analysis of three ML classifiers RF, BN, and LB have been used and a considerably very high classification ratio of 96.67 %, 97.22 %, and 97.78 % have been achieved respectively when the AOI size (200×200) have been deployed to the classifiers.

Evaluation of image partitioning strategies for preserving spatial information of cross-sectional micrographs in automated wood recognition of Fagaceae

Although wood cross sections contain spatiotemporal information regarding tree growth, computer vision-based wood identification studies have traditionally favored disordered image representations that do not take such information into account. This paper describes image partitioning strategies that preserve the spatial information of wood cross-sectional images. Three partitioning strategies are designed, namely grid partitioning based on spatial pyramid matching and its variants, radial and tangential partitioning, and their recognition performance is evaluated for the Fagaceae micrograph dataset. The grid and radial partitioning strategies achieve better recognition performance than the bag-of-features model that constitutes their underlying framework. Radial partitioning, which is a strategy for preserving spatial information from pith to bark, further improves the performance, especially for radial-porous species. The Pearson correlation and autocorrelation coefficients produced from radially partitioned sub-images have the potential to be used as auxiliaries in the construction of multi-feature datasets. The contribution of image partitioning strategies is found to be limited to species recognition and is unremarkable at the genus level.

Discrimination of sunflower seeds using multispectral and texture dataset in combination with region selection and supervised classification methods.

The purpose of this study is to discriminate sunflower seeds with the help of a dataset having spectral and textural features. The production of crop based on seed purity and quality other hand sunflower seed used for oil content worldwide. In this regard, the foundation of a dataset categorizes sunflower seed varieties (Syngenta CG, HS360, S278, HS30, Armani, and High Sun 33), which were acquired from the agricultural farms of The Islamia University of Bahawalpur, Pakistan, into six classes. For preprocessing, a new region-oriented seed-based segmentation was deployed for the automatic selection of regions and extraction of 53 multi-features from each region, while 11 optimized fused multi-features were selected using the chi-square feature selection technique. For discrimination, four supervised classifiers, namely, deep learning J4, support vector machine, random committee, and Bayes net, were employed to optimize the multi-feature dataset. We observe very promising accuracies of 98.2%, 97.5%, 96.6%, and 94.8%, respectively, when the size of a region is (180 × 180).

RETRACTED: Identifying Asphalt Pavement Distress Using UAV LiDAR Point Cloud Data and Random Forest Classification

Asphalt pavement ages and incurs various distresses due to natural and human factors. Thus, it is crucial to rapidly and accurately extract different types of pavement distress to effectively monitor road health status. In this study, we explored the feasibility of pavement distress identification using low-altitude unmanned aerial vehicle light detection and ranging (UAV LiDAR) and random forest classification (RFC) for a section of an asphalt road that is located in the suburb of Shihezi City in Xinjiang Province of China. After a spectral and spatial feature analysis of pavement distress, a total of 48 multidimensional and multiscale features were extracted based on the strength of the point cloud elevations and reflection intensities. Subsequently, we extracted the pavement distresses from the multifeature dataset by utilizing the RFC method. The overall accuracy of the distress identification was 92.3%, and the kappa coefficient was 0.902. When compared with the maximum likelihood classification (MLC) and support vector machine (SVM), the RFC had a higher accuracy, which confirms its robustness and applicability to multisample and high-dimensional data classification. Furthermore, the method achieved an overall accuracy of 95.86% with a validation dataset. This result indicates the validity and stability of our method, which highway maintenance agencies can use to evaluate road health conditions and implement maintenance.

Machine vision approach for classification of citrus leaves using fused features

ABSTRACT The objective of this study was to observe the potential of machine vision (MV) approach for the classification of eight citrus varieties. The leaf images of eight citrus varieties that were grapefruit, Moussami, Malta, Lemon, Kinow, Local lemon, Fuetrells, and Malta Shakri. These were acquired by a digital camera in an open environment without any complex laboratory setup. The acquired digital images dataset was transformed into the multi-feature dataset that was the combination of binary, histogram, texture, spectral, rotational, scalability and translational (RST) invariant features. For each citrus leaf image, total 57 multi-features were acquired on every non-overlapping region of interest (ROI), i.e. (32x32), (64x64), (128x128), and (256x256). Furthermore, the optimized 15 features using the supervised correlation-based feature selection (CFS) technique were acquired. The optimized multi-features dataset to different MV classifiers namely Multilayer Perceptron (MLP), Random Forest (RF), J48 and Naïve Bayes using10-fold cross-validation method were plugged-in. The results produced by MLP presented an average overall accuracy of 98.14% on ROIs (256x256) outperforming the other classifiers. The classification accuracy values by MLP on the eight citrus leaf varieties, namely; Grapefruit, Moussami, Malta, Lemon, Kinow, Local lemon, Fuetrells, and Malta Shakri were observed 98%, 98.75%, 99.25%, 97.5%, 97%, 95.87%, 95.5%, and 99.37% respectively.

Multi-feature based benchmark for cervical dysplasia classification evaluation

Cervical cancer is one of the most common types of cancer in women worldwide. Most deaths due to the disease occur in less developed areas of the world. In this work, we introduce a new image dataset along with expert annotated diagnoses for evaluating image-based cervical disease classification algorithms. A large number of Cervigram® images are selected from a database provided by the US National Cancer Institute. For each image, we extract three complementary pyramid features: Pyramid histogram in L*A*B* color space (PLAB), Pyramid Histogram of Oriented Gradients (PHOG), and Pyramid histogram of Local Binary Patterns (PLBP). Other than hand-crafted pyramid features, we investigate the performance of convolutional neural network (CNN) features for cervical disease classification. Our experimental results demonstrate the effectiveness of both our hand-crafted and our deep features. We intend to release this multi-feature dataset and our extensive evaluations using seven classic classifiers can serve as the baseline.

Feature-based multiblock finite element mesh generation

Hexahedral finite element mesh development for anatomic structures and biomedical implants can be cumbersome. Moreover, using traditional meshing techniques, detailed features may be inadequately captured. In this paper, we describe methodologies to handle multi-feature datasets (i.e., feature edges and surfaces). Coupling multi-feature information with multiblock meshing techniques has enabled anatomic structures, as well as orthopaedic implants, to be readily meshed. Moreover, the projection process, node and element set creation are automated, thus reducing the user interaction during model development. To improve the mesh quality, Laplacian- and optimization-based mesh improvement algorithms have been adapted to the multi-feature datasets.

Avoiding Pitfalls in the Statistical Analysis of Heterogeneous Tumors

Information about tumors is usually obtained from a single assessment of a tumor sample, performed at some point in the course of the development and progression of the tumor, with patient characteristics being surrogates for natural history context. Differences between cells within individual tumors (intratumor heterogeneity) and between tumors of different patients (intertumor heterogeneity) may mean that a small sample is not representative of the tumor as a whole, particularly for solid tumors which are the focus of this paper. This issue is of increasing importance as high-throughput technologies generate large multi-feature data sets in the areas of genomics, proteomics, and image analysis. Three potential pitfalls in statistical analysis are discussed (sampling, cut-points, and validation) and suggestions are made about how to avoid these pitfalls.

Multivariate analysis of complex gene expression and clinical phenotypes with genetic marker data.

This paper summarizes contributions to group 12 of the 15th Genetic Analysis Workshop. The papers in this group focused on multivariate methods and applications for the analysis of molecular data including genotypic data as well as gene expression microarray measurements and clinical phenotypes. A range of multivariate techniques have been employed to extract signals from the multi-feature data sets that were provided by the workshop organizers. The methods included data reduction techniques such as principal component analysis and cluster analysis; latent variable models including structural equations and item response modeling; joint multivariate modeling techniques as well as multivariate visualization tools. This summary paper categorizes and discusses individual contributions with regard to multiple classifications of multivariate methods. Given the wide variety in the data considered, the objectives of the analysis and the methods applied, direct comparison of the results of the various papers is difficult. However, the group was able to make many interesting comparisons and parallels between the various approaches. In summary, there was a consensus among authors in group 12 that the genetic research community should continue to draw experiences from other fields such as statistics, econometrics, chemometrics, computer science and linear systems theory.