Publications
A critical review of heart sound signal segmentation algorithms
Authors:
Milani, M.G. Manisha
Abas, Pg Emeroylariffion
De Silva, Liyanage C.
This paper discusses four heart sound segmentation (HSS) methods: Wavelet transform, Fractal decomposition, Hilbert Transform, and Shannon Energy Envelogram, in order to identify the different cardiac sounds. Many research studies related to heart signal analysis, have adopted these methods to give high heart sound segmentation results, especially, for the identification of first and second heart sounds and murmurs. Performance of the heart sound segmentation results have also been compared with one other to identify the most efficient method(s), and it has been found that Shannon energy envelogram provides the best accuracies among the segmentation methods. Understandings of the segmentation methods for heart sound may pave the way for more advanced studies in other heart-related researches, including heart sound classifications. © 2022 Elsevier Inc.
Authors:
Ramashini, Murugaiya
Abas, Pg Emeroylariffion
De Silva, Liyanage C.
A novel approach of audio based feature optimisation for bird classification
Authors:
Ramashini, Murugaiya
Abas, Pg Emeroylariffion
Mohanchandra,Kusuma
De Silva, Liyanage C.
Robust cepstral feature for bird sound classification
Birds are excellent environmental indicators and may indicate sustainability of the ecosystem; birds may be used to provide provisioning, regulating, and supporting services. Therefore, birdlife conservation-related researches always receive centre stage. Due to the airborne nature of birds and the dense nature of the tropical forest, bird identifications through audio may be a better solution than visual identification. The goal of this study is to find the most appropriate cepstral features that can be used to classify bird sounds more accurately. Fifteen (15) endemic Bornean bird sounds have been selected and segmented using an automated energy-based algorithm. Three (3) types of cepstral features are extracted; linear prediction cepstrum coefficients (LPCC), mel frequency cepstral coefficients (MFCC), gammatone frequency cepstral coefficients (GTCC), and used separately for classification purposes using support vector machine (SVM). Through comparison between their prediction results, it has been demonstrated that model utilising GTCC features, with 93.3% accuracy, outperforms models utilising MFCC and LPCC features. This demonstrates the robustness of GTCC for bird sounds classification. The result is significant for the advancement of bird sound classification research, which has been shown to have many applications such as in eco-tourism and wildlife management. © 2022 Institute of Advanced Engineering and Science. All rights reserved.
Probability Enhanced Entropy (PEE) Novel Feature for Improved Bird Sound Classification
Authors:
Ramashini, Murugaiya
Abas, Pg Emeroylariffion
De Silva, Liyanage C.
Identification of bird species from their sounds has become an important area in biodiversity-related research due to the relative ease of capturing bird sounds in the commonly challenging habitat. Audio features have a massive impact on the classification task since they are the fundamental elements used to differentiate classes. As such, the extraction of informative properties of the data is a crucial stage of any classification-based application. Therefore, it is vital to identify the most significant feature to represent the actual bird sounds. In this paper, we propose a novel feature that can advance classification accuracy with modified features, which are most suitable for classifying birds from its audio sounds. Modified Gammatone frequency cepstral coefficient (GTCC) features have been extracted with their frequency banks adjusted to suit bird sounds. The features are then used to train and test a support vector machine (SVM) classifier. It has been shown that the modified GTCC features are able to give 86% accuracy with twenty Bornean birds. Furthermore, in this paper, we are proposing a novel probability enhanced entropy (PEE) feature, which, when combined with the modified GTCC features, is able to improve accuracy further to 89.5%. These results are significant as the relatively low-resource intensive SVM with the proposed modified GTCC, and the proposed novel PEE feature can be implemented in a real-time system to assist researchers, scientists, conservationists, and even eco-tourists in identifying bird species in the dense forest. © 2022, Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature.
Reconstruction of damaged herbarium leaves using deep learning techniques for improving classification accuracy
Authors:
Burham Rashid Hussein
Owais Ahmed Malik
Wee-Hong Ong
Johan Willem Fredrik Slik
Leaf is one of the most commonly used organs for species identification. The traditional identification process involves a manual analysis of individual dried or fresh leaf’s features by the botanists. Recent advancements in computer vision techniques have assisted in automating the plants families/species identification process based on the digital images of leaves. However, most of the existing studies have focused on using datasets for fresh and intact leaves. A huge amount of data for preserved plants in the form of digitized herbaria specimens have not been effectively utilized for the task of automated identification because of the presence of damaged leaves in specimens. In this study, deep learning techniques have been proposed as a tool for reconstructing the damaged herbarium leaves in order to maximize the usefulness of the digitized specimens for automated plant identification task by increasing the number of individual samples of leaves. The reconstruction results of two different families of convolutionneural networks (CNNs) have been compared for data from ten different plant families namely Anacardiaceae, Annonaceae, Dipterocarpaceae, Ebenaceae, Euphorbiaceae, Malvaceae, Phyllanthaceae, Polygalaceae, Rubiaceae and Sapotaceae. The performance of automated identification task was improved by more than 20% using the reconstructed leaves images as compared to using the original data (i.e. images of specimens with damaged leaves). This work evidently suggests that deep learning techniques can be utilized for reconstruction of damaged leaves even on a challenging herbarium leaves dataset.
Authors:
Jiajia Liu
Yunpeng Zhao
Xingfeng Si
Gang Feng
Ferry Slik
Jian zhang
University campuses as valuable resources for urban biodiversity research and conversation
University campuses (including college campuses) are home to many ecologsits and conservationists, resulting in a large number of studies on campus plant and animal taxa. However, a systematic review on the biodiversity of university campuses is still lacking. We conducted a comprehensive review covering the history, diversity and distribution patterns of living biodiversity on university campuses globally. We found over 300 university campuses that conducted biodiversity surveys, mostly on plants and birds, with China and India as research hotspots. These university campuses harboured high biodiversity, with an average of 199 plant species and 66 bird species on each campus, including many endemic and endangered species. Hence, university campuses provide a unique opportunity for urban biodiversity research, conservation and education, as well as connecting the public with nature through citizen science.
Authors:
Burham Rashid Hussein
Owais Ahmed Malik
Wee-Hong Ong
Johan Willem Fredrik Slik
Automated extraction of phenotypic leaf traits of individual intact herbarium leaves from herbarium specimen images using deep learning based semantic segmentation
With the increase in the digitization efforts of herbarium collections worldwide, dataset repositories such as iDigBio and GBIF now have hundreds of thousands of herbarium sheet images ready for exploration. Although this serves as a new source of plant leaves data, herbarium datasets have an inherent challenge to deal with the sheets containing other non-plant objects such as color charts, barcodes, and labels. Even for the plant part itself, a combination of different overlapping, damaged, and intact individual leaves exist together with other plant organs such as stems and fruits, which increases the complexity of leaf trait extraction and analysis. Focusing on segmentation and trait extraction on individual intact herbarium leaves, this study proposes a pipeline consisting of deep learning semantic segmentation model (DeepLabv3+), connected component analysis, and a single-leaf classifier trained on binary images to automate the extraction of an intact individual leaf with phenotypic traits. The proposed method achieved a higher F1-score for both the in-house dataset (96%) and on a publicly available herbarium dataset (93%) compared to object detection-based approaches including Faster R-CNN and YOLOv5. Furthermore, using the proposed approach, the phenotypic measurements extracted from the segmented individual leaves were closer to the ground truth measurements, which suggests the importance of the segmentation process in handling background noise. Compared to the object detection-based approaches, the proposed method showed a promising direction toward an autonomous tool for the extraction of individual leaves together with their trait data directly from herbarium specimen images.
Are street trees friendly to biodiversity?
Authors:
Jiang Liu
Ferry Slik
Urban areas are home to more than half the world’s population, but also habitats for a wide range of plant and animal species. While street trees in urban areas have been recognized as important for human well-being, however, how they can contribute to wildlife conservation is less explored. Here we compiled a database of street tree inventories in China, that included species diversity, abundance and origin information of street trees from 59 cities to explore how different cities rank with regards to the use of native and diversity of street trees, which are both considered beneficial to urban biodiversity. We found the most abundant species contributed an average of 35.8% of all street trees in the studied cities, and non-native species contributed an average of 40.6% of the street trees. Most cities are dominated by only a few species of trees, and a large proportion of these trees are non-native tree species, indicating that streetscapes are likely not friendly to biodiversity. Our proposed ranking schedule provides an easy tool for classifying cities according to their street tree wildlife friendliness, while also providing clear management directions on how to improve city tree composition for biodiversity conservation. To build a sustainable society in which nature and humans can coexist, we recommend that city planners should consider biodiversity conservation as a core value of urban planning. Specifically, we encourage the planting of more native trees and use of a more diverse set of species capable of attracting wildlife, thus promoting biodiversity in cities. Furthermore, awareness of biodiversity friendly tree planting systems needs special attention in developing regions and densely populated areas. We emphasize that more regional research needs to go into identifying local species that can be used as street trees while simultaneously functioning as wildlife attractants.
