Fast training procedure for Viola–Jones type object detectors using Laplacian clutter models

This paper presents a fast training strategy for the Viola–Jones (VJ) type object-detection systems. The VJ object- detection system, popular for its high accuracy at real-time testing speeds, has a drawback that it is slow to train. A face detector, for example, can take days to train. In content-based image retrieval (CBIR), where search needs to be performed instantaneously, VJ’s long training time is not affordable. Therefore, VJ’s method is hardly used for such applications. This paper proposes two modifications to the training algorithm of VJ-type object detection systems which reduces the training time to the order of seconds. Firstly, Laplacian clutter (non-object) models are used to train the weak classifier, thus eliminating the need to read and evaluate thousands of clutter images. Secondly, the training procedure is simplified by removing the time-consuming AdaBoost-based feature selection procedure. An object detector, trained with 500 images, approximately takes 2 s for training in a conventional 3 GHz machine. Our results show that the accuracy of the detector, built with the proposed approach, is inferior to that of VJ for difficult object class such as frontal faces. However, for objects with lesser degree of intra-class variations such as hearts, state-of-the-art accuracy can be obtained. Importantly, for CBIR applications, the fast testing speed of the VJ type object detector is maintained.     

Deciding k-Colorability of P 5-Free Graphs in Polynomial Time

The problem of computing the chromatic number of a P ₅-free graph (a graph which contains no path on 5 vertices as an induced subgraph) is known to be NP-hard. However, we show that for every fixed integer k, there exists a polynomial-time algorithm determining whether or not a P ₅-free graph admits a k-coloring, and finding one, if it does.     

Development of a robust canopy height model derived from ALS point clouds for predicting individual crown attributes at the species level

ABSTRACT

Tree crown attributes are important parameters during the assessment and monitoring of forest ecosystems. Canopy height models (CHMs) derived from airborne laser scanning (ALS) data have proved to be a reliable source for extracting different biophysical characteristics of single trees and at stand level. However, ALS-derived tree measurements (e.g., mean crown diameter) can be negatively affected by pits that appear in the CHMs. Thus, we propose a novel method for generating pit-free CHMs from ALS point clouds for estimating crown attributes (i.e., area and mean diameter) at the species level. The method automatically calculates a threshold for a pixel based on the range of height values within neighbouring pixels; if the pixel falls below the threshold then it is recognized as a pitted pixel. The pit is then filled with the median of the values of the neighbouring pixels. Manually delineated individual tree crowns (ITC) of four deciduous and two coniferous species on Colour Infrared (CIR) stereo images were used as a reference in the analysis. In addition, a variety of different algorithms for constructing CHMs were compared to investigate the performance of different CHMs in similar forest conditions. Comparisons between the estimated and observed crown area (R² = 0.95, RMSE% = 19.12% for all individuals) and mean diameter (R² = 0.92, RMSE% = 12.16% for all individuals) revealed that ITC attributes were correctly estimated by segmentation of the pit-free CHM proposed in this study. The goodness of matching and geometry revealed that the delineated crowns correctly matched up to the reference data and had identical geometry in approximately 70% of cases. The results showed that the proposed method produced a CHM that estimates crown attributes more accurately than the other investigated CHMs. Furthermore, the findings suggest that the proposed algorithm used to fill pits with the median of height observed in surrounding pixels significantly improve the accuracy of the results the species level due to a higher correlation between the estimated and observed crown attributes. Based on these results, we concluded that the proposed pit filling method is capable of providing an automatic and objective solution for constructing pit-free CHMs for assessing individual crown attributes of mixed forest stands.     

Vocal-based emotion recognition using random forests and decision tree

This paper proposes a new vocal-based emotion recognition method using random forests, where pairs of the features on the whole speech signal, namely, pitch, intensity, the first four formants, the first four formants bandwidths, mean autocorrelation, mean noise-to-harmonics ratio and standard deviation, are used in order to recognize the emotional state of a speaker. The proposed technique adopts random forests to represent the speech signals, along with the decision-trees approach, in order to classify them into different categories. The emotions are broadly categorised into the six groups, which are happiness, fear, sadness, neutral, surprise, and disgust. The Surrey Audio-Visual Expressed Emotion database is used. According to the experimental results using leave-one-out cross-validation, by means of combining the most significant prosodic features, the proposed method has an average recognition rate of \(66.28\%\), and at the highest level, the recognition rate of \(78\%\) has been obtained, which belongs to the happiness voice signals. The proposed method has \(13.78\%\) higher average recognition rate and \(28.1\%\) higher best recognition rate compared to the linear discriminant analysis as well as \(6.58\%\) higher average recognition rate than the deep neural networks results, both of which have been implemented on the same database.     

On the Role of C Addition on α Precipitation in a β Titanium Alloy

The onset of α nucleation in a carbon containing β-titanium alloy has been investigated by coupling atom probe tomography (APT) with transmission electron microscopy. The analysis of the APT results indicates that in addition to ω precipitates that can act as potential α nucleation sites, carbon atoms tend to form clusters within the β-matrix, which in turn give rise to additional nucleation sites for α, resulting in finer scale α precipitates due to increased nucleation density.     

Brain Mechanisms of Exercise-Induced Hypoalgesia: To Find a Way Out from “Fear-Avoidance Belief”

It is well known that exercise produces analgesic effects (exercise-induced hypoalgesia (EIH)) in animal models and chronic pain patients, but the brain mechanisms underlying these EIH effects, especially concerning the emotional aspects of pain, are not yet fully understood. In this review, we describe drastic changes in the mesocorticolimbic system of the brain which permit the induction of EIH effects. The amygdala (Amyg) is a critical node for the regulation of emotions, such as fear and anxiety, which are closely associated with chronic pain. In our recent studies using neuropathic pain (NPP) model mice, we extensively examined the association between the Amyg and EIH effects. We found that voluntary exercise (VE) activated glutamate (Glu) neurons in the medial basal Amyg projecting to the nucleus accumbens (NAc) lateral shell, while it almost completely suppressed NPP-induced activation of GABA neurons in the central nucleus of the Amyg (CeA). Furthermore, VE significantly inhibited activation of pyramidal neurons in the ventral hippocampus-CA1 region, which play important roles in contextual fear conditioning and the retrieval of fear memory. This review describes novel information concerning the brain mechanisms underlying EIH effects as a result of overcoming the fear-avoidance belief of chronic pain.     

Towards Designing a Trusted Routing Solution in Mobile Ad Hoc Networks

Designing a trusted and secure routing solution in an untrustworthy scenario is always a challenging problem. Lack of physical security and low trust levels among nodes in an ad hoc network demands a secure end-to-end route free of any malicious entity. This is particularly challenging when malicious nodes collude with one another to disrupt the network operation. In this paper we have designed a secure routing solution to find an end-to-end route free of malicious nodes with collaborative effort from the neighbors. We have also extended the solution to secure the network against colluding malicious nodes, which, to the best of our knowledge, is the first such solution proposed. We have also proposed a framework for computing and distributing trusts that can be used with out trusted routing protocol. Our proposed framework is unique and different from the other schemes in that it tries to analyze the psychology of the attacker and quantifies the behavior in the computational model. Extensive simulation has been carried out to evaluate the design of our protocol. Partially funded by Department of Defense Award No. H98230-04-C-0460, Department of Transportation Project No. FL-26-7102-00 and National Science Foundation Grant Nos. ANI-0123950 and CCR-0196557. Tirthankar Ghosh is a PhD candidate in the Telecommunications and Information Technology Institute at Florida International University. His area of research is routing security and trust computation in wireless ad hoc and sensor networks. He received his Bachelor of Electrical Engineering from Jadavpur University, India and Masters in Computer Engineering from Florida International University. Dr. Niki Pissinou received her Ph.D. in Computer Science from the University of Southern California, her M.S. in Computer Science from the University of California at Riverside, and her B.S.I.S.E. in Industrial and Systems Engineering from The Ohio State University. She is currently a tenured professor and the director of the Telecommunication & Information Technology Institute at FIU. Previously Dr. Pissinou was a tenured faculty at the Center for Advanced Computer Studies at the University of Louisiana at Lafayette where she was also the director of the Telecommunication & Information & Technology Laboratory partially funded by NASA, and the co-director of the NOMAD: A Wireless and Nomadic Laboratory partially funded by NSF, and the Advanced Network Laboratory. Dr. Pissinou is active in the fields computer networks, information technology and distributed systems. Dr. Kami (Sam) Makki has earned his Ph.D. in Computer Science from the University of Queensland in Brisbane Australia, his Masters degree in Computer Science and Engineering from the University of New South Wales in Sydney Australia, and his Bachelor and Masters Degrees in Civil Engineering from the University of Tehran Iran. Before joining the department of Electrical Engineering and Computer Science at the University of Toledo he has held a number of academic positions and research appointments at the Queensland University of Technology in Brisbane, Royal Melbourne Institution of Technology in Melbourne and at The University of Queensland in Brisbane Australia. He is an active researcher in the fields of distributed systems, databases, mobile and wireless communications, and has more than 30 publications in peerreviewed journals and international proceedings. He has served as a chair and technical program committee member and reviewer for a number of IEEE and ACM sponsored technical conferences and has received a number of achievement awards.     

Theoretical studies of the pressure-induced zinc-blende to cinnabar phase transition in CdTe and thermodynamical properties of each phase

Luminescence of CdTe quantum dots embedded in ZnTe is quenched at pressure of about 4.5 GPa in the high-pressure experiments. This pressure-induced quenching is attributed to the “zinc-blende–cinnabar” phase transition in CdTe, which was confirmed by the first-principles calculations. Theoretical analysis of the pressure at which the phase transition occurs for CdTe was performed using the CASTEP module of Materials Studio package with both generalized gradient approximation (GGA) and local density approximation (LDA). The calculated phase transition pressures are equal to about 4.4 GPa and 2.6 GPa, according to the GGA and LDA calculations, respectively, which is in a good agreement with the experimental value. Theoretically estimated value of the pressure coefficient of the band-gap luminescence in zinc-blende structure is in very good agreement with that recently measured in the QDs structures. The calculated Debye temperature, elastic constants and specific heat capacity for the zinc-blend structure agree well with the experimental data; the data for the cinnabar phase are reported here for the first time to the best of the authors' knowledge.     

A study on fluorescence properties of Eu3+ ions in alkali lead tellurofluoroborate glasses

Glasses with chemical composition of (in mol.%): 26 RF-20 PbO-10 TeO2-43 H3BO3-1 EuO3 (RLTB) were prepared by conventional melt quenching method. The Judd-Ofelt intensity parameters Ω2 and Ω6 were obtained from the absorption intensities of 7F0→5D2 and 7F0→5L6 transitions, respectively. In order to overcome the problem of applicability of Judd-Ofelt analysis at room temperature due to the overlapping of the transitions originating from 7F0 and 7F1 levels of Eu3+ ion, the effect of the thermalization on the population of energy levels was taken into account. The photoluminescence spectra contained five emission bands originating from the 5D0 metastable state to 7FJ (J=0, 1, 2, 3, 4) lower lying states. The decay profiles were found to be single exponential in all the three glasses. The measured lifetimes (τmes) were in good agreement with the calculated lifetimes (τcal) obtained by using the thermally corrected Judd-Ofelt intensity parameters.     

Fabrication of switchable liquid crystal devices using surface relief gratings in photopolymer

Holographically recorded surface relief gratings in dry, self-developing acrylamide based photopolymer were used to fabricate two types of switchable liquid crystal (LC) device. One is an electrically switchable LC diffraction grating and the other is an electrically switchable polarization rotator. The electrically switchable diffraction grating was characterized by measuring the dependence of the intensity in the first diffracted order on the applied electric field. The polarization rotator was characterized by studying the influence of the applied electric field on the twist angle and the variation of intensity in the zero and the first orders of diffraction.