Search

Optical coherence tomography (OCT) has been identified as a non-invasive and inexpensive imaging modality to discover potential biomarkers for Alzheimer's diagnosis and progress determination. Current hypotheses presume the thickness of the retinal layers, which are analyzable within OCT scans, as an effective biomarker for the presence of Alzheimer's. As a logical first step, this work concentrates on the accurate segmentation of retinal layers to isolate the layers for further analysis. This paper proposes a generative adversarial network (GAN) that concurrently learns to increase the image resolution for higher clarity and then segment the retinal layers. We propose a multi-stage and multi-discriminatory generative adversarial network (MultiSDGAN) specifically for superresolution and segmentation of OCT scans of the retinal layer. The resulting generator is adversarially trained against multiple discriminator networks at multiple stages. We aim to avoid early saturation of generator model training leading to poor segmentation accuracies and enhance the process of OCT domain translation by satisfying all the discriminators in multiple scales. We also investigated incorporating the Dice loss and Structured Similarity Index Measure (SSIM) as additional loss functions to specifically target and improve our proposed GAN architecture's segmentation and superresolution performance, respectively. The ablation study results conducted on our data set suggest that the proposed MultiSDGAN with ten-fold cross-validation (10-CV) provides a reduced equal error rate with 44.24% and 34.09% relative improvements, respectively (p-values of the improvement level tests .01). Furthermore, our experimental results also demonstrate that the addition of the new terms to the loss function improves the segmentation results significantly by relative improvements of 31.33% (p-value .01).

Establishing spatial correspondence between subject and template images is necessary in neuroimaging research and clinical applications such as brain mapping and stereotactic neurosurgery. Our anatomical fiducial (AFID) framework has recently been validated to serve as a quantitative measure of image registration based on salient anatomical features. In this study, we sought to apply the AFIDs protocol to the clinic, focusing on structural magnetic resonance images obtained from patients with Parkinson’s disease (PD). We confirmed AFIDs could be placed to millimetric accuracy in the PD dataset with results comparable to those in normal control subjects. We evaluated subject-to-template registration using this framework by aligning the clinical scans to standard template space using a robust open preprocessing workflow. We found that registration errors measured using AFIDs were higher than previously reported, suggesting the need for optimization of image processing pipelines for clinical grade datasets. Finally, we examined the utility of using point-to-point distances between AFIDs as a morphometric biomarker of PD, finding evidence of reduced distances between AFIDs that circumscribe regions known to be affected in PD including the substantia nigra. Overall, we provide evidence that AFIDs can be successfully applied in a clinical setting and utilized to provide localized and quantitative measures of registration error. AFIDs provide clinicians and researchers with a common, open framework for quality control and validation of spatial correspondence and the location of anatomical structures, facilitating aggregation of imaging datasets and comparisons between various neurological conditions. Supplementary Information The online version contains supplementary material available at 10.1007/s00429-021-02408-3.

In the 21st era, technological progressions challenged the dental professional to perform extremely risky and multifaceted procedures more reliably and harmless way using the finite element method (FEM) that can simulate and analyze the dental structures. As orthodontic revolve about the forces so FEM is one of the most accurate tools for the researchers in this ground. This review highlights the use of the finite element method in orthodontics and craniofacial research. This stores the different researches performed by using the finite element model to study the growth of the cranial structure, biomechanical reaction to orthopedic forces, orthodontic tooth movement, orthognathic surgeries application, and orthodontic implants

Muskingum models are a type of hydrological flood routing approach and vary only in the form of storage relationship. The storage relationship was first established based on the weighted arithmetic...

Structural engineering is focused on the safe and efficient design of infrastructure. Projects can range in size and complexity, many requiring massive amounts of materials and expensive construction and operational costs. Therefore, one of the primary objectives for structural engineers is a cost-effective design. Incorporating optimality criteria into the design procedure introduces additional complexities that result in problems that are nonlinear, nonconvex, and have a discontinuous solution space. Population-based optimization algorithms (known as metaheuristics) have been found to be very efficient approaches to these problems. Many researchers have developed and applied state-of-art metaheuristics to automate and optimize the design of real-world civil engineering problems. While there is a large body of published papers in this area, there are few comprehensive reviews that list, summarize, and categorize metaheuristic optimization in structural engineering. This paper provides an extensive survey of a wide range of metaheuristic techniques to structural engineering optimization problems. Also, information is provided on available structural engineering benchmark problems, the formulation of different objective functions, and the handling of various types of constraints. The performance of different optimization techniques is compared for many benchmark problems.

Computational modeling of microbial communities using GEnome-scale Models (GEMs) of metabolism is a new frontier in systems biology. Here, we discuss recent developments in this area ranging from high-throughput GEMs reconstruction pipelines to approaches for modeling under steady-state and for simulating temporal, evolutionary, and spatiotemporal dynamics of microbial communities. We categorize these approaches based on flux balance analysis or elementary mode analysis of mixed-bag and compartmentalized GEMs and discuss their scope of applications and scalability for large-scale simulations. In addition, we review computational tools using GEMs for the design of microbial communities and recent efforts to integrate GEMs and machine learning for predicting interspecies interactions. We conclude by discussing best practices for using these tools and potential avenues for future development.

In this study, the utility of using Google Street View (GSV) for evaluating the quality of pavement is investigated. A convolutional neural network (CNN) is developed to perform image classification on GSV pavement images. Pavement images are extracted from GSV and then divided into smaller image patches to form data sets. Each image patch is visually classified into different categories of pavement cracks based on the standard practice. A comparative study of pavement quality assessment is conducted between the results of the CNN classified image patches obtained from GSV and those from a sophisticated commercial visual inspection company. The result of the comparison indicates the feasibility and effectiveness of using GSV images for pavement evaluation. The trained network is then tested on a new data set. This study shows that the designed CNN helps classify the pavement images into different defined crack categories.

Modern machine learning (ML) tools, such as artificial neural networks (ANNs) and support vector machines (SVMs), can provide highly accurate/precise predictions and estimations. However, in terms of explainability and interpretability, they are poor. To compromise between these key performance criteria, symbolic regression (SR) techniques could be used. However, they are hard to program because they have complicated mechanisms and need special optimization algorithms. The universal functions originator (UFO) is a new ML computing system that can be used in many computationbased applications. In addition to describing the variability of data sets as pure mathematical equations, this unique computing system has a very simple structure, and it can be initiated by any known optimization algorithm, including the most primitive ones, such as random search algorithms. This article introduces the UFO and shows why the system is so important to cybernetic applications.

Docker containers have become a prominent solution for supporting modern enterprise applications due to the highly desirable features of isolation, low overhead, and efficient packaging of the application’s execution environment. Containers are created from images which are shared between users via a registry. The amount of data registries store is massive. For example, Docker Hub, a popular public registry, stores at least half a million public images. In this article, we analyze over 167 TB of uncompressed Docker Hub images, characterize them using multiple metrics and evaluate the potential of file-level deduplication. Our analysis helps to make conscious decisions when designing storage for containers in general and Docker registries in particular. For example, only 3 percent of the files in images are unique while others are redundant file copies, which means file-level deduplication has a great potential to save storage space. Furthermore, we carry out a comprehensive analysis of both small I/O request performance and copy-on-write performance for multiple popular container storage drivers. Our findings can motivate and help improve the design of data reduction and caching methods for images, pulling optimizations for registries, and storage drivers.

Developing a land-use model for large-scale cases is a topic that has received less attention in the literature, while it is crucial for transportation engineers and urban planners to analyze the effect of various policies in multi-jurisdiction metropolitan areas and to some extent on a statewide scale. While gravity-based models are too simplistic, microsimulation models require extensive data and massive computation. This paper presents a land-use model that can be applied to large-scale geographies using publicly available data and be able to forecast demographic and socioeconomic attributes with reasonable accuracy and acceptable computational time. The proposed model incorporates Putman’s Integrated Transportation–Land-Use Package (ITLUP) and Kockelman’s Gravity-based Land-Use Model (G-LUM) fundamentals with enhanced formulation of newly added variables and structural changes. Considering the nonconvex and nonlinear nature of the proposed model, we utilize an enhanced genetic algorithm for base year calibration. Further, we assess the accuracy of the model with backcasting validation. We utilize the state of Tennessee as the case study area and utilized all open-source data available to the model application. The model results show reasonably accurate estimates of households by size, employment by industry, and land utilization by condition. As applicable, the model outperforms G-LUM by accuracy ( R2 and Percentage of Good Prediction ( PGP)) and error measures (Mean Absolute Percentage Error ( MAPE)). The proposed land-use model has the potential to be applied for medium to large-scale geographies with reasonable accuracy in predicting socioeconomic, demographic, and land condition estimates by using publicly available data.

Virtual reality (VR) is an emerging technology that enables creation of digital objects and virtual animations in a digital immersive environment that can be visualised and interacted with through head mounted displays (HMD) and controllers.1 2 In the fields of cardiovascular medicine and surgery, an increasing number of reports have become available to demonstrate potential benefits of VR for education, surgical planning and simulation.2–7 In addition, VR has made its entrance into the world of communication and is an ongoing topic of interest in scientific research and promising new tools are being developed.8 Due to the recent COVID-19 outbreak, local authorities have implemented several protective measures such as physical distancing and gathering restrictions. These restrictions have also been partly implemented in hospitals, however, in the fields of cardiology and cardiac surgery, full restrictions could potentially be harmful to patients, and therefore, alternative meeting methods should be implemented locally. Recently, we have published an article in which we present examples of alternative methods for multidisciplinary meetings to minimise the risk of viral infection and to ensure good and ongoing regular patient care.8 By combining VR meeting platforms with various HMD’s, the user is able to immerse in a reality-like and fully 3D digital environment. VR-meeting platforms enable the users to get immersed in a virtual environment and provide them with digital tools (such as laser pointers and various meeting rooms) that enable VR-guided remote digital conferencing and televirtuality. By organising remote multidisciplinary meetings, direct physical interaction can be avoided, and the risk of viral transmission can be minimised. Until now, no studies on the organisation of clinical multidisciplinary heart team meetings in immersive VR are available in the literature. In order to study the feasibility, effectiveness and user experience of a VR-based multidisciplinary heart team meeting, we have set up an observational proof-of-concept study, which was accelerated by the COVID-19 pandemic. Here, we describe our first experience on the application of VR meeting platforms in the setting of multidisciplinary coronary revascularisation heart team meetings.

Performance variability is an important measure for a reliable high performance computing (HPC) system. Performance variability is affected by complicated interactions between numerous factors, suc...

There has been a prolific rise in the popularity of cloud storage in recent years. While cloud storage offers many advantages such as flexibility and convenience, users are typically unable to tell or control the actual locations of their data. This limitation may affect users’ confidence and trust in the storage provider, or even render cloud unsuitable for storing data with strict location requirements. To address this issue, we propose a system called LAST-HDFS which integrates Location-Aware Storage Technique (LAST) into the open source Hadoop Distributed File System (HDFS). The LAST-HDFS system enforces location-aware file allocations and continuously monitors file transfers to detect potentially illegal transfers in the cloud. Illegal transfers here refer to attempts to move sensitive data outside the (“legal”) boundaries specified by the file owner and its policies. Our underlying algorithms model file transfers among nodes as a weighted graph, and maximize the probability of storing data items of similar privacy preferences in the same region. We equip each cloud node with a socket monitor that is capable of monitoring the real-time communication among cloud nodes. Based on the real-time data transfer information captured by the socket monitors, our system calculates the probability of a given transfer to be illegal. We have implemented our proposed framework and carried out an extensive experimental evaluation in a large-scale real cloud environment to demonstrate the effectiveness and efficiency of our proposed system.

The growing use of nonlinear devices is introducing harmonics in the power system networks that results in distortion of current and voltage signals causing damage to the power distribution system. Therefore, in power systems, the elimination of harmonics is of great concern. This paper presents an efficient techno-economical approach to suppress harmonics and improve the power factor in the power distribution network using neural network algorithms-based Shunt Hybrid Active Power Filter (SHAPF), such as Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Recurrent Neural Network (RNN). The objective of the proposed algorithms for SHAPF is to reduce Total Harmonic Distortion (THD) within an acceptable range to improve system quality. In our filter design approach, we tested and compared conventional pq0 theory and neural networks to detect the harmonics present in the power system. Moreover, for the regulation of the DC supply to the inverter of the SHAPF, the conventional PI controller and neural networks-based controllers are used and compared. The applicability of the proposed filter is tested for three different nonlinear load cases. The simulation results show that the neural networks-based filter control techniques satisfy all international standards with minimum current THD, neutral wire current elimination, and small DC voltage fluctuations for voltage regulation current. Furthermore, all three neural network architectures are tested and compared based on accuracy and computational complexity, with RNN outperforming the rest.

DELAUNAYSPARSE contains both serial and parallel codes written in Fortran 2003 (with OpenMP) for performing medium- to high-dimensional interpolation via the Delaunay triangulation. To accommodate the exponential growth in the size of the Delaunay triangulation in high dimensions, DELAUNAYSPARSE computes only a sparse subset of the complete Delaunay triangulation, as necessary for performing interpolation at the user specified points. This article includes algorithm and implementation details, complexity and sensitivity analyses, usage information, and a brief performance study.

Data services such as search, discovery, and management in scalable distributed environments have traditionally been decoupled from the underlying file systems, and are often deployed using external databases and indexing services. However, modern data production rates, looming data movement costs, and the lack of metadata, entail revisiting the decoupled file system-data services design philosophy. In this article, we present TagIt, a scalable data management service framework aimed at scientific datasets, which can be integrated into prevalent distributed file system architectures. A key feature of TagIt is a scalable, distributed metadata indexing framework, which facilitates a flexible tagging capability to support data discovery. Furthermore, the tags can also be associated with an active operator, for pre-processing, filtering, or automatic metadata extraction, which we seamlessly offload to file servers in a load-aware fashion. We have integrated TagIt into two popular distributed file systems, i.e., GlusterFS and CephFS. Our evaluation demonstrates that TagIt can expedite data search operation by up to 10× over the extant decoupled approach.

Enterprise KV stores are often not well suited for HPC applications, and thus cumbersome end-to-end KV design customization is required to meet the needs of modern HPC applications. To this end, in this article we present bespoKV, an adaptive, extensible, and scale-out KV store framework. bespoKV decouples the KV store design into the control plane for distributed management and the data plane for local data store. For the control plane, bespoKVprovides pre-built modules, called controlets, supporting common distributed functionalities (e.g., replication, consistency, and topology) and their various combinations. This decoupling allows bespoKV to take a user-provided single-server KV store, called a datalet, and transparently enables a scalable and fault-tolerant distributed KV store service. The resulting distributed stores are also adaptive to consistency or topology requirement changes and can be easily extended for new types of services. Such specializations enable innovative uses of KV stores in HPC applications, especially for emerging applications that utilize KV-friendly workloads. We evaluate bespoKV in a local testbed as well as in a public cloud settings. Experiments show that bespoKV-enabled distributed KV stores scale horizontally to a large number of nodes, and performs comparably and sometimes 1.2× to 2.6× better than the state-of-the-art systems.

The surge in the uptake of harmonic producing loads in 21st-century smart distribution networks has necessitated that robust data-driven approaches for harmonic assessment be developed. Moreover, there exists abundant harmonic data which can be leveraged on for the construction of this harmonic assessment tool. This is the objective of this study. Large volumes of time-stamped data acquired from a practical distribution network in Edmonton, Canada, have been used to construct a time-dependent cross-coupled harmonic model that has been combined with a formulated iterative time-dependent robust extended computer-aided harmonic power flows. The constructed harmonic power flow formulation also considered the constraints relating to the power conservation principle at the fundamental frequency. Practical network conditions including untransposed lines, load unbalance and skin effects of conductors have been thoroughly modelled. The proposed method has been applied to practical radial and weakly meshed medium voltage distribution networks and it demonstrated robustness to initialisation of the iterative procedure. Moreover, findings from this detailed data-driven technique reveal that harmonic impacts in the distribution networks depend on the quantum of harmonic levels, type of network and location of the harmonic sources.

The next-generation cellular systems, including fifth-generation cellular systems (5G), are empowered with the recent advances in artificial intelligence (AI) and other recent paradigms. The internet of things (IoT) and the tactile internet are paradigms that can be empowered with AI solutions and integrated with 5G systems to deliver novel services that impact the future. Machine learning technologies (ML) can understand examples of nonlinearity from the environment and are suitable for network traffic prediction. Network traffic prediction is one of the most active research areas that integrates AI with information networks. Traffic prediction is an integral approach to ensure security, reliability, and quality of service (QoS) requirements. Nowadays, it can be used in various applications, such as network monitoring, resource management, congestion control, network bandwidth allocation, network intrusion detection, etc. This paper performs time series prediction for IoT and tactile internet delays, using the k-step-ahead prediction approach with nonlinear autoregressive with external input (NARX)-enabled recurrent neural network (RNN). The ML was trained with four different training functions: Bayesian regularization backpropagation (Trainbr), Levenberg–Marquardt backpropagation (Trainlm), conjugate gradient backpropagation with Fletcher–Reeves updates (Traincgf), and the resilient backpropagation algorithm (Trainrp). The accuracy of the predicted delay was measured using three functions based on ML: mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE).

The Brain Imaging Data Structure (BIDS) established community consensus on the organization of data and metadata for several neuroimaging modalities. Traditionally, BIDS had a strong focus on functional magnetic resonance imaging (MRI) datasets and lacked guidance on how to store multimodal structural MRI datasets. Here, we present and describe the BIDS Extension Proposal 001 (BEP001), which adds a range of quantitative MRI (qMRI) applications to the BIDS application sphere. In general, the aim of qMRI is to characterize brain microstructure by quantifying the physical MR parameters of the tissue via computational, biophysical models. By proposing this new standard, we envision standardization of qMRI which makes multicenter dissemination of interoperable data possible. As a result, BIDS can act as a catalyst of convergence between qMRI methods development and application-driven neuroimaging studies that can help develop quantitative biomarkers for neural tissue characterization. Finally, our BIDS extension offers a common ground for developers to exchange novel imaging data and tools, reducing the practical barriers to standardization that is currently lacking in the field of neuroimaging.

The interior search algorithm (ISA) is an optimization algorithm inspired by esthetic techniques used for interior design and decoration. The algorithm has only one parameter, controlled by θ, and uses an evolutionary boundary constraint handling (BCH) strategy to keep itself within an admissible solution space while approaching the optimum. We apply the ISA to find optimal weight design of truss structures with frequency constraints. Sensitivity of the ISA's performance to the θ parameter and the BCH strategy is investigated by considering different values of θ and BCH techniques. This is the first study in the literature on the sensitivity of truss optimization problems to various BCH approaches. Moreover, we also study the impact of different BCH methods on diversification and intensification. Through extensive numerical simulations, we identified the best BCH methods that provide consistently better results for all truss problems studied, and obtained a range of θ that maximizes the ISA's performance for all problem classes studied. However, results also recommend further fine‐tuning of parameter settings for specific case studies to obtain the best results.

Brain atlases that encompass detailed anatomical or physiological features are instrumental in the research and surgical planning of various neurological conditions. Magnetic resonance imaging (MRI) has played important roles in neuro-image analysis while histological data remain crucial as a gold standard to guide and validate such analyses. With cellular-scale resolution, the BigBrain atlas offers 3D histology of a complete human brain, and is highly valuable to the research and clinical community. To bridge the insights at macro- and micro-levels, accurate mapping of BigBrain and established MRI brain atlases is necessary, but the existing registration is unsatisfactory. The described dataset includes co-registration of the BigBrain atlas to the MNI PD25 atlas and the ICBM152 2009b atlases (symmetric and asymmetric versions) in addition to manual segmentation of the basal ganglia, red nucleus, amygdala, and hippocampus for all mentioned atlases. The dataset intends to provide a bridge between insights from histological data and MRI studies in research and neurosurgical planning. The registered atlases, anatomical segmentations, and deformation matrices are available at: https://osf.io/xkqb3/., Measurement(s)neuroantomical mappingTechnology Type(s)computational modeling techniqueSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.9914126

In the current study, the performance of three evolutionary algorithms, differential algorithm (DE), evolution strategy (ES), and biogeography-based optimization algorithm (BBO), is examined for foundation design optimization. Moreover, four recent variations of evolutionary-based algorithms [i.e., improved differential evolution algorithm based on an adaptive mutation scheme, weighted differential evolution algorithm (WDE), linear population size reduction success-history-based adaptive differential evolution algorithm, and biogeography-based optimization with covariance matrix-based migration] have been tackled for handling the current problem. The objective function is based on the cost of shallow foundation designs that satisfy ACI 318-05 requirements is formulated as the objective function. This study addresses shallow footing optimization with two attitudes, routine optimization, and sensitivity analysis. As a further study, the effect of the location of the column at the top of the foundation is examined by adding two additional design variables. Three numerical case studies are used for both routine and sensitivity analysis. Moreover, the most common evolutionary-based technique, genetic algorithm (GA), is considered as a benchmark to evaluate the proposed methods’ efficiency. Based on the results, there is no algorithm which works as the most efficient solver over all the cases; while, BBO and WDE showed an acceptable performance because of satisfying records in most cases. There were several cases in which GA, DE, and ES were incapable of finding a valid solution which meets all the constraints simultaneously.

In this paper, the design of a macro strip patch antenna with a photonic crystal structure has been studied. The purpose of this study is to create a photonic band gap (PBG) structure that can be used to design macro strip antennas. With this method, we can increase the bandwidth several times and increase the antenna’s gain. The noise and radiation loss of the antenna will also be significantly reduced by the use of PGB technology. The bandwidth of the antenna is 0.6 GHz to 1.6 THz. At 1.4 THz, the gain is 7.703 dB. This antenna is widely used in high frequency microwave transmitter and microwave receiver systems.

Exponential increases in complexity and scale make variability a growing threat to sustaining HPC performance at exascale. Performance variability in HPC I/O is common, acute, and formidable. We take the first step towards comprehensively studying linear and nonlinear approaches to modeling HPC I/O system variability in an effort to demonstrate that variability is often a predictable artifact of system design. Using over 8 months of data collection on 6 identical systems, we propose and validate a modeling and analysis approach (MOANA) that predicts HPC I/O variability for thousands of software and hardware configurations on highly parallel shared-memory systems. Our findings indicate nonlinear approaches to I/O variability prediction are an order of magnitude more accurate than linear regression techniques. We demonstrate the use of MOANA to accurately predict the confidence intervals of unmeasured I/O system configurations for a given number of repeat runs – enabling users to quantitatively balance experiment duration with statistical confidence.

Accurate spatial correspondence between template and subject images is a crucial step in neuroimaging studies and clinical applications like stereotactic neurosurgery. In the absence of a robust quantitative approach, we sought to propose and validate a set of point landmarks, anatomical fiducials (AFIDs), that could be quickly, accurately, and reliably placed on magnetic resonance images of the human brain. Using several publicly available brain templates and individual participant datasets, novice users could be trained to place a set of 32 AFIDs with millimetric accuracy. Furthermore, the utility of the AFIDs protocol is demonstrated for evaluating subject-to-template and template-to-template registration. Specifically, we found that commonly used voxel overlap metrics were relatively insensitive to focal misregistrations compared to AFID point-based measures. Our entire protocol and study framework leverages open resources and tools, and has been developed with full transparency in mind so that others may freely use, adopt, and modify. This protocol holds value for a broad number of applications including alignment of brain images and teaching neuroanatomy.

© 2019, Springer-Verlag London Ltd., part of Springer Nature. This study addresses the optimum cost design of mechanically stabilized earth (MSE) using geosynthetics. The design process of MSEs is mathematically programmed based on an objective function depending on the length of reinforcements and vertical distance of reinforced layers. Design restrictions control the final design to be valid in terms of constraints. The aim is to explore the efficiency of evolutionary-based algorithms in dealing with MSE optimization problem along with automating the minimum cost design of MSE walls. To this end, three evolutionary algorithms, differential evolution (DE), evolution strategy, and biogeography-based optimization algorithm (BBO), are tackled to solve this problem. Comprehensive computational simulations confirm the impact of different effective parameters variation on the final design. Finally, the BBO algorithm performed the best, while DE recorded the most unsatisfactory results.

During navigation, information at multiple scales needs to be integrated. Single-unit recordings in rodents suggest that gradients of temporal dynamics in the hippocampus and entorhinal cortex support this integration. In humans, gradients of representation are observed, such that granularity of information represented increases along the long axis of the hippocampus. The neural underpinnings of this gradient in humans, however, are still unknown. Current research is limited by coarse fMRI analysis techniques that obscure the activity of individual voxels, preventing investigation of how moment-to-moment changes in brain signal are organized and how they are related to behavior. Here, we measured the signal stability of single voxels over time to uncover previously unappreciated gradients of temporal dynamics in the hippocampus and entorhinal cortex. Using our novel, single voxel autocorrelation technique, we show a medial-lateral hippocampal gradient, as well as a continuous autocorrelation gradient along the anterolateral-posteromedial entorhinal extent. Importantly, we show that autocorrelation in the anterior-medial hippocampus was modulated by navigational difficulty, providing the first evidence that changes in signal stability in single voxels are relevant for behavior. This work opens the door for future research on how temporal gradients within these structures support the integration of information for goal-directed behavior.

COVID-19 gains from the research and technology component's establishment of information science, artificial intelligence, and computer understanding. The article aims to discuss the numerous facets of today's modern technology utilized to combat COVID-19 emergencies on various scales, such as medicinal picture handling, illness tracking, expected outcomes, computational science, and medications. Techniques: A complex search of the knowledge base associated with existing COVID-19 innovation is conducted. Furthermore, a concise survey of the excluded data is conducted, analyzing the various aspects of current developments for dealing with the COVID-19 pandemic. The below are the outcomes: We have a window of musings on the audit of the tech propellers used to mitigate and mask the significant impact of the upheaval. Even though several investigations into current innovation in COVID-19 have surfaced, there are still required implementations and contributions of innovation in this war. Consequently, a thorough presentation of the available data is given, and several modern technology implementations for combating the pandemic of COVID-19. Continuous advancements of advanced technologies have aided in improving the public's lives, and there is a strong belief that proven study plans utilizing AI would be of great benefit in assisting people in combating this infection.

Sensors and sensor networks are the future of fully automated industry solutions. With more capability and complex machinery, the requirements for sensing in larger factories are critical, considering the data amount, latency, and the number of sensors in operation. Given the excellent time-critical operation, bandwidth and the number of devices connected, the 5G indoor femtocells could prove an excellent option for building industrial sensor grids. For more flexibility in control and reliability, operating the 5G indoor femtocell network in license-free frequency bands could be an alternative to commercial 5G services. The 5G networks incorporate a very dense network of indoor femtocells. The Femtocells also enhance data rates, indoor performance, and coverage area both in residential and industrial environments. Therefore, keeping in view the above-stated actualities, this paper addresses different indoor scenarios for radio wave propagation and simulates several path loss models to calculate the likely and most suitable propagation model for indoor signaling. Multiple models for frequencies in the unlicensed band below 6 GHz and above 6 GHz (licensed) 5G femtocells are discussed in the paper considering the constraints of material types, attenuation due to obstacles, various floors, carrier frequency, and distance from the transmitter. The comparative analysis indicates that the ITU model and Keenan–Motley model give the highest path loss in residential and industrial environments, respectively, while the log-distance model has the lowest path loss in both environments for below 6 GHz frequencies in the unlicensed spectrum. For the above 6 GHz licensed bands, the Alpha Beta Gamma (ABG) model and Path Loss Exponent (CIF) model are observed to have the minimum path loss difference.

Neuroimaging stands to benefit from emerging ultrahigh-resolution histological atlases of the human brain; the first of which is “BigBrain”. Ongoing research aims to characterise regional differentiation of cytoarchitecture with BigBrain and to optimise registration of BigBrain with standard neuroimaging templates. Together, this work paves the way for multi-scale investigations of brain organisation. However, working with BigBrain can present new challenges for neuroimagers, including dealing with cellular resolution neuroanatomy and complex transformation procedures. To simplify workflows and support adoption of best practices, we developed BigBrainWarp, a toolbox for integration of BigBrain with multimodal neuroimaging. The primary BigBrainWarp function wraps multiple state-of-the-art deformation matrices into one line of code, allowing users to easily map data between BigBrain and standard MRI spaces. Additionally, the toolbox contains ready-to-use cytoarchitectural features to improve accessibility of histological information. The present article discusses recent contributions to BigBrain-MRI integration and demonstrates the utility of BigBrainWarp for further investigations.

This paper presents a novel incentive-based load shedding management scheme within a microgrid environment equipped with the required IoT infrastructure. The proposed mechanism works on the principles of reverse combinatorial auction. We consider a region of multiple consumers who are willing to curtail their load in the peak hours in order to gain some incentives later. Using the properties of combinatorial auctions, the participants can bid in packages or combinations in order to maximize their and overall social welfare of the system. The winner determination problem of the proposed combinatorial auction, determined using particle swarm optimization algorithm and hybrid genetic algorithm, is also presented in this paper. The performance evaluation and stability test of the proposed scheme are simulated using MATLAB and presented in this paper. The results indicate that combinatorial auctions are an excellent choice for load shedding management where a maximum of 50 users participate.

Gait recognition is a promising video-based biometric for identifying individual walking patterns from a long distance. At present, most gait recognition methods use silhouette images to represent a person in each frame. However, silhouette images can lose fine-grained spatial information, and most papers do not regard how to obtain these silhouettes in complex scenes. Furthermore, silhouette images contain not only gait features but also other visual clues that can be recognized. Hence these approaches can not be considered as strict gait recognition. We leverage recent advances in human pose estimation to estimate robust skeleton poses directly from RGB images to bring back model-based gait recognition with a cleaner representation of gait. Thus, we propose GaitGraph that combines skeleton poses with Graph Convolutional Network (GCN) to obtain a modern model-based approach for gait recognition. The main advantages are a cleaner, more elegant extraction of the gait features and the ability to incorporate powerful spatio-temporal modeling using GCN. Experiments on the popular CASIA-B gait dataset show that our method archives state-of-the-art performance in model-based gait recognition. The code and models are publicly available., 5 pages, 2 figures

Supercomputer design is a complex, multi-dimensional optimization process, wherein several subsystems need to be reconciled to meet a desired figure of merit performance for a portfolio of applications and a budget constraint. However, overall, the HPC community has been gravitating towards ever more Flops, at the expense of many other subsystems. To draw attention to overall system balance, in this paper, we analyze balance ratios and architectural trends in the world’s most powerful supercomputers. Specifically, we have collected the performance characteristics of systems between 1993 and 2019 based on the Top500 lists and then analyzed their architectures from diverse system design perspectives. Notably, our analysis studies the performance balance of the machines, across a variety of subsystems such as compute, memory, I/O, interconnect, intra-node connectivity and power. Our analysis reveals that balance ratios of the various subsystems need to be considered carefully alongside the application workload portfolio to provision the subsystem capacity and bandwidth specifications, which can help achieve optimal performance.

Medical image segmentation is a critical field in the domain of computer vision and with the growing acclaim of deep learning based models, research in this field is constantly expanding. Optical coherence tomography (OCT) is a non-invasive method that scans the human's retina with depth. It has been hypothesized that the thickness of the retinal layers extracted from OCTs could be an efficient and effective biomarker for early diagnosis of AD. In this work, we aim to design a self-training model architecture for the task of segmenting the retinal layers in OCT scans. Neural architecture search (NAS) is a subfield of AutoML domain, which has a significant impact on improving the accuracy of machine vision tasks. We integrate the NAS algorithm with a Unet auto-encoder architecture as its backbone. Then, we employ our proposed model to segment the retinal nerve fiber layer in our preprocessed OCT images with the aim of AD diagnosis. In this work, we trained a super-resolution generative adversarial network on the raw OCT scans to improve the quality of the images before the modeling stage. In our architecture search strategy, different primitive operations suggested to find down- & up-sampling Unet cell blocks and the binary gate method has been applied to make the search strategy more practical. Our architecture search method is empirically evaluated by training on the Unet and NAS-Unet from scratch. Specifically, the proposed NAS-Unet training significantly outperforms the baseline human-designed architecture by achieving 95.1% in the mean Intersection over Union metric and 79.1% in the Dice similarity coefficient.

Flow measurement is of great importance in many industrial applications. Ultrasonic flow measurement using time-of-flight technique can equip adequate solutions for such processes. The estimation of time of flights of the ultrasonic signals has a key role in the measurement process under the case of ultrasonic signal technology. In this work, a robust technique is proposed based on numerical methods in order to estimate the time-of-flights of the ultrasonic signals. Due to the discrete nature of the ultrasonic signals, the proposed method shows efficient results in order to estimate the time of flights. The proposed method is validated through experimental works. According to the results, Lagrange-Taylor, Taylor (forward) numerical schemes supplied better performance over correlation based method at overall volumetric flow rates, respectively.

Every day, millions of people place their trust in products based on Terrestrial Trunked Radio (TETRA). TETRA is a Private Mobile Radio (PMR) criteria purposed for meeting the special requirement for voice communication, which is reliable and secure communication links. The data rate’s narrowband and on-demand applications required big data rate, fast communication, and security in different environments. So, new TETRA Release introduces in this work to support novel high data rate applications which require wideband such as video streaming and adapting with cases of congestion or density of communication when special cases of application occur which they effect on link cause bottlenecks and stop services like denial of service (DoS). An adaptive TETRA system has been suggested in the selection of the advanced network based on the input of the modulation objects. As well as, based on these modulations (π/4 DQPSK, 4 QAM, 16 QAM, 64 QAM), they give us more data rate from the single module modulation-based system. All parts and techniques of the proposed work are implemented in ‘OMNET++’ tool of simulation and programming language of visual C# with visual studio. Finally, we show that our proposed work gives us more adaptation way when we use multiple modulation comparing with single modulation.

© 2020, CIMNE, Barcelona, Spain. Optimization techniques have drawn much attention for solving geotechnical engineering problems in recent years. Particle swarm optimization (PSO) is one of the most widely used population-based optimizers with a wide range of applications. In this paper, we first provide a detailed review of applications of PSO on different geotechnical problems. Then, we present a comprehensive computational study using several variants of PSO to solve three specific geotechnical engineering benchmark problems: the retaining wall, shallow footing, and slope stability. Through the computational study, we aim to better understand the algorithm behavior, in particular on how to balance exploratory and exploitative mechanisms in these PSO variants. Experimental results show that, although there is no universal strategy to enhance the performance of PSO for all the problems tackled, accuracies for most of the PSO variants are significantly higher compared to the original PSO in a majority of cases.

In this study, the main effort was evaluating the efficiency of artificial intelligence-based machine learning algorithms in the ground motion acceleration prediction (GMPE). To this end, a backpropagation neural networks (BPNN) is selected to build a data-driven model. This research evaluates the results of 25,745 records provided by the Pacific Earthquake Engineering Research Center (PEER). A total of nine independent variables have been considered to describe ground motion acceleration. Linear regression is applied to the model as a benchmark. The effect of a number of hidden layers, different activation functions, and optimizers are also examined. The results declared that one-hidden layer BPNN with ‘RMSprop’ optimizer and ‘Softplus’ activation function performed as the best predictor.

Nature-inspired optimization algorithms have been designed for unconstrained problems. However, real-world optimization problems usually deal with a lot of limitations, either boundary of design variables, or equality/inequality constraints. Therefore, an extensive number of efforts have been made to make these limitations understandable for the optimization algorithms. Here, a more important fact is that those constraint handling approaches affect the algorithms’ performances considerably. In this study, some of the well-known strategies are incorporated into particle swarm optimization algorithms (PSO). The performance of the PSO algorithm is examined through several benchmarks, constrained problems, and the results discussed comprehensively.

Establishing spatial correspondence between subject and template images is necessary in neuroimaging research and clinical applications such as brain mapping and stereotactic neurosurgery. In the absence of other quantitative approaches, a point-based set of anatomical fiducials (AFIDs) was recently developed and validated to serve as a quantitative measure of image registration based on salient anatomical features. In this study, we sought to apply the AFIDs protocol to the clinic, specifically focussing on structural magnetic resonance images (MRI) obtained from patients with Parkinsons Disease (PD). We first confirmed that AFIDs could be placed to millimetric accuracy in the PD dataset with results comparable to those in normal control subjects. With localization error established, we evaluated subject-to-template registration using this framework by aligning the clinical scans to standard template space using a robust open preprocessing workflow for MRI scans. We found that registration errors from this workflow as measured using AFIDs were higher than previously reported suggesting the need for optimization of image processing pipelines for clinical grade datasets. Finally, we examined the utility of using point-to-point distances between AFID points as a morphometric biomarker of PD, finding evidence of reduced distances between AFIDs around the left temporal horn, brainstem and pineal gland in the clinical group, structures that circumscribe regions known to be affected in PD including the substantia nigra. Overall, we provide evidence that AFIDs can be successfully applied in a clinical setting and utilized to provide localized and quantitative measures of registration error. AFIDs provide clinicians and researchers with a common, open framework for quality control and validation of spatial correspondence and the location of anatomical structures, facilitating accurate aggregation of imaging datasets and comparisons between various neurological conditions.

Chemometrics is chemical discipline in which mathematical and statistical methods are coupled with chemical data to extract useful information which cannot be extracted by the use of conventional methods. When experimental techniques are assisted by chemometric methods, very interesting studies will be performed which enable us to obtain valuable information about the system under our study. Chemico-biological interactions are very useful studies which are performed to obtain information about binding of small molecules with biological macromolecules. Recently, these studies have been assisted by chemometric methods to perform advanced studies which can help us to have a deep insight to them. Literature survey showed us that multivariate analysis of the chemico-biological interactions is becoming popular and nowadays, chemometricians are using multivariate chemometric methods for resolving chemico-biological interactions. This article focuses on the works published in the literature to provide a background for those who are interested to work in this field and finally, the results will be discussed and concluded.

The processor performance of high performance computing (HPC) systems is increasing at a much higher rate than storage performance. This imbalance leads to I/O performance bottlenecks in massively parallel HPC applications. Therefore, there is a need for improvements in storage and file system designs to meet the ever-growing I/O needs of HPC applications. Storage and file system designers require a deep understanding of how HPC application I/O behavior affects current storage system installations in order to improve them. In this work, we contribute to this understanding using application-agnostic file system statistics gathered on compute nodes as well as metadata and object storage file system servers. We analyze file system statistics of more than 4 million jobs over a period of three years on two systems at Lawrence Livermore National Laboratory that include a 15 PiB Lustre file system for storage. The results of our study add to the state-of-the-art in I/O understanding by providing insight into how general HPC workloads affect the performance of large-scale storage systems. Some key observations in our study show that reads and writes are evenly distributed across the storage system; applications which perform I/O, spread that I/O across ∼78% of the minutes of their runtime on average; less than 22% of HPC users who submit write-intensive jobs perform efficient writes to the file system; and I/O contention seriously impacts I/O performance.

Nowadays, the literature is very rich with many techniques proposed especially for optimal relay coordination (ORC) problems of directional overcurrent relays (DOCRs). Many approaches have been applied to solve this stiff problem by considering different scenarios on protective relays and their network. However, the literature lacks a realistic model to deal with the inevitable fact that modern electric power networks have different relay technologies. Protection engineers could face electromechanical, static, digital “hardware-based”, and numerical “software-based” relays all together in the same network. Thus, existing ORC solvers are inapplicable to optimally coordinate such realistic networks. This paper presents a corrected model to deal with different relay technologies where the original problem dimension increases by 1.5× to indicate the relay types. To validate its correctness, the biogeography-based optimization (BBO) algorithm is used with the IEEE 6-bus, 15-bus, and 42-bus test systems. The results show that this realistic ORC problem can be solved, which means that it is possible to coordinate DOCRs that come with different speeds, coordination time intervals (CTI), and resolutions of time multiplier settings (TMS) and pickup settings (PS).

Modern machine learning (ML) computing systems proved themselves as effective tools to forecast electric load demand. However, their internal learning optimization algorithms could trap into local optima. To tackle this issue, one of the practical ways is to optimize their hyperparameters. This paper presents a simple way to do that by using the most basic random search algorithm (RSA) as a global optimizer. Support vector regression (SVR), which is a special type of support vector machine (SVM), is used. To do that, the total number of iterations is divided into multiple stages, and then RSA is sequentially executed where the search space is minimized at the end of each stage. The process ensures reaching a very rich area of near-optimal SVR settings, which can then be picked up as final candidate solutions. This technique is applied to forecast the peak-load of Nova Scotia - Canada during the winter of 2018-2019. The prediction accuracy of this effective simple technique can reach 99.89% and 97.17% for the training and test sets, respectively.

It is not revealing a secret to say that most of the power system studies highly depend on power flow (PF) analysis. This tool provides a frozen picture of dynamic electric networks under certain conditions. Nowadays, many iterative techniques are available to solve PF problems. The most popular one is built based on the Newton-Raphson (NR) algorithm. Although NR can obtain highly accurate solutions, its processing speed significantly decreases as the problem dimension increases. Thus, a wise selection should be taken to compromise between the processing speed and the solution accuracy. For some critical studies, such as contingency analysis, the processing speed is a very important factor that forces some energy management systems (EMS) to apply DC and AC-DC approximations. This paper studies the processing speed when artificial neural networks (ANNs) are adopted to solve PF problems. First, the standard 9-bus test system is used. Then, the processing speed of ANNs is examined through a very large virtual network. This AI-based technique can hit multiple birds with one stone. Adding to the processing speed and the solution accuracy, it can also solve the uncertainty issue by feeding ANNs with actual PF readings measured from some mounted instrument devices.