Evapotranspiration Modeling Using Different Tree Based Ensembled Machine Learning Algorithm

Water Resources Management - The present study investigates and evaluate the scope and potential of modern computing tools and techniques such as ensembled machine learning methods in estimating...     

Electrospun microporous gelatin–polycaprolactone blend tubular scaffold as a potential vascular biomaterial

The work reported involved the fabrication of an electrospun tubular conduit of a gelatin and polycaprolactone (PCL) blend as an adventitia‐equivalent construct. Gelatin was included as the matrix for increased biocompatibility with the addition of PCL for durability. This is contrary to most of the literature available for biomaterials based on blends of gelatin and PCL where PCL is the major matrix. The work includes the assiduous selection of key electrospinning parameters to obtain smooth bead‐free fibres with a narrow distribution of pore size and fibre diameter. Few reports elucidate the optimization of all electrospinning parameters to fabricate tubular conduits with a focus on obtaining homogeneous pores and fibres. This stepwise investigation would be unique for the fabrication of gelatin–PCL electrospun tubular constructs. The fabricated microfibrous gelatin–PCL constructs had pores of size ca 50–100 μm reportedly conducive for cell infiltration. The measured value of surface roughness of 57.99 ± 17.4 nm is reported to be favourable for protein adhesion and cell adhesion. The elastic modulus was observed to be similar to that of the tunica adventitia of the native artery. Preliminary in vitro and in vivo biocompatibility tests suggest safe applicability as a biomaterial. Minimal cytotoxicity was observed using MTT assay. Subcutaneous implantation of the scaffold demonstrated acute inflammation which decreased by day 15. The findings of this study could enable the fabrication of smooth bead‐free microfibrous gelatin–PCL tubular construct as viable biomaterial which can be included in a bilayer or a trilayer scaffold for vascular tissue engineering. © 2019 Society of Chemical Industry     

A novel binary gaining–sharing knowledge-based optimization algorithm for feature selection

Neural Computing and Applications - To obtain the optimal set of features in feature selection problems is the most challenging and prominent problem in machine learning. Very few human-related...     

PRATIT: a CNN-based emotion recognition system using histogram equalization and data augmentation

Multimedia Tools and Applications - Emotions are spontaneous feelings that are accompanied by fluctuations in facial muscles, which leads to facial expressions. Categorization of these facial...     

Attribute Allocation and Retrieval Scheme for Large-Scale Sensor Networks

Wireless sensor network is an emerging technology that enables remote monitoring of large geographical regions. In this paper, we address the problem of distributing attributes over such a large-scale sensor network so that the cost of data retrieval is minimized. The proposed scheme is a data-centric storage scheme where the attributes are distributed over the network depending on the correlations between them. The problem addressed here is similar to the Allocation Problem of distributed databases. In this paper, we have defined the Allocation Problem in the context of sensor networks and have proposed a scheme for finding a good distribution of attributes to the sensor network. We also propose an architecture for query processing given such a distribution of attributes. We analytically determine the conditions under which the proposed architecture is beneficial and present simulation results to demonstrate the same. To the best of our knowledge, this is the first attempt to determine an allocation of attributes over a sensor network based on the correlations between attributes.     

Why does it pay to be selfish in a MANET?

Routing protocols for a mobile ad hoc network have assumed that all mobile nodes voluntarily participate in forwarding others' packets. This was a reasonable assumption because all MNs in a MANET belonged to a single authority. In the near future, however, a MANET may consist of MNs that belong to many different organizations since numerous civilian applications are expected to crop up. In this situation, some MNs may run independently and purposely decide not to forward packets so as to save their own energy. This could potentially lead to network partitioning and corresponding performance degradation. To minimize such situations in MANETs, many studies have explored the use of both the carrot and the stick approaches by having reputation-based, credit-payment, and game theory schemes. This article summarizes existing schemes, identifies their relative advantages, and projects future directions     

A new finite-difference-based method for wide-angle beam propagation

A novel split-step finite-difference method for wide-angle beam propagation is presented. The formulation allows solution of the second-order scalar wave equation without having to make the slowly varying envelope and one-way propagation approximations. The method is highly accurate and numerically efficient requiring only simple matrix multiplication for propagation.     

Sintering studies of nano-crystalline zinc oxide

Sintering and grain growth of nano-crystalline undoped ZnO has been studied in detail over a wide range of temperature and holding time. Below 800 °C, sintering of over 70% theoretical density is not observed, irrespective of particle size. At 900 °C for 6 h, the nano-crystalline sample sinters to 99% of theoretical density whereas the density for as received sample is 93% of theoretical density. However, at 1300 °C or higher, the densification is found to be much faster and after a few hours becomes independent of holding time. Grain growth studies reveal a similar feature of attaining saturation over holding time. The average saturated grain size is found to be ∼1.5 and ∼2.2 μm at 800 and 900 °C, respectively, while at 1300 °C or higher, it is in between 12 and 13 μm.     

Exploring spatial datasets with histograms

As online spatial datasets grow both in number and sophistication, it becomes increasingly difficult for users to decide whether a dataset is suitable for their tasks, especially when they do not have prior knowledge of the dataset. In this paper, we propose browsing as an effective and efficient way to explore the content of a spatial dataset. Browsing allows users to view the size of a result set before evaluating the query at the database, thereby avoiding zero-hit/mega-hit queries and saving time and resources. Although the underlying technique supporting browsing is similar to range query aggregation and selectivity estimation, spatial dataset browsing poses some unique challenges. In this paper, we identify a set of spatial relations that need to be supported in browsing applications, namely, the contains, contained and the overlap relations. We prove a lower bound on the storage required to answer queries about the contains relation accurately at a given resolution. We then present three storage-efficient approximation algorithms which we believe to be the first to estimate query results about these spatial relations. We evaluate these algorithms with both synthetic and real world datasets and show that they provide highly accurate estimates for datasets with various characteristics. Recommended by: Sunil Prabhakar Work supported by NSF grants IIS 02-23022 and CNF 04-23336. An earlier version of this paper appeared in the 17th International Conference on Data Engineering (ICDE 2001).