Polysomnography, the gold standard of sleep measurement, is a time-intensive, costly, and rather invasive procedure. Using under-bed pressure sensor arrays data simultaneously recorded with standard polysomnography, t...
Polysomnography, the gold standard of sleep measurement, is a time-intensive, costly, and rather invasive procedure. Using under-bed pressure sensor arrays data simultaneously recorded with standard polysomnography, this study demonstrates that deep learning can be used to classify body position and differentiate sleep from wake. All measurements were performed in people with suspected sleep disorders referred for clinical assessments at a sleep laboratory. To perform the classification tasks, we used supervised learning and temporal convolution networks. Performance was assessed with leave-one-out cross validation on 84 participants for body position classification and 70 participants for sleep-wake classification. Results demonstrate that a pressure sensor array placed under the mattress with less than 100 sensors can outperform previous sleep-wake detection methods and is competitive with previous methods for body position classification. Our pressure sensor arrays differ from the mats used in previous work as they use significantly less sensors and are located under the mattress, making them less obtrusive. This tool has great potential as a cost-efficient mean of assessing sleep while reducing patient burden and the workload of specialized staff.
In this paper, we analyze the coordination problem of groups of aerial robots for assembly applications. With the enhancement of aerial physical interaction, construction applications are becoming more and more popula...
详细信息
ISBN:
(数字)9781728142784
ISBN:
(纸本)9781728142791
In this paper, we analyze the coordination problem of groups of aerial robots for assembly applications. With the enhancement of aerial physical interaction, construction applications are becoming more and more popular. In this domain, the multi-robot solution is very interesting to reduce the execution time. However, new methods to coordinate teams of aerial robots for the construction of complex structures are required. In this work, we propose an assembly planner that considers both assembly and geometric constraints imposed by the particular desired structure and employed robots, respectively. An efficient graph representation of the task dependencies is employed. Based on this framework, we design two assembly planning algorithms that are robust to robot failures. The first is centralized and communication-based. The second is distributed and communication-less. The latter is a solution for scenarios in which the communication network is not reliable. Both methods are validated by numerical simulations based on the assembly scenario of Challenge 2 of the robotic competition MBZIRC2020.
In this paper, we present a novel method (Contrast Source Inversion - Electric Properties Tomography or CSI-EPT) to dielectric imaging of biological tissue using so-called B 1 + data measurable by Magnetic Resonance ...
详细信息
In this paper, we present a novel method (Contrast Source Inversion - Electric Properties Tomography or CSI-EPT) to dielectric imaging of biological tissue using so-called B 1 + data measurable by Magnetic Resonance Imaging (MRI) systems. Integral representations for the electromagnetic field quantities are taken as a starting point and we follow an iterative contrast source inversion approach to retrieve the dielectric tissue parameters from measured field data. Numerical results illustrate the performance of the method and show that reliable results are produced near tissue boundaries as opposed to the currently used methods. Fine structures can be resolved as well and since CSI-EPT reconstructs the electric field strength inside a scanning region of interest, it is also a promising candidate to determine the patient-specific SAR deposition during an MRI scan.
This contribution shows how a resonance-induced extraordinary acoustic transmission through a phononic crystal structure can be used as sensor for liquid properties. The phononic crystal consists of a metal plate with...
详细信息
ISBN:
(纸本)9781424492909
This contribution shows how a resonance-induced extraordinary acoustic transmission through a phononic crystal structure can be used as sensor for liquid properties. The phononic crystal consists of a metal plate with a periodic array of holes. Ultrasound propagates in a way that the incidence direction of sound is perpendicular to the plate. A characteristic transmission peak has been found to strongly depend on liquid sound velocity. The respective peak maximum frequency serves as measure for liquid composition. Numerical calculations based on FDTD and FEA reveal more insides to the propagation characteristics, in particular the presence of specific plate modes. Experimental investigations using a laser vibrometer and the Schlieren method support the theoretical findings.
A thermo-hydrodynamic lubrication (THL) theory is applied to journal bearings that support large-sized high-speed rotary machineries and it is confirmed that the maximum pad surface temperature under operation is belo...
详细信息
This paper presents a slip ratio controller using sliding mode control for electric vehicle with parameter variations, which is important in obtaining desired vehicle motion in acceleration. A robust sliding mode cont...
详细信息
ISBN:
(纸本)9781467322591
This paper presents a slip ratio controller using sliding mode control for electric vehicle with parameter variations, which is important in obtaining desired vehicle motion in acceleration. A robust sliding mode controller is designed to obtain the maximum driving force by maintaining the value of slip ratio at a reference value. The simulations for one wheel model of vehicle under variations in mass of vehicle and road conditions are performed and analyzed to show the effectiveness of the proposed controller.
Various e-learning systems that support remote education have been developed utilizing information technology. However, it is still not easy to communicate smoothly and to evaluate how well users of such systems have ...
详细信息
ISBN:
(纸本)9784907764388
Various e-learning systems that support remote education have been developed utilizing information technology. However, it is still not easy to communicate smoothly and to evaluate how well users of such systems have understood. We focus on communication support with make-believe play and propose a real-space sharing edutainment system that allows its users to enjoy make-believe play. We develop a prototype of the system in which we introduce distinctive CG characters and communication support functions to enhance user communication through a virtual environment. Finally, we confirm the effectiveness of the system through an evaluation experiment.
Visible light communication (VLC) is a rapidly growing wireless communication technology for the Internet of Things (IoT) that offers high data rates and low latency, making it ideal for massive connectivity. Efficien...
Visible light communication (VLC) is a rapidly growing wireless communication technology for the Internet of Things (IoT) that offers high data rates and low latency, making it ideal for massive connectivity. Efficient resource allocation is essential in VLC networks to minimize inter-symbol and cochannel interferences, which can greatly improve network performance and user satisfaction. This paper focuses on an indoor IoT-based VLC system that utilizes photodetectors (PDs) on users’ cell phones as receivers, with the goal of maximizing system performances and reducing power consumption by selectively activating some PDs while deactivating others. However, this objective presents a challenge due to the inherent non-convex nature of the multi-objective optimization problem, which cannot be solved by analytical means. To address this, we propose an enhanced Aquila optimization (EAO) scheme that improves upon the Aquila Optimizer (AO) by incorporating a fitness distance balance (FDB) function. We evaluate our proposed EAO in various scenarios under different settings, considering both capacity and fairness metrics. Through simulations, we demonstrate the effectiveness of our approach and its superiority over classical algorithms such as Aquila Optimizer (AO), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO) in finding the optimal solution. Our results confirm that the proposed EAO algorithm can efficiently optimize the system capacity and ensure fairness among all users, providing a promising solution for indoor VLC systems.
This paper presents the value of good attributes in carrying out the package classification process Furthermore, attribute selection results can be of value in determining one type of data packet traffic. In obtaining...
This paper presents the value of good attributes in carrying out the package classification process Furthermore, attribute selection results can be of value in determining one type of data packet traffic. In obtaining the results (data) this study uses several stages of Data Capture, Feature Extraction and Feature Selection, but in this study only focuses on the process of feature selection using the gain and Entropy Information and Naïve Bayes algorithm. The testing process by dividing raw data into parts is 70 per cent for Training data and 30 per cent for testing data. The total data used is 6632, so for the training data obtained is 4642, while the data for testing is 1990. The results obtained are for the https data package type is 9 attributes, while for the HTTP data is 10 attributes. For further research can be added using another classification method as a comparison of data.
With the substantial increase in Cybercrime, the pressing need for effective solutions in the light of the rising amount of corporate financial losses, is a concern f or many researchers. The widespread adoption of ec...
详细信息
ISBN:
(数字)9798350362633
ISBN:
(纸本)9798350362640
With the substantial increase in Cybercrime, the pressing need for effective solutions in the light of the rising amount of corporate financial losses, is a concern f or many researchers. The widespread adoption of ecommerce and diverse online payment methods has contributed to the surge in a major form of cybercrime—online payment fraud. This further highlights the critical need to control and reduce the widespread danger of fraudulent behaviour on the internet. However, predicting online payment fraud is difficult as fraudsters are constantly changing their tactics, transactions happen quickly and in large volumes, transactions involve different regions and countries, stolen data is often used and other factors. Our goal is to improve the accuracy and usability of online payment fraud prediction through the use of machine learning. A well-established and widely recognized dataset specifically designed for studying online payment fraud was used. The six proposed algorithms trained and tested were (SVM), Decision Tree, Naïve Bayes, Random Forest, (KNN) and Logistic Regression. After rigorous testing, Decision Tree presented the highest accuracy in performance of 98.58%. However, as ten-fold cross validation was implemented on the dataset, Decision Tree suffered a loss while Random Forest had an increase in accuracy making it the best model with accuracy of 98.47%. As shown in this paper, machine learning has proven to be a reliable and ever-evolving approach for the prediction of Online Payment Fraud and results can be further improved in collaboration with financial and cybercrime specialists.
暂无评论