1
|
Sa'adi Z, Al-Suwaiyan MS, Yaseen ZM, Tan ML, Goliatt L, Heddam S, Halder B, Ahmadianfar I, Homod RZ, Shafik SS. Observed and future shifts in climate zone of Borneo based on CMIP6 models. JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024; 360:121087. [PMID: 38735071 DOI: 10.1016/j.jenvman.2024.121087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/10/2024] [Revised: 03/21/2024] [Accepted: 05/03/2024] [Indexed: 05/14/2024]
Abstract
Climate change has significantly altered the characteristics of climate zones, posing considerable challenges to ecosystems and biodiversity, particularly in Borneo, known for its high species density per unit area. This study aimed to classify the region into homogeneous climate groups based on long-term average behavior. The most effective parameters from the high-resolution daily gridded Princeton climate datasets spanning 65 years (1950-2014) were utilized, including rainfall, relative humidity (RH), temperatures (Tavg, Tmin, Tmax, and diurnal temperature range (DTR)), along with elevation data at 0.25° resolution. The FCM clustering method outperformed K-Mean and two Ward's hierarchical methods (WardD and WardD2) in classifying Borneo's climate zones based on multi-criteria assessment, exhibiting the lowest average distance (2.172-2.180) and the highest compromise programming index (CPI)-based correlation ranking among cluster averages across all climate parameters. Borneo's climate zones were categorized into four: 'Wet and cold' (WC) and 'Wet' (W) representing wetter zones, and 'Wet and hot' (WH) and 'Dry and hot' (DH) representing hotter zones, each with clearly defined boundaries. For future projection, EC-Earth3-Veg ranked first for all climate parameters across 961 grid points, emerging as the top-performing model. The linear scaling (LS) bias-corrected EC-Earth3-Veg model, as shown in the Taylor diagram, closely replicated the observed datasets, facilitating future climate zone reclassification. Improved performance across parameters was evident based on MAE (35.8-94.6%), MSE (57.0-99.5%), NRMSE (42.7-92.1%), PBIAS (100-108%), MD (23.0-85.3%), KGE (21.1-78.1%), and VE (5.1-9.1%), with closer replication of empirical probability distribution function (PDF) curves during the validation period. In the future, Borneo's climate zones will shift notably, with WC elongating southward along the mountainous spine, W forming an enclave over the north-central mountains, WH shifting northward and shrinking inland, and DH expanding northward along the western coast. Under SSP5-8.5, WC is expected to expand by 39% and 11% for the mid- and far-future periods, respectively, while W is set to shrink by 46%. WH is projected to expand by 2% and 8% for the mid- and far-future periods, respectively. Conversely, DH is expected to expand by 43% for the far-future period but shrink by 42% for the mid-future period. This study fills a gap by redefining Borneo's climate zones based on an increased number of effective parameters and projecting future shifts, utilizing advanced clustering methods (FCM) under CMIP6 scenarios. Importantly, it contributes by ranking GCMs using RIMs and CPI across multiple climate parameters, addressing a previous gap in GCM assessment. The study's findings can facilitate cross-border collaboration by providing a shared understanding of climate dynamics and informing joint environmental management and disaster response efforts.
Collapse
Affiliation(s)
- Zulfaqar Sa'adi
- Centre for Environmental Sustainability and Water Security (IPASA), School of Civil Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, 81310, UTM Sekudai, Johor, Malaysia; Department of Water & Environmental Engineering, School of Civil Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, 81310, Johor Bahru, Malaysia.
| | - Mohammad Saleh Al-Suwaiyan
- Civil and Environmental Engineering Department, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia; Interdisciplinary Research Center for Construction and Building Materials, King Fahd University of Petroleum and Minerals, Dhahran, 31261, Saudi Arabia.
| | - Zaher Mundher Yaseen
- Civil and Environmental Engineering Department, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia.
| | - Mou Leong Tan
- Geography Section, School of Humanities, Universiti Sains Malaysia, 11800, Penang, Malaysia.
| | - Leonardo Goliatt
- Computational Modeling Program, Federal University of Juiz de Fora, Juiz de Fora, MG, Brazil.
| | - Salim Heddam
- Faculty of Science, Agronomy Department, Hydraulics Division University, 20 Août 1955, Route El Hadaik, BP 26, Skikda, Algeria.
| | - Bijay Halder
- Department of Earth Sciences and Environment, Faculty of Science and Technology, Universiti Kebangsaan Malaysia, Bangi, 43600, Selangor, Malaysia.
| | - Iman Ahmadianfar
- Department of Civil Engineering, Behbahan Khatam Alanbia University of Technology, Behbahan, Iran.
| | - Raad Z Homod
- Department of Oil and Gas Engineering, Basrah University for Oil and Gas, Iraq.
| | - Shafik S Shafik
- Experimental Nuclear Radiation Research Group, Scientific Research Center, Al-Ayen University, Thi-Qar, 64001, Iraq.
| |
Collapse
|
2
|
Chan HL, Chang HW, Hsu WY, Huang PJ, Fang SC. Convolutional Neural Network for Individual Identification Using Phase Space Reconstruction of Electrocardiogram. SENSORS (BASEL, SWITZERLAND) 2023; 23:3164. [PMID: 36991875 PMCID: PMC10056305 DOI: 10.3390/s23063164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Revised: 03/08/2023] [Accepted: 03/14/2023] [Indexed: 06/19/2023]
Abstract
Electrocardiogram (ECG) biometric provides an authentication to identify an individual on the basis of specific cardiac potential measured from a living body. Convolutional neural networks (CNN) outperform traditional ECG biometrics because convolutions can produce discernible features from ECG through machine learning. Phase space reconstruction (PSR), using a time delay technique, is one of the transformations from ECG to a feature map, without the need of exact R-peak alignment. However, the effects of time delay and grid partition on identification performance have not been investigated. In this study, we developed a PSR-based CNN for ECG biometric authentication and examined the aforementioned effects. Based on a population of 115 subjects selected from the PTB Diagnostic ECG Database, a higher identification accuracy was achieved when the time delay was set from 20 to 28 ms, since it produced a well phase-space expansion of P, QRS, and T waves. A higher accuracy was also achieved when a high-density grid partition was used, since it produced a fine-detail phase-space trajectory. The use of a scaled-down network for PSR over a low-density grid with 32 × 32 partitions achieved a comparable accuracy with using a large-scale network for PSR over 256 × 256 partitions, but it had the benefit of reductions in network size and training time by 10 and 5 folds, respectively.
Collapse
Affiliation(s)
- Hsiao-Lung Chan
- Department of Electrical Engineering, Chang Gung University, Taoyuan 333, Taiwan
- Biomedical Engineering Research Center, Chang Gung University, Taoyuan 333, Taiwan
- Neuroscience Research Center, Chang Gung Memorial Hospital, Linkou, Taoyuan 333, Taiwan
| | - Hung-Wei Chang
- Department of Electrical Engineering, Chang Gung University, Taoyuan 333, Taiwan
| | - Wen-Yen Hsu
- Department of Electrical Engineering, Chang Gung University, Taoyuan 333, Taiwan
| | - Po-Jung Huang
- Department of Electrical Engineering, Chang Gung University, Taoyuan 333, Taiwan
| | - Shih-Chin Fang
- Department of Neurology, Cardinal Tien Hospital Yung Ho Branch, New Taipei City 234, Taiwan
| |
Collapse
|
3
|
Ran C, Li X, Yang F. Multi-Step Structure Image Inpainting Model with Attention Mechanism. SENSORS (BASEL, SWITZERLAND) 2023; 23:2316. [PMID: 36850914 PMCID: PMC9959622 DOI: 10.3390/s23042316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 02/13/2023] [Accepted: 02/17/2023] [Indexed: 06/18/2023]
Abstract
The proliferation of deep learning has propelled image inpainting to an important research field. Although the current image inpainting model has made remarkable achievements, the two-stage image inpainting method is easy to produce structural errors in the rough stage because of insufficient treatment of the rough inpainting stage. To address this problem, we propose a multi-step structured image inpainting model combining attention mechanisms. Different from the previous two-stage inpainting model, we divide the damaged area into four sub-areas, calculate the priority of each area according to the priority, specify the inpainting order, and complete the rough inpainting stage several times. The stability of the model is enhanced by the multi-step method. The structural attention mechanism strengthens the expression of structural features and improves the quality of structure and contour reconstruction. Experimental evaluation of benchmark data sets shows that our method effectively reduces structural errors and improves the effect of image inpainting.
Collapse
Affiliation(s)
- Cai Ran
- School of Cyber Security and Computer, Hebei University, Baoding 071002, China
- Machine Vision Engineering Research Center, Hebei University, Baoding 071002, China
| | - Xinfu Li
- School of Cyber Security and Computer, Hebei University, Baoding 071002, China
- Machine Vision Engineering Research Center, Hebei University, Baoding 071002, China
| | - Fang Yang
- School of Cyber Security and Computer, Hebei University, Baoding 071002, China
- Machine Vision Engineering Research Center, Hebei University, Baoding 071002, China
| |
Collapse
|
4
|
Lekkoksung S, Iampan A, Julatha P, Lekkoksung N. Representations of ordered semigroups and their interconnection. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022. [DOI: 10.3233/jifs-223356] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
It is known that any ordered semigroup embeds into the structure consisting of the set of all fuzzy sets together with an associative binary operation and a partial order with compatibility. In this study, we provide two classes of ordered semigroups in which any model in these classes is a representation of any ordered semigroup. Moreover, we give an interconnection of a class we constructed.
Collapse
Affiliation(s)
- Somsak Lekkoksung
- Division of Mathematics, Faculty of Engineering, Rajamangala University of Technology Isan, Khon Kaen Campus, Khon Kaen, Thailand
| | - Aiyared Iampan
- Fuzzy Algebras and Decision-Making Problems Research Unit Department of Mathematics, School of Science, University of Phayao, Phayao, Thailand
| | - Pongpun Julatha
- Department of Mathematics, Faculty of Science and Technology, Pibulsongkram Rajabhat University, Phitsanulok, Thailand
| | - Nareupanat Lekkoksung
- Division of Mathematics, Faculty of Engineering, Rajamangala University of Technology Isan, Khon Kaen Campus, Khon Kaen, Thailand
| |
Collapse
|
5
|
Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:8571970. [PMID: 36132548 PMCID: PMC9484938 DOI: 10.1155/2022/8571970] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/28/2022] [Revised: 08/08/2022] [Accepted: 08/24/2022] [Indexed: 11/23/2022]
Abstract
The level of patient's illness is determined by diagnosing the problem through different methods like physically examining patients, lab test data, and history of patient and by experience. To treat the patient, proper diagnosis is very much important. Arrhythmias are irregular variations in normal heart rhythm, and detecting them manually takes a long time and relies on clinical skill. Currently machine learning and deep learning models are used to automate the diagnosis by capturing unseen patterns from datasets. This research work concentrates on data expansion using augmentation technique which increases the dataset size by generating different images. The proposed system develops a medical diagnosis system which can be used to classify arrhythmia into different categories. Initially, machine learning techniques like Support Vector Machine (SVM), Naïve Bayes (NB), and Logistic Regression (LR) are used for diagnosis. In general deep learning models are used to extract high level features and to provide improved performance over machine learning algorithms. In order to achieve this, the proposed system utilizes a deep learning algorithm known as Convolutional Neural Network-baseline model for arrhythmia detection. The proposed system also adopts a novel hyperparameter tuned CNN model to acquire optimal combination of parameters that minimizes loss function and produces better result. The result shows that the hyper-tuned model outperforms other machine learning models and CNN baseline model for accurate classification of normal and other five different arrhythmia types.
Collapse
|