The local averaging technique adopted for the construction of 2D histogram in Otsu's method fails to preserve the edge information. Further, the consideration of the diagonal pixels only results in the loss of inf...
详细信息
The local averaging technique adopted for the construction of 2D histogram in Otsu's method fails to preserve the edge information. Further, the consideration of the diagonal pixels only results in the loss of information. These make the 2D Otsu method of multi-level thresholding inefficient to retain the spatial correlation information. Although the computation of 2D histogram based on gray gradient information is a better way to threshold an image, it faces a backlash due to the high magnitude peaks. To solve these problems, we suggest a new normalized local variance (NLV) method for constructing 2D histogram using the local variance followed by a novel evolutionary row class entropy (ERCE) method for optimal multi-level image thresholding, which tries to preserve maximum spatial information through normalization of the local variance. A new optimization technique called hybrid Adaptive Cuckoo search-squirrel search algorithm (ACS-SSA) is also introduced. A new fitness function is suggested. The standard CEC 2005 benchmark test functions are used to validate the performance of our proposed ACS-SSA technique. The optimum threshold values obtained are used to segment 100 slices of T-2 weighted axial brain MR images (taken from the Harvard Medical School database). Several performance evaluation metrics are computed to compare the performance of our method with the state-of-the-art methods. The analysis of the results shows that ERCE method outperforms other methods. This method may set a new direction in the multilevel image thresholding research.
Leak location using cross-correlation of acoustic signals collected by acceleration sensors is easily disturbed by the environmental noises resulting in inaccurate identification of its location, especially at low SNR...
详细信息
Leak location using cross-correlation of acoustic signals collected by acceleration sensors is easily disturbed by the environmental noises resulting in inaccurate identification of its location, especially at low SNR. Aiming at this problem, an adaptive signal denoising algorithm based on squirrel search algorithm referred to as improved variational mode decomposition (SSA-VMD) is proposed to improve the accuracy of leak location. First, a fitness function based on the ratio of the envelope entropy to the kurtosis of the power spectrum of intrinsic mode functions (IMF) is established. Second, the leak signal is decomposed into IMFs using VMD with optimized parameters searched using the squirrel search algorithm. Then, a new method combining kurtosis analysis with crest factor and impulse factor is applied to select effective IMF components to reconstruct the leak signal at low SNR effectively. Finally, location search based on cross-correlation is performed using the reconstructed signal. Simulation and experiments results show that the proposed method can effectively suppress noise and reduce the error of leak location. The average relative leak location error of this method is within 2%, which proves the feasibility and effectiveness of the proposed adaptive signal noise reduction method.
In recent years, due to the reduction of non-renewable resources and increasing environmental pollution, exploiting of renewable energy sources is a good solution. Wind turbines and fuel cells are appropriate sources ...
详细信息
In recent years, due to the reduction of non-renewable resources and increasing environmental pollution, exploiting of renewable energy sources is a good solution. Wind turbines and fuel cells are appropriate sources of renewable energy. On the other hand, FACTS devices are used to maximize the power injection capability to supply electricity demand and minimizing voltage deviation, power losses and operational cost of power system. Generalized Unified Power Flow Controller (GUPFC) and Interline Power Flow Controller (IPFC) are two kinds of the best FACTS devices. GUPFC can adjust the voltage and the power flow in the connected transmission lines synchronically. IPFC is capable of minimizing voltage drops and reactive power of line, enhancing the system stability against the dynamic disturbance, and load ability of the system. In this paper, with the aim of minimizing the cost function and improving the performance of system wind farm and fuel cell are integrated with power system in the presence of GUPFC and IPFC via power injection model. Then, using a new algorithm integrated with the Newton-Raphson method, the best place for installing IPFC and GUPFC is funded. This algorithm is improved squirrelsearch which is inspired by nature. On the other hand, the optimum range of parameter (value and angle of injected voltage) is determined with the aim of achieving the best performance of system. Ultimately, the proposed method has been applied in IEEE 57 Bus system in the presence of wind turbine, fuell cell and DG to test the effect of M-FACTS. The result confirms that the new method improved voltage profile, minimized the operational cost and power losses of system. Final, it is concluded that the performance of GUPFC is better than the IPPFC. (C) 2020 Elsevier Ltd. All rights reserved.
Diabetes is a potentially sight-threatening condition that can lead to blindness if left undetected. Timely diagnosis of diabetic retinopathy, a persistent eye ailment, is critical to prevent irreversible vision loss....
详细信息
Diabetes is a potentially sight-threatening condition that can lead to blindness if left undetected. Timely diagnosis of diabetic retinopathy, a persistent eye ailment, is critical to prevent irreversible vision loss. However, the traditional method of diagnosing diabetic retinopathy through retinal testing by ophthalmologists is labor-intensive and time-consuming. Additionally, early identification of glaucoma, indicated by the Cup-to-Disc Ratio (CDR), is vital to prevent vision impairment, yet its subtle initial symptoms make timely detection challenging. This research addresses these diagnostic challenges by leveraging machine learning and deep learning techniques. In particular, the study introduces the application of Restricted Boltzmann Machines (RBM) to the domain. By extracting and analyzing multiple features from retinal images, the proposed model aims to accurately categorize anomalies and automate the diagnostic process. The investigation further advances with the utilization of a U-network model for optic segmentation and employs the squirrel search algorithm (SSA) to fine-tune RBM hyperparameters for optimal performance. The experimental evaluation conducted on the RIM-ONE DL dataset demonstrates the efficacy of the proposed methodology. A comprehensive comparison of results against previous prediction models is carried out, assessing accuracy, cross-validation, and Receiver Operating Characteristic (ROC) metrics. Remarkably, the proposed model achieves an accuracy value of 99.2% on the RIM-ONE DL dataset. By bridging the gap between automated diagnosis and ophthalmological practice, this research contributes significantly to the medical field. The model's robust performance and superior accuracy offer a promising avenue to support healthcare professionals in enhancing their decision -making processes, ultimately improving the quality of care for patients with retinal anomalies.
An affective state of a learner in E-learning has gained enormous interest. The prediction of the emotional state of a learner can enhance the outcome of learning by including designated mediation. Many techniques are...
详细信息
An affective state of a learner in E-learning has gained enormous interest. The prediction of the emotional state of a learner can enhance the outcome of learning by including designated mediation. Many techniques are developed for anticipating emotional states using video, audio, and bio-sensors. Still, examining video, and audio will not confirm secretiveness and is exposed to security issues. Here the creator devises a fusion technique, to be specific squirrelsearch and Rider optimization-grounded Deep LSTM for affect prediction. The Deep LSTM is trained to exercise the new fusion SS-ROA. Then, the SS-ROA-grounded Deep LSTM classifies the states like frustration, confusion, engagement, wrathfulness, and so on. It is based on the interaction log data of the E-learner. In conclusion, the course and student ID, predicted state, test marks, and course completion status are taken as result information to find out the correlations. The new algorithm gives the best performance in comparison to other present methods with the highest prediction accurateness of 0.962 and the most noteworthy connection of 0.379 respectively. After discovering affective states, students may get the advantage of getting real comments from a teacher for improving one's performance during learning. However, such systems should also give feedback about the learner's affective state or passion because it greatly affects the student's encouragement toward better learning.
In order to extract complete leaf image contours of cowpea diseases under natural environment, cowpea disease leaf image segmentation method combining squirrel search algorithm and Kmeans clustering algorithm was prop...
详细信息
ISBN:
(纸本)9781450397148
In order to extract complete leaf image contours of cowpea diseases under natural environment, cowpea disease leaf image segmentation method combining squirrel search algorithm and Kmeans clustering algorithm was proposed. Firstly, the images were converted from RGB color space to HSV color space; then the squirrel search algorithm was used to obtain the initial cluster centers to improve the Kmeans algorithm for image segmentation; morphological operations were used to smooth the images; finally, after removing small area noise, the Canny algorithm was used to extract the complete cowpea diseased leaf outline. The experimental results show that the cowpea diseased leaf images segmented by the algorithm used in this paper have smooth edges and can effectively segment cowpea leaves, which provides a basis for the application of computer vision in cowpea disease identification.
暂无评论