Advancing Ocular Imaging: A Hybrid Attention Mechanism-Based U-Net Model for Precise Segmentation of Sub-Retinal Layers in OCT Images.

This paper presents a novel U-Net model incorporating a hybrid attention mechanism for automating the segmentation of sub-retinal layers in Optical Coherence Tomography (OCT) images. OCT is an ophthalmology tool that provides detailed insights into retinal structures. Manual segmentation of these layers is time-consuming and subjective, calling for automated solutions. Our proposed model combines edge and spatial attention mechanisms with the U-Net architecture to improve segmentation accuracy. By leveraging attention mechanisms, the U-Net focuses selectively on image features. Extensive evaluations using datasets demonstrate that our model outperforms existing approaches, making it a valuable tool for medical professionals. The study also highlights the model's robustness through performance metrics such as an average Dice score of 94.99%, Adjusted Rand Index (ARI) of 97.00%, and Strength of Agreement (SOA) classifications like "Almost Perfect", "Excellent", and "Very Strong". This advanced predictive model shows promise in expediting processes and enhancing the precision of ocular imaging in real-world applications.

Human Behavior Recognition via Hierarchical Patches Descriptor and Approximate Locality-Constrained Linear Coding.

Human behavior recognition technology is widely adopted in intelligent surveillance, human-machine interaction, video retrieval, and ambient intelligence applications. To achieve efficient and accurate human behavior recognition, a unique approach based on the hierarchical patches descriptor (HPD) and approximate locality-constrained linear coding (ALLC) algorithm is proposed. The HPD is a detailed local feature description, and ALLC is a fast coding method, which makes it more computationally efficient than some competitive feature-coding methods. Firstly, energy image species were calculated to describe human behavior in a global manner. Secondly, an HPD was constructed to describe human behaviors in detail through the spatial pyramid matching method. Finally, ALLC was employed to encode the patches of each level, and a feature coding with good structural characteristics and local sparsity smoothness was obtained for recognition. The recognition experimental results on both Weizmann and DHA datasets demonstrated that the accuracy of five energy image species combined with HPD and ALLC was relatively high, scoring 100% in motion history image (MHI), 98.77% in motion energy image (MEI), 93.28% in average motion energy image (AMEI), 94.68% in enhanced motion energy image (EMEI), and 95.62% in motion entropy image (MEnI).

Improving APT Systems' Performance in Air via Impedance Matching and 3D-Printed Clamp.

This paper presents a study on improving the performance of the acoustic piezoelectric transducer system in air, as the low acoustic impedance of air leads to suboptimal system performance. Impedance matching techniques can enhance the acoustic power transfer (APT) system's performance in air. This study integrates an impedance matching circuit into the Mason circuit and investigates the impact of fixed constraints on the piezoelectric transducer's sound pressure and output voltage. Additionally, this paper proposes a novel equilateral triangular peripheral clamp that is entirely 3D-printable and cost-effective. This study analyses the peripheral clamp's impedance and distance characteristics and confirms its effectiveness through consistent experimental and simulation results. The findings of this study can aid researchers and practitioners in various fields that employ APT systems to improve their performance in air.

On Machine Learning in Clinical Interpretation of Retinal Diseases Using OCT Images.

Optical coherence tomography (OCT) is a noninvasive imaging technique that provides high-resolution cross-sectional retina images, enabling ophthalmologists to gather crucial information for diagnosing various retinal diseases. Despite its benefits, manual analysis of OCT images is time-consuming and heavily dependent on the personal experience of the analyst. This paper focuses on using machine learning to analyse OCT images in the clinical interpretation of retinal diseases. The complexity of understanding the biomarkers present in OCT images has been a challenge for many researchers, particularly those from nonclinical disciplines. This paper aims to provide an overview of the current state-of-the-art OCT image processing techniques, including image denoising and layer segmentation. It also highlights the potential of machine learning algorithms to automate the analysis of OCT images, reducing time consumption and improving diagnostic accuracy. Using machine learning in OCT image analysis can mitigate the limitations of manual analysis methods and provide a more reliable and objective approach to diagnosing retinal diseases. This paper will be of interest to ophthalmologists, researchers, and data scientists working in the field of retinal disease diagnosis and machine learning. By presenting the latest advancements in OCT image analysis using machine learning, this paper will contribute to the ongoing efforts to improve the diagnostic accuracy of retinal diseases.

Deep Learning-Based Wrist Vascular Biometric Recognition.

The need for contactless vascular biometric systems has significantly increased. In recent years, deep learning has proven to be efficient for vein segmentation and matching. Palm and finger vein biometrics are well researched; however, research on wrist vein biometrics is limited. Wrist vein biometrics is promising due to it not having finger or palm patterns on the skin surface making the image acquisition process easier. This paper presents a deep learning-based novel low-cost end-to-end contactless wrist vein biometric recognition system. FYO wrist vein dataset was used to train a novel U-Net CNN structure to extract and segment wrist vein patterns effectively. The extracted images were evaluated to have a Dice Coefficient of 0.723. A CNN and Siamese Neural Network were implemented to match wrist vein images obtaining the highest F1-score of 84.7%. The average matching time is less than 3 s on a Raspberry Pi. All the subsystems were integrated with the help of a designed GUI to form a functional end-to-end deep learning-based wrist biometric recognition system.

An efficient framework for automated screening of Clinically Significant Macular Edema.

The present study proposes a new approach to automated screening of Clinically Significant Macular Edema (CSME) and addresses two major challenges associated with such screenings, i.e., exudate segmentation and imbalanced datasets. The proposed approach replaces the conventional exudate segmentation based feature extraction by combining a pre-trained deep neural network with meta-heuristic feature selection. A feature space over-sampling technique is being used to overcome the effects of skewed datasets and the screening is accomplished by a k-NN based classifier. The role of each data-processing step (e.g., class balancing, feature selection) and the effects of limiting the region of interest to fovea on the classification performance are critically analyzed. Finally, the selection and implication of operating points on Receiver Operating Characteristic curve are discussed. The results of this study convincingly demonstrate that by following these fundamental practices of machine learning, a basic k-NN based classifier could effectively accomplish the CSME screening.

Quality and content analysis of fundus images using deep learning.

Automatic retinal image analysis has remained an important topic of research in the last ten years. Various algorithms and methods have been developed for analysing retinal images. The majority of these methods use public retinal image databases for performance evaluation without first examining the retinal image quality. Therefore, the performance metrics reported by these methods are inconsistent. In this article, we propose a deep learning-based approach to assess the quality of input retinal images. The method begins with a deep learning-based classification that identifies the image quality in terms of sharpness, illumination and homogeneity, followed by an unsupervised second stage that evaluates the field definition and content in the image. Using the inter-database cross-validation technique, our proposed method achieved overall sensitivity, specificity, positive predictive value, negative predictive value and accuracy of above 90% when tested on 7007 images collected from seven different public databases, including our own developed database-the UoA-DR database. Therefore, our proposed method is generalised and robust, making it more suitable than alternative methods for adoption in clinical practice.

Root locus analysis and design of the adaptation process in active noise control.

This paper applies root locus theory to develop a graphical tool for the analysis and design of adaptive active noise control systems. It is shown that the poles of the adaptation process performed in these systems move on typical trajectories in the z-plane as the adaptation step-size varies. Based on this finding, the dominant root of the adaptation process and its trajectory can be determined. The first contribution of this paper is formulating parameters of the adaptation process root locus. The next contribution is introducing a mechanism for modifying the trajectory of the dominant root in the root locus. This mechanism creates a single open loop zero in the original root locus. It is shown that appropriate localization of this zero can cause the dominant root of the locus to be pushed toward the origin, and thereby the adaptation process becomes faster. The validity of the theoretical findings is confirmed in an experimental setup which is implemented using real-time multi-threading and multi-core processing techniques.

On the stability of adaptation process in active noise control systems.

The stability analysis of the adaptation process, performed by the filtered-x least mean square algorithm on weights of active noise controllers, has not been fully investigated. The main contribution of this paper is conducting a theoretical stability analysis for this process without utilizing commonly used simplifying assumptions regarding the secondary electro-acoustic channel. The core of this analysis is based on the root locus theory. The general rules for constructing the root locus plot of the adaptation process are derived by obtaining root locus parameters, including start points, end points, asymptote lines, and breakaway points. The conducted analysis leads to the derivation of a general upper-bound for the adaptation step-size beyond which the mean weight vector of the active noise controller becomes unstable. Also, this analysis yields the optimum step-size for which the adaptive active noise controller has its fastest dynamic performance. The proposed upper-bound and optimum values apply to general secondary electro-acoustic channels, unlike the commonly used ones which apply to only pure delay channels. The results are found to agree very well with those obtained from numerical analyses and computer simulation experiments.

Time-frequency evaluation of segmentation methods for neonatal EEG signals.

In order to analyse non-stationary signals, like neonatal EEG, it is sometimes easier to segment signals into pseudo-stationary segments. An evaluation was performed on three previously proposed EEG segmentation methods in order to determine which method is most suited to neonatal EEG analysis. The three methods evaluated are spectral error measurement (SEM), generalised likelihood ratio (GLR) and non-linear energy operator (NLEO). A windowed version of NLEO was also tested in an attempt to minimise the effect of any temporary transients on the segmentation algorithm. The results from the segmentation algorithm were compared with the time-frequency distribution of the original signal to determine the appropriateness of the segments. It was found that GLR was the most appropriate segmentation method, and that the windowed version of the NLEO method performed better than the non-windowed version, both of which are less computationally expensive than the other methods.