Remote sensing object detection plays a major role in satellite imaging and is required in various scenarios such as transportation, forestry, and the ocean. Deep learning techniques provide efficient performance in remote sensing object detection. The existing techniques have the limitations of data imbalance, overfitting, and lower efficiency in detecting small objects. This research proposes the spiral search grasshopper (SSG) optimization technique to increase the exploitation in feature selection. Augmentation is applied in input images to generate more images, and this helps to train the model and reduces data imbalance problems. The VGG-19 and ResNet50 model is applied for feature extraction, and this helps to extract deep features to represent objects. The SSG feature selection technique increases the exploitation and select unique features for object detection that helps to overcome the data imbalance and overfitting problem. The SSG feature selection model helps to balance the exploration and exploitation that escape from the local optima trap. The SSG model has 82.45% mAP, the SSD model has 52.6% mAP, and the MPFP-Net model has 80.43% mAP.
15 July 2025 in e-Prime - Advances in Electrical Engineering, Electronics and Energy
Manual diagnosis of tumors on magnetic resonance images (MRIs) entails more time and doing so increases the risk of human error and incorrect tumor type identification and classification. Cells develop quickly and uncontrollably, which causes brain tumors and may cause death unless handled in the beginning stages. Therefore, a transfer learning framework for brain tumor classification is presented to simplify the task of healthcare professionals by automating tough medical processes. MRI image analysis was done on a publicly available dataset from Kaggle. The proposed method is implemented on VGG16, ResNet50, EfficientNetB0, and U-Net architectures. Training accuracy and test accuracy of all these four neural architectures compared and results that U-Net performs better in the classification of brain tumors compared to the other networks.
In the case of sensorineural hearing loss, the hearing aid needs to amplify the audio signal selectively based and frequency and very sensitively based on the hearing threshold. In this paper, we proposed to implement a new 16-point Discrete Cosine Transform (DCT) base delay efficient algorithm for hearing aid applications. This proposed algorithm gives better matching error with smaller delay due to uniform resampling and recursive modification of hearing thresholds in an audiogram. Delay and matching error are the main parameters in analysing the performance of the hearing aid algorithm. Four audiograms with various degrees of hearing loss are used to test the suggested method. When compared to filter bank approaches, the suggested algorithm has a lower matching error and a faster response time. The proposed algorithm is implemented on a TMS320C5505 DSP processor to validate the simulation results.
1 July 2022 in Indonesian Journal of Electrical Engineering and Computer Science
This paper presents the improvements in the combined solution for the noise estimation and the speech enhancement in digital hearing aids in time domain. This study focuses on the single channel statistical temporal speech enhancement using adaptive Wiener filtering. In this technique, the noise is updated based on the short-term uncleaned signal to noise threshold ratio (ST-USNTR) of the frame. It works best if and only if the back ground noise level is low compared to that of speech of interest. We considered the time domain algorithms in order to consider the time varying nature of speech signal. The performance of the proposed algorithm is evaluated for speech signal with seven ty pes of noises and three signal to noise ratios (SNR) levels in each type of noise. From the results, it is clear that the basic level of adaptive speech enhancement is obtained using statistical parameters of noisy speech without the need for reference input.