Data Transfer Research Articles

P-245 Evaluating the impact of embryos undergoing multiple freeze-thaw cycles in preimplantation genetic testing for aneuploidy (PGT-A) on treatment outcomes in IVF

Abstract Study question Do cryopreserved embryos subjected to thaw, biopsy, re-freeze (TBR) exhibit inferior pregnancy outcomes compared to embryos undergoing standard PGT-A with a single vitrification-warming cycle? Summary answer Transfer of twice-thawed euploid embryos demonstrated comparable clinical pregnancy outcomes, yet elevated miscarriage rates following a repeated vitrification-warming cycle warrants further scientific inquiry. What is known already There is often hesitancy to test cryopreserved embryos that were not initially PGT-A tested due to concerns about embryo survival during the additional freeze-thaw cycle those embryos will endure. However, the TBR technique has shown efficacy, particularly for IVF patients with recurrent failed attempts using fresh, untested embryos. Previous studies on TBR consistently report comparable embryo survival rates to fresh cycles. Nevertheless, there is no consensus on whether transferring euploid TBR embryos adversely affects pregnancy outcomes compared to euploid fresh biopsy embryos, potentially due to the relatively low number of transferred TBR embryos in such studies. Study design, size, duration This study retrospectively analysed euploid freeze-thaw single embryo transfer (SET) data from embryos that underwent PGT-A at a large fertility clinic in London, between January 2019 and June 2022. Pregnancy outcomes were compared between freshly biopsied embryos (control group, n = 349) and cryopreserved embryos that underwent thaw and biopsy before freeze-thaw SET (twice-thawed group, n = 35). Embryos previously biopsied with PGT-A, subsequently cryopreserved, and then subjected to thaw and re-biopsy were classified in the twice-thawed group. Participants/materials, setting, methods Blastocysts cultured from fresh embryos (control group) or derived from frozen-thawed blastocysts (twice-thawed group) underwent PGT-A using standard protocols before freeze-thaw SET. The study assessed biopsy rates, post first thaw and survival rates post second thaw in the twice-thawed group, comparing to the control group. The clinical outcomes evaluated were Implantation rate (IR), Live Birth Rate (LBR), and Miscarriage Rate (MR). Statistical analysis included one-way ANOVA for continuous and Pearson’s chi-squared test for categorical variables Main results and the role of chance Blastocyst characteristics, including morphological quality (characterised into ‘GOOD’, ‘FAIR’ and ‘POOR’) and day of biopsy (5 or 6), did not significantly differ between blastocyst transfers of the twice-thawed and control group. Furthermore, maternal factors including age, number of previous PGT-A attempts and endometrial thickness did not significantly differ between groups. However, compared with the control group, the number of eggs collected was significantly higher in the twice-thawed group (15.8±8.20 vs. 25.8±18.7, p = <0.001). The biopsy rate of previously cryopreserved embryos that underwent TBR was 79%. However, there was no significant difference between the survival rate after the second thaw and before SET between the twice-thawed and control groups. There was no difference in IRs (71.1% vs. 74.3%, p = 0.687) and LBRs (56.4% vs. 40.0%, p = 0.062) between groups. Although, compared to the control, MRs were significantly higher in the twice-thawed group (20.6% vs. 46.2% p = 0.003). Limitations, reasons for caution The twice-thawed group includes patients with diminished ovarian reserve, previously undergoing single freeze-thaw SET resulting in recurrent miscarriages. Thus, further research is essential to clarify whether elevated miscarriage rates result from repeated freeze-thaw cycles. Additionally, as single freeze-thaw SET is preferred, small sample size in the twice-thawed group limits conclusions. Wider implications of the findings This study suggests employing TBR on previously frozen blastocysts yields non-inferior IRs and LBRs, with an additional freeze-thaw cycle not adversely affecting embryo survival before SET. Therefore, such techniques should be considered in previously frozen IVF embryos to reduce wastage, mitigate unforeseen fertility complications, and concurrently achieve favourable pregnancy outcomes. Trial registration number Not applicable

Hardware Implementation of Next Generation Reservoir Computing with RRAM‐Based Hybrid Digital‐Analog System

Reservoir computing (RC) possesses a simple architecture and high energy efficiency for time‐series data analysis through machine learning algorithms. To date, RC has evolved into several innovative variants. The next generation reservoir computing (NGRC) variant, founded on nonlinear vector autoregression (NVAR) distinguishes itself due to its fewer hyperparameters and independence from physical random connection matrices, while yielding comparable results. However, NGRC networks struggle with massive Kronecker product calculations and matrix‐vector multiplications within the read out layer, leading to substantial efficiency challenges for traditional von Neumann architectures. In this work, a hybrid digital‐analog hardware system tailored for NGRC is developed. The digital part is a Kronecker product calculation unit with data filtering, which realizes transformation of nonlinear vector of the input linear vector. For matrix‐vector multiplication, a computing‐in‐memory architecture based on resistive random access memory array offers an energy‐efficient hardware solution, which markedly reduces data transfer and greatly improve computational parallelism and energy efficiency. The predictive capabilities of this hybrid NGRC system are validated through the Lorenz63 model, achieving a normalized root mean square error (NRMSE) of 0.00098 and an energy efficiency of 19.42TOPS W−1.

O-025 An artificial intelligence (AI) model non-invasively evaluates endometrial receptivity from ultrasound images, surpassing endometrial thickness (EMT) in predicting implantation

Abstract Study question Can an AI image-based model be trained to predict whether an endometrium, prior to progesterone, is receptive for successful embryo implantation from ultrasound images? Summary answer An endometrial receptivity AI model, utilizing ultrasound images and clinical features, is predictive of successful implantation and outperforms endometrial thickness as a predictor of implantation. What is known already Despite its importance in successful embryo implantation and subsequent live birth, endometrial receptivity is difficult to measure. The standard of care at some clinics is to cancel an embryo transfer if EMT is measuring less than 7 mm on ultrasound assessment – however, achieving an EMT threshold does not guarantee success, even with euploid blastocysts. Currently available receptivity tests (e.g. endometrial receptivity assays) are unreliable and have not shown significant improvements in reproductive outcomes, necessitating the development of new evaluation methods for endometrial receptivity. AI can potentially address this gap in clinical care and understanding, aiming to increase patient success. Study design, size, duration 79,602 ultrasound images (40,910 patients) of the endometrium, on the day of progesterone start according to patient’s frozen embryo transfer cycle, were retrospectively collected from 4 clinic networks including 70 clinic locations. PGT-A outcomes and blastocyst quality were available for 15,466 and 36,070 blastocysts respectively, with 14,538 having labels for both. Different image samples (based on embryo quality) were selected to train and test several AI models, with implantation (positive beta-hCG) as a binary outcome. Participants/materials, setting, methods Three criteria for negative (implantation) class sample selection were tested for receptivity model development: 1) high- or medium-quality and/or euploid blastocysts; 2) high-quality blastocysts; 3) all blastocysts. Models were ensembles consisting of an image-based deep learning (DL)-model and a feature-based machine learning (ML)-model. Model performance was measured by Area-under-the-curve (AUC), sensitivity, and specificity. Feature importance from the ML model was assessed, while receptivity model performance was compared to the power of EMT to predict implantation. Main results and the role of chance A receptivity model trained on scenario 1) (n = 27,424) achieved AUC 0.613, sensitivity 0.716, and specificity 0.439 on a test set of 9197 samples, in predicting implantation. Another receptivity model trained on scenario 2) (n = 25,625) achieved AUC 0.627, sensitivity 0.637, and specificity 0.543 on a test set of 8642. Whereas a third receptivity model trained on scenario 3) (n = 31,238) was selected for further analysis as it attained the best performance with AUC 0.631, sensitivity 0.628, and specificity 0.556 on a test set of 10,422. The ensemble model also utilizes relevant clinical features, which were ranked by importance to model predictions: EMT; progesterone blood test value; age at transfer; previous total embryo transfers; days between ultrasound date and transfer date; age at retrieval; and oocyte origin. EMT was assessed for its ability to predict implantation at thresholds between 5–20 mm. The threshold that best separates positive and negative implantation was determined by evaluating AUC on a validation set of 5682. A threshold of 8.8 mm achieved an AUC 0.576, sensitivity 0.694, and specificity 0.455 in predicting implantation on a test set of 5686. However, the receptivity model AUC (0.631) was significantly higher (p < 0.001; DeLong test for differences in AUC), outperforming EMT predictability. Limitations, reasons for caution The endometrial receptivity model was built and tested on retrospective frozen embryo transfer data. Results should be corroborated in prospective and non-selection studies, as well as in multiple geographical locations (all clinics included reside in the United States). The dataset requires greater diversification, with a greater representation of EMT (<7mm). Wider implications of the findings This study indicates that an AI model can be built to predict implantation from ultrasound images and clinical features, surpassing current standards - EMT alone. Further experimentation, with additional clinical features, may improve performance to facilitate development of a model that can accurately predict the gold-standard of live birth. Trial registration number Not applicable

Consensus for Operating Room Multimodal Data Management: Identifying Research Priorities for Data-Driven Surgery

Introduction: This study aimed to identify research areas that demand attention in multimodal data-driven surgery for improving data management in minimally invasive surgery. Background: New surgical procedures, high-tech equipment, and digital tools are increasingly being introduced, potentially benefiting patients and surgical teams. These innovations have resulted in operating rooms evolving into data-rich environments, which, in turn, requires a thorough understanding of the data pipeline for improved and more intelligent real-time data usage. As this new domain is vast, it is necessary to identify where efforts should be focused on developing seamless and practical data usage. Methods: A modified electronic Delphi approach was used; 53 investigators were divided into the following groups: a research group (n=9) for problem identification and a narrative literature review, a medical and technical expert group (n=14) for validation, and an invited panel (n=30) for two electronic survey rounds. Round 1 focused on a consensus regarding bottlenecks in surgical data science areas and research gaps, while round 2 prioritized the statements from round 1, and a roadmap was created based on the identified essential and very important research gaps. Results: Consensus panelists have identified key research areas, including digitizing operating room (OR) activities, improving data streaming through advanced technologies, uniform protocols for handling multimodal data, and integrating AI for efficiency and safety. The roadmap prioritizes standardizing OR data formats, integrating OR data with patient information, ensuring regulatory compliance, standardizing surgical AI models, and securing data transfers in the next generation of wireless networks. Conclusions: This work is an international expert consensus regarding the current issues and key research targets in the promising field of data-driven surgery, highlighting the research needs of many operating room stakeholders with the aim of facilitating the implementation of novel patient care strategies in minimally invasive surgery.

SQL2FPGA: Automated Acceleration of SQL Query Processing on Modern CPU-FPGA Platforms

Today’s big data query engines are constantly under pressure to keep up with the rapidly increasing demand for faster processing of more complex workloads. In the past few years, FPGA-based database acceleration efforts have demonstrated promising performance improvement with good energy efficiency. However, few studies target the programming and design automation support to leverage the FPGA accelerator benefits in query processing. Most of them rely on the SQL query plan generated by CPU query engines and manually map the query plan onto the FPGA accelerators, which is tedious and error-prone. Moreover, such CPU-oriented query plans do not consider the utilization of FPGA accelerators and could lose more optimization opportunities. In this paper, we present SQL2FPGA, an FPGA accelerator-aware compiler to automatically map SQL queries onto the heterogeneous CPU-FPGA platforms. Our SQL2FPGA front-end takes an optimized logical plan of a SQL query from a database query engine and transforms it into a unified operator-level intermediate representation. To generate an optimized FPGAaware physical plan, SQL2FPGA implements a set of compiler optimization passes to 1) improve operator acceleration coverage by the FPGA, 2) eliminate redundant computation during physical execution, and 3) minimize data transfer overhead between operators on the CPU and FPGA. Furthermore, it also leverages machine learning techniques to predict and identify the optimal platform, either CPU or FPGA, for the physical execution of individual query operations. Finally, SQL2FPGA generates the associated query acceleration code for heterogeneous CPU-FPGA system deployment. Compared to the widely used Apache Spark SQL framework running on the CPU, SQL2FPGA—using two AMD/Xilinx HBM-based Alveo U280 FPGA boards and Ver.2020 AMD/Xilinx FPGA overlay designs—achieves an average performance speedup of 10.1x and 13.9x across all 22 TPC-H benchmark queries in a scale factor of 1GB (SF1) and 30GB (SF30), respectively. While evaluated on AMD/Xilinx Alveo U50 FPGA boards, SQL2FPGA using Ver. 2022 AMD/Xilinx FPGA overlay designs also achieve an average speedup of 9.6x at SF1 scale factor.

A Proposal for a Mobility-Control Data Transfer Mechanism Based on a Block Network Utilizing End-to-End Authentication Data

Advances in communications technology have had tremendous influence on network implementation to date, and as communication devices get smaller and technologies more intelligent, a great number of solutions are emerging that converge communications with a multitude of domains. In particular, as transportation modes assisting with mobility have developed, many studies are in the pipeline on the domain of mobility. The development of mobility services has prompted the spread of car sharing, which also highlights the need for a system that controls shared vehicles. The data of such control system can be used not only for the operational management of vehicles but also the management of users in terms of user driving analysis or monitoring safe driving. In addition, it can be utilized in a variety of other applications that analyze traffic flow based on vehicle driving data, determine required vehicle maintenance intervals, or schedule vehicle maintenance in advance. However, if forged/altered by a third party, control data might pose a lot of challenges to data utilization. This study proposes a mechanism that manages control data on a blockchain to enhance the integrity of control data created in the communications process. In this paper, we propose a mechanism for applying a blockchain to the communication process between clients and servers. In the proposed mechanism, platform operators generate and provide independent identification information and identification numbers for users. The identification information and identification numbers are used to prove that the generated blocks were created by specific users. Data generated by clients create a block with a hash including user identification information alongside the user identification number. Verification of the generated block is performed on the platform vendor’s server, validating that the user identification number in the block matches the server-side user identification information and the hash of the data within the block. Thus, even when the contents of the block are shared in a public blockchain environment, user identification information is only held by the server and clients, preventing third parties from impersonating specific users to create data blocks. Furthermore, the verification process of the data includes hashes received from other nearby vehicles, preventing data tampering by the block creator.

Evaluation and comparison of liquid chromatography/high-resolution mass spectrometry platforms for the separation and characterization of ginsenosides from the leaves of Panax ginseng.

The measurement of data repeatability in small-molecule metabolites acquired within and among different liquid chromatography-mass spectrometry (LC-MS) platforms is crucial for data sharing or data transfer in natural products research. This work was designed to investigate and evaluate the separation and detection performance of three commercial high-resolution LC-MS platforms (e.g., Agilent 6550 QTOF, Waters Vion IM-QTOF, and Thermo Scientific Orbitrap Exploris 120) using 68 ginsenoside references and the extract of Panax ginseng leaf. The retention time (tR), measured on these three platforms (under the same chromatography condition), showed good stability in different concentration tests, and within/among different instruments for both intra-day and inter-day precision examinations. Correlation in tR of ginsenosides was also highly determined on these three platforms. In spite of the different mass analyzers involved, these three platforms gave the accurate mass determination ability, especially enhanced resolution gained because of the ion mobility (IM) separation facilitated by IM-quadrupole time-of-flight. The current study has systematically evaluated the separation and MS detection performance enabled by three high-resolution LC-MS platforms taking ginsenosides as the template, and the reported findings can benefit the researchers for the selection of analytical platforms and the purpose of data sharing or data transfer.

A Comprehensive Review of 5G Networks for Sustainable and Smart Cities

Abstract: The transition from the first generation of technology, which only had an analog voice, to the fifth generation, which also had connected gadgets, gave the technology a new structure and changed how people used it. Fifth-generation wireless technology, often known as 5G, is on the cusp of reaching its potential maximum data transfer rate with a peak data throughput of 20 gigabits per second (Gbps) and a typical data transfer rate of more than 100 megabits per second (Mbps). The Internet of Things serves as the cornerstone of the future, and it is projected that by 2025, individual users will use 13 times the amount of data that we do at this time. Therefore, 5G is extremely important and the main feature of the 2030 Sustainable Development Agenda, which was ratified by all of the Member States of the United Nations in 2015, and is the 17 Sustainable Development Goals (SDGs), which represent an urgent call to action for all nations. These goals are referred to collectively as the "SDGs." This study intends to examine how 5G networks might serve as important facilitators for achieving sustainability and meeting some of the 17 SDGs. This is further highlighted by evaluating the sustainability metrics for 5G networks. Ultimately, this helps to demonstrate that 5G networks are environmentally, socially, and economically responsible. This study focuses on the five primary SDGs that are important for the growth of smart cities.

Halide perovskite photovoltaics for in-sensor reservoir computing

As intelligent electronics get laden with multimodal sensors, the data transfer and computation increase their energy expenditure. Consequently, researchers aim to develop efficient computing paradigms or integrate energy harvesting from ambient sources. Halide perovskites possess unique photophysics and coupled ionic-electronic dynamics that actualise memory devices for brain-inspired computing. Synergising the computing capability with their conventional light harvesting efficacy could aptly address the aforementioned problem. In a novel approach, the transient open circuit voltage (VOC) of a methylammonium lead bromide-based solar cell was exploited to serve as a self-powered volatile short-term memory for optoelectronic in-sensor reservoir computing. The origin of the memory is attributed to the influence of mobile ions on the carrier generation and recombination in the device. The system's versatility and task specificity were shown by engineering the volatility of the memory. The benchmarking task of MNIST handwritten digit recognition was performed with the highly reproducible and robust transformation of optical inputs into unique reservoir states. To demonstrate the high nonlinearity, second-order time-series prediction (NARMA2) was performed. Finally, an exemplary cardiac health-monitoring application was showcased by monolithic reading and processing of a physiological time series known as photoplethysmography (PPG) to identify atrial fibrillation with increased computational efficiency.

Authorized Redundant Check Support in a Hybrid Cloud Environment

A hybrid cloud is made up of public and private clouds connected by standardized or proprietary technologies to provide data and application mobility. The deduplication with uneven privileges issue in cloud computing is addressed efficiently. an architecture for a hybrid cloud that employs both public and private clouds, with the data owners only using the public cloud for storage and the private cloud for data administration. To make data management in cloud computing scalable, duplication has lately become a commonly employed method. Deduplication reduces the amount of bandwidth you need, speeds up data transfers, and keeps your need for cloud storage to a minimum. To enable authorized duplicate checks in hybrid cloud architecture, the proposed system comprises a variety of new deduplication structures. Data confidentiality was protected before outsourcing by employing the convergent encryption method. A system authorized to use deduplication supports differential authorization duplicate checks. In the authorized duplication check approach, testbed tests are carried out using a prototype as proof of concept.

Evaluation of technical approaches for real-time data transfer from electronic health record systems

Background and ObjectiveReal-time data (RTD) are data that are delivered immediately after creation. The key feature of RTD is low delivery latency. Information systems in health care are extremely time-sensitive and their building block is the electronic health record (EHR). Real-time data from EHRs play an important role to support decision-making, analytics and coordination of care. This is well mentioned in the literature, but the process has not yet been described, providing reference implementations and testing. Real-time data delivery can technically be achieved using several methods. The objective of this work is to evaluate the performance of different transfer methods of RTD from EHRs by measuring delivery latency. MethodsIn our work we used four approaches to transfer RTD from EHRs: REST hooks, WebSocket notifications, reverse proxy and database triggers. We deployed a Fast Health Interoperability Resources (FHIR) server as it is one of the most widely used EHR standard. For the reference implementations we used Python and Golang. Delivery latency was selected as performance metric, derived by subtracting the timestamp of the EHR resource creation from the timestamp of the EHR resource receipt in millisecond. The data was analyzed using descriptive statistics, cumulative distribution function (CDF), Kruskal-Wallis and post-hoc tests. ResultsThe database trigger approach had the best mean delivery latency 13.52±5.56 ms, followed by the reverse proxy 14.43±4.58 ms, REST hooks 19.26±5.76 ms and WebSocket 27.32±9.44 ms. The reverse proxy showed a tighter range of the values and lower variability. There were significant differences in the latencies between all pairs of approaches, except for reverse proxy and database trigger. ConclusionReal-time data transfer is vital for the development of robust and innovative healthcare applications. Properties of current EHR systems as a data source predefine the approaches for transfer. In our work for the first time the performance of RTD transfer from the EHRs with reference implementations is measured and evaluated. We found that database triggers achieve lowest delivery latency. Reverse proxy performed slightly slower, but offered more stability, followed by REST hooks and WebSocket notifications.

Design and performance analysis of asynchronous network on chip for streaming data transmission on FPGA

The majority of the system on chip (SoC) uses the network on chip (NoC) as routing ports for data transfer from node-to-node with minimal power consumption and low latency and high throughput. This paper concentrates on the ability to model the asynchronous NoCs on the asynchronous circuits on field programmable gate arrays (FPGAs). A 3×3 NoC and its universal asynchronous receiver transmitter (UART) protocol is designed and its simulation of the Verilog hardware description language (VHDL) code is done and tested on the Artix-7 FPGA kit, the testing processes in done using the Chipscope tool. In order to meet target requirements in terms of power consumption and latency, the label switching (LS) technique is used as routing. The proposed LS-NoC with level-encoded dual-rail (LEDR) encoding technique provides throughput by registering the packet between the different routers and it helps to improve throughput and speed. The effectiveness of the data transfer is measured and analyzed through a synthesis summary in terms of lookup table’s (LUT’s), slice registers, flip flops’s (FF’s), latency, and packet delivery ratio (PDR) for the traffic pattern generator. The proposed NoC is designed for 8×8 and each port size is 21 bits including ID’s of source and destination routers. The results can be justified by following results: improvement of LUTs is about 12%, flip-flops are 7%, improvement of throughput is 23% and delay is reduced by 26%.

Integrating optical security management with optical‐layer controller architecture for enhanced network security

AbstractTo guarantee the availability, confidentiality, and integrity of data transferred over optical channels—especially in the context of fifth‐generation (5G) communication infrastructure—optical network security management is essential. This paper provides an overview of security management for optical networks, emphasizing the importance of this practice in today's communication infrastructure and the difficulties presented by ever changing cyberthreats. The architecture of optical security management is shown, with special attention to how well it integrates with current optical‐layer controllers and how it facilitates the coordination of security operations among optical networks. The study also looks at use cases for optical network security management in 5G networks, such as safe data transfer, defense against cyberattacks, maintaining privacy in 5G apps, network slicing security, and resistance to physical assaults. Such instances highlight the adaptability and significance of optical network security management in bolstering 5G networks' security, privacy, and resilience across a range of businesses and applications.

Comparing Leach protocol and its descendants on transferring scalar data

In the last years, The CMOS was developed and miniaturized rapidly, which, made sensors very fast, small and accurate. Hence, the creation of wireless sensor network (WSN) which are a network of nodes that exchange the data between them until it reaches the sink (base station). It is responsible for treating the data and transfer them to other servers linked to the internet for further treatment or storage. Therefore, everything related to WSN is a big topic of research for scientific community, especially transferring scalar data. In fact, many factors enter into account when it comes to send data like a radio, range of transmission, energy consumption and routing protocol. Routing protocols are very important in transferring data. They also have a big impact on energy consumption by nodes. Many categories of routing protocols exist: planning and level routing. Each type has its strength and weakness points. So, using a routing protocol in high-density environments is very challenging in energy consumption and data delivery. In addition, since level routing protocols like Leach are known for their energy efficiency. We choose three level routing protocol (Leach, MLD-Leach and MRE-Leach) to put them in a harsh environment to test their energy consumption and data transferring. We found that MLD-Leach has better energy consumption and data delivery.

A Comprehensive Survey for Hiding Medical Data Based DNA Lossless Technique

The health information data includes reports on the patient’s condition, including addresses, names, tests, treatments, diagnoses, and medical history. It is sensitive information for patients, and all means of protection must be provided to prevent third parties from manipulation or fraudulent use. The goal of this paper presents studies of safeguard the transfer of sensitive data over an unsecured network using DNA techniques to enhance security. A comparison analysis is used to show the security issues of the various DNA-based data (ciphering, concealing, and compression) techniques that are studied and investigated. Also, in our study is to provide future researchers with the necessary knowledge to conduct data security research to develop or improve DNA-based data- ciphering, compression-hiding strategies that are more reliable, secure, and efficient. Thus, future researchers need to propose a trustworthy DNA-based data (ciphering, hiding, and compression) techniques. The result of our study appears the perceived vulnerability of medical data and health insurance to concerns of security as well as common security issues, also the nature of these common security concerns, for reducing medical data security risks.

Data-driven prediction of tool wear using Bayesian regularized artificial neural networks

The prediction of wear in cutting tools is pivotal for boosting productivity and reducing manufacturing costs. Although current data-driven models in machine learning and deep learning have advanced predictive capabilities, they often lack generality and demand substantial data training. This paper presents a novel approach using Bayesian Regularized Artificial Neural Networks (BRANNs) to precisely forecast wear in milling tools. Unlike conventional machine learning models, BRANNs merge the strengths of artificial neural networks (ANNs) and Bayesian regularization, yielding a more robust and generalized predictive model. We utilized three open-access datasets from the literature alongside an in-house dataset generated by our milling setup. Initially, we assessed the model’s predictive ability by training and testing it against individual open-access datasets. We investigated the impact of input features, training data size, hidden units, training algorithms, and transfer functions on the model’s predictive capability. Subsequently, we trained the model using three open-access datasets and tested it against our in-house data. Our findings demonstrate that the developed model surpasses existing state-of-the-art models in accuracy and transferability

Adapting UWB AoA estimation towards unseen environments using transfer learning and data augmentation

Ultra-wideband technology has become increasingly prevalent in localization systems, particularly with the emergence of multi-antenna systems capable of estimating both distance and angle of arrival (AoA) for incoming signals. However, most scientific research analyses the accuracy of AoA in one specific environment for which the estimator is trained. In this paper, we analyze the performance of various AoA estimation algorithms, such as deep convolutional neural networks (DCNN), multiple signal classification (MUSIC), and phase difference of arrival (PDoA), in unseen environments. Prior work already demonstrated the superior performance of ML for AoA estimation compared to PDoA or MUSIC. We show that MUSIC, PDoA and ML solutions suffer from degradation in unseen environments at the 90th percentile of error, with ML-based AoA estimation degrading by about 14 degrees in unseen environments compared to 4 degrees for PDoA. We demonstrate that while PDoA more effectively corrects AoA at the median level in unseen environments, ML-based methods excel at correcting higher-percentile AoA errors, including outliers. Finally, we propose a novel framework to further improve the correction of AoA outliers for DCNN-based AoA estimators using data augmentation and transfer learning, resulting in a median angular error of only 5 degrees in unseen environments, even considering a field of view up to 90 degrees.

GraphADT: empowering interpretable predictions of acute dermal toxicity with multi-view graph pooling and structure remapping.

Accurate prediction of acute dermal toxicity (ADT) is essential for the safe and effective development of contact drugs. Currently, graph neural networks, a form of deep learning technology, accurately model the structure of compound molecules, enhancing predictions of their ADT. However, many existing methods emphasize atom-level information transfer and overlook crucial data conveyed by molecular bonds and their interrelationships. Additionally, these methods often generate "equal" node representations across the entire graph, failing to accentuate "important" substructures like functional groups, pharmacophores, and toxicophores, thereby reducing interpretability. We introduce a novel model, GraphADT, utilizing structure remapping and multi-view graph pooling (MVPool) technologies to accurately predict compound ADT. Initially, our model applies structure remapping to better delineate bonds, transforming "bonds" into new nodes and "bond-atom-bond" interactions into new edges, thereby reconstructing the compound molecular graph. Subsequently, we use MVPool to amalgamate data from various perspectives, minimizing biases inherent to single-view analyses. Following this, the model generates a robust node ranking collaboratively, emphasizing critical nodes or substructures to enhance model interpretability. Lastly, we apply a graph comparison learning strategy to train both the original and structure remapped molecular graphs, deriving the final molecular representation. Experimental results on public datasets indicate that the GraphADT model outperforms existing state-of-the-art models. The GraphADT model has been demonstrated to effectively predict compound ADT, offering potential guidance for the development of contact drugs and related treatments. Our code and data are accessible at: https://github.com/mxqmxqmxq/GraphADT.git.

Creating a digital approach for promoting physical activity in pediatric pulmonary hypertension: A framework for future interventions.

Children with pulmonary hypertension (PH) often demonstrate limited exercise capacity. Data support exercise as an effective nonpharmacologic intervention among adults with PH. However, data on exercise training in children and adolescents are limited, and characteristics of the optimal exercise program in pediatric PH have not been identified. Exercise programs may have multiple targets, including muscle deficits which are associated with exercise limitations in both adult and pediatric PH. Wearable accelerometer sensors measure physical activity volume and intensity in the naturalistic setting and can facilitate near continuous data transfer and bidirectional communication between patients and the study team when paired with informatics tools during exercise interventions. To address the knowledge gaps in exercise training in pediatric PH, we designed a prospective, single arm, nonrandomized pilot study to determine feasibility and preliminary estimates of efficacy of a 16-week home exercise intervention, targeting lower extremity muscle mass and enriched by wearable mobile health technology. The exercIse Training in pulmONary hypertEnsion (iTONE) trial includes (1) semistructured exercise prescriptions tailored to the participant's baseline level of activity and access to resources; (2) interval goal setting fostering self-efficacy; (3) real time monitoring of activity via wearable devices; (4) a digital platform enabling communication and feedback between participant and study team; (5) multiple avenues to assess participant safety. This pilot intervention will provide information on the digital infrastructure needed to conduct home-based exercise interventions in PH and will generate important preliminary data on the effect of exercise interventions in youth with chronic cardiorespiratory conditions to power larger studies in the future.

Geomechanical risk assessment for CO2 storage in deep saline aquifers

We study CO2 injection into a saline aquifer intersected by a tectonic fault using a coupled modeling approach to evaluate potential geomechanical risks. The simulation approach integrates the reservoir and mechanical simulators through a data transfer algorithm. MUFITS simulates non-isothermal multiphase flow in the reservoir, while FLAC3D calculates its mechanical equilibrium state. We accurately describe the tectonic fault, which consists of damage and core zones, and derive novel analytical closure relations governing the permeability alteration in the fault zone. We estimate the permeability of the activated fracture network in the damage zone and calculate the permeability of the main crack in the fault core, which opens on asperities due to slip. The coupled model is applied to simulate CO2 injection into synthetic and realistic reservoirs. In the synthetic reservoir model, we examine the impact of formation depth and initial tectonic stresses on geomechanical risks. Pronounced tectonic stresses lead to inelastic deformations in the fault zone. Regardless of the magnitude of tectonic stress, slip along the fault plane occurs, and the main crack in the fault core opens on asperities, causing CO2 leakage out of the storage aquifer. In the realistic reservoir model, we demonstrate that sufficiently high bottomhole pressure induces plastic deformations in the near-wellbore zone, interpreted as rock fracturing, without slippage along the fault plane. We perform a sensitivity analysis of the coupled model, varying the mechanical and flow properties of the storage layers and fault zone to assess fault stability and associated geomechanical risks.