Article
Psychology, Multidisciplinary
E. F. Haghish, Bruno Laeng, Nikolai Czajkowski
Summary: Using a large population-based longitudinal dataset, this study found that false positives in machine learning suicide attempt classification models are at a higher risk of attempting suicide in the future compared to true negatives. The risk of suicide attempts for false positives increases as the specificity threshold increases. Additionally, as specificity increases, the severity of risk factors between false positives and true positives becomes more similar.
FRONTIERS IN PSYCHOLOGY
(2023)
Article
Mathematics, Interdisciplinary Applications
Kookyoung Han, Jin Hyuk Choi
Summary: Cyber-threats such as computer viruses, data breaches, and denial-of-service attacks are on the rise and require effective handling. The imperfections in cyber-attack prevention often lead to false alarms in defense systems. This study examines the implications of false alarms in various contexts, including the cyber-insurance market, operational risk, and government intervention. The findings indicate a low demand and supply for cyber-insurance, explain the underdevelopment of the market, and propose a policy for achieving socially optimal outcomes through government intervention.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Neurosciences
Kyle M. Roddick, Emre Fertan, Heather M. Schellinck, Richard E. Brown
Summary: Olfactory dysfunction begins in the early stages of Alzheimer's disease, with female patients showing worse learning impairments compared to male patients. Signal detection analysis can help differentiate cognitive and sensory deficits.
JOURNAL OF ALZHEIMERS DISEASE
(2022)
Article
Environmental Sciences
Zheng Zhang, Ping Tang, Changmiao Hu, Zhiqiang Liu, Weixiong Zhang, Liang Tang
Summary: This paper proposes a seeded SITS classification method based on lower-bounded Dynamic Time Warping, which only requires a few labeled samples and uses a combination of cascading lower bounds and early abandoning of DTW as an accurate yet efficient similarity measure. Experimental results demonstrate the utility of this method for SITS classification in large-scale tasks.
Article
Computer Science, Artificial Intelligence
Matthieu Herrmann, Chang Wei Tan, Geoffrey I. Webb
Summary: Dynamic time warping (DTW) is a widely used method for measuring the distance between time series data. In this paper, we investigate the use of different cost functions and the tuning of cost functions for time series classification tasks. We show that adjusting the cost function parameters can significantly improve the accuracy of DTW classifiers.
DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Article
Computer Science, Artificial Intelligence
Matthieu Herrmann, Chang Wei Tan, Geoffrey I. Webb
Summary: Dynamic time warping (DTW) is a widely used method for measuring the distance between time series by aligning their points. This paper investigates the impact of different cost functions and the potential for tuning cost functions to different time series classification tasks. The authors propose a tunable cost function lambda(gamma) with parameter gamma and show that training gamma significantly improves the accuracy of both the DTW nearest neighbor and Proximity Forest classifiers.
DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Article
Cardiac & Cardiovascular Systems
Sandeep Chandra Bollepalli, Rahul K. Sevakula, Wan-Tai M. Au-Yeung, Mohamad B. Kassab, Faisal M. Merchant, George Bazoukis, Richard Boyer, Eric M. Isselbacher, Antonis A. Armoundas
Summary: Accurate detection of life-threatening arrhythmias in the ICU is crucial but traditional monitors often result in false alarms. This study introduces an algorithm using deep learning to improve detection accuracy, achieving superior performance compared with methods solely based on convolutional neural networks.
JOURNAL OF THE AMERICAN HEART ASSOCIATION
(2021)
Article
Psychology, Biological
Elif Yuvruk, Jeffrey Starns, Aycan Kapucu
Summary: Previous evidence suggests that emotion leads to more false alarms and faster response times in a recognition memory task. This could be because participants have a more liberal response style for emotional stimuli and/or because emotional lures are more likely to produce misleading memory retrieval. A recent study further examined the basis of false alarms to emotional lures and tested predictions of the diffusion model. The findings provide insights into how emotion affects memory retrieval and offer a new methodology for measuring recognition performance.
QUARTERLY JOURNAL OF EXPERIMENTAL PSYCHOLOGY
(2022)
Article
Green & Sustainable Science & Technology
Yi Wang, Xianfang Xue, Han Guo
Summary: This study examines the impact of market orientation on firm performance in a dynamic environment, considering different types of market orientation and the mediating effect of dynamic capability. It also discusses the moderating role of error management climate in the relationship between market orientation and performance.
Article
Chemistry, Analytical
Ahmed Shahat, Khadiza Tul Kubra, Md. Shad Salman, Md. Nazmul Hasan, Md. Munjur Hasan
Summary: In this study, a solid-state sensor for simultaneous detection and adsorption of cadmium ion was successfully fabricated. The sensor exhibited high selectivity and reusability, with the ability to detect ultra-trace levels of Cd(II) ion and a suitable pH of 7.0. The sensor showed a good adsorption capacity and was able to be reused after desorption using HCl without significant loss in performance.
MICROCHEMICAL JOURNAL
(2021)
Article
Engineering, Manufacturing
Chensheng Wang, Yonghao Guo, Hongda Liu, Wentie Niu
Summary: The trajectory error of the tool center point (TCP) in machine tools is caused by the dynamic positioning error of the feed drive system, including axial and lateral dynamic errors. This study analyzed the influence of lateral dynamic error on TCP trajectory error in multi-axis machine tools by designing circular and butterfly trajectories. The tracking error models were constructed with and without considering lateral dynamic error, and the Sobol method was used to analyze sensitivity. Experiments on a three-axis machine tool showed that the maximum lateral dynamic error perpendicular to motion direction was 0.026 mm, negatively affecting TCP tracking and contour errors.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2023)
Article
Computer Science, Interdisciplinary Applications
Maximilian Leodolter, Claudia Plant, Norbert Brandle
Summary: This paper introduces the R package IncDTW for incremental calculation of DTW, reducing computational costs and expanding its application scope.
JOURNAL OF STATISTICAL SOFTWARE
(2021)
Article
Automation & Control Systems
Huan Wu, Yong-Ping Zhao, Hui-Jun Tan
Summary: This study proposes a method for monitoring the flow patterns of supersonic inlets using neural network technology, which integrates dynamic time warping and Kalman filter techniques to achieve better performance in feature extraction and classification.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Multidisciplinary Sciences
Anupama Nair, Chun-Yu Lin, Feng-Chun Hsu, Ta-Hsiang Wong, Shu-Chun Chuang, Yi-Shan Lin, Chung-Hwan Chen, Paul Campagnola, Chi-Hsiang Lien, Shean-Jen Chen
Summary: This study proposes a ResNet approach based on multipolarization SHG imaging for the categorization and regression of collagen type I and II blend hydrogels. Compared to previous methods, this approach does not require model fitting and can more accurately classify and regress the blend hydrogels.
SCIENTIFIC REPORTS
(2023)
Article
Robotics
Y. Chouaibi, A. H. Chebbi, Z. Affi, L. Romdhane
Summary: This paper presents a comparative study of two translational parallel manipulators (TPMs) with three Degrees of Freedom (3-DOF) based on the orientation errors due to joint clearances. The precision of the DELTA and RAF manipulators is compared by considering the maximum and sensitivity of the orientation errors. The results show that the RAF robot precision is more sensitive to the joint clearances than the DELTA one, except for a portion of the workspace that is free from singular configurations.
Article
Mathematics
Naheed Akhtar, Mubbashar Saddique, Khurshid Asghar, Usama Ijaz Bajwa, Muhammad Hussain, Zulfiqar Habib
Summary: This paper provides a detailed review of existing passive video tampering detection techniques and analyzes the state-of-the-art research work and commonly used datasets. The limitations of existing algorithms are discussed, and future research challenges and directions are proposed.
Article
Computer Science, Information Systems
Zulfiqar Ali, Fazal-e Amin, Muhammad Hussain
Summary: This study proposes a novel hybrid approach using fragile zero watermarking to protect the privacy and integrity of patients' personal information and medical data transmitted from remote health facilities. By incorporating visual cryptography and chaotic randomness, the algorithm effectively prevents information leakage.
Article
Mathematics
Muhammad Nadeem Ashraf, Muhammad Hussain, Zulfiqar Habib
Summary: Diabetic retinopathy (DR) is a vision-threatening complication, and a deep convolutional neural network (CNN) can effectively diagnose and screen DR patients. Training deep models with minimal data is challenging, but fine-tuning pre-trained CNNs and making architectural amendments can improve performance. The modified model (DR-ResNet50) outperforms state-of-the-art methods in terms of various metrics and shows high sensitivity and low false-positive rate in testing, demonstrating its value and suitability for early screening.
Article
Computer Science, Artificial Intelligence
Rawan Alsughayer, Muhammad Hussain, Fahman Saeed, Hatim AboalSamh
Summary: Remote sensing image tampering detection is crucial for hiding important information, but existing methods lack robustness. In this study, we propose an image-to-image transformation method based on U-Net architecture, focusing on residual noise and introducing a constrained convolutional layer. The method effectively detects and localizes splicing tampering.
APPLIED INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Mohammed Isam Al-Hiyali, Norashikin Yahya, Ibrahima Faye, Maged S. Al-Quraishi, Abdulhakim Al-Ezzi
Summary: This study proposed a new method for detecting autism spectrum disorder (ASD) based on wavelet coherence and singular value decomposition. The method, called principal wavelet coherence (PWC), showed better performance in representing functional connectivity (FC) dynamics between brain nodes compared to previous methods. The results suggest the potential of PWC in diagnosing other neuropsychiatric disorders.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
Danish M. Khan, Norashikin Yahya, Nidal Kamel, Ibrahima Faye
Summary: The study proposes a novel technique called Efficient Effective Connectivity (EEC) for estimating brain connectivity between multivariate sources. Compared to traditional techniques, EEC achieves higher accuracy and sensitivity, and can be used for reliable understanding of brain mechanisms and clinical diagnosis of mental disorders.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Biology
Abida Hussain, Mohana Sundaram Muthuvalu, Ibrahima Faye, Mudasar Zafar, Mustafa Inc, Farkhanda Afzal, Muhammad Sajid Iqbal
Summary: A brain tumor is a rapidly developing and abnormal system where aberrant cells cause the healthy cells to perish. This study presents a mathematical model for brain glioma growth and compares different methods for predicting the growth of glioma cells in treating the brain tumor. The results show that the TSSOR method is faster and more efficient than the TSGS and GS methods, reducing the number of iterations and computational time.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Mathematics
Fahman Saeed, Muhammad Hussain, Hatim A. A. Aboalsamh, Fadwa Al Adel, Adi Mohammed Al Owaifeer
Summary: Diabetic retinopathy (DR) is a leading cause of blindness in middle-aged diabetic patients, and regular screening using fundus imaging is crucial to detect complications and delay disease progression. To address the time-consuming and subjective nature of manual screening, a method for automatically customizing CNN models based on fundus image lesions is proposed, which outperforms existing pre-trained CNN models and other neural architecture search models.
Article
Mathematics, Applied
Walaa Alsumari, Muhammad Hussain, Laila Alshehri, Hatim A. Aboalsamh
Summary: Using biometric modalities for person recognition is crucial, and recent studies have focused on using electroencephalography (EEG) as a secure modality. Existing methods have limitations in terms of usability and generalization, but this study addresses these issues by proposing a lightweight convolutional neural network (CNN) model. The proposed EEG-based recognition system achieved high performance on a benchmark dataset, with a rank-1 identification result of 99% and an equal error rate of 0.187%.
Review
Biotechnology & Applied Microbiology
Ibrahima Abdullah, Ibrahima Faye, Md Rafiqul Islam
Summary: This paper focuses on the channel selection problem in brain-computer interface (BCI) systems using electroencephalography (EEG) signals. Through thorough analysis, the authors identify several effective channel selection algorithms and classification methods. The research findings suggest that choosing fewer channels (typically 10-30% of total channels) can yield excellent performance.
BIOENGINEERING-BASEL
(2022)
Article
Medicine, General & Internal
Farah Muhammad, Muhammad Hussain, Hatim Aboalsamh
Summary: A multimodal emotion recognition method based on deep canonical correlation analysis (DCCA) is proposed in this study, which fuses electroencephalography (EEG) and facial video clips. The proposed method achieves an average accuracy of 93.86% and 91.54% on MAHNOB-HCI and DEAP datasets, respectively.
Article
Mathematics
Hend Alshaya, Muhammad Hussain
Summary: Accurately identifying seizure types is crucial for treating epilepsy patients. This paper presents a deep network model based on ResNet and LSTM for classifying seizure types from EEG trials. The proposed model outperforms other state-of-the-art models with an F1-score of 97.4%.
Review
Mathematics, Applied
Abida Hussain, Ibrahima Faye, Mohana Sundaram Muthuvalu, Tong Boon Tang, Mudasar Zafar
Summary: In the field of biomedical image reconstruction, functional near infra-red spectroscopy (fNIRs) is a promising technology that uses near infra-red light for non-invasive imaging and reconstruction. Researchers are using various numerical methods to solve both the forward and backward problems in fNIRs. This study presents the latest advancements in numerical methods for solving the forward and backward problems in fNIRs.
Article
Computer Science, Information Systems
Muhammad Hussain, Emad-Ul-Haq Qazi, Hatim A. Aboalsamh, Ihsan Ullah
Summary: This study proposes an automatic emotion recognition system based on deep learning and electroencephalogram signals. It introduces a lightweight pyramidal one-dimensional convolutional neural network model with a small number of learnable parameters, and a two-level ensemble classifier. The method scans each channel incrementally in the first level and fuses the predictions using majority vote. In the second level, predictions from all channels are fused to predict the emotional state. The method was validated using the DEAP dataset and achieved high accuracies in distinguishing different emotion states.
Article
Neurosciences
Jose Sanchez-Bornot, Roberto C. Sotero, J. A. Scott Kelso, Ozguer Simsek, Damien Coyle
Summary: This study proposes a multi-penalized state-space model for analyzing unobserved dynamics, using a data-driven regularization method. Novel algorithms are developed to solve the model, and a cross-validation method is introduced to evaluate regularization parameters. The effectiveness of this method is validated through simulations and real data analysis, enabling a more accurate exploration of cognitive brain functions.
