Article
Engineering, Biomedical
Fang Dong, Zhanxing Yuan, Duanpo Wu, Lurong Jiang, Junbiao Liu, Wei Hu
Summary: The number of features directly affects the performance of models in machine learning based seizure detection research studies. In order to decrease the amount of features while ensuring model performance, a seizure detection algorithm based on multi-dimension feature selection is proposed. The algorithm applies wavelet packet decomposition (WPD) method to EEG signal and extracts different features from original EEG signals and sub-band signals. It then analyzes feature importance using random forest (RF) to remove redundant features. The evaluation results show high accuracy, specificity, and sensitivity in both cross-validation and real-time seizure detection.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Clinical Neurology
Andrew G. G. Herzog, Enrique Carrazana, Adrian L. L. Rabinowicz
Summary: This study assessed the relationship between statistical clustering of daily seizure counts or seizure intervals and clinical clustering in women with epilepsy. The findings showed that women with statistical clustering had a higher frequency of seizures ≥3 times per day, and this frequency was correlated with the average daily seizure frequencies. Statistical clustering of seizure intervals was more common in catamenial epilepsy. Logistic regression and ROC analysis identified specific classifiers for clustering.
Article
Computer Science, Interdisciplinary Applications
Essam Abdellatef, Heba M. Emara, Mohamed R. Shoaib, Fatma E. Ibrahim, Mohamed Elwekeil, Walid El-Shafai, Taha E. Taha, Adel S. El-Fishawy, El-Sayed M. El-Rabaie, Ibrahim M. Eldokany, Fathi E. Abd El-Samie
Summary: This paper presents two approaches for EEG signal classification: one using machine learning tools and the other using a CNN-based residual learning model. Both approaches are evaluated on the CHB-MIT dataset and show promising results for seizure detection and prediction.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Review
Oncology
Gan You, Zhiyi Sha, Tao Jiang
Summary: Glioma-related epilepsy (GRE) is symptomatic epileptic seizures secondary to gliomas, with various treatment options including surgical resection, but still a proportion of patients have poor seizure control after surgery.
FRONTIERS IN ONCOLOGY
(2021)
Review
Clinical Neurology
Jennifer Shum, Daniel Friedman
Summary: Seizure detection devices can greatly benefit people with epilepsy, caregivers, and clinicians by improving care quality and reducing mortality rates. Choosing the most suitable device involves considering various factors such as the device's main purpose, age, seizure type, and personal preferences.
JOURNAL OF THE NEUROLOGICAL SCIENCES
(2021)
Article
Engineering, Electrical & Electronic
Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka
Summary: A novel approach is proposed for recovering sparse signals from quadratic measurements, reducing problem dimensionality by recovering only the diagonal of the unknown matrix and using an efficient Noise Collector to absorb cross-correlated data. The theory shows that exact support recovery is possible with low noise levels and no false positives. The level of sparsity recovered scales almost linearly with the number of data, as demonstrated in numerical experiments.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2021)
Article
Clinical Neurology
Johannes Koren, Sebastian Hafner, Moritz Feigl, Christoph Baumgartner
Summary: The study compared three commercially available seizure-detection software packages (Besa, Encevis, Persyst) in 81 epilepsy patients undergoing long-term video-EEG monitoring. While all three packages showed similar sensitivities in detecting seizures, they differed in false alarm rates and detection delays. Persyst 13 had the highest detection rate and false alarm rate with the shortest detection delay, while Encevis 1.7 had slightly lower sensitivity, the lowest false alarm rate, and longer detection delay.
Article
Chemistry, Multidisciplinary
Marcin Kolodziej, Andrzej Majkowski, Andrzej Rysz
Summary: This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. It presents standard approaches for analyzing iEEG signals and discusses modern deep learning algorithms. The study shows that CNN and LSTM networks yield significantly better results, and the gradient-weighted class activation mapping algorithm can identify important iEEG signal fragments for seizure detection.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Analytical
Gul Hameed Khan, Nadeem Ahmad Khan, Muhammad Awais Bin Altaf, Qammer Abbasi
Summary: This paper proposes a trainable hybrid approach for epileptic seizure detection using a shallow autoencoder (AE) and a conventional classifier. The encoded AE representation is used as a feature vector for classifying EEG signal segments as epileptic or non-epileptic. The algorithm has low computational complexity and can be used in body sensor networks and wearable devices. Experimental results show that the proposed method achieves high accuracy and sensitivity in detecting abnormal seizure activity.
Article
Clinical Neurology
Ali A. Asadi-Pooya, Mohsen Farazdaghi
Summary: The study aimed to differentiate childhood absence epilepsy (CAE) from juvenile absence epilepsy (JAE) based on their clinical characteristics. The age at onset of seizures was found to be an important indicator for distinguishing between the two syndromes, with significant implications for treatment strategy and outcome prediction.
SEIZURE-EUROPEAN JOURNAL OF EPILEPSY
(2022)
Article
Engineering, Biomedical
Xuyang Zhao, Noboru Yoshida, Tetsuya Ueda, Hidenori Sugano, Toshihisa Tanaka
Summary: This study applies commonly used models such as LeNet, VGG, ResNet, and ViT to the EEG image classification task, and solves the problems of data imbalance and model interpretation through data augmentation and model explanation methods. The models achieve good performance in seizure detection and provide visual and quantitative information for clinical experts in diagnosis.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Young-Jin Kang, Yoojeong Noh, Min-Sung Jang, Sunyoung Park, Ju-Tae Kim
Summary: This study proposes a hierarchical level fault detection and diagnosis method that combines domain knowledge of ship engines and advanced data analysis techniques. The method extracts key features through clustering and dimension reduction, and uses regression models and dynamic thresholds to determine the engine's condition. The efficiency, reliability, and accuracy of the proposed method are verified using actual data collected by ship operators.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Veterinary Sciences
Jos Bongers, Rodrigo Gutierrez-Quintana, Catherine Elizabeth Stalin
Summary: The unpredictable nature of seizures in epileptic dogs poses challenges for caregivers, necessitating the use of alternative management strategies like seizure detection devices. These systems aim to detect seizures and provide prompt intervention to improve the overall seizure history of the dog.
FRONTIERS IN VETERINARY SCIENCE
(2022)
Review
Behavioral Sciences
Giuditta Pellino, Raffaella Faggioli, Laura Madrassi, Raffaele Falsaperla, Agnese Suppiej
Summary: This meta-analysis aimed to investigate the risk of recurrence after a first unprovoked seizure in neurotypical children without a history of neurological pathology. Factors such as focal seizure, epileptiform abnormalities on EEG, and family history of epilepsy were found to be significantly associated with an increased risk of recurrence.
EPILEPSY & BEHAVIOR
(2022)
Article
Clinical Neurology
Shuang Yu, Rima El Atrache, Jianbin Tang, Michele Jackson, Adam Makarucha, Sarah Cantley, Theodore Sheehan, Solveig Vieluf, Bo Zhang, Jeffrey L. Rogers, Iven Mareels, Stefan Harrer, Tobias Loddenkemper
Summary: This study demonstrates the detection of various seizure types through wearable devices worn on the wrist or ankle, using custom-developed deep-learning models.
Article
Automation & Control Systems
Natasa Vlahovic, Zeljko Djurovic
Summary: The article presents an algorithm design for tracking a moving object in a thermal image using a SURF descriptor and a robust Kalman filter. Tunable parameters of the robust influence function are used to balance robustness and efficiency, adapting to the current conditions of the observed scene. Outliers contaminating the data are addressed, resulting in better performance compared to standard or fixed-parameter robust Kalman filters.
INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING
(2021)
Article
Automation & Control Systems
Cuauhtemoc Acosta Lua, Stefano Di Gennaro, Antonio Navarrete Guzman, Jorge Rivera Dominguez
Summary: This paper aims to design controllers using sliding mode techniques in a discrete-time setting for a ground vehicle to track desired lateral and yaw velocities. Three controllers have been tested and compared under different conditions, showing their effectiveness in handling parameter variations and external disturbances.
ASIAN JOURNAL OF CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Slobodan Draskovic, Zeljko Durovic, Vera Petrovic
Summary: The study introduces a novel non-stationarity detection algorithm based on finite differences analysis of the processed signal, with a suitable procedure for the forgetting factor design. The algorithm demonstrates effective tracking of slow and abrupt changes in signal stationarity, with a small steady-state error.
IET SIGNAL PROCESSING
(2022)
Article
Mathematics
Riccardo Cespi, Renato Galluzzi, Ricardo A. Ramirez-Mendoza, Stefano Di Gennaro
Summary: This paper introduces an active controller for electric vehicles, combining active front steering and torque vectoring for improved driving safety. The control approach relies on an inverse optimal controller based on a neural network identifier and a discrete-time reduced-order state observer to reduce the number of required sensors, enhancing control accuracy.
Article
Medicine, Research & Experimental
Anvar Ahmedov, Yesim Ahmedov
Summary: This study examined the impact of high body mass index on self-esteem and sexual functions in obese women, and found that weight loss had a positive effect on body perception and sexual satisfaction.
CLINICAL AND EXPERIMENTAL HEALTH SCIENCES
(2021)
Article
Engineering, Electrical & Electronic
Subham Dey, Michael Defoort, Mohamed Djemai, Stefano Di Gennaro
Summary: This article introduces the concept of measure chain theory to design event-triggered controllers for systems evolving on arbitrary time domains. The event-triggering mechanism is derived from input-to-state (ISS) stable Lyapunov functions defined on measure chains. Numerical simulations illustrate the effectiveness of the designed event-triggered controllers.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2022)
Article
Automation & Control Systems
Cuauhtemoc Acosta Lua, Stefano Di Gennaro, Jean-Pierre Barbot
Summary: An Antilock Braking System (ABS) is characterized by nonlinear dynamics and parameter uncertainties. This paper proposes a super-twisting controller to overcome the challenges posed by the uncertainties. The controller is implemented in a laboratory setup mimicking a quarter car model and utilizes a super-twisting estimator to estimate the friction coefficient between the tire and the road. Experimental results show a considerable increase in the efficiency of the control system.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Energy & Fuels
Goran S. Kvascev, Zeljko M. Djurovic
Summary: This paper presents a PID controller tuning procedure based on the IFOPDT model for integrating processes in power plants. Experimental verification shows that this method achieves better results in water-level control, while also providing a safer and faster approach for parameter estimation and controller tuning.
Article
Automation & Control Systems
Mario Di Ferdinando, Pierdomenico Pepe, Stefano Di Gennaro
Summary: This article studies the stability preservation problem for locally Lipschitz nonlinear time-delay systems using emulation of continuous-time dynamic output feedback controllers. Sufficient Lyapunov-like conditions are provided to ensure the semiglobal exponential stability of the sampled-data closed-loop system by suitably fast sampling with the Euler emulation. If other emulation schemes are used, practical semiglobal exponential stability can be guaranteed with arbitrarily small final target ball by suitably fast sampling. The intersampling system behavior and time-varying sampling intervals are taken into account. The practical applicability of the provided results is demonstrated through the study of a nonlinear chemical reactor system with recycle and a glucose-insulin system.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Domenico Bianchi, Stefano Di Gennaro, Mario Di Ferdinando, Cuauhtemoc Acosta Lua
Summary: In this work, a nonlinear estimator-based robust controller is designed for the position and yaw control of a quadrotor with uncertainty estimation. It improves the dynamic behavior of the controlled system by using high-order sliding mode (HOSM) estimators to estimate perturbations that can be canceled by the control. The performance of the designed controller is evaluated using a Simcenter Amesim quadrotor based on physical models generated from experimental data in a co-simulation framework with Matlab-Simulink and FPGA implementation.
Article
Chemistry, Multidisciplinary
Jelena Kljajic, Goran Kvascev, Zeljko Durovic
Summary: This article introduces a computational model-based algorithm for nerve structure reconstruction, which simulates nerve stimulation effects to provide realistic sensory feedback for amputees. The algorithm effectively addresses the challenges of point set reconstruction and demonstrates flexibility for complex nerve structures. In addition to its application in neuroprosthetics, this model has the potential to spark innovations in biomedicine and other fields.
APPLIED SCIENCES-BASEL
(2023)
Article
Automation & Control Systems
M. Di Ferdinando, P. Pepe, S. Di Gennaro
Summary: This letter investigates the robust sampled-data stabilization of nonlinear systems and provides a methodology for the design of robust sampled-data Dynamic Output Feedback Controllers (DOFCs). The results are validated on a chemical reactor system.
IEEE CONTROL SYSTEMS LETTERS
(2022)
Article
Automation & Control Systems
Alessandro Borri, Mario Di Ferdinando, Domenico Bianchi, Pierdomenico Pepe, Stefano Di Gennaro
Summary: This letter presents a quantized sampled-data approach to the attitude control problem of ground vehicles. By combining classical nonlinear design with quantized sampled-data event-based controllers, the approach achieves tracking of prescribed trajectories and has practical stability.
IEEE CONTROL SYSTEMS LETTERS
(2022)
Article
Automation & Control Systems
M. Di Ferdinando, B. Castillo-Toledo, S. Di Gennaro, P. Pepe
Summary: This letter presents a robust quantized sampled-data controller for nonlinear systems affected by time-varying uncertainties, disturbances, and noises. It provides sufficient conditions for the existence of the proposed controller based on linear matrix inequalities. The controller considers quantization of both state measurements and input signals, and utilizes the input-to-state stability redesign technique to mitigate the effects of disturbances and observation errors. The controller achieves semi-global practical stability under suitably fast sampling and accurate quantization, as long as the observation errors do not significantly affect the robustification term and the bounds of disturbances and observation errors are known. The theory also covers the cases of time-varying sampling intervals and non-uniform quantization of input/output channels, and includes the stability analysis of the inter-sampling system behavior.
IEEE CONTROL SYSTEMS LETTERS
(2022)
Article
Automation & Control Systems
Oscar Jaramillo, Bernardino Castillo-Toledo, Stefano Di Gennaro
Summary: In this study, an impulsive observer-based control design for a class of nonlinear systems with time-varying uncertainties is proposed based on the LMI framework, with the use of local Lipschitz conditions. By utilizing sampled measurements of the system output and a time-varying Lyapunov function, sufficient conditions for the existence of the control are provided. Feasible solutions of the LMIs proposed are used to determine the observer and controller gain, showing that the approach effectively estimates and stabilizes all states both mathematically and through simulation.
IEEE CONTROL SYSTEMS LETTERS
(2021)
