Computer-aided diagnosis (CAD) helps physicians in tumors' identification into various biomedical tissues, breast is one. Through the last few years, image classification techniques based on deep learning (DL), ha...
详细信息
ISBN:
(纸本)9798350335569
Computer-aided diagnosis (CAD) helps physicians in tumors' identification into various biomedical tissues, breast is one. Through the last few years, image classification techniques based on deep learning (DL), have obtained noticeable success in differentiating breast ultrasound images automatically. More researches, concerned with breast cancer detection, are representing the output as a black and white segmented image (mask) or a selected region on the breast ultrasound image which will in role submitted to physicians to help them in making a better diagnosis decision. Our paper represents the second step. In this paper: ten pre-trained Convolutional neural networks (CNNs) classification models (ResNet18, ResNet50, ResNet101, InceptionV3, InceptionResNetV2, GoogleNet, MobilenetV2, SqueezeNet, DenseNet201, and Xception) have been utilized to classify segmented breast ultrasound images by transfer learning (TL). A dataset of 375 breast ultrasound images' masks (ground truths), divided as 125 normal, 125 benign, and 125 malignant, has been utilized in training and validation. A dataset of 255 breast ultrasound images' ground truths (masks), divided as 85 normal, 85 benign, and 85 malignant, has been utilized to evaluate the classification accuracy of each CNN model after TL process. Each CNN model's evaluation (over the 255 breast ultrasound images' masks) has represented different accuracy values evaluated. The best accuracy value was for ResNet50 with an accuracy of 97.25 %. The proposed classification scheme for segmented ultrasound images can be regarded as a step that may help in an automatic breast cancer diagnosis system. The produced trained ten CNNs models in this study (input image size: 128 by 128 by 3) are not in their optimum case but it can be considered as a start to any researcher interests in studying the classification of segmented binary images of breast cancers, the ten produced CNNs models are available to researchers at: https://***/
Problem: People with Down Syndrome must be served special because they have an intellectual disability with abnormality in memory and learning, so, creating a model for DS recognition may provide safe services to them...
详细信息
This paper considers the problem of static output feedback (SOF) synthesis for linear time-invariant (LTI) systems. Static output feedback, and more generally structured controller synthesis, is of special interest to...
详细信息
This paper considers the problem of static output feedback (SOF) synthesis for linear time-invariant (LTI) systems. Static output feedback, and more generally structured controller synthesis, is of special interest to any industrial application where a reduced-order controller is desired, e.g., high-order systems, or a specific structure is to be imposed, i.e., distributed/decentralised control. A simple two-step process is proposed, solving one Riccati equation and one optimisation problem with linear matrix inequality (LMI) constraints, enabled via a dilation using the distance to the full-state feedback optimum gain. Numerical analysis shows considerable computational savings, with negligible differences in the performance, when compared to current iterative methods.
This paper introduces a rigid-flexible coupling wearable exoskeleton robot for lower limb,which is designed in light of gait biomechanics and beneficial for low limb movement disorders by implementing gait *** rationa...
详细信息
This paper introduces a rigid-flexible coupling wearable exoskeleton robot for lower limb,which is designed in light of gait biomechanics and beneficial for low limb movement disorders by implementing gait *** rationality of the proposed mechanism is shown with the implementation of the dynamic simulation through MSC *** the purposes of lightweight,the exoskeleton mechanism is optimized through finite element *** can be concluded from performance evaluation experiment,the mechanism has certain advantages over existing exoskeleton robots,namely,comfortable,lightweight,low cost,which can be utilized for rehabilitation training in medical institutions or as a daily-walking ancillary equipment for patients.
This paper considers the problem of structured observer synthesis for linear-time-invariant (LTI) systems. The importance of the problem is demonstrated through two motivational examples: utilizing high-fidelity black...
详细信息
ISBN:
(数字)9798350374261
ISBN:
(纸本)9798350374278
This paper considers the problem of structured observer synthesis for linear-time-invariant (LTI) systems. The importance of the problem is demonstrated through two motivational examples: utilizing high-fidelity black-box models as part of observers, and anti-windup gain design. The problem is connected with its control counterpart: static output feedback, and the process is illustrated through the design of an anti-windup gain for a multi-variable PID controller. A numerical example shows how the resulting closed-loop system converges faster than a recent method in the literature, with the added benefit of solving the problem with a non-iterative method, which decreases the computational effort.
The Common Spatial Patterns (CSP) algorithm has shown great efficacy in extracting features for Brain-Computer Interfaces (BCIs), particularly in motor imagery BCIs. However, CSP performs poorly when dealing with limi...
详细信息
ISBN:
(数字)9798350378009
ISBN:
(纸本)9798350378016
The Common Spatial Patterns (CSP) algorithm has shown great efficacy in extracting features for Brain-Computer Interfaces (BCIs), particularly in motor imagery BCIs. However, CSP performs poorly when dealing with limited labeled data, which leads to long calibration time at the beginning of each session. To overcome this challenge, we leverage source data, i.e., labeled data from other subjects, to transfer knowledge across subjects. This work proposes a novel approach termed Scaled and Warped CSP-based Transfer Learning (SW-CSP-TL). This method aligns source data with the temporal and amplitude structure of target data before computing CSP filters, ensuring optimization for capturing discriminative features relevant to the target domain. We evaluate the proposed SW-CSP-TL algorithm using the publicly available dataset 2a from BCI Competition IV and compare its performance with that of the classical CSP algorithm and the transfer learning CSP algorithm (CSP-TL) without amplitude scaling and temporal warping. Our algorithm exhibits superior performance particularly when the training data size is relatively small. Results demonstrate that for 5 and 15 training trials per class from the target session, SW-CSP-TL outperformed the classical CSP by an average of 10%, and 8%, respectively.
The transition towards electric aircraft is particularly challenging due to the relatively low specific energy densities of electrical energy storage systems. If electric aircraft are to be realised, flight paths must...
详细信息
ISBN:
(数字)9783907144107
ISBN:
(纸本)9798331540920
The transition towards electric aircraft is particularly challenging due to the relatively low specific energy densities of electrical energy storage systems. If electric aircraft are to be realised, flight paths must be optimised to take advantage of the unique features of electric propulsion systems. In this paper, the problem of determining the optimal flight trajectories for aircraft powered by a combination of a fuel cell stack and lithium-ion battery pack is considered. Particular emphasis is given to the role of the battery pack's temperature and in-flight charging requirements on the results. Solutions that minimise the fuel consumption and the flight time are first considered. For both cases, the optimal solution was observed to discharge the battery during the climb with only minimal in-flight recharging of the battery by the fuel cell. A scenario that requires a fast climb and descent and the battery to be charged upon arrival was identified and shown to lead to an oscillatory profile for optimal in-flight charging. These results demonstrate the potential of solving optimal control problems to generate tailored electric aircraft trajectories.
The paper presents a comprehensive analysis of the design parameters, operational characteristics and performance evaluation of a modular step-down DC-DC converter. The converter is engineered for applications demandi...
详细信息
This paper explores the feasibility of using a propulsion-only control scheme for a high-altitude long-endurance UAV. This approach enables aircraft to operate even in the face of total control surface failures. A sli...
详细信息
ISBN:
(数字)9798350353686
ISBN:
(纸本)9798350353693
This paper explores the feasibility of using a propulsion-only control scheme for a high-altitude long-endurance UAV. This approach enables aircraft to operate even in the face of total control surface failures. A sliding mode scheme is used for the control law due to its invariance to matched uncertainty, and the reduced control authority is accommodated via a model-reference method. Similar performance compared to the fault-free case has been achieved in terms of following altitude and heading commands, in a numerical simulation using a 6-DOF nonlinear model.
There has a been a growing interest in virtual laboratories as a supplement to hardware laboratories in supporting student learning and experience. This paper focuses specifically on virtual laboratories built using t...
详细信息
ISBN:
(数字)9798350374261
ISBN:
(纸本)9798350374278
There has a been a growing interest in virtual laboratories as a supplement to hardware laboratories in supporting student learning and experience. This paper focuses specifically on virtual laboratories built using the MATLAB environment and highlights some recent developments. Specifically, these virtual laboratories aim to give users an overview of the core content of an entire 1st course in control in a single virtual laboratory interface. This paper highlights two such laboratories and shows how they can be used to supplement other learning resources and activities.
暂无评论