Automatic Strategy Research Articles

Autonomous Attack Mitigation Through Firewall Reconfiguration

ABSTRACTPacket filtering firewalls represent a main defense line against cyber attacks that target computer networks daily. However, the traditional manual approaches for their configuration are no longer applicable to next‐generation networks, which have become much more complex after the introduction of virtualization paradigms. Some automatic strategies have been investigated in the literature to change that old‐fashioned configuration approach, but they are not fully autonomous and still require several human interventions. In order to overcome these limitations, this paper proposes an autonomous approach for firewall reconfiguration where all steps are automated, from the derivation of the security requirements coming from the logs of IDSs to the deployment of the automatically computed configurations. A core component of this process is React‐VEREFOO, which models the firewall reconfiguration problem as a Maximum Satisfiability Modulo Theories problem, allowing the combination of full automation, formal verification, and optimization in a single technique. An implementation of this proposal has undergone experimental validation to show its effectiveness and performance.

A two-stage adaptive consensus reaching process with improved automatic strategy for multi-attribute large group emergency decision-making

The multi-attribute large group emergency decision-making (MALGEDM) problem has gained increasing attention and becomes an important topic in the field of decision-making. The existing consensus models, however, rarely consider the effective balance between experts’ willingness and time consumption. To address this problem, we design a two-stage adaptive consensus reaching process that combines two models of the minimum adjustment amount and the minimum iteration number in the MALGEDM context. The process can achieve consensus with an improved automatic strategy that considers experts’ willingness. Firstly, the self-organizing map algorithm is employed to classify large group heterogeneous experts into multiple subgroups for the dual decision of clustering and expert categories. Secondly, we classify different degrees of consensus into four scenarios (low, medium, medium-high, and high). On this basis, we have constructed a two-stage adaptive consensus model that incorporates the novel possibility degree. The minimum adjustment amount of the adaptive feedback process can be obtained by the optimization model in the first stage, which is used as a constraint for considering the experts’ willingness in the second stage. Finally, the practicality and timeliness of the proposed model is verified through an illustrative example of emergency decision-making. Moreover, comparative analyses are conducted to highlight the superiority of the proposed model.

DRRGlobal: Uncovering the weak phases from global seismograms using the damped rank-reduction method

Some target seismic signals in the earthquake data can be very weak compared with interfering phases, and are thus difficult to detect, which further hinders the effective usage of these weak phases for subsequent high-resolution imaging of earth interiors. The strong ambient noise makes this situation even more troublesome since the weak signals can be mostly buried in the noise. Here, we present an open-source package for uncovering the weak phases from global seismograms. We adopt a two-step scheme to reconstruct and denoise array data. The first step is weighted average interpolation which puts the data into irregular grids. The second step adopts the weighted projection-onto-convex sets based on damped rank-reduction to further interpolate and denoise for the binned data. Taking the complexity of the weak signal into consideration, we adopt the automatic strategy to select an appropriate rank in different localized windows. We conduct several synthetic tests to carefully investigate the performance regarding effectiveness, robustness, and efficiency, and compare the algorithm with the frequency–wavenumber-domain projection onto convex sets method that is already used in the global seismology literature. Finally, the proposed framework is validated via a recorded array data set of the 1995 May 5 Philippines earthquake.

The Self-Control of Eating.

Many individuals struggle to regulate their own consumption of food. Beginning with general theories of self-control, we review psychological factors that have been shown to influence the regulation of eating, including those related to particular personality variables, such as external eating, restrained eating, and reward sensitivity, as well as situational constraints, including normative influences, emotions, and calorie deprivation. Strategies for the self-control of eating, including reappraisal, effortful inhibition, and various automatic strategies are also reviewed, along with a discussion of the strengths and limitations of historical and contemporary psychological studies investigating food consumption. Whereas extensive examinations of food preferences and body weight have appeared in the psychological literature, we call for more robust research that prioritizes actual eating as the primary dependent measure.

Buildability of complex 3D-printed concrete geometries using Peridynamics

As a formwork-free construction method, 3D–printed concrete (3DPC) shows great advantages in forming complex structures; but encounters buildability problems. To address this, this paper presents a fluid-solid integrated peridynamic (PD) model to describe the fluid-to-solid transition of 3DPC. On this basis, an automatic strategy is proposed to deal with complex geometries. Programming by Python, PD particles are automatically generated by the input geometric model and arranged in a layer-wise manner for 3D printing simulation. The particles are then connected into inter- and intra-layer bonds to model the weak interface between layers. This establishes a connection between digital fabrication and PD simulation and offers a general way for 3DPC buildability analysis, which is assessed by the modeling of a 3D printing test and two digitally designed structures. The satisfactory results prove that the proposed method is applicable to structures with different geometries, thus enhancing the advantages of 3D printing.

Pulsed radiation image restoration based on unsupervised deep learning

The process of pulsed X-ray imaging generates noise and blurring that significantly degrade image quality, lead to loss of image information, and interfere with accurate diagnosis of X-ray spot size and objects. Traditional radiation image restoration methods lack flexibility and generalization. Furthermore, neural network methods based on supervised learning require many actual image data sets to be obtained in advance, which limits network training. In this paper, we propose an unsupervised radiation image restoration method based on a deep image prior. The classical DeepRED framework is extended by adding weight-adaptive variational regularization. Automatic strategies are employed to estimate local regularization parameters, resulting in better noise removal and preservation of image edges and texture structures. The proposed method is evaluated through numerical simulations and experimental studies of X-ray source images and flash radiographic images. The results indicate that the proposed method is effective in restoring pulsed radiation images, removing noise, and preserving boundary region information. Additionally, this method produces satisfactory results for the restoration of real neutron images, demonstrating its applicability in the field of radiation imaging.

Artificial compressibility method for high-pressure transcritical fluids at low Mach numbers

Supercritical fluids possess unique properties that makes them relevant in various scientific and engineering applications. However, the experimental investigation of these fluids is challenging due to the high pressures involved and their complex thermophysical behavior. To overcome these limitations, computational researchers employ scale-resolving methods, such as direct numerical simulation and large-eddy simulation to study them. Nonetheless, these methods require substantial computational resources, especially in the case of low-Mach-number regimes due to the disparity between acoustic and hydrodynamic/thermal time scales. This work, therefore, addresses this problem by extending the artificial compressibility method to high-pressure transcritical fluids. This method is based on decoupling the thermodynamic and hydrodynamic parts of the pressure field, such that the acoustic time scales can be externally modified without severely impacting the flow physics of the problem. In addition, the method proposed has two key characteristics: (i) the splitting method presents low computational complexity, and (ii) an automatic strategy for selecting the speedup factor of the approach is introduced. The effectiveness of the resulting methodology is demonstrated through comprehensive numerical tests of increasing complexity, showcasing its ability to accurately simulate a wide range of high-pressure transcritical flows including turbulence. The results obtained indicate that the approach proposed can readily lead to computational speedups larger than 10× without significantly compromising the accuracy of the numerical solutions.

A comprehensive model for assessing and classifying patients with thrombotic microangiopathy: the TMA-INSIGHT score

BackgroundThrombotic Microangiopathy (TMA) is a syndrome characterized by the presence of anemia, thrombocytopenia and organ damage and has multiple etiologies. The primary aim is to develop an algorithm to classify TMA (TMA-INSIGHT score).MethodsThis was a single-center retrospective cohort study including hospitalized patients with TMA at a single center. We included all consecutive patients diagnosed with TMA between 2012 and 2021. TMA was defined based on the presence of anemia (hemoglobin level < 10 g/dL) and thrombocytopenia (platelet count < 150,000/µL), signs of hemolysis, and organ damage. We classified patients in eight categories: infections; Malignant Hypertension; Transplant; Malignancy; Pregnancy; Thrombotic Thrombocytopenic Purpura (TTP); Shiga toxin-mediated hemolytic uremic syndrome (STEC-SHU) and Complement Mediated TMA (aHUS). We fitted a model to classify patients using clinical characteristics, biochemical exams, and mean arterial pressure at presentation.ResultsWe retrospectively retrieved TMA phenotypes using automatic strategies in electronic health records in almost 10 years (n = 2407). Secondary TMA was found in 97.5% of the patients. Primary TMA was found in 2.47% of the patients (TTP and aHUS). The best model was LightGBM with accuracy of 0.979, and multiclass ROC-AUC of 0.966. The predictions had higher accuracy in most TMA classes, although the confidence was lower in aHUS and STEC-HUS cases.ConclusionSecondary conditions were the most common etiologies of TMA. We retrieved comorbidities, associated conditions, and mean arterial pressure to fit a model to predict TMA and define TMA phenotypic characteristics. This is the first multiclass model to predict TMA including primary and secondary conditions.

An Integral R-Banded Karyotype Analysis System of Bone Marrow Metaphases Based on Deep Learning.

Conventional karyotype analysis, which provides comprehensive cytogenetic information, plays a significant role in the diagnosis and risk stratification of hematologic neoplasms. The main limitations of this approach include long turnaround time and laboriousness. Therefore, we developed an integral R-banded karyotype analysis system for bone marrow metaphases, based on deep learning. To evaluate the performance of the internal models and the entire karyotype analysis system for R-banded bone marrow metaphase. A total of 4442 sets of R-banded normal bone marrow metaphases and karyograms were collected. Accordingly, 4 deep learning-based models for different analytic stages of karyotyping, including denoising, segmentation, classification, and polarity recognition, were developed and integrated as an R-banded bone marrow karyotype analysis system. Five-fold cross validation was performed on each model. The whole system was implemented by 2 strategies of automatic and semiautomatic workflows. A test set of 885 metaphases was used to assess the entire system. The denoising model achieved an intersection-over-union (IoU) of 99.20% and a Dice similarity coefficient (DSC) of 99.58% for metaphase acquisition. The segmentation model achieved an IoU of 91.95% and a DSC of 95.79% for chromosome segmentation. The accuracies of the segmentation, classification, and polarity recognition models were 96.77%, 98.77%, and 99.93%, respectively. The whole system achieved an accuracy of 93.33% with the automatic strategy and an accuracy of 99.06% with the semiautomatic strategy. The performance of both the internal models and the entire system is desirable. This deep learning-based karyotype analysis system has potential in a clinical application.

A novel integrated automatic strategy for amino acid composition analysis of seeds from 67 species.

The composition and quantity of amino acids (AAs) in seeds are complicated due to the various origins and modifications of different species. In this study, a novel automatic neutral loss filtering (ANLF) strategy based on accurate mass searching by Python was developed to analyze the free and hydrolyzed AA-phenyl isothiocyanate (PITC) derivatives from seeds of Gymnosperm and Angiosperm phyla. Compared with traditional strategies, ANLF showed much higher accuracy in screening AA derivatives by filtering nitrogen-containing non-AA compounds and efficiency in processing large datasets. Meanwhile, the content phenotype of 20 proteinogenic AAs from seeds of these two families was characterized by a 35-min HPLC method combined with an automated peak-matching strategy. AA profiles of 232 batches of seeds from 67 species, consisting of 19 proteinogenic AAs, 21 modified AAs, and 77 unknown AAs, would be a good reference for their application in food and medicine.

An automatic and smart platform for rapid detection of cadmium and lead simultaneously in rice using triple-amplified chemiluminescence immunoassay

Rapid detection of trace ions is urgently needed for large-scale screening to ensure food safety. This study developed an innovative and automatic strategy, based on a smart-designed platform for rapid detection of cadmium and lead in rice. As bridge antibody, the antigen was conjugated with goat anti-mouse immunoglobulin G labeled alkaline phosphatase. Meanwhile, a biotin-streptavidin system was introduced to micromagnetic particles, thus providing a triple-amplified chemiluminescence immunoassay with high sensitivity, accuracy and specificity. The limits of detection for cadmium and lead were 0.06 and 1.00 ng mL−1, respectively, within 30 min. The recoveries ranged from 89.81 to 114.92 %, with relative standard deviations less than 9.2 %. The results obtained agreed with those of inductively coupled plasma–mass spectrometry and certified reference materials. Additionally, the auto-operation avoided human errors as well as being convenient, fast, automatic and high-throughput. Therefore, this smart platform can be applied for large-scale Cd2+ and Pb2+ screening.

An adaptive consensus model in large-scale group decision making with noncooperative and compromising behaviors

In recent years, different feedback mechanisms have been reported in many consensus models to improve decision levels. However, the improvement of decision level often leads to the reduction of decision efficiency, which has been rarely considered in existing consensus models. This paper proposes an adaptive consensus model consisting of automatic strategy and interactive strategy, which are implemented in different consensus stages to balance decision efficiency and decision level. In addition, the behavior diversity of decision makers (DMs) is often unavoidable, such as noncooperative behavior, which brings greater complexity to the consensus reaching. Meanwhile, cooperative behavior is usually accompanied by compromise behavior. Considering that the compromise behavior of DMs will change subgroup structure, dynamic cluster analysis is performed in the consensus reaching process. On the premise of dynamic clustering, the traditional weight penalty mechanism will fail to manage the noncooperative behaviors of subgroups. To this end, this paper proposes a new penalty mechanism. The proposed adaptive consensus model is applied to the selection of cities for establishing the freight hub. Finally, some numerical simulations and comparative analyses are presented to verify the effectiveness of the proposed model.

A Review on Pulsed Laser Fabrication of Nanomaterials in Liquids for (Photo)catalytic Degradation of Organic Pollutants in the Water System.

The water pollution caused by the release of organic pollutants has attracted remarkable attention, and solutions for wastewater treatment are being developed. In particular, the photocatalytic removal of organic pollutants in water systems is a promising strategy to realize the self-cleaning of ecosystems under solar light irradiation. However, at present the semiconductor-based nanocatalysts can barely satisfy the industrial requirements because their wide bandgaps restrict the effective absorption of solar light, which needs an energy band modification to boost the visible light harvesting via surface engineering. As an innovative approach, pulsed laser heating in liquids has been utilized to fabricate the nanomaterials in catalysis; it demonstrates multi-controllable features, such as size, morphology, crystal structure, and even optical or electrical properties, with which photocatalytic performances can be precisely optimized. In this review, focusing on the powerful heating effect of pulsed laser irradiation in liquids, the functional nanomaterials fabricated by laser technology and their applications in the catalytic degradation of various organic pollutants are summarized. This review not only highlights the innovative works of pulsed laser-prepared nanomaterials for organic pollutant removal in water systems, such as the photocatalytic degradation of organic dyes and the catalytic reduction of toxic nitrophenol and nitrobenzene, it also critically discusses the specific challenges and outlooks of this field, including the weakness of the produced yields and the relevant automatic strategies for massive production.

A Comparative Study of Deep Learning Methods for Multi-Class Semantic Segmentation of 2D Kidney Ultrasound Images.

Ultrasound (US) imaging is a widely used medical imaging modality for the diagnosis, monitoring, and surgical planning for kidney conditions. Thus, accurate segmentation of the kidney and internal structures in US images is essential for the assessment of kidney function and the detection of pathological conditions, such as cysts, tumors, and kidney stones. Therefore, there is a need for automated methods that can accurately segment the kidney and internal structures in US images. Over the years, automatic strategies were proposed for such purpose, with deep learning methods achieving the current state-of-the-art results. However, these strategies typically ignore the segmentation of the internal structures of the kidney. Moreover, they were evaluated in different private datasets, hampering the direct comparison of results, and making it difficult to determination the optimal strategy for this task. In this study, we perform a comparative analysis of 7 deep learning networks for the segmentation of the kidney and internal structures (Capsule, Central Echogenic Complex (CEC), Cortex and Medulla) in 2D US images in an open access multi-class kidney US dataset. The dataset includes 514 images, acquired in multiple clinical centers using different US machines and protocols. The dataset contains the annotation of two experts, but 321 images with complete segmentation of all 4 classes were used. Overall, the results demonstrate that the DeepLabV3+ network outperformed the inter-rater variability with a Dice score of 78.0% compared to 75.6% for inter-rater variability. Specifically, DeepLabV3Plus achieved mean Dice scores of 94.2% for the Capsule, 85.8% for the CEC, 62.4% for the Cortex, and 69.6% for the Medulla. These findings suggest the potential of deep learning-based methods in improving the accuracy of kidney segmentation in US images.Clinical Relevance- This study shows the potential of DL for improving accuracy of kidney segmentation in US, leading to increased diagnostic efficiency, and enabling new applications such as computer-aided diagnosis and treatment, ultimately resulting in improved patient outcomes and reduced healthcare costs.1.

Correlation-based sparse inverse Cholesky factorization for fast Gaussian-process inference

Gaussian processes are widely used as priors for unknown functions in statistics and machine learning. To achieve computationally feasible inference for large datasets, a popular approach is the Vecchia approximation, which is an ordered conditional approximation of the data vector that implies a sparse Cholesky factor of the precision matrix. The ordering and sparsity pattern are typically determined based on Euclidean distance of the inputs or locations corresponding to the data points. Here, we propose instead to use a correlation-based distance metric, which implicitly applies the Vecchia approximation in a suitable transformed input space. The correlation-based algorithm can be carried out in quasilinear time in the size of the dataset, and so it can be applied even for iterative inference on unknown parameters in the correlation structure. The correlation-based approach has two advantages for complex settings: It can result in more accurate approximations, and it offers a simple, automatic strategy that can be applied to any covariance, even when Euclidean distance is not applicable. We demonstrate these advantages in several settings, including anisotropic, nonstationary, multivariate, and spatio-temporal processes. We also illustrate our method on multivariate spatio-temporal temperature fields produced by a regional climate model.

Systematic assessment and review of techniques based on tumour detection in brain using MRI

ABSTRACT Detecting tumour with Magnetic Resonance imaging (MRI) has been promising in recent years. The current tumour detection strategies are used for visualising, digitising and modelling the images for medical diagnosis. Automatic tumour region segmentation from 3D MRIs is essential for monitoring, diagnosing, and planning the treatment remedies for the disease. However, manual outlining needs an anatomical understanding which requires more time and can be imprecise due to human error. Brain tumour is serious diseases whose exposure must be quick and precise. It is attained by the accomplishment of the automatic detection of the tumour using MRI. Several automatic strategies are employed in literary works, which utilise image segmentation. Here, 50 research papers are surveyed with brain tumour detection strategies like ANN, clustering, deep learning, edge-based techniques, optimisation and transformation strategies. Furthermore, complete exploration is done in terms of publication year, employed strategy, datasets utilised, execution tool, performance measures and its values. At last, the problems of classical strategies and its issues with classical brain tumour detection methods are illustrated to generate the contribution.

Digital Warehouse System for Vegetable Preservation

Vegetable preservation is the process of storing vegetables for longer days by treating them in a right way. This enables the vegetables to not get waste from natural process. There are several technics followed in the agriculture field for preservation based on the nature of vegetables and fruits. Drying, pickling, canning, freezing, fermenting, salting and oil packing are some of the techniques that are widely employed for vegetable preservation. The proposed work aims to regulate the vegetable preservation process in the warehouse system by treating them with an automatic strategy. The strategy controls the temperature and humidity of the warehouse through customized fuzzy control algorithm included in the arduino microcontroller. The algorithm is designed to specify the kind of vegetable placed in the warehouse module for estimating the required temperature and humidity by its own. An experimental study is performed in the work to project the betterment of the work in terms of vegetable preserving days and efficiency over the manual and uncontrolled preservation methods.

A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Chronic Venous Disorders (CVD) of the lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. Due to the exponential growth of the aging population and the worsening of CVD with age, it is expected that the healthcare costs and the resources needed for the treatment of CVD will increase in the coming years. The early diagnosis of CVD is fundamental in treatment planning, while the monitoring of its treatment is fundamental to assess a patient’s condition and quantify the evolution of CVD. However, correct diagnosis relies on a qualitative approach through visual recognition of the various venous disorders, being time-consuming and highly dependent on the physician’s expertise. In this paper, we propose a novel automatic strategy for the joint segmentation and classification of CVDs. The strategy relies on a multi-task deep learning network, denominated VENet, that simultaneously solves segmentation and classification tasks, exploiting the information of both tasks to increase learning efficiency, ultimately improving their performance. The proposed method was compared against state-of-the-art strategies in a dataset of 1376 CVD images. Experiments showed that the VENet achieved a classification performance of 96.4%, 96.4%, and 97.2% for accuracy, precision, and recall, respectively, and a segmentation performance of 75.4%, 76.7.0%, 76.7% for the Dice coefficient, precision, and recall, respectively. The joint formulation increased the robustness of both tasks when compared to the conventional classification or segmentation strategies, proving its added value, mainly for the segmentation of small lesions.

Automatic digital optical heterodyne phase locking loop in the milliradian domain for spaceborne laser interferometry.

We developed a digital optical phase locking loop (OPLL) with three advantages, including high precision of phase locking, high control bandwidth up to 2.8 MHz, and automatic laser locking strategy. Spaceborne laser interferometers will be used to measure tiny displacements caused by gravitational waves in millions of kilometers range. A slave laser will be heterodyne phase locked to the incoming weak light at the end of an arm, emitting a higher power light back to the other satellite to measure pathlength variations at the picometer level. Such accuracy requires extremely precise OPLL. We report an experiment to demonstrate a digital OPLL that can automatically lock two independent free-running Nd:YAG lasers with residual phase error below 1mrad/Hz above 0.01 Hz, which is the best performance recorded for digital servos, to our knowledge. Such performance tested under a normal laboratory environment will be highly improved in a vacuum environment with temperature and vibration well controlled. Both the digital OPLL and the automatic strategy were implemented on a field programmable gate array that could be potentially used for future gravitational-wave detection. Our experiment might change the thinking of scientists who study phasemeters of gravitational-wave detection because we are aware that the digital phase locking loop used for "optical phase tracking" is differently designed from "optical phase locking."

Application of Deep Learning Approach for the Classification of Buildings’ Degradation State in a BIM Methodology

Currently, there is extensive research focused on automatic strategies for the segmentation and classification of 3D point clouds, which can accelerate the study of a landmark and integrate it with heterogeneous data and attributes, useful to facilitate the digital management of architectural heritage data. In this work, an automated image-based survey has been exploited a Region- Based Convolutional Neural Network. The training phase has been executed providing examples of images with the anomalies to be detected. At the same time, a laser scanning process was conducted to obtain a point cloud, which acts as a reference for the BIM process. In a final step, a process of projecting information from the images onto the BIM recreates the pathology shapes on the model’s objects, which generates a decision support system for the built environment. The innovation of this research concerns the development of a workflow in which it is possible to automatize the recognition and classification of defects in historical buildings, to finally interpolate this geometric and numerical information with a BIM methodology, obtaining a representation and quantification of the information adapted to the facility management process. The use of innovative techniques such as artificial intelligence algorithms and different plug-ins becomes the main strength of this project.