Retinal vessel segmentation underpins computer-assisted screening and monitoring of ocular and systemic disease. While encoder–decoder networks such as U-Net are widely used, their behavior is strongly shaped by the training objective. This work presents a controlled empirical study of loss functions for vessel segmentation using a U-Net architecture that employs strided convolutions in the encoder, together with a consistent pre-processing pipeline based on morphological enhancement and principal component analysis. We compare cross-entropy, weighted cross-entropy, and Dice losses on the DRIVE and STARE datasets under identical settings, reporting pixel-wise and overlap-based measures to reflect both detection and spatial agreement. The configuration with weighted cross-entropy provides a balanced outcome, achieving sensitivity and accuracy of 0.873 and 0.969 on DRIVE, and 0.821 and 0.961 on STARE. Rather than proposing architectural novelty, the contribution of this study is a reproducible data-driven comparison that clarifies the tradeoffs each loss imposes on recall, specificity, and boundary fidelity, offering practical guidance for selecting objectives in retinal vessel segmentation.

Recent advances in robotics have increased the reliance on networked middleware, such as Robot Operating System 2 (ROS 2), for orchestrating Unmanned Ground Vehicles (UGVs) in dynamic and safety-critical settings. However, this distributed architecture exposes platforms like the Turtlebot4 to Denial-of-Service (DoS) vulnerabilities, which can incapacitate critical sensor and control messages. This paper presents a deep learning-based framework for near-real-time detection of DoS attacks in a ROS 2-enabled UGV. A novel adversarial script, generated using a Large Language Model (LLM), systematically floods targeted ROS 2 topics to simulate genuine network-based intrusions. The resulting dataset, comprising both benign and adversarial conditions, undergoes rigorous cleaning, feature engineering, and one-second binning to capture key metrics such as burstiness and topic entropy. Four neural architectures are evaluated: a Multilayer Perceptron (MLP), a Long Short-Term Memory (LSTM), a 1D Convolutional Neural Network (CNN), and an unsupervised Variational Autoencoder (VAE). Experimental findings show that the MLP, leveraging the engineered features, achieves 97% accuracy and an AUC of 0.998 in classifying DoS traffic, outperforming sequence-based models and the VAE. Integrated Gradients analysis further reveals that metrics reflecting abrupt message spikes and imbalanced topic usage are highly discriminative of malicious behavior. These results underscore the impact of domain-specific feature design in safeguarding ROS 2-based robotic platforms against emerging cyber threats.

This research presents the On-POP-Overlay architecture, a novel contribution to Multi-site Software-Defined Data Centers (SDDC). Our work contrasts this new architecture with the established On-Premises-Overlay, focusing on their deployment in SD-WAN settings. Central to our investigation is the On-POP-Overlay’s effectiveness in managing latency, jitter, and enhancing security. Our findings reveal that this architecture markedly boosts network performance, particularly in reducing latency. This attribute is especially beneficial for sectors like finance where latency sensitivity is paramount. This study optimizes network paths and reduces latency in intercontinental SD-DCs through Hybrid Edge Cloud Network Acceleration, laying the foundation for future AI-driven route selection in SD-WAN frameworks. This approach offers promising opportunities to enhance network path optimization and reinforce security measures. Such integration signifies a practical and valuable progression in the application of SD-WAN within the realm of global network infrastructures.

The eye disease such as Diabetic Retinopathy(DR) can be analysed through segmentation of retinal blood vessels. In the last five years, many methods for retinal blood vessels segmentation were proposed. These methods give arise to the improved accuracy, however the sensitivity of low contrast vessels is often ignored. The performance of diagnosis in terms of segmentation of vessels can be degraded due to missing tiny vessels. In this study, we propose a novel algorithm aiming at improving the performance of segmenting small vessels. The proposed approach adopts a morphological and filtering method to handle the background noise and uneven illumination and uses anisotropic diffusion filtering to coherent the vessels and give initial detection of vessels, followed by a double threshold based region growing method.

This paper presents a new method to recognize human facial expression by feeding hybrid features to Self-organizing maps (SOM). Facial expression recognition is still a challenging problem that can be seen in many real applications such as security systems, behavioral science and clinical practices. In this work, we present a new way to analyze, represent and recognize human facial expressions from a video sequence. The proposed facial expression recognition framework comprises of following components: face detection, facial feature extraction and classification. Firstly, faces are detected based on skin color after removing background and noise effects from raw video sequences. Then each face image is aligned using vertex mask generation and the 1D transformation features are extracted to utilize the local information for each facial image. After reducing the dimension of features and doing independent component analysis, the new features are trained and tested using SOM. The experimental evaluation demonstrates the proposed approach over two public datasets such as Cohn-Kanade and AT&T datasets of facial expression videos achieves superior recognition performance of 96.81% and 96.55% over state of the art methods.

This paper presents a novel approach to action recognition using synthetic multi-view data from depth maps. Specifically, multiple views are first generated by rotating 3D point clouds from depth maps. A pyramid multi-view depth motion template is then adopted for multi-view action representation, characterizing the multi-scale motion and shape patterns in 3D. Empirically, despite the view-specific information, the latent information between multiple views often provides important cues for action recognition. Concentrating on this observation and motivated by the success of the dictionary learning framework, this paper proposes to explicitly learn a view-specific dictionary (called specificity) for each view, and simultaneously learn a latent dictionary (called latent correlation) across multiple views. Thus, a novel method, specificity and latent correlation learning, is put forward to learn the specificity that captures the most discriminative features of each view, and learn the latent correlation that contributes the inherent 3D information to multiple views. In this way, a compact and discriminative dictionary is constructed by specificity and latent correlation for feature representation of actions. The proposed method is evaluated on the MSR Action3D, the MSR Gesture3D, the MSR Action Pairs, and the ChaLearn multi-modal data sets, consistently achieving promising results compared with the state-of-the-art methods based on depth data.

This paper presents a vision based sign language gesture recognition framework that can assist people with impaired hearing and speech with their social interaction and interactive communications. Utilizing a low-cost sensor, such as Microsoft Kinect combined with advanced machine learning analysis, it aims to ease the challenging issue of increasing demand for professional sign language interpreting services. Specifically, this paper discusses a powerful discriminating descriptor called 3D motion map based pyramid histograms of oriented gradient (M-PHOG) which is proposed for depth-based human gesture recognition. The 3D motion map is generated through the entire depth video sequence to encode additional motion information from three projected orthogonal planes. By adding pyramid representation, HOG descriptor is extended to M-PHOG which can characterize local shapes at different spatial grid sizes for gesture recognition. The proposed approach is evaluated on MSR Gesture3D and DEVISIGN two data sets captured by depth cameras. Experimental results show that the proposed approach outperforms the current state-of-the-art methods and demonstrates the effectiveness and robustness of the proposed 3D M-PHOG descriptor. The proposed approach can translate the meaning of captured gestures as professional interpreters currently do. The novelty framework has the potential to improve the quality of life for the deaf community and reduce the communication barriers they currently experience.

This paper presents a novel framework, spatio-temporal pyramid cuboid matching (STPCM), which is designed to recognize human actions from sequences captured by depth cameras. A depth sequence is partitioned into sub-volumes and represented using pyramid motion history templates (PMHT), which maintain the multi-scale 3D motion and shape information along the temporal direction. In order to capture the spatial information of PMHT, each projected plane from PMHT is subdivided into pyramid spatio-temporal grids. We then propose a novel cuboid fusion scheme to combine spatial dependent grids from projected planes to construct pyramid cuboids that consider the 3D spatial locations in conjunction with temporal information. In the experiments, we evaluate the proposed framework on three public benchmark datasets. Experimental results demonstrate that the proposed method achieves state-of-the-art performance.

Asset prices fluctuate up and down chaotically. Traders, investors and fund managers comb the chaos for exploitable patterns with methods such as moving averages from the realm of technical analysis. In this paper we focus on linear moving averages which aim to smooth asset prices removing fluctuations. First, we will develop a method to measure the smoothness for a linear filter. We will also discuss how to measure estimation lag. We will develop a new linear filter and show that, for short to medium time frames, it is smoother than competing filters.

Human action recognition based on the depth maps is an important yet challenging task. In this paper, a new framework based on the 3D motion trail model (3DMTM) and Pyramid Histograms of Oriented Gradient (PHOG) is proposed to recognize human actions from sequences of depth maps. Specifically, a discriminative descriptor called 3DMTM-PHOG is proposed for depth-based human action recognition. The 3DMTM is generated through the entire depth video sequence to encode additional motion information from three projected orthogonal planes. By adding pyramid representation, Histograms of Oriented Gradient (HOG) descriptor is extended to PHOG which can well characterize local shapes at different spatial grid sizes for action recognition. PHOG is then computed from the 3DMTM as the 3DMTM-PHOG descriptor for the representation of an action. The proposed approach based on 3DMTM-PHOG descriptor is evaluated on MSR Action3D dataset captured by depth cameras. Experimental results show that the proposed approach outperforms the state-of-the-art methods and demonstrate the effectiveness and robustness of the proposed 3DMTM-PHOG descriptor.

Wireless Body Area Networks (WBAN) have emerged as an extension to conventional wireless sensor networks in recent years to comply with the needs in providing timely and effective response in healthcare as one of the many target applications such networks have. The traffic of a WBAN is diverse due to different monitoring tasks carried on by sensor nodes. It brings difficulty in how to efficiently organize the access to the medium for the dynamic and various generated traffic. This paper analyses the traffic diversity problem in WBAN for healthcare applications and proposes a dynamic delayed Medium Access Control (MAC) algorithm. A fuzzy logic system is used to incorporate both application and protocol related parameters of the real time traffic to make the backoff time produced in IEEE 802.15.4 MAC protocol traffic adaptive. The simulation results demonstrate a significant reliability in packet transmissions and decrease in the latency with no change in energy consumption level.

This paper proposes a new and optimal moving average model that reduces the problems of alternative models. The random (noisy) nature of financial time series creates difficulties when modelling with any method. The most common linear model to deal with this issue of noise is the moving average. These filters come with the drawback of lag, a delay between the model output and the financial data. As more noise reduction is demanded from the models the lag increases. This lag is a hindrance in a market place where individuals are competing for timely and quality information. This paper derives an optimal moving average model which reduces the lag and increases the level of noise reduction. The proposed model was compared against four of the common moving averages and shown to be superior in both lag reduction and noise reduction.

The Gaussian process (GP) latent variable model (GPLVM) has the capability of learning low-dimensional manifold from highly nonlinear data of high dimensionality. As an unsupervised dimensionality reduction (DR) algorithm, the GPLVM has been successfully applied in many areas. However, in its current setting, GPLVM is unable to use label information, which is available for many tasks; therefore, researchers proposed many kinds of extensions to the GPLVM in order to utilize extra information, among which the supervised GPLVM (SGPLVM) has shown better performance compared with other SGPLVM extensions. However, the SGPLVM suffers in its high computational complexity. Bearing in mind the issues of the complexity and the need of incorporating additionally available information, in this paper, we propose a novel SGPLVM, called supervised latent linear GPLVM (SLLGPLVM). Our approach is motivated by both SGPLVM and supervised probabilistic principal component analysis (SPPCA). The proposed SLLGPLVM can be viewed as an appropriate compromise between the SGPLVM and the SPPCA. Furthermore, it is also appropriate to interpret the SLLGPLVM as a semiparametric regression model for supervised DR by making use of the GP to model the unknown smooth link function. Complexity analysis and experiments show that the developed SLLGPLVM outperforms the SGPLVM not only in the computational complexity but also in its accuracy. We also compared the SLLGPLVM with two classical supervised classifiers, i.e., a GP classifier and a support vector machine, to illustrate the advantages of the proposed model.

In this paper an improved hill climbing algorithm based method is presented to cut character out of the license plate images. Although there are many existing commercial LPR systems, with poor illumination conditions and moving vehicle the accuracy impaired. After examination and comparison of two different types of image segmentation approaches, the hill climbing algorithm based method gave a better image segmentation results. The hill climbing algorithm was modified by introducing automatic parameter determination and smart searching. After modification it efficiently detects the peaks (local maxima) that represent different clusters in the global histogram of an image. The process is successful by getting a clean license plate image removing all unwanted areas. While testing by the OCR software, the experimental results show a high accuracy of image segmentation and significantly higher recognition rate after non-character areas are removed. The recognition rate increased from about 30.6% before our proposed process to about 91.3% after all unwanted non-character areas are removed. Hence, the overall recognition accuracy of LPR was improved.

License plate recognition usually contains three steps, namely license plate detection/localization, character segmentation and character recognition. When reading characters on a license plate one by one after license plate detection step, it is crucial to accurately segment the characters. The segmentation step may be affected by many factors such as license plate boundaries (frames). The recognition accuracy will be significantly reduced if the characters are not properly segmented. This paper presents an efficient algorithm for character segmentation on a license plate. The algorithm follows the step that detects the license plates using an AdaBoost algorithm. It is based on an efficient and accurate skew and slant correction of license plates, and works together with boundary (frame) removal of license plates. The algorithm is efficient and can be applied in real-time applications. The experiments are performed to show the accuracy of segmentation.

Automatic number plate recognition method is required due to increasing traffic management. In this paper, we first briefly review some knowledge of Support Vector Machines (SVMs). Then a number plate recognition algorithm is proposed. This algorithm employs an SVM to recognize numbers. The algorithm starts from a collection of samples of numbers from number plates. Each character is recognized by an SVM, which is trained by some known samples in advance. In order to recognize a number plate correctly, all numbers are tested one by one using the trained model. The recognition results are achieved by finding the maximum value between the outputs of SVMs. In this paper, experimental results based on SVMs are given. From the experimental results, we can make the conclusion that SVM is bettr than others such as inductive learning-based number recognition

In this paper, a number recognition algorithm is proposed on spiral architecture, a hexagonal image structure. This algorithm employs RULES-3 inductive learning method to recognize numbers. The algorithm starts from a collection of samples of numbers from number plates. Edge maps of the samples are then detected based on spiral architecture. A set of rules are extracted using these samples by RULES-3. The rules describe the frequencies of 9 different edge masks appearing in the samples. Each mask is a cluster of 7 hexagonal pixels. In order to recognize a number plate, all numbers are tested one by one using the extracted rules. The number recognition is achieved by counting the frequencies of the 9 masks. In this paper, a comparison between results based on rectangular structure and the results based on spiral architecture is given. From the experimental results, we can make the conclusion that Spiral Architecture is better than rectangular structure for inductive learning-based number recognition