Hierarchical Boosting Dual-Stage Feature Reduction Ensemble Model for Parkinson’s Disease Speech Data

As a neurodegenerative disease, Parkinson’s disease (PD) is hard to identify at the early stage, while using speech data to build a machine learning diagnosis model has proved effective in its early diagnosis. However, speech data show high degrees of redundancy, repetition, and unnecessary noise, which influence the accuracy of diagnosis results. Although feature reduction (FR) could alleviate this issue, the traditional FR is one-sided (traditional feature extraction could construct high-quality features without feature preference, while traditional feature selection could achieve feature preference but could not construct high-quality features). To address this issue, the Hierarchical Boosting Dual-Stage Feature Reduction Ensemble Model (HBD-SFREM) is proposed in this paper. The major contributions of HBD-SFREM are as follows: (1) The instance space of the deep hierarchy is built by an iterative deep extraction mechanism. (2) The manifold features extraction method embeds the nearest neighbor feature preference method to form the dual-stage feature reduction pair. (3) The dual-stage feature reduction pair is iteratively performed by the AdaBoost mechanism to obtain instances features with higher quality, thus achieving a substantial improvement in model recognition accuracy. (4) The deep hierarchy instance space is integrated into the original instance space to improve the generalization of the algorithm. Three PD speech datasets and a self-collected dataset are used to test HBD-SFREM in this paper. Compared with other FR algorithms and deep learning algorithms, the accuracy of HBD-SFREM in PD speech recognition is improved significantly and would not be affected by a small sample dataset. Thus, HBD-SFREM could give a reference for other related studies.

Stray light characterization with ultrafast time-of-flight imaging

Understanding stray light (SL) is a crucial aspect in the development of high-end optical instruments, for instance space telescopes. As it drives image quality, SL must be controlled by design and characterized experimentally. However, conventional SL characterization methods are limited as they do not provide information on its origins. The problem is complex due to the diversity of light interaction processes with surfaces, creating various SL contributors. Therefore, when SL level is higher than expected, it can be difficult to determine how to improve the system. We demonstrate a new approach, ultrafast time-of-flight SL characterization, where a pulsed laser source and a streak camera are used to record individually SL contributors which travel with a specific optical path length. Furthermore, the optical path length offers a means of identification to determine its origin. We demonstrate this method in an imaging system, measuring and identifying individual ghosts and scattering components. We then show how it can be used to reverse-engineer the instrument SL origins.

Towards Understanding Clustering Problems and Algorithms: An Instance Space Analysis

Various criteria and algorithms can be used for clustering, leading to very distinct outcomes and potential biases towards datasets with certain structures. More generally, the selection of the most effective algorithm to be applied for a given dataset, based on its characteristics, is a problem that has been largely studied in the field of meta-learning. Recent advances in the form of a new methodology known as Instance Space Analysis provide an opportunity to extend such meta-analyses to gain greater visual insights of the relationship between datasets’ characteristics and the performance of different algorithms. The aim of this study is to perform an Instance Space Analysis for the first time for clustering problems and algorithms. As a result, we are able to analyze the impact of the choice of the test instances employed, and the strengths and weaknesses of some popular clustering algorithms, for datasets with different structures.

Stray Light Characterization With Ultrafast Time-of-flight Imaging

Understanding stray light (SL) is a crucial aspect in the development of high-end optical instruments, for instance space telescopes. As it drives image quality, SL must be controlled by design and characterized experimentally. However, conventional SL characterization methods are limited as they do not provide information on its origins. The problem is complex due to the diversity of light interaction processes with surfaces, creating various SL contributors. Therefore, when SL level is higher than expected, it can be difficult to determine how to improve the system. We demonstrate a new approach, ultrafast time-of-flight SL characterization, where a pulsed laser source and a streak camera are used to record individually SL contributors which travel with a specific optical path length. Furthermore, the optical path length offers a means of identification to determine its origin. We demonstrate this method in an imaging system, measuring and identifying individual ghosts and scattering components. We then show how it can be used to reverse-engineer the instrument SL origins.

An Instance Space Analysis of Regression Problems

The quest for greater insights into algorithm strengths and weaknesses, as revealed when studying algorithm performance on large collections of test problems, is supported by interactive visual analytics tools. A recent advance is Instance Space Analysis, which presents a visualization of the space occupied by the test datasets, and the performance of algorithms across the instance space. The strengths and weaknesses of algorithms can be visually assessed, and the adequacy of the test datasets can be scrutinized through visual analytics. This article presents the first Instance Space Analysis of regression problems in Machine Learning, considering the performance of 14 popular algorithms on 4,855 test datasets from a variety of sources. The two-dimensional instance space is defined by measurable characteristics of regression problems, selected from over 26 candidate features. It enables the similarities and differences between test instances to be visualized, along with the predictive performance of regression algorithms across the entire instance space. The purpose of creating this framework for visual analysis of an instance space is twofold: one may assess the capability and suitability of various regression techniques; meanwhile the bias, diversity, and level of difficulty of the regression problems popularly used by the community can be visually revealed. This article shows the applicability of the created regression instance space to provide insights into the strengths and weaknesses of regression algorithms, and the opportunities to diversify the benchmark test instances to support greater insights.

Grey-based multiple instance learning with multiple bag-representative

Multiple instance learning is a modification in supervised learning that handles the classification of collection instances, which called bags. Each bag contains a number of instances whose features are extracted. In multiple instance learning, the standard assumption is that a positive bag contains at least one positive instance, whereas a negative bag is only comprised of negative instances. The complexity of multiple instance learning relies heavily on the number of instances in the training datasets. Since we are usually confronted with a large instance space, it is important to design efficient instance selection techniques to speed up the training process, without compromising the performance. Firstly, a multiple instance learning model of support vector machine based on grey relational analysis is proposed in this paper. The data size can be reduced, and the importance of instances in the bag can be preliminarily judged. Secondly, this paper introduces an algorithm with the bag-representative selector that trains the support vector machine based on bag-level information. Finally, this paper shows how to generalize the algorithm for binary multiple instance learning to multiple class tasks. The experimental study evaluates and compares the performance of our method against 8 state-of-the-art multiple instance methods over 10 datasets, and then demonstrates that the proposed approach is competitive with the state-of-art multiple instance learning methods.