Article
Neurosciences
Huize Pang, Ziyang Yu, Hongmei Yu, Miao Chang, Jibin Cao, Yingmei Li, Miaoran Guo, Yu Liu, Kaiqiang Cao, Guoguang Fan
Summary: An automatic classification method based on multimodal striatal alterations was developed to distinguish between parkinsonian variant of multiple system atrophy (MSA-P) and Idiopathic Parkinson's disease (IPD). The machine learning algorithm accurately classified the two diseases by depicting dysfunction in the dorsal striatum and the prefrontal lobe and cerebellum through specific brain connections, with the functional activity of the dorsolateral putamen being the most important marker.
CNS NEUROSCIENCE & THERAPEUTICS
(2022)
Article
Computer Science, Artificial Intelligence
Veronica Munoz-Ramirez, Virgilio Kmetzsch, Florence Forbes, Sara Meoni, Elena Moro, Michel Dojat
Summary: This study utilizes deep learning models to detect anomalies in brain diffusion tensor imaging (DTI) parameter maps of patients with Parkinson's disease (PD). The model is able to identify potentially pathological regions without expert delineation, and may enable the extraction of neuroimaging biomarkers for PD in the future. Further testing on larger cohorts is needed.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Neurosciences
Boyu Chen, Wenzhuo Cui, Shanshan Wang, Anlan Sun, Hongmei Yu, Yu Liu, Jiachuan He, Guoguang Fan
Summary: This study aimed to differentiate the parkinsonian variant of multiple system atrophy (MSA-P) from idiopathic Parkinson's disease (IPD) by investigating the differences and similarities in brain functional connectomes using resting-state fMRI data. The results showed that early IPD and MSA-P patients shared network topological properties and both conditions disrupted the cerebellum-basal ganglia-cortical network. Machine learning models using connectome measurements achieved a high diagnostic performance in distinguishing between IPD and MSA-P patients.
HUMAN BRAIN MAPPING
(2023)
Article
Computer Science, Artificial Intelligence
Konstantinos Sechidis, Riccardo Fusaroli, Juan Rafael Orozco-Arroyave, Detlef Wolf, Yan-Ping Zhang
Summary: This study provides an objective evaluation of Parkinson's disease (PD) speech characteristics using a transfer learning system with a Mixture-of-Experts (MoE) model. It found that PD speech exhibits more negative emotional characteristics than healthy controls, with these judgments being related to disease severity and speech impairment severity in PD patients. The findings demonstrate the potential of using publicly available datasets to train models for insights into clinical data.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)
Article
Medicine, General & Internal
Alex Li, Chenyu Li
Summary: This study aims to build a classifier using gait data from Parkinson patients and healthy controls as input, utilizing machine learning methods to achieve a more accurate and cost-effective diagnostic method for Parkinson's disease.
Review
Mathematical & Computational Biology
Annalisa Vitale, Rossella Villa, Lorenzo Ugga, Valeria Romeo, Arnaldo Stanzione, Renato Cuocolo
Summary: Idiopathic Parkinson's Disease is a common neurodegenerative disorder that primarily affects elderly individuals, causing significant emotional burden for patients and caregivers. The diagnosis of this disease is challenging due to its similarity to other neurodegenerative disorders, and currently relies heavily on the clinical experience and knowledge of physicians. Advances in artificial intelligence and machine learning have shown promise in analyzing neuroimaging data to better understand the pathophysiology and progression of the disease.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
Article
Neurosciences
Xue-ning Li, Da-peng Hao, Mei-jie Qu, Meng Zhang, An-bang Ma, Xu-dong Pan, Ai-jun Ma
Summary: By combining plasma FAM19A5 and MRI-based radiomics, the study successfully developed a predictive tool for PD and PDD, which showed excellent accuracy in clinical settings.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Clinical Neurology
Katsuki Eguchi, Hiroaki Yaguchi, Ikue Kudo, Ibuki Kimura, Tomoko Nabekura, Ryuto Kumagai, Kenichi Fujita, Yuichi Nakashiro, Yuki Iida, Shinsuke Hamada, Sanae Honma, Asako Takei, Fumio Moriwaka, Ichiro Yabe
Summary: The study evaluated a DNN model with a transformer architecture to distinguish speech data of PD patients from SCD patients, achieving relatively high accuracy and AUC in fivefold cross-validation.
JOURNAL OF NEUROLOGY
(2023)
Article
Computer Science, Information Systems
M. Tanveer, A. H. Rashid, Rahul Kumar, R. Balasubramanian
Summary: This article provides a comprehensive review of the diagnosis of Parkinson's disease and its subtypes using artificial neural networks and deep neural networks. The paper analyzes various modalities, datasets, architectures, and experimental configurations, and presents an in-depth comparative analysis of different proposed architectures. The article also suggests future research directions in this field.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Clinical Neurology
Urs Kleinholdermann, Max Wullstein, David Pedrosa
Summary: This study aimed to develop a mobile, objective, and unobtrusive method for measuring motor symptoms in Parkinson's disease. Data from 45 PD patients were collected using surface electromyography (sEMG) electrodes attached to a wristband. A random forest regression model showed the highest correlation of 0.739 between true and predicted UPDRS values, indicating the potential of sEMG data in extrapolating motor symptoms of PD patients.
CLINICAL NEUROPHYSIOLOGY
(2021)
Article
Automation & Control Systems
Houssem Meghnoudj, Bogdan Robu, Mazen Alamir
Summary: This study proposes a novel approach for the diagnosis of Parkinson's Disease (PD) based on electroencephalogram (EEG) signals, which extracts new discriminant features using the dynamics, frequency, and temporal content of EEGs. The generated sparse dynamic features (SDFs) provide more informative and faithful features to the concept of EEG generation. By using a linear classifier and only two extracted features from the SDFs, the healthy and unhealthy subjects can be separated with an accuracy of 90.0% (p < 0.03).
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Biochemistry & Molecular Biology
Chen Dong, Chandrashekhar Honrao, Leonardo O. Rodrigues, Josephine Wolf, Keri B. Sheehan, Matthew Surface, Roy N. Alcalay, Elizabeth M. O'Day
Summary: Parkinson's disease is a progressive neurodegenerative disease with motor and nonmotor function loss. This study identified metabolic markers of PD in plasma and developed a machine learning model for PD diagnosis with high accuracy. The findings provide insights for the development of diagnostic tools for PD.
Article
Computer Science, Artificial Intelligence
Bruno Fonseca Oliveira Coelho, Ana Beatriz Rodrigues Massaranduba, Carolline Angela dos Santos Souza, Giovanni Guimaraes Viana, Ivani Brys, Rodrigo Pereira Ramos
Summary: This study evaluates the performance of Hjorth features extracted from electroencephalographic signals as biomarkers for Parkinson's disease. By analyzing EEG data from PD patients, the differences in Hjorth features between healthy individuals and PD patients were observed in the parietal, frontal, central, and occipital lobes. Using a Support Vector Machine algorithm, the proposed model achieved an accuracy of 89.56% in classifying PD patients and healthy individuals.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Clinical Neurology
Anat Mirelman, Mor Ben Or Frank, Michal Melamed, Lena Granovsky, Alice Nieuwboer, Lynn Rochester, Silvia Del Din, Laura Avanzino, Elisa Pelosin, Bastiaan R. Bloem, Ugo Della Croce, Andrea Cereatti, Paolo Bonato, Richard Camicioli, Theresa Ellis, Jamie L. Hamilton, Chris J. Hass, Quincy J. Almeida, Maidan Inbal, Avner Thaler, Julia Shirvan, Jesse M. Cedarbaum, Nir Giladi, Jeffrey M. Hausdorff
Summary: This study utilized wearable sensors to record gait and mobility measures in PD patients and healthy controls, and applied machine-learning algorithms to distinguish between different stages of PD severity. The findings suggest that gait and mobility measures can reflect distinct PD stages with high discriminatory values.
MOVEMENT DISORDERS
(2021)
Review
Geriatrics & Gerontology
Jie Mei, Christian Desrosiers, Johannes Frasnelli
Summary: Diagnosis of Parkinson's disease relies on medical observations and clinical signs, but traditional methods can be subjective. Machine learning approaches have shown potential in improving diagnosis and informing clinical decision making.
FRONTIERS IN AGING NEUROSCIENCE
(2021)
Article
Computer Science, Information Systems
Dong Zhang, Xiujian Liu, Jun Xia, Zhifan Gao, Heye Zhang, Victor Hugo C. de Albuquerque
Summary: The IoT-based smart healthcare system is of significant importance for the accurate diagnosis of cardiovascular disease. This paper proposes a physics-guided deep learning network that incorporates artificial intelligence techniques and considers the importance of coronary artery features to provide explainable and accurate functional assessment for cardiovascular disease.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Khan Muhammad, Hayat Ullah, Mohammad S. Obaidat, Amin Ullah, Arslan Munir, Muhammad Sajjad, Victor Hugo C. de Albuquerque
Summary: This article proposes an efficient deep-learning-based framework for multiperson salient soccer event recognition in the IoT-enabled FinTech. The framework performs event recognition through frames preprocessing, frame-level discriminative features extraction, and high-level events recognition in soccer videos. The results validate the suitability of the proposed framework for salient event recognition in Nx-IoT environments.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Muhammad Irfan, Khan Muhammad, Muhammad Sajjad, Khalid Mahmood Malik, Faouzi Alaya Cheikh, Joel J. P. C. Rodrigues, Victor Hugo C. de Albuquerque
Summary: This article discusses the significant bandwidth consumption of immersive videos in industry 4.0 and proposes a solution using convolutional neural networks to select the user's region of interest and reduce bandwidth usage.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Jiarong Chen, Mingzhe Jiang, Xianbin Zhang, Daniel S. da Silva, Victor Hugo C. de Albuquerque, Wanqing Wu
Summary: Implementing internet of things technologies in health monitoring systems is gaining attention. However, running the model at edge is challenging due to limited computational capacities and storage resources.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Gaowei Xu, Chenxi Huang, Daniel Santos da Silva, Victor Hugo C. de Albuquerque
Summary: Fault diagnosis is crucial for the safe operation of equipment in industrial applications. Existing fault diagnosis methods based on deep learning often assume the same data distribution for training and testing, which is practically impossible. Moreover, these methods are memory-intensive and computationally expensive. This study proposes a compressed unsupervised domain adaption model for fault diagnosis. The model extracts features from training and testing data using an unsupervised domain adaption approach, reduces discrepancy between the features, compresses the model by pruning redundant convolutional channels, and achieves comparable or better accuracy with reduced memory occupation and computational cost.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Hardware & Architecture
Mohammed Altaf Ahmed, Sara A. Althubiti, Victor Hugo C. de Albuquerque, Marcello Carvalho dos Reis, Chitra Shashidhar, T. Satyanarayana Murthy, E. Laxmi Lydia
Summary: The study introduces a technique called CSOTL-VDCRS for vehicle detection and classification in remote sensing images. It utilizes Mask RCNN for vehicle detection and FWNN for classification. By using CSO as a hyperparameter optimizer, the performance of vehicle detection is enhanced. Experimental results demonstrate the superior performance of the proposed CSOTL-VDCRS technique.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Gui-Bin Bian, Zhang Chen, Zhen Li, Bing-Ting Wei, Wei-Peng Liu, Daniel Santos da Silva, Wan-Qing Wu, Victor Hugo C. de Albuquerque
Summary: Learning surgical skills from trained surgeons can enhance the autonomy of surgical robots and provide appropriate assistance during surgery. This study addresses the challenging issue of the remote center of motion (RCM) constraint, which is often neglected in other works. The proposed method models the implicit constraints of manipulation skills using a probabilistic model to maintain flexibility. It also introduces a novel approach to reconcile the inconsistency between the RCM constraint and surgical task space, improving the generalization of learned skills. Experimental validation demonstrates the effectiveness of the proposed method in a tracking task under the RCM constraint, with a root mean square error exceeding the average for operator demonstrations.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jefferson S. Almeida, Senthil Kumar Jagatheesaperumal, Fabricio G. Nogueira, Victor Hugo C. de Albuquerque
Summary: Forest fires have significant impacts on the environment and human communities, causing soil erosion, habitat and biodiversity loss, as well as releasing carbon dioxide and other pollutants. They also damage properties, displace residents, and put responders at risk. Forest fires can contribute to climate change by releasing stored carbon and altering ecosystems. This study proposes a novel algorithm for real-time monitoring of small areas in forest reserves through video streaming, complementing existing monitoring methods. The algorithm, called EdgeFireSmoke++, combines artificial neural networks and deep learning methods, achieving high accuracy in detecting forest fires from the evaluated dataset. Real-time experiments using Internet Protocol cameras showed excellent performance, surpassing other methods in the literature.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Tanveer Hussain, Fath U. Min Ullah, Samee Ullah Khan, Amin Ullah, Umair Haroon, Khan Muhammad, Sung Wook Baik, Victor Hugo C. de Albuquerque
Summary: Video summarization is important for suppressing high-dimensional video data. However, prior research has not focused on the need for surveillance video summarization, and mainstream techniques lack event occurrence detection. Therefore, we propose a two-fold 3-D deep learning-assisted framework for video summarization.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Waseem Ullah, Tanveer Hussain, Fath U. Min Ullah, Khan Muhammad, Mahmoud Hassaballah, Joel J. P. C. Rodrigues, Sung Wook Baik, Victor Hugo C. de Albuquerque
Summary: The main challenge faced by video-based real-world anomaly detection systems is accurately learning irregular, complicated, diverse, and heterogeneous unusual events. To address this, a weakly supervised graph neural-network-assisted video anomaly detection framework called AD-Graph is proposed. It extracts 3D visual and motion features and represents them in a language-based knowledge graph format to identify temporal information. It applies a robust clustering strategy to group meaningful neighborhoods of the graph and uses spectral filters and graph theory to detect anomalous events. Extensive experimental results show improvements over state-of-the-art models on challenging datasets.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Biotechnology & Applied Microbiology
Artur Gomes Barreto, Juliana Martins de Oliveira, Francisco Nauber Bernardo Gois, Paulo Cesar Cortez, Victor Hugo Costa de Albuquerque
Summary: The automatic generation of descriptions for medical images has attracted increasing interest in the healthcare field. However, there are gaps in the literature, such as the lack of studies on specific model performance and objective evaluation of generated descriptions. To address these issues, this study combines natural language processing and features extraction to develop a generative model with the goal of achieving model generalization across different image modalities and medical conditions.
BIOENGINEERING-BASEL
(2023)
Article
Engineering, Biomedical
Han Wang, Lei Cao, Chenxi Huang, Jie Jia, Yilin Dong, Chunjiang Fan, Victor Hugo C. de Albuquerque
Summary: This study proposes an algorithmic structure combining EEG channel-attention and Swin Transformer for motor pattern recognition, which effectively captures temporal-spectral-spatial features hidden in EEG data. The experimental results show that our proposed methods outperformed other state-of-the-art approaches with an average accuracy of 87.67%. This paper demonstrates that channel-attention combined with Swin Transformer methods has great potential for implementing high-performance motor pattern-based BCI systems.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Proceedings Paper
Computer Science, Information Systems
Puneet Goswami, Victor Hugo C. de Albuquerque, Lakshita Aggarwal
Summary: The rapid advances in crypto wallet are re-defining privacy around transactions. Crypto wallet enables secure transfers and exchange of funds between different healthcare consumers by using a blockchain-based system that records and stores every transaction. It solves traditional wallet problems, providing features such as sending/receiving coins, portfolio balance, and cryptocurrency trading, while ensuring user privacy with a hexadecimal address.
BIG DATA ANALYTICS IN ASTRONOMY, SCIENCE, AND ENGINEERING, BDA 2022
(2023)
Article
Computer Science, Artificial Intelligence
Changqin Huang, Ming Li, Feilong Cao, Hamido Fujita, Zhao Li, Xindong Wu
Summary: Graph Convolutional Networks (GCNs) have powerful capabilities in learning node representations on graphs, and there are various extensions to further improve their performance, scalability, and applicability. However, there is still room for improvement in learning efficiency, especially for large graphs where batch gradient descent using the full dataset is not feasible. This motivates us to consider GCNs with random weights as a potential solution.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Gui-Bin Bian, Jia-Ying Zheng, Zhen Li, Jie Wang, Pan Fu, Chen Xin, Daniel Santos da Silva, Wan-Qing Wu, Victor Hugo C. De Albuquerque
Summary: This study proposes a multimodal, multi-timescale data fusion network based on deep learning to improve the accuracy of continuous circular capsulorhexis (CCC) procedures. Through validation on an ophthalmologist CCC multimodal maneuver dataset, the model demonstrates superior performance in continuous action sequence segmentation and minority class recognition.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Qianghua Liu, Yu Tian, Tianshu Zhou, Kewei Lyu, Ran Xin, Yong Shang, Ying Liu, Jingjing Ren, Jingsong Li
Summary: This study proposes a few-shot disease diagnosis decision making model based on a model-agnostic meta-learning algorithm (FSDD-MAML). It significantly improves the diagnostic process in primary health care and helps general practitioners diagnose few-shot diseases more accurately.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)
Article
Computer Science, Artificial Intelligence
Balazs Borsos, Corinne G. Allaart, Aart van Halteren
Summary: The study demonstrates the feasibility of predicting functional outcomes for ischemic stroke patients and the usability of multimodal deep learning architectures for this purpose.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)
Article
Computer Science, Artificial Intelligence
Abdelmoniem Helmy, Radwa Nassar, Nagy Ramdan
Summary: This study utilizes machine learning models to detect depression symptoms in Arabic and English texts, and provides manually and automatically annotated tweet corpora. The study also develops an application that can detect tweets with depression symptoms and predict depression trends.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)