Local Machine Research Articles

Self‐Adaptive Activation of DNAzyme Nanoassembly for Synergistically Combined Gene Therapy

AbstractDNAzyme represents a promising gene silencing toolbox yet is obstructed by the poor substrate accessibility in specific cells. Herein, a compact DNA nanoassembly, incorporating multimeric therapeutic DNAzyme, was prepared for selective delivery of gene‐silencing DNAzyme with requisite cofactors and auxiliary chemo‐drugs. By virtue of the sequence‐conservative duplex‐specific nuclease, the endogenous miRNA catalyzes the successive and site‐specific cleavage of DNA nanoassembly substrate (nominated as the localized RNA walking machine) and thus ensures the liberation/activation of therapeutic agents with high accuracy and efficacy. The miR‐10b‐stimulated DNAzyme was designed to downregulate the TWIST transcription factor, an upstream promotor of miR‐10b, thus acquiring the self‐sufficient downregulation of TWIST/miR‐10b signaling nodes (self‐adaptive negative feedback loop) for abrogating tumor metastasis and chemo‐resistance issues.

Missing Data Imputation in Balanced Construction for Incomplete Block Designs

Observational data with massive sample sizes are often distributed on many local machines. From an experimental design perspective, investigators often desire to identify the effect of new treatments (even ML algorithms) on many blocks of experimental data. With time requirements or budget constraints, assigning all treatments to each block is not always feasible. This creates incomplete responses with respect to a randomized complete block design (RCBD). These incomplete responses are missing by design. However, whether they can be estimated with missing imputation methods is not well understood. Thus, it is challenging to correctly identify the treatment effects with missing data. To this end, this paper provides a method for imputation and analysis of the responses with missing data. The proposed method consists of three steps: Reconstruction, Imputation, and `Complete’-data Analysis (RICA). The incomplete responses are imputed with the expectation-maximization (EM) algorithm. The RCBD model is then fitted by the resulting dataset. The identifiability result suggests that the missing may be nonignorable for each block, but the whole data of an incomplete design are missing by design when the design is balanced. Theoretical results on relative efficiency also inform us when the missingness should be imputed for incomplete designs with the role of balanced variance. Applications on real-world data verify the efficacy of this method.

Enhancing Chimp Optimization Algorithm Using Local Search Capabilities and Machine Learning for Real Engineering Problems

Enhancing Chimp Optimization Algorithm Using Local Search Capabilities and Machine Learning for Real Engineering Problems

Self-Adaptive Activation of DNAzyme Nanoassembly for Synergistically Combined Gene Therapy.

DNAzymes represents a promising toolbox for gene silencing but face challenges related to poor substrate accessibility in specific cells. Herein, a compact DNA nanoassembly, incorporating multimeric therapeutic DNAzyme, was prepared for selective delivery of gene-silencing DNAzyme with requisite cofactors and auxiliary chemo-drugs. By virtue of the sequence-conservative duplex-specific nuclease, the endogenous miRNA catalyzes the successive and site-specific cleavage of DNA nanoassembly substrate (nominated as the localized RNA walking machine) and thus ensures the liberation/activation of therapeutic agents with high accuracy and efficacy. The miR-10b-stimulated DNAzyme was designed to downregulate the TWIST transcription factor, an upstream promotor of miR-10b, thus acquiring the self-sufficient downregulation of TWIST/miR-10b signaling nodes (self-adaptive negative feedback loop) for abrogating tumor metastasis and chemo-resistance issues.

AniMAIRE‐A New Openly Available Tool for Calculating Atmospheric Ionising Radiation Dose Rates and Single Event Effects During Anisotropic Conditions

AbstractAniMAIRE (Anisotropic Model for Atmospheric Ionising Radiation Effects) is a new model and Python toolkit for calculating radiation dose rates experienced by aircraft during anisotropic solar energetic particle events. AniMAIRE expands the physics of the MAIRE + model such that dose rate calculations can be performed for anisotropic solar energetic particle conditions by supplying a proton or alpha particle rigidity spectrum, a pitch angle distribution, and the conditions of Earth's magnetosphere. In this paper, we describe the algorithm and top‐level structure of AniMAIRE and showcase AniMAIRE's capabilities by analyzing the dose rate maps that AniMAIRE produces when the time‐dependent spectra and pitch angle distribution for Ground Level Enhancement (GLE) 71 are input. We find that the dose rates AniMAIRE produces for the event fall between the dose rates produced by the WASAVIES and CRAC:DOMO models. Dose rate maps that evolve throughout the event are also shown, and it is found that each peak in the input pitch angle distribution generates a dose rate hotspot in each of the polar regions. AniMAIRE has been made available openly online so that it can be downloaded and run freely on local machines and so that the space weather community can easily contribute to it using Github forking.

Analysis of regularized federated learning

Federated learning is an efficient machine learning tool for dealing with heterogeneous big data and privacy protection. Federated learning methods with regularization can control the level of communications between the central and local machines. Stochastic gradient descent is often used for implementing such methods on heterogeneous big data, to reduce the communication costs. In this paper, we consider such an algorithm called Loopless Local Gradient Descent which has advantages in reducing the expected communications by controlling a probability level. We improve the method by allowing flexible step sizes and carry out novel analysis for the convergence of the algorithm in a non-convex setting in addition to the standard strongly convex setting. In the non-convex setting, we derive rates of convergence when the smooth objective function satisfies a Polyak-Łojasiewicz condition. When the objective function is strongly convex, a sufficient and necessary condition for the convergence in expectation is presented.

An Improved Divide-and-Conquer Approach to Estimating Mean Functional, with Application to Average Treatment Effect Estimation

Mean estimation is an important issue in statistical inference and machine learning. We are concerned with estimating mean functional that is a function of several nonparametric functions when there is a large amount of observations. Directly estimating such mean functional through nonparametric smoothing has the complexity of at least a quadratic order of the sample size, which is computationally prohibitive for massive data. The divide-and-conquer approach are thus readily used to alleviate the computational complexity issue, which however imposes a stringent condition on the sample size in each local machine if a locally optimal bandwidth is used. To address this issue, we suggest to use a globally optimal bandwidth in each local machine, which alleviates the restriction on the local sample sizes substantially. We show that the divide-and-conquer approach with a globally optimal bandwidth achieves the estimation efficiency bound as if all observations were pooled together. In terms of computational efficiency, our proposal outperforms the pooled algorithm dramatically. We demonstrate these properties through average treatment effect estimation from both the asymptotic and the non-asymptotic perspectives.

Distributed Learning in Intelligent Transportation Systems: A Survey

The development of artificial intelligence (AI) and self-driving technology is expected to enhance intelligent transportation systems (ITSs) by improving road safety and mobility, increasing traffic flow, and reducing vehicle emissions in the near future. In an ITS, each autonomous vehicle acts as a node with its own local machine learning models, which can be updated using locally collected data. However, for autonomous vehicles to learn effective models, they must be able to learn from data sources provided by other vehicles and infrastructure, utilizing innovative learning methods to adapt to various autonomous driving scenarios. Distributed learning plays a crucial role in implementing these learning tasks in an ITS. This review provides a systematic overview of distributed learning in the field of ITSs. Within an ITS, vehicles can engage in distributed learning by interacting with peers through opportunistic encounters and clustering. This study examines the challenges associated with distributed learning, focusing on issues related to privacy and security in data intelligence sharing, communication quality and speed, and trust. Through a thorough analysis of these challenges, this study presents potential research avenues to address these issues, including the utilization of incentive mechanisms that rely on reputation, the adoption of rapid convergence techniques, and the integration of opportunistic federated learning with blockchain technology.

Breaking the size limitation of nonadiabatic molecular dynamics in condensed matter systems with local descriptor machine learning

Nonadiabatic molecular dynamics (NA-MD) is a powerful tool to model far-from-equilibrium processes, such as photochemical reactions and charge transport. NA-MD application to condensed phase has drawn tremendous attention recently for development of next-generation energy and optoelectronic materials. Studies of condensed matter allow one to employ efficient computational tools, such as density functional theory (DFT) and classical path approximation (CPA). Still, system size and simulation timescale are strongly limited by costly ab initio calculations of electronic energies, forces, and NA couplings. We resolve the limitations by developing a fully machine learning (ML) approach in which all the above properties are obtained using neural networks based on local descriptors. The ML models correlate the target properties for NA-MD, implemented with DFT and CPA, directly to the system structure. Trained on small systems, the neural networks are applied to large systems and long timescales, extending NA-MD capabilities by orders of magnitude. We demonstrate the approach with dependence of charge trapping and recombination on defect concentration in MoS2. Defects provide the main mechanism of charge losses, resulting in performance degradation. Charge trapping slows with decreasing defect concentration; however, recombination exhibits complex dependence, conditional on whether it occurs between free or trapped charges, and relative concentrations of carriers and defects. Delocalized shallow traps can become localized with increasing temperature, changing trapping and recombination behavior. Completely based on ML, the approach bridges the gap between theoretical models and realistic experimental conditions and enables NA-MD on thousand-atom systems and many nanoseconds.

Analyzing AWS Edge Computing Solutions to Enhance IoT Deployments

This paper explores integrating Internet of Things (IoT) deployments with edge computing, focusing on Amazon Web Services (AWS) as a key facilitator. It provides an analysis of AWS IoT services and their integration with edge computing technologies, addressing challenges, and practical applications across industries, and outlining future research directions. IoT and edge computing revolutionize data processing by enabling real-time analytics, reduced latency, and enhanced operational efficiency. IoT involves interconnected devices autonomously gathering and exchanging data, while edge computing processes data near its source, decentralizing data processing and minimizing data transmission to centralized servers. AWS facilitates scalable and secure infrastructures for IoT and edge computing. AWS IoT Core manages IoT device connectivity and data ingestion, AWS Greengrass extends AWS capabilities to edge devices, and AWS Lambda enables serverless computing, empowering efficient deployment and scaling of IoT applications. Centralized cloud architectures often struggle with vast IoT data. Edge computing decentralizes data processing, reducing latency, enhancing real-time capabilities, and minimizing bandwidth. AWS ensures secure device connectivity through AWS IoT Core, supporting various protocols for seamless integration with IoT devices. AWS Greengrass allows local data processing and machine learning at the edge, vital for environments with limited connectivity or stringent latency requirements. AWS Lambda supports serverless computing, enabling scalable, event-driven architectures without server management, crucial for fluctuating IoT workloads. In conclusion, AWS advances IoT capabilities at the edge, with practical implementations across industries. As IoT evolves, AWS remains pivotal, innovating to meet dynamic IoT deployment demands.

Interval-Censored Linear Quantile Regression

Censored quantile regression has emerged as a prominent alternative to classical Cox’s proportional hazards model or accelerated failure time model in both theoretical and applied statistics. While quantile regression has been extensively studied for right-censored survival data, methodologies for analyzing interval-censored data remain limited in the survival analysis literature. This article introduces a novel local weighting approach for estimating linear censored quantile regression, specifically tailored to handle diverse forms of interval-censored survival data. The estimation equation and the corresponding convex objective function for the regression parameter can be constructed as a weighted average of quantile loss contributions at two interval endpoints. The weighting components are nonparametrically estimated using local kernel smoothing or ensemble machine learning techniques. To estimate the nonparametric distribution mass for interval-censored data, a modified EM algorithm for nonparametric maximum likelihood estimation is employed by introducing subject-specific latent Poisson variables. The proposed method’s empirical performance is demonstrated through extensive simulation studies and real data analyses of two HIV/AIDS datasets. Supplementary materials for this article are available online.

Global and Local Interpretable Machine Learning Allow Early Prediction of Unscheduled Hospital Readmission

Global and Local Interpretable Machine Learning Allow Early Prediction of Unscheduled Hospital Readmission

Examining Beam Matching in the Commissioning of a Halcyon Accelerator

This study aims to describe the steps needed to be made in developing a commissioning report of a Halcyon linear accelerator utilizing the manufacturer’s golden beam data (GBD) as a reference in making the evaluation. The platform herein has determined the performance alignment of our local machine with the GBD obtained through comprehensive analyses. This made use of the gamma index and relative dose difference. This paper details the methodologies and outcomes of comparing local measurements against GBD during commissioning. For the Halcyon linear accelerator, dosimetric data, including percentage depth doses, dose profiles, and output factors, were acquired using a three-dimensional scanning water tank and various ionization chambers. The GBD were exported from the treatment planning system and compared to the measurements. To evaluate the agreement between the GBD and measurements, gamma index and relative dose difference analyses were conducted. For field sizes greater than 4 × 4 cm2, percentage depth doses and beam profiles, the gamma indices between GBD and measurements were less than 1%/1 mm. The gamma indices were found to be slightly greater for field sizes 2 × 2 cm2 and 4 × 4 cm2, remaining within 2%/2 mm, satisfying the American Association of Physicists in Medicine Medical Physics Practice Guideline 5 for commissioning and quality assurance of mega-volt photon beams. Deviations in the output factor between the GBD and measurements were not significant, remaining within 1%. The GBD data were evaluated in the commissioning of a Halcyon linear accelerator, with analyses being made of the gamma index and relative dose difference. The gamma index analysis is shown to be an effective method for comprehensively evaluating deviations between the GBD and measurements in the beam matching process.

Simulation analysis of deformation during machining curved thin-walled structures of aluminum alloy

Abstract Impeller parts are widely used in key parts of equipment such as aerospace, ocean, and energy. Their curved thin-walled structures are prone to local machining deformation and elastic tool yielding during the cutting process, reducing their machining quality. Therefore, to improve the machining accuracy of such parts, an empirical formula and simulation model for cutting force machining are established. Based on the Abaqus secondary development platform, the deformation patterns of parts machining are simulated and predicted, and the machining deformation amounts of different cutting methods are compared and analyzed. The results show that the deformation of single-side cutting is significantly greater than that of symmetrical and stepped cutting, and the maximum deformation is reduced from 0.047 mm to 0.029 mm, which can effectively improve the machining accuracy.

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

Federated learning (FL) refers to a system of training and stabilizing local machine learning models at the global level by aggregating the learning gradients of the models. It reduces the concern of sharing the private data of participating entities for statistical analysis to be carried out at the server. It allows participating entities called clients or users to infer useful information from their raw data. As a consequence, the need to share their confidential information with any other entity or the central entity called server is eliminated. FL can be clearly interpreted as a privacy-preserving version of traditional machine learning and deep learning algorithms. However, despite this being an efficient distributed training scheme, the client’s sensitive information can still be exposed to various security threats from the shared parameters. Since data has always been a major priority for any user or organization, this article is primarily concerned with discussing the significant problems and issues relevant to the preservation of data privacy and the viability and feasibility of several proposed solutions in the FL context. In this work, we conduct a detailed study on FL, the categorization of FL, the challenges of FL, and various attacks that can be executed to disclose the users’ sensitive data used during learning. In this survey, we review and compare different privacy solutions for FL to prevent data leakage and discuss secret sharing (SS)-based security solutions for FL proposed by various researchers in concise form. We also briefly discuss quantum federated learning (QFL) and privacy-preservation techniques in QFL. In addition to these, a comparison and contrast of several survey works on FL is included in this work. We highlight the major applications based on FL. We discuss certain future directions pertaining to the open issues in the field of FL and finally conclude our work.

CCW-YOLOv5: A forward-looking sonar target method based on coordinate convolution and modified boundary frame loss.

Multi beam forward looking sonar plays an important role in underwater detection. However, due to the complex underwater environment, unclear features, and susceptibility to noise interference, most forward looking sonar systems have poor recognition performance. The research on MFLS for underwater target detection faces some challenges. Therefore, this study proposes innovative improvements to the YOLOv5 algorithm to address the above issues. On the basis of maintaining the original YOLOv5 architecture, this improved model introduces transfer learning technology to overcome the limitation of scarce sonar image data. At the same time, by incorporating the concept of coordinate convolution, the improved model can extract features with rich positional information, significantly enhancing the model's detection ability for small underwater targets. Furthermore, in order to solve the problem of feature extraction in forward looking sonar images, this study integrates attention mechanisms. This mechanism expands the receptive field of the model and optimizes the feature learning process by highlighting key details while suppressing irrelevant information. These improvements not only enhance the recognition accuracy of the model for sonar images, but also enhance its applicability and generalization performance in different underwater environments. In response to the common problem of uneven training sample quality in forward looking sonar imaging technology, this study made a key improvement to the classic YOLOv5 algorithm. By adjusting the bounding box loss function of YOLOv5, the model's over sensitivity to low-quality samples was reduced, thereby reducing the punishment on these samples. After a series of comparative experiments, the newly proposed CCW-YOLOv5 algorithm has achieved detection accuracy in object detection mAP@0.5 Reached 85.3%, and the fastest inference speed tested on the local machine was 54 FPS, showing significant improvement and performance improvement compared to existing advanced algorithms.

Estimation of mode I quasi-static fracture of notched aluminum–lithium AW2099-T83 alloy using local approaches and machine learning

Aluminum–lithium (Al–Li) alloys offer superior performance under different conditions that involve mechanical loading, high temperature and corrosive environment. Therefore, Al–Li alloys are being used in the defense, aerospace, and aircraft industries, specifically in structural parts such as fuselage, empennage, and wings. By modifying the chemical composition, a third generation of Al–Li alloys has been introduced to overcome the mechanical and thermal shortcomings of previous Al–Li generations. As structural parts usually contain notches, it is of paramount importance to study the strength of the newly introduced alloys in the presence of such geometrical discontinuities to select the suitable alloy for a particular application. The aim of this work is to analyze the strength of U and V-notched specimens machined from extruded AW2099-T83 Al–Li alloys under quasi-static loading. The fracture stress of specimens with various notch radii and angles were estimated using strain energy density (SED) and the theory of critical distances (TCD) methods. A support vector machine (SVM) regression model was also implemented to assess the applicability of estimating fracture stress using machine learning approaches. The results show an average absolute discrepancy of 6.6 %, 7.8 % and 2.8 % for SED, TCD and SVM methods, respectively.

Perception-Dominant Control Types for Human/Machine Systems

We explore a novel approach to complex domain modelling by emphasising primitives based on perception. The usual approach either focuses on actors or cognition associated with tokens that convey information. In related research, we have examined using effects and/or outcomes as primitives, and influences as the generator of those outcomes via categoric functors. That approach (influences, effects) has advantages: it leverages what is known and supports the expanded logics we use, where we want to anticipate and engineer possible futures. But it has weaknesses when placed in a dynamic human-machine system where what is perceived or assumed matters more than what is known. The work reported here builds on previous advances in type specification and reasoning to ‘move the primitives forward’ more toward situation encounter and away from situation understanding. The goal is in the context of shared human-machine systems where: • reaction times are shorter than the traditional ingestion/comprehension/response loop can support; • situations that are too complex or dynamic for current comprehension by any means; • there simply is insufficient knowledge about governing situations for the comprehension model to support action; and/or, • the many machine/human and system/system interfaces that are incapable of conveying the needed insights; that is, the communication channels choke the information or influence flows. While the approach is motivated by the above unfriendly conditions, we expect significant benefits. We will explore these but engineer toward a federated decision paradigm where decisions by local human, machine or synthesis are not whole-situation-aware, but that collectively ‘swarm’ locally across the larger system to be more effective, ‘wiser’ than a convention paradigm may produce. The supposed implementation strategy will be through extending an existing ‘playbooks as code’ project whose goals are to advise on local action by modelling and gaming complex system dynamics. A sponsoring context is ‘grey zone’ competition that avoids armed conflict, but that can segue to a mixed system course of action advisory. The general context is a costly ‘blue swan’ risk in large commercial and government enterprises. The method will focus on patterns and relationships in synthetic categories used to model type transitions within topological models of system influence. One may say this is applied intuitionistic type theory, following mechanisms generally described by synthetic differential geometry. In this context, the motivating supposition of this study is that information-carrying influence channels are best modelled in our challenging domain as perceived types rather than understood types.

A Novel Strategy for Automatic Selection of Cross‐Basin Data to Improve Local Machine Learning‐Based Runoff Models

AbstractPrevious studies have shown that regional deep learning (DL) models can improve runoff prediction by leveraging large hydrological datasets. However, training a DL regional model using all data without screening may degrade local performance. This study focuses on constructing enhanced local models through the utilization of cross‐basin data. To this end, we propose an approach that employs a novel training strategy to optimize DL model training for specific basins. The approach measures the impact of any one basin's gradient on the loss of the basin of interest, providing insights into the relationships between different basins. The approach was validated using 531 basins from the CAMELS dataset. Results suggest that local performance degradation is a common occurrence in regional models, and imbalanced data are likely to result in a specific pattern dominating the entire regional model. In comparison to a regional model simply trained with all basins, the median Nash‐Sutcliffe efficiency (NSE) for our models is 0.031 higher. In particular, the increase in NSE can exceed 0.2 for some dry basins. Our findings indicate that this novel DL strategy can significantly improve model performance in specific basins using large hydrological datasets, while mitigating local performance loss.

Computational Techniques in PET/CT Image Processing for Breast Cancer: A Systematic Mapping Review

The problem arises from the lack of sufficient and comprehensive information about the necessary computer techniques. These techniques are crucial for developing information systems that assist doctors in diagnosing breast cancer, especially those related to positron emission tomography and computed tomography (PET/CT). Despite global efforts in breast cancer prevention and control, the scarcity of literature poses an obstacle to a complete understanding in this area of interest. The methodologies studied were systematic mapping and systematic literature review. For each article, the journal, conference, year of publication, dataset, breast cancer characteristics, PET/CT processing techniques, metrics and diagnostic yield results were identified. Sixty-four articles were analyzed, 44 (68.75%) belong to journals and 20 (31.25%) belong to the conference category. A total of 102 techniques were identified, which were distributed in preprocessing with 7 (6.86%), segmentation with 15 (14.71%), feature extraction with 15 (14.71%), and classification with 65 (63.73%). The techniques with the highest incidence identified in each stage are: Gaussian Filter, SLIC, Local Binary Pattern, and Support Vector Machine with 4, 2, 7, and 35 occurrences, respectively. Support Vector Machine is the predominant technique in the classification stage, due to the fact that Artificial Intelligence is emerging in medical image processing and health care to make expert systems increasingly intelligent and obtain favorable results.