Diffusion-Based PPG-to-ECG Translation with Dynamic ROI Selection

Modern sensors have a range of modalities including SAR, EO, and IR. Registration of multimodal imagery from such sensors is becoming an increasingly common pre-processing step for various image exploitation activities such as image fusion for ATR. Over the past decades, several approaches to multisensor image registration have been developed. However, performance of these image registration algorithms is highly dependent on scene content and sensor operating conditions, with no single algorithm working well across the entire operating conditions space. To address this problem, in this paper we present an approach for dynamic selection of an appropriate registration algorithm, tuned to the scene content and feature manifestation of the imagery under consideration. We consider feature-based registration using Harris corners, Canny edge detection, and CFAR features, as well as pixel-based registration using cross-correlation and mutual information. We develop an approach for selecting the optimal combination of algorithms to use in the dynamic selection algorithm. We define a performance measure which balances contributions from convergence redundancy and convergence coverage components calculated over sample imagery, and optimize the measure to define an optimal algorithm set. We present numerical results demonstrating the improvement in registration performance through use of the dynamic algorithm selection approach over results generated through use of a fixed registration algorithm approach. The results provide registration convergence probabilities for geo-registering test SAR imagery against associated EO reference imagery. We present convergence results for various match score normalizations used in the dynamic selection algorithm.

Deep learning using electrocardiographs

A session-based communication network is a store-and-forward message (or packet) switching network in which each session (conversation from logon until logoff) is assigned to a single communication route (or path) until its termination. Examples of such networks are TYMNET and SNA. A route selection algorithm can be either static or dynamic. A static selection is based on given route selection tables which are usually provided to the system by the system generation process. A dynamic selection uses dynamically changing information of the network for determining an optimal route for the new session to be assigned to. This paper develops both static and dynamic route selection algorithms which may be used in a session-based communication network. Route selection algorithms will be classified into several classes depending on the network work-load information available for making decisions. It will be shown that very simple algorithms give good robustness with good response time.

The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture, such as difficulties in capturing long-range dependencies, limited temporal coherence, and scalability challenges. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion , a diffusion, and transformers-based generative model to generate high-quality long-sequence time-series data. We extended the sequence length to 384, surpassing the previous limit, and successfully generated high-quality synthetic data. Also, we introduce two evaluation metrics to evaluate the quality of the synthetic data as well as its predictive characteristics. TransFusion is evaluated using a diverse set of visual and empirical metrics, consistently outperforming the previous state-of-the-art by a significant margin.

Automated Real-time Classification of Functional States based on Physiological Parameters

The current increase in the Internet traffic along with the global crisis have accelerated the roll-out of the next generation 5G network and key enabling technologies. In this context, addressing the end-to-end Quality of Service (QoS) provisioning in order to guarantee a sustainable service delivery to the end-users became of paramount importance. Some of the enabling technologies that could play a key role in this regard are Software Defined Network (SDN) and Machine Learning (ML). This paper proposes REDO, a Reinforcement lEarning-based Dynamic rOuting algorithm selection method that decides on the conventional routing algorithm to be applied on the traffic flows within a SDN environment. REDO will dynamically select the most appropriate routing algorithm from a set of centralized routing algorithms (MHA, WSP, SWP, MIRA) that maximizes the reward function from the network. The proposed REDO solution is implemented and evaluated using an experimental setup based on Mininet, Floodlight controller and Open vSwitch switches. The results show that REDO outperforms other state-of-the-art solutions.

Diffusion models have gained significant attention in the field of generative modeling due to their capability to produce high-quality samples. However, recent studies show that applying a uniform treatment to all distributions during the training of diffusion models is sub-optimal. In this paper, we present a comprehensive theoretical analysis of the forward process in diffusion models. Our findings indicate that distribution variations are not uniform throughout the diffusion process, with the sharpest changes occurring during the initial stages. Moreover, we observe that the initial distribution converges to a Gaussian distribution at an exponential rate, indicating that different initial distributions rapidly become quite similar during the forward diffusion process. Consequently, employing a uniform timestep sampling strategy does not effectively capture these dynamics, potentially leading to sub-optimal training outcomes for diffusion models. To remedy this, we introduce the Bidirectional Beta-Tuned Diffusion Model (BB-TDM). The BB-TDM leverages the Beta distribution to design the timestep sampling distribution and enhance the separation between different initial distributions during the diffusion process. By selecting appropriate parameters, the BB-TDM ensures that the timestep sampling distribution is aligned with the properties of the forward diffusion process and moderates the convergence speed of different initial distributions. Extensive experiments across various benchmark datasets on different diffusion models confirm the efficacy of the proposed BB-TDM.

A dynamic predictor selection algorithm for predicting stock market movement

Feature selection is an important pre-processing step in many fields, such as data mining, machine learning and pattern recognition. This paper focuses on dynamically updating a subset of features with new samples arriving and provides a hypergraph model to deal with dynamic feature selection problem. Firstly, we discuss the relationship between feature selection of information system and minimum vertex cover of hypergraph, and feature selection is converted to a minimum vertex cover problem based on this relationship. Then, an algorithm for generating induced hypergraph from information system is presented, the induced hypergraph can be divided into two part: the original induced hypergraph and the added hypergraph with new samples arriving. Finally, a novel dynamic feature selection algorithm based on minimum vertex cover of hypergraph is proposed, and this algorithm only needs a small amount of computation. Experiments show that the proposed method is feasible and highly effective.

This article studies the relation between electrocardiogram (ECG) and photoplethysmogram (PPG) and investigates the inference of the ECG waveforms from the PPG signals that can be obtained from affordable wearable Internet-of-Things (IoT) devices for mobile health. In order to address this inverse problem, a transform is proposed to map the discrete cosine transform (DCT) coefficients of each PPG cycle to those of the corresponding ECG cycle based on the proposed cardiovascular signal model. The proposed method is evaluated with different morphologies of the PPG and ECG signals on three benchmark data sets with a variety of combinations of age, weight, and health conditions under several training setups. The experimental results show that the proposed method can achieve a high prediction accuracy greater than 0.92 in averaged correlation for each data set when the model is trained subjectwise. With a signal processing and learning system that is designed synergistically, we are able to reconstruct ECG signals by exploiting the relation of these two types of cardiovascular measurement. The reconstruction capability of the proposed method can enable low-cost ECG screening from affordable wearable IoT devices for continuous and long-term monitoring. This work opens up a new research direction to transfer the clinical ECG knowledge base to build a knowledge base for PPG and sensing data from wearable devices.

Fragile watermarking is designed to protect content integrity of digital data, meaning to detect any change in the content as well as localize areas that have been changed. In this paper, we propose a fragile watermarking scheme, which embeds dual watermarks (one is naturally fragile and the other is actually robust) in JPEG-2000 compressed images with ROI (region of interest) selection. In this scheme, the fragile watermark is embedded in ROI coefficients at the first decomposition layer, while the robust watermark embedded in ROB (region of backgrounds) coefficients at the third decomposition layer. The combinational working of them is not only capable of detecting malicious changes precisely and flexibly but also estimating the degree of alteration to discriminate intended attacks from unintended ones (e.g., such normal image processing as compression, low-pass filtering, sharpening, etc). Experiments show that our functionally fragile watermarking scheme is scalable in view of detecting attack's intension as well as accuracy in localizing the tampered areas.

With the increasing complexity of networked cooperative detection environment, new targets appear and leave in the detection area, and the mobility of targets is increasing. The emergence of sensors makes the sensors in the sensor network have certain motion characteristics. These uncertainties increase the complexity of the problem. At the same time, the dynamic selection of sensor resources needs to consider the needs of different priority tasks, platform survival risk, sensor cost and other factors. In view of these problems to be solved, based on the qualitative synthesis theory of predictive control and stochastic dynamic programming optimization theory, the dynamic sensor selection decision theory and method based on multi-step forward decision are explored. This paper studies the dynamic sensor strategy based on multi-step forward decision scheduling, and carries out the research on the optimization decomposition method of sensor selection under different structural characteristics, the dynamic optimization method of sensor selection under complex and uncertain environment, and the multi-objective optimization method of dynamic sensor selection under heterogeneous targets, so as to explore a new way of dynamic sensor selection algorithm design and performance analysis under networked collaborative tracking A new way. The research of dynamic target tracking algorithm in mobile sensor networks has important theoretical and engineering significance to improve the resource efficient utilization and the overall target tracking performance of sensor networks.

In healthcare, electrocardiography (ECG) sensors generate a large amount of heart electrical signal that must be efficiently compressed to enable fast data transfer and reduce storage costs. Existing methods for ECG data compression do not fully exploit the characteristics of ECG signals, leading to suboptimal compression. This study proposes a data compression technique for ECG data by exploiting the known characteristics of ECG signals. Our approach combines Savitzky-Golay filtering, detrending, discrete cosine transform, scalar quantization, run-length encoding, and Huffman coding for the effective compression. To optimize the compression performance, we generated quantization intervals tailored to the ECG data characteristics. The proposed method experimentally produces a high compression ratio of 127.61 for a design parameter K = 8, a minimum percentage root mean square difference of 1.03% for K = 128, and a maximum quality score (QS) of 39.78, where K is the number of quantization intervals. Moreover, we compared the proposed method to state-of-the-art methods on a widely used ECG benchmark dataset. We found that the proposed method outperforms the others in terms of the QS, which measures the overall compression-decompression ability. By enabling more storage and faster data transfer, the proposed method can facilitate the widespread use and analysis of large volumes of ECG data, thereby contributing to advances in healthcare.

Data imputation and data generation have important applications across many domains where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful generative models capable of capturing complex data distributions across various data modalities such as image, audio, and time series. Recently, they have been also adapted to generate tabular data. In this article, we propose a diffusion model for tabular data that introduces three key enhancements: (1) a conditioning attention mechanism, (2) an encoder–decoder transformer as the denoising network, and (3) dynamic masking. The conditioning attention mechanism is designed to improve the model’s ability to capture the relationship between the condition and synthetic data. The transformer layers help model interactions within the condition (encoder) or synthetic data (decoder), while dynamic masking enables our model to efficiently handle both missing data imputation and synthetic data generation tasks within a unified framework. We conduct a comprehensive evaluation by comparing the performance of diffusion models with transformer conditioning against state-of-the-art techniques such as Variational Autoencoders, Generative Adversarial Networks, and Diffusion Models, on benchmark datasets. Our evaluation focuses on the assessment of the generated samples with respect to three important criteria, namely: (1) machine learning efficiency, (2) statistical similarity, and (3) privacy risk mitigation. For the task of data imputation, we consider the efficiency of the generated samples across different levels of missing features. The results demonstrate average superior machine learning efficiency and statistical accuracy compared to the baselines, while maintaining privacy risks at a comparable level, particularly showing increased performance in datasets with a large number of features. By conditioning the data generation on a desired target variable, the model can mitigate systemic biases, generate augmented datasets to address data imbalance issues, and improve data quality for subsequent analysis. This has significant implications for domains such as healthcare and finance, where accurate, unbiased, and privacy-preserving data are critical for informed decision-making and fair model outcomes.

Aiming at improving the predictive ability of corporate financial distress, a method integrating decision tree and genetic algorithms is put forward to realize dynamic selection of financial ratios in the process of modeling. It uses genetic algorithms to optimize financial ratio set, so the ultimate decision tree model for financial distress prediction has a good balance between accuracy and generalization. Empirical study shows that this model's prediction accuracy for training samples and validation samples are respectively 94.67% and 93.75%. This indicates that the proposed method for financial distress prediction can dynamically optimize the financial ratio set and effectively avoid the over-fitting problem of decision tree to improve the generalization ability