BOND

In a large-scale wireless sensor network, hundreds and thousands of sensors sample and forward data back to the sink periodically. In two real outdoor deployments GreenOrbs and CitySee, we observe that some bottleneck nodes strongly impact other nodes’ data collection and thus degrade the whole network performance. To figure out the importance of a node in the process of data collection, system manager is required to understand interactive behaviors among the parent and child nodes. So we present a management tool BOND (BOttleneck Node Detector), which explains the concept of Node Dependence to characterize how much a node relies on each of its parent nodes, and also models the routing process as a Hidden Markov Model and then uses a machine learning approach to learn the state transition probabilities in this model. Moreover, BOND can predict the network dataflow if some nodes are added or removed to avoid data loss and flow congestion in network redeployment. We implement BOND on real hardware and deploy it in an outdoor network system. The extensive experiments show that Node Dependence indeed help to explore the hidden bottleneck nodes in the network, and BOND infers the Node Dependence with an average accuracy of more than 85%.

Download Full-text

Extended Calculations of Energy Levels and Transition Rates for Singly Ionized Lanthanide Elements. II. Tb−Yb

The Astrophysical Journal Supplement Series ◽

10.3847/1538-4365/ac1ad2 ◽

2021 ◽

Vol 257 (2) ◽

pp. 29

Author(s):

Laima Radžiūtė ◽

Gediminas Gaigalas ◽

Daiji Kato ◽

Pavel Rynkun ◽

Masaomi Tanaka

Keyword(s):

Large Scale ◽

Transition Probabilities ◽

Energy Levels ◽

General Purpose ◽

Hartree Fock ◽

Lanthanide Elements ◽

Average Accuracy ◽

Nist Database ◽

Relativistic Configuration ◽

Relativistic Configuration Interaction

Abstract In this work, we continue large-scale ab initio computations for single ionized lanthanides. Extended atomic calculations for the set of ions from Pr ii (Z = 59) to Gd ii (Z = 64) have been performed in our previous work. In this study, ions from Tb ii (Z = 65) to Yb ii (Z = 70) are analyzed. By employing the same multiconfiguration Dirac–Hartree–Fock and relativistic configuration interaction methods that are implemented in the general-purpose relativistic atomic structure package GRASP2018, the energy levels and transition data of electric dipole (E1) transitions are computed. These computations are based on the strategies (with small variations) of Paper I. Accuracy of data is evaluated by comparing the computed energy levels with the data provided by the National Institute of Standards and Technology (NIST) database and with data from various methods. We obtain the average accuracy in the energy level compared with the NIST database: 6%, 5%, 4%, 5%, 3%, and 3% for Tb ii, Dy ii, Ho ii, Er ii, Tm ii, and Yb ii, respectively. We also provide extensive comparison of transition probabilities and wavelengths. Our results reach the average accuracy of transition wavelengths: 9%, 9%, 9%, 3%, 4%, and 11% for Tb ii, Dy ii, Ho ii, Er ii, Tm ii, and Yb ii, respectively.

Download Full-text

HTPC: heterogeneous traffic-aware partition coding for random packet spraying in data center networks

Journal of Cloud Computing Advances Systems and Applications ◽

10.1186/s13677-021-00248-4 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Jiawei Huang ◽

Shiqi Wang ◽

Shuping Li ◽

Shaojun Zou ◽

Jinbin Hu ◽

...

Keyword(s):

Data Center ◽

Large Scale ◽

Network Performance ◽

Rooted Tree ◽

Heterogeneous Traffic ◽

Data Center Networks ◽

Packet Reordering ◽

Traffic Characteristics ◽

Network Utilization ◽

The Impact

AbstractModern data center networks typically adopt multi-rooted tree topologies such leaf-spine and fat-tree to provide high bisection bandwidth. Load balancing is critical to achieve low latency and high throughput. Although the per-packet schemes such as Random Packet Spraying (RPS) can achieve high network utilization and near-optimal tail latency in symmetric topologies, they are prone to cause significant packet reordering and degrade the network performance. Moreover, some coding-based schemes are proposed to alleviate the problem of packet reordering and loss. Unfortunately, these schemes ignore the traffic characteristics of data center network and cannot achieve good network performance. In this paper, we propose a Heterogeneous Traffic-aware Partition Coding named HTPC to eliminate the impact of packet reordering and improve the performance of short and long flows. HTPC smoothly adjusts the number of redundant packets based on the multi-path congestion information and the traffic characteristics so that the tailing probability of short flows and the timeout probability of long flows can be reduced. Through a series of large-scale NS2 simulations, we demonstrate that HTPC reduces average flow completion time by up to 60% compared with the state-of-the-art mechanisms.

Download Full-text

Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach

Journal of Clinical Medicine ◽

10.3390/jcm10040570 ◽

2021 ◽

Vol 10 (4) ◽

pp. 570

Author(s):

María A Callejon-Leblic ◽

Ramon Moreno-Luna ◽

Alfonso Del Cuvillo ◽

Isabel M Reyes-Tejero ◽

Miguel A Garcia-Villaran ◽

...

Keyword(s):

Machine Learning ◽

Modelling Framework ◽

Visual Analog Scales ◽

Average Accuracy ◽

Machine Learning Approach ◽

Taste Disorders ◽

Polymerase Chain ◽

Fold Cross Validation ◽

Validation Scheme ◽

Control Study

The COVID-19 outbreak has spread extensively around the world. Loss of smell and taste have emerged as main predictors for COVID-19. The objective of our study is to develop a comprehensive machine learning (ML) modelling framework to assess the predictive value of smell and taste disorders, along with other symptoms, in COVID-19 infection. A multicenter case-control study was performed, in which suspected cases for COVID-19, who were tested by real-time reverse-transcription polymerase chain reaction (RT-PCR), informed about the presence and severity of their symptoms using visual analog scales (VAS). ML algorithms were applied to the collected data to predict a COVID-19 diagnosis using a 50-fold cross-validation scheme by randomly splitting the patients in training (75%) and testing datasets (25%). A total of 777 patients were included. Loss of smell and taste were found to be the symptoms with higher odds ratios of 6.21 and 2.42 for COVID-19 positivity. The ML algorithms applied reached an average accuracy of 80%, a sensitivity of 82%, and a specificity of 78% when using VAS to predict a COVID-19 diagnosis. This study concludes that smell and taste disorders are accurate predictors, with ML algorithms constituting helpful tools for COVID-19 diagnostic prediction.

Download Full-text

Winter fidelity, movements, and energy expenditure of Midcontinent Greater White-fronted Geese

Movement Ecology ◽

10.1186/s40462-020-00236-4 ◽

2021 ◽

Vol 9 (1) ◽

Author(s):

Jay A. VonBank ◽

Mitch D. Weegman ◽

Paul T. Link ◽

Stephanie A. Cunningham ◽

Kevin J. Kraai ◽

...

Keyword(s):

Energy Expenditure ◽

Time Allocation ◽

Large Scale ◽

Animal Movement ◽

Transition Probabilities ◽

Winter Period ◽

Daily Movement ◽

Regional Energy ◽

Wintering Areas ◽

Wintering Distribution

Abstract Background Animal movement patterns are the result of both environmental and physiological effects, and the rates of movement and energy expenditure of given movement strategies are influenced by the physical environment an animal inhabits. Greater white-fronted geese in North America winter in ecologically distinct regions and have undergone a large-scale shift in wintering distribution over the past 20 years. White-fronts continue to winter in historical wintering areas in addition to contemporary areas, but the rates of movement among regions, and energetic consequences of those decisions, are unknown. Additionally, linkages between wintering and breeding regions are generally unknown, and may influence within-winter movement rates. Methods We used Global Positioning System and acceleration data from 97 white-fronts during two winters to elucidate movement characteristics, model regional transition probabilities using a multistate model in a Bayesian framework, estimate regional energy expenditure, and determine behavior time-allocation influences on energy expenditure using overall dynamic body acceleration and linear mixed-effects models. We assess the linkages between wintering and breeding regions by evaluating the winter distributions for each breeding region. Results White-fronts exhibited greater daily movement early in the winter period, and decreased movements as winter progressed. Transition probabilities were greatest towards contemporary winter regions and away from historical wintering regions. Energy expenditure was up to 55% greater, and white-fronts spent more time feeding and flying, in contemporary wintering regions compared to historical regions. White-fronts subsequently summered across their entire previously known breeding distribution, indicating substantial mixing of individuals of varying breeding provenance during winter. Conclusions White-fronts revealed extreme plasticity in their wintering strategy, including high immigration probability to contemporary wintering regions, high emigration from historical wintering regions, and high regional fidelity to western regions, but frequent movements among eastern regions. Given that movements of white-fronts trended toward contemporary wintering regions, we anticipate that a wintering distribution shift eastward will continue. Unexpectedly, greater energy expenditure in contemporary wintering regions revealed variable energetic consequences of choice in wintering region and shifting distribution. Because geese spent more time feeding in contemporary regions than historical regions, increased energy expenditure is likely balanced by increased energy acquisition in contemporary wintering areas.

Download Full-text

A Machine Learning Approach For Classifying Low-mass X-ray Binaries Based On Their Compact Object Nature

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/staa3899 ◽

2020 ◽

Author(s):

R Pattnaik ◽

K Sharma ◽

K Alabarta ◽

D Altamirano ◽

M Chakraborty ◽

...

Keyword(s):

Machine Learning ◽

Black Hole ◽

Neutron Star ◽

Binary Systems ◽

Compact Object ◽

X Ray ◽

Average Accuracy ◽

Machine Learning Approach ◽

Low Mass ◽

X Ray Binaries

Abstract Low Mass X-ray binaries (LMXBs) are binary systems where one of the components is either a black hole or a neutron star and the other is a less massive star. It is challenging to unambiguously determine whether a LMXB hosts a black hole or a neutron star. In the last few decades, multiple observational works have tried, with different levels of success, to address this problem. In this paper, we explore the use of machine learning to tackle this observational challenge. We train a random forest classifier to identify the type of compact object using the energy spectrum in the energy range 5-25 keV obtained from the Rossi X-ray Timing Explorer archive. We report an average accuracy of 87±13% in classifying the spectra of LMXB sources. We further use the trained model for predicting the classes for LMXB systems with unknown or ambiguous classification. With the ever-increasing volume of astronomical data in the X-ray domain from present and upcoming missions (e.g., SWIFT, XMM-Newton, XARM, ATHENA, NICER), such methods can be extremely useful for faster and robust classification of X-ray sources and can also be deployed as part of the data reduction pipeline.

Download Full-text

Bearing Anomaly Recognition Using an Intelligent Digital Twin Integrated with Machine Learning

Applied Sciences ◽

10.3390/app11104602 ◽

2021 ◽

Vol 11 (10) ◽

pp. 4602

Author(s):

Farzin Piltan ◽

Jong-Myon Kim

Keyword(s):

Machine Learning ◽

Variable Structure ◽

Vibration Signal ◽

Crack Size ◽

Approximation Technique ◽

Digital Twin ◽

Average Accuracy ◽

Machine Learning Approach ◽

The Impact ◽

Signal Approximation

In this study, the application of an intelligent digital twin integrated with machine learning for bearing anomaly detection and crack size identification will be observed. The intelligent digital twin has two main sections: signal approximation and intelligent signal estimation. The mathematical vibration bearing signal approximation is integrated with machine learning-based signal approximation to approximate the bearing vibration signal in normal conditions. After that, the combination of the Kalman filter, high-order variable structure technique, and adaptive neural-fuzzy technique is integrated with the proposed signal approximation technique to design an intelligent digital twin. Next, the residual signals will be generated using the proposed intelligent digital twin and the original RAW signals. The machine learning approach will be integrated with the proposed intelligent digital twin for the classification of the bearing anomaly and crack sizes. The Case Western Reserve University bearing dataset is used to test the impact of the proposed scheme. Regarding the experimental results, the average accuracy for the bearing fault pattern recognition and crack size identification will be, respectively, 99.5% and 99.6%.

Download Full-text