Article
Clinical Neurology
Roman Schniepp, Anna Huppert, Julian Decker, Fabian Schenkel, Cornelia Schlick, Atal Rasoul, Marianne Dieterich, Thomas Brandt, Klaus Jahn, Max Wuehr
Summary: The study evaluated the predictive validity of multimodal clinical assessment outcomes and quantitative measures for fall-risk estimation in patients with neurological gait disorders. Results showed that falls and fall-related injuries are a significant health issue in these patients. Fall history taking and instrument-based measures of gait and mobility are important for predicting fall status, frequency, and severity in patients at risk of falling.
JOURNAL OF NEUROLOGY
(2021)
Article
Chemistry, Multidisciplinary
Xin-Cheng Zhu, Deng-Huang Zhao, Yi-Hua Zhang, Xiao-Jun Zhang, Zhi Tao
Summary: This paper proposes a method of multiscale recurrence quantification measures (MRQMs) for voice disorder detection, achieving a high accuracy and potential for multi-classification of voice disorders.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Xinjiang Lu, Yunxu Bai
Summary: This article proposes a novel probabilistic LS-SVM method to enhance the modeling reliability of data contaminated by non-Gaussian noise. The effectiveness of the proposed method is demonstrated using both artificial and real cases.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Medicine, General & Internal
Ming-hui Lai, Hai-chen Xu, Meng-cui Huang, Yan Lu, Kun Yang, Li-ming Jiang, Xiao-ming Yu
Summary: This study aims to investigate the synergistic effects of integrating bodyweight support-t'ai chi (BWS-TC) and transcranial direct current stimulation (tDCS) on improving motor function in stroke survivors. The study will involve a 12-week intervention and a 6-month follow-up, with three groups compared. Outcome measures include neurological assessment, balance ability, walking function, brain structure and function, among others. The results will be disseminated through scientific conferences and peer-reviewed journals.
Article
Sport Sciences
Hideharu Tanaka, Tomoya Kinoshi, Shota Tanaka, Ryo Sagisaka, Hiroyuki Takahashi, Etsuko Sone, Takahiro Hara, Yui Takeda, Hiroshi Takyu
Summary: This study describes the neurological outcomes after sudden cardiac arrests (SCAs) in road and long-distance races, and analyzes the impact of interventions and resuscitation characteristics on patient recovery. The results demonstrate that the use of a rapid mobile automated external defibrillator system (RMAEDS) intervention improves both survival rates and neurological outcomes.
BRITISH JOURNAL OF SPORTS MEDICINE
(2022)
Article
Computer Science, Interdisciplinary Applications
Tanvir Ibna Kaisar, Kais Zaman, Mohammad T. Khasawneh
Summary: This paper proposes three algorithms that combine Support Vector Machine and Gaussian Process to efficiently classify large datasets and obtain probability information on the classification results. Experimental results demonstrate that these algorithms have good performance in terms of computational efficiency and accuracy.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Review
Pharmacology & Pharmacy
Narges Norouzkhani, Arian Ghannadi Karimi, Negar Badami, Erfan Jalalifar, Behnaz Mahmoudvand, Arina Ansari, Neda Pakrou Sariyarighan, Dorsa Alijanzadeh, Sara Aghakhani, Reza Shayestehmehr, Mohammadreza Arzaghi, Zahra Sheikh, Yasaman Salimi, Mohammad Hesam Marabi, Amir Abdi, Niloofar Deravi
Summary: This article summarizes the neuroprotective potential of common Indian spices widely used in Ayurveda, which may have positive effects in age-related neurological disorders.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Haeun Park, Baekdong Cha, Chanhee Park, Jeha Ryu, Joshua (Sung) H. You
Summary: The aim of this study was to analyze the impact of body weight support and speed on muscle activity torques in the knee and hip joints during robot-assisted gait training (RAGT). The results showed that adjusting the parameters of body weight support and speed had an influence on lower limb muscle activity and joint torques.
APPLIED SCIENCES-BASEL
(2022)
Article
Psychiatry
Andreas Joos, Christoph Herrmann, Claas Lahmann, Merle Flottman, Theresa Jansen, Corinna Schede, Philipp Maner, Kai Schoerner, Dominik Klaasen von Husen, Michael Joebges, Armin Hartmann
Summary: This study compared the condition of Functional Neurological Disorder (FND) patients with psychosomatic (PSM) patients and post-stroke patients. The results showed that FND and PSM patients scored highly in biopsychosocial complexity and had lower mental and somatic quality of life. These findings emphasize the importance of evaluating FND from a biopsychosocial perspective.
GENERAL HOSPITAL PSYCHIATRY
(2023)
Article
Computer Science, Interdisciplinary Applications
Amir Feizi, Alireza Nazemi, Mohammad Reza Rabiei
Summary: This paper introduces a recurrent neural network to assist support vector machine learning in stochastic support vector regression, demonstrating its effectiveness in three illustrative examples.
ENGINEERING WITH COMPUTERS
(2022)
Article
Medicine, General & Internal
Xuanzhen Cen, Lidong Gao, Meimei Yang, Minjun Liang, Istvan Biro, Yaodong Gu
Summary: This study investigated the acute effects of arch-supporting intervention on lower extremity segment coordination in patients with mild flatfoot during unplanned gait termination. Significant differences were found in joint kinematics and frontal plane MPJ-ankle coordination under arch support, while no significant difference was observed in coordination angle variability compared to non-arch-support conditions. Further research is needed to explore the long-term effects of arch orthoses on lower limb inter-joint coordination during gait termination.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Zichen Zhang, Yongquan Dong, Wei-Chiang Hong
Summary: Accurate and reliable probabilistic load forecasting is essential for efficient operation of power systems and efficient use of energy resources. This study proposes a probabilistic load forecasting model that estimates uncertainties in forecasting models and nonstationary electric load data using data filtering, feature extraction, and parameter optimization. Experimental results demonstrate significant improvement in probabilistic and point forecasting compared to suboptimal models.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Review
Sport Sciences
Fabio Carlos Lucas de Oliveira, Samuel Williamson, Clare L. Ardern, Kristina Fagher, Neil Heron, Dina Christina (Christa) Janse van Rensburg, Marleen G. T. Jansen, Nikki Kolman, Sean Richard O'Connor, Tobias Saueressig, Linda Schoonmade, Jane S. Thornton, Nick Webborn, Babette M. Pluim
Summary: This scoping review examines the impacts of different levels and types of partial foot amputation on gait and discusses how these findings may affect the minimal impairment criteria for wheelchair tennis. The study found that different types of foot amputation can lead to various gait abnormalities, which may have implications for tennis performance.
BRITISH JOURNAL OF SPORTS MEDICINE
(2023)
Article
Computer Science, Information Systems
Wei Zeng, Limin Ma, Yu Zhang
Summary: This study aimed to develop an automatic and highly accurate diagnosis system for knee osteoarthritis (OA) by investigating the classification capability of different dynamical features extracted from gait kinematic signals. Various dynamical features were included in a general feature extraction framework, which were evaluated using different shallow classifiers. The proposed method demonstrated superior performance in discriminating between patients with knee OA and asymptomatic healthy controls.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Civil
Bin Li, Yong Fu, Yi Hong, Zijun Cao
Summary: This paper presents a convenient approach for deterministic and probabilistic evaluations of tunnel face stability using support vector machine classifiers, consisting of constructing the training dataset and determining instance-based classifiers. The method utilizes orthogonal design to generate representative samples, labels the training dataset through two-dimensional strength reduction analyses, and applies ad hoc Python program for classification. Probabilistic evaluations are conducted through Monte Carlo simulation based on SVM-KNN classifier, computing the ratio of unstable samples to total simulated samples as failure probability, validated and compared with response surface method.
GEOMECHANICS AND ENGINEERING
(2021)
Article
Neurosciences
Baptiste Gauthier, Pooja Prabhu, Karunakar A. Kotegar, Virginie van Wassenhove
JOURNAL OF COGNITIVE NEUROSCIENCE
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Pooja Prabhu, A. K. Karunakar, Sanjib Sinha, N. Mariyappa, G. K. Bhargava, J. Velmurugan, H. Anitha
Summary: This study introduces an automatic tilt correction method for brain MR images, measuring angles in X, Z, and Y axes to achieve correction. Experimental results demonstrate that this method outperforms existing studies in correcting tilt.
JOURNAL OF DIGITAL IMAGING
(2021)
Article
Computer Science, Artificial Intelligence
Manjunath Hegde, Adnan Anwar, Karunakar Kotegar, Zubair Baig, Robin Doss
Summary: Research on smart meter data security is considered a top priority to ensure the safety and reliability of critical energy system infrastructure. A distributed, dynamic multistage authenticated key agreement scheme has been proposed for secure authentication in smart meter communication, which has been proved to resist various attacks and provide secure authentication.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Manishaa, A. K. Karunakar, Chang-Tsun Li
Summary: Identification of image provenance is crucial in image forensics, and a deep learning approach can efficiently identify the social network origin of images. The proposed method outperforms state-of-the-art techniques on well-known datasets, showing promise for identifying image provenance in a new way.
PATTERN RECOGNITION LETTERS
(2021)
Article
Computer Science, Software Engineering
Abhilash K. Pai, Prahaladh Chandrahasan, U. Raghavendra, A. K. Karunakar
Summary: Automated crowd behaviour analysis and monitoring is challenging due to the unpredictable nature of the crowd. This paper proposes an approach to automatically detect the type of a crowded scene based on global motion patterns. The method utilizes angular features and a novel feature vector called Histogram of Angular Deviations (HAD) to classify crowded scenes. Experimental results show the superior performance of the proposed approach compared to existing methods.
Article
Multidisciplinary Sciences
Gururaj Bijur, M. Ramakrishna, Karunakar A. Kotegar
Summary: In a Software Defined Network environment, the dynamic traffic of multicast communication, which is often overlooked, is more natural and practical. This paper proposes a multicast tree construction algorithm that considers receiving devices and network capability for efficient handling of dynamic multicast traffic. The proposed method generates a stable common path for multicast communication with reduced tree alteration.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Information Systems
K. R. Akshatha, A. Kotegar Karunakar, Satish B. Shenoy, Abhilash K. Pai, Nikhil Hunjanal Nagaraj, Sambhav Singh Rohatgi
Summary: This study evaluates the performance of Faster R-CNN and SSD algorithms in detecting human targets in aerial thermal imagery, and analyzes the impact of different backbone networks and anchor parameters on algorithm performance.
Article
Chemistry, Analytical
Manisha, Chang-Tsun Li, Xufeng Lin, Karunakar A. Kotegar
Summary: Source-camera identification tools assist investigators in associating images with specific cameras. Traditional PRNU methods are susceptible to various factors, while a new data-driven approach based on deep learning can identify individual cameras of the same model with high resilience.
Article
Geography, Physical
K. R. Akshatha, A. K. Karunakar, B. Satish Shenoy, K. Phani Pavan, Chinmay V. Dhareshwar, Dennis George Johnson
Summary: Intelligent UAV video analysis has gained attention for its potential in computer vision applications. In order to address the challenge of small object detection, a Manipal-UAV person detection dataset was created, consisting of images captured from UAVs in varying conditions. The dataset provides a benchmark for evaluating state-of-the-art object detection algorithms on small person objects in aerial view scenarios. The dataset is publicly available for researchers to advance UAV and small object detection research.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Engineering, Multidisciplinary
Shavantrevva Bilakeri, A. K. Karunakar
Summary: Multi-object tracking aims to estimate object trajectory in videos using either a public or private detection approach. We propose an improved data association method by integrating multiple features, leading to better accuracy and track quality.
COGENT ENGINEERING
(2022)
Article
Chemistry, Analytical
Karunakar A. Manisha, Chang-Tsun Li, Karunakar A. Kotegar
Summary: With the prevalence of digital multimedia content, reliable source camera identification has become crucial in digital forensics. Existing techniques for image-based source identification are inadequate for video-based identification due to disruptive effects during video processing. We propose a novel approach that leverages a global stochastic fingerprint in low- and mid-frequency bands to address this challenge and establish new benchmarks for source camera and device identification.
Article
Computer Science, Information Systems
Manisha, Chang-Tsun Li, Karunakar A. Kotegar
Summary: Source camera identification is a crucial task in image forensics, linking an image to the camera used to capture it. Existing techniques fail if the image was taken by a new camera not included in the training process. To address this issue, we propose a data-driven system based on convolutional neural networks that can identify the source camera in an open-set scenario. Experimental results demonstrate the system's high accuracy in identifying previously unseen devices and its resilience to unknown post-processing applied by social networks.
Proceedings Paper
Computer Science, Artificial Intelligence
Pooja Prabhu, Karunakar A. Kotegar, N. Mariyappa, H. Anitha, G. K. Bhargava, Jitender Saini, Sanjib Sinha
Summary: Epilepsy, a common neurological disorder, affects a large population worldwide. This study proposes a deep learning model to classify epileptic and nonepileptic EEG data, addressing the subjective errors caused by manual interpretation and the time-consuming process of identifying seizure instances in high temporal resolution data.
MACHINE LEARNING AND AUTONOMOUS SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
K. R. Akshatha, A. K. Karunakar, B. Satish Shenoy
Summary: This study explores the automatic detection of people in aerial images and reduces computation time by using custom-designed CNN classifiers. The performance is compared with the standard VGG-16 based classifier.
MACHINE LEARNING AND AUTONOMOUS SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Gururaj Bijur, Ramakrishna Mundugar, Vinayak Mantoor, Karunakar Kotegar
Summary: A wireless network provides flexibility to users, but video communication may face QoS and QoE issues. Parameters like node mobility and distance between nodes play a major role in video communication quality. Scalable Video Coding (SVC) allows partial removal of layers, enabling smooth streaming over wireless networks.