An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

Mango Leaf Disease Identification Using Fully Resolution Convolutional Network

Due to the high demand for mango and being the king of all fruits, it is the need of the hour to curb its diseases to fetch high returns. Automatic leaf disease segmentation and identification are still a challenge due to variations in symptoms. Accurate segmentation of the disease is the key prerequisite for any computer-aided system to recognize the diseases, i.e., Anthracnose, apical-necrosis, etc., of a mango plant leaf. To solve this issue, we proposed a CNN based Fully-convolutional-network (FrCNnet) model for the segmentation of the diseased part of the mango leaf. The proposed FrCNnet directly learns the features of each pixel of the input data after applying some preprocessing techniques. We evaluated the proposed FrCNnet on the real-time dataset provided by the mango research institute, Multan, Pakistan. To evaluate the proposed model results, we compared the segmentation performance with the available state-of-the-art models, i.e., Vgg16, Vgg-19, and Unet. Furthermore, the proposed model's segmentation accuracy is 99.2% with a false negative rate (FNR) of 0.8%, which is much higher than the other models. We have concluded that by using a FrCNnet, the input image could learn better features that are more prominent and much specific, resulting in an improved and better segmentation performance and diseases’ identification. Accordingly, an automated approach helps pathologists and mango growers detect and identify those diseases.     

Half-Metallic Ferromagnetism in New Half-Heusler Compounds: an Ab Initio Study of CrTiX (X = Si,Ge, Sn,Pb)

In this work, half-metallic (HM) properties of new Half-Heusler (HH) ferromagnetic compounds CrTiX (X = Si, Ge, Sn, Pb) are studied by means of first principle band structure calculation within the framework of density functional theory (DFT). From the spin-polarized calculations using full-potential linearized augmented plane-wave (FP-LAPW)method, we found that all of these compounds are stable in ferromagnetic MgAgAs-type crystal structure. The latticeparameters of CrTiX compounds increase with increasing atomic radius of X atom and ranges from 5.76 to 6.38 Å. The calculated electronic structure of these compounds in MgAgAs-type structure shows that they are HM materials with an integer magnetic moment of 4 μ _B. Densities of states, electronic band structure, and origin of ferromagnetism have been discussed, and robust HM nature of these compounds is analyzed which makes them fascinating compounds for spintronic devices.     

Branch-and-bound method for minimizing the weighted completion time scheduling problem on a single machine with release dates

In this paper, we consider a single-machine scheduling problem with release dates. The aim is to minimize the total weighted completion time. This problem is known to be strongly NP-hard. We propose two new lower bounds that can be, respectively, computed in O(n²) and in O(nlogn) time where n is the number of jobs. We prove a sufficient and necessary condition for local optimality, which can also be considered as a priority rule. We present an efficient heuristic using such a condition. We also propose some dominance properties. A branch-and-bound algorithm incorporating the heuristic, the lower bounds and the dominance properties is proposed and tested on a large set of instances.     

Three dimensional polyurethane/ hydroxyapatite bioactive scaffolds: The role of hydroxyapatite on pore generation

Fabrication of a suitable scaffold with highly interconnected and well-distributed pores for cell proliferation and growth in the field of bone tissue engineering is of high importance. In this study, three-dimensional porous polyurethane (PU) scaffolds, with 0, 15, 25, and 32 wt% hydroxyapatite (HA), were fabricated. In this regard, HA was incorporated into PU constituents prior to starting in-situ polymerization of PU. Porosity and density measurement of the scaffolds revealed that higher amount of HA in the scaffolds led to increasing the former and decreasing the latter quantity. The field emission scanning electron microscopy (FESEM) images revealed that by increasing HA content, the pore size showed a descending trend while the number of pores increased. This would be attributed to the type of interactions between HA and PU, and the role of HA in pore formation. Mechanical test revealed that Young's Modulus of the samples was reduced by increasing scaffold porosity caused by the increase of HA content. Bioactivity tests in the simulated body fluid (SBF) showed the ability of scaffolds forming apatite precipitates. MTT assay showed that by increasing HA content, MG63 osteoblast cell viability increased and FESEM images revealed proper attachment of the cells to the scaffold surface.     

Physical,mechanical, and in vitro biological analysis of bioactive fibers-based dental composite

This study aimed to synthesize experimental composites reinforced with various concentrations (0, 40, 50, and 60 wt%) of nano-hydroxyapatite grafted glass fibers. The release of monomers, residual monomers, and in-vitro bioactivity of composite groups were evaluated after 1, 7, and 28 days. Compressive strength/ modulus, cell viability (by direct and indirect method), and bacterial adhesion were evaluated. The results showed that bis-GMA was released from all samples. TEGDMA released from 50 and 60 wt% samples on day 1 and UDMA showed negligible release. Compressive strength values of 40 wt% sample were higher than other experimental groups. New apatite layer was formed, whereby both direct and indirect methods demonstrated cell viability. The numbers of active colonies grown were least for 60 wt% sample while their number increased over time. The nano-hydroxyapatite/glass fibers have potential to be used as filler in dental composites and experimental composites were found to be biocompatible and comparable with commercial material.     

System Dynamics Approach to Exploring Performance Enhancement in a Construction Organization

Governments and firms in developing economies are concerned about ways to improve performance of local firms. A wealth of research has already discussed the reasons for decline in performance and suggested a number of possible improvement strategies. Among these documented strategies, there are many options for developing economies. The selection among these options, however, depends upon the unique organizational set-up and many other local factors. Moreover an implementation scenario of the selected options requires an experimentation period either by actually implementing the option as a policy or simulating the complete process in a model and thus creating a laboratory for learning. The former option is costly while the latter requires dynamic modeling of engineering processes integrated with the local influencing factors on overall performance. The latter approach is adopted in the present research using system dynamics techniques to model the problem. The effects of three strategic policies on the performance of a construction firm have been simulated. A case study is conducted to validate the utility of some selected policies for performance enhancement.