Reinforcement learning applications in dynamic pricing of retail markets

In this paper, we investigate the use of reinforcement learning (RL) techniques to the problem of determining dynamic prices in an electronic retail market. As representative models, we consider a single seller market and a two seller market, and formulate the dynamic pricing problem in a setting that easily generalizes to markets with more than two sellers. We first formulate the single seller dynamic pricing problem in the RL framework and solve the problem using the Q-learning algorithm through simulation. Next we model the two seller dynamic pricing problem as a Markovian game and formulate the problem in the RL framework. We solve this problem using actor-critic algorithms through simulation. We believe our approach to solving these problems is a promising way of setting dynamic prices in multi-agent environments. We illustrate the methodology with two illustrative examples of typical retail markets.

Subject independent human action recognition using spatio-depth information and meta-cognitive RBF network

In this paper, we present a machine learning approach for subject independent human action recognition using depth camera, emphasizing the importance of depth in recognition of actions. The proposed approach uses the flow information of all 3 dimensions to classify an action. In our approach, we have obtained the 2-D optical flow and used it along with the depth image to obtain the depth flow (Z motion vectors). The obtained flow captures the dynamics of the actions in space time. Feature vectors are obtained by averaging the 3-D motion over a grid laid over the silhouette in a hierarchical fashion. These hierarchical fine to coarse windows capture the motion dynamics of the object at various scales. The extracted features are used to train a Meta-cognitive Radial Basis Function Network (McRBFN) that uses a Projection Based Learning (PBL) algorithm, referred to as PBL-McRBFN, henceforth. PBL-McRBFN begins with zero hidden neurons and builds the network based on the best human learning strategy, namely, self-regulated learning in a meta-cognitive environment. When a sample is used for learning, PBLMcRBFN uses the sample overlapping conditions, and a projection based learning algorithm to estimate the parameters of the network. The performance of PBL-McRBFN is compared to that of a Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers with representation of every person and action in the training and testing datasets. Performance study shows that PBL-McRBFN outperforms these classifiers in recognizing actions in 3-D. Further, a subject-independent study is conducted by leave-one-subject-out strategy and its generalization performance is tested. It is observed from the subject-independent study that McRBFN is capable of generalizing actions accurately. The performance of the proposed approach is benchmarked with Video Analytics Lab (VAL) dataset and Berkeley Multimodal Human Action Database (MHAD). (C) 2013 Elsevier Ltd. All rights reserved.

Design of a Low Power 64 Point FFT Architecture for WLAN Applications

This paper presents a Radix-4(3) based FFT architecture suitable for OFDM based WLAN applications. The radix-4(3) parallel unrolled architecture presented here, uses a radix-4 butterfly unit which takes all four inputs in parallel and can selectively produce one out of the four outputs. A 64 point FFT processor based on the proposed architecture has been implemented in UMC 130nm 1P8M CMOS process with a maximum clock frequency of 100 MHz and area of 0.83mm(2). The proposed processor provides a throughput of four times the clock rate and can finish one 64 point FFT computation in 16 clock cycles. For IEEE 802.11a/g WLAN, the processor needs to be operated at a clock rate of 5 MHz with a power consumption of 2.27 mW which is 27% less than the previously reported low power implementations.

NESTED SPARSE BAYESIAN LEARNING FOR BLOCK-SPARSE SIGNALS WITH INTRA-BLOCK CORRELATION

In this work, we address the recovery of block sparse vectors with intra-block correlation, i.e., the recovery of vectors in which the correlated nonzero entries are constrained to lie in a few clusters, from noisy underdetermined linear measurements. Among Bayesian sparse recovery techniques, the cluster Sparse Bayesian Learning (SBL) is an efficient tool for block-sparse vector recovery, with intra-block correlation. However, this technique uses a heuristic method to estimate the intra-block correlation. In this paper, we propose the Nested SBL (NSBL) algorithm, which we derive using a novel Bayesian formulation that facilitates the use of the monotonically convergent nested Expectation Maximization (EM) and a Kalman filtering based learning framework. Unlike the cluster-SBL algorithm, this formulation leads to closed-form EMupdates for estimating the correlation coefficient. We demonstrate the efficacy of the proposed NSBL algorithm using Monte Carlo simulations.

Action Recognition from Motion Capture Data using Meta-cognitive RBF Network Classifier

Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 31) angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).

Chemically Programmed Ultrahigh Density Two-Dimensional Semiconductor Superlattice Array

Designing an ultrahigh density linear superlattice array consisting of periodic blocks of different semiconductors in the strong confinement regime via a direct synthetic route remains an unachieved challenge in nanotechnology. We report a general synthesis route for the formulation of a large-area ultrahigh density superlattice array that involves adjoining multiple units of ZnS rods by prolate US particles at the tips. A single one-dimensional wire is 300-500 nm long and consists of periodic quantum wells with a barrier width of 5 nm provided by ZnS and a well width of 1-2 nm provided by CdS, defining a superlattice structure. The synthesis route allows for tailoring of ultranarrow laserlike emissions (fwhm approximate to 125 meV) originating from strong interwell energy dispersion along with control of the width, pitch, and registry of the superlattice assembly. Such an exceptional high-density superlattice array could form the basis of ultrahigh density memories in addition to offering opportunities for technological advancement in conventional heterojunction-based device applications.

A New Iterative FIR Filter for Image and Video Restoration

Image and video filtering is a key image-processing task in computer vision especially in noisy environment. In most of the cases the noise source is unknown and hence possess a major difficulty in the filtering operation. In this paper we present an error-correction based learning approach for iterative filtering. A new FIR filter is designed in which the filter coefficients are updated based on Widrow-Hoff rule. Unlike the standard filter the proposed filter has the ability to remove noise without the a priori knowledge of the noise. Experimental result shows that the proposed filter efficiently removes the noise and preserves the edges in the image. We demonstrate the capability of the proposed algorithm by testing it on standard images infected by Gaussian noise and on a real time video containing inherent noise. Experimental result shows that the proposed filter is better than some of the existing standard filters

Human Action Recognition in Compressed Domain using PBL-McRBFN Approach

Large variations in human actions lead to major challenges in computer vision research. Several algorithms are designed to solve the challenges. Algorithms that stand apart, help in solving the challenge in addition to performing faster and efficient manner. In this paper, we propose a human cognition inspired projection based learning for person-independent human action recognition in the H.264/AVC compressed domain and demonstrate a PBL-McRBEN based approach to help take the machine learning algorithms to the next level. Here, we use gradient image based feature extraction process where the motion vectors and quantization parameters are extracted and these are studied temporally to form several Group of Pictures (GoP). The GoP is then considered individually for two different bench mark data sets and the results are classified using person independent human action recognition. The functional relationship is studied using Projection Based Learning algorithm of the Meta-cognitive Radial Basis Function Network (PBL-McRBFN) which has a cognitive and meta-cognitive component. The cognitive component is a radial basis function network while the Meta-Cognitive Component(MCC) employs self regulation. The McC emulates human cognition like learning to achieve better performance. Performance of the proposed approach can handle sparse information in compressed video domain and provides more accuracy than other pixel domain counterparts. Performance of the feature extraction process achieved more than 90% accuracy using the PTIL-McRBFN which catalyzes the speed of the proposed high speed action recognition algorithm. We have conducted twenty random trials to find the performance in GoP. The results are also compared with other well known classifiers in machine learning literature.

Photocytotoxic luminescent lanthanide complexes of DTPA-bisamide using quinoline as photosensitizer

Lanthanide complexes Ln(DTPAAQ)(DMF)] (1-3) (Ln - Pr (1), Eu (2), Tb (3), H(3)DTPAAQ - N, N `'-bis(3-amidoquinolyl) diethylenetriamine-N, N', N `'-triacetic acid, DMF - N, N-dimethylformamide) were studied for their structures, photophysical properties, DNA and protein binding, DNA photocleavage, photocytotoxicity and cellular internalization. The crystal structures of complexes Ln(DTPAAQ)(DMF)] (1-3) display a discrete mononuclear nine-coordinate {LnN(3)O(6)} tricapped-trigonal prism (TTP) coordination geometry. The europium and terbium complexes show strong luminescence properties in the visible region having a long luminescence lifetime (tau = 0.51-0.64 ms). The conjugated 3-aminoquinoline moieties act as efficient light harvesting antennae, which upon photoexcitation transfer their energy to Eu(III) or Tb(III) for their characteristic D-5(0) -> F-7(J) or D-5(4) -> F-7(J) f-f transitions respectively. The complexes display efficient binding affinity to DNA (K-b = 3.4 x 10(4) - 9.8 x 10(4) M-1) and BSA (KBSA = 3.03 x 10(4) - 6.57 x 10(4) M-1). Europium and terbium complexes give enhanced luminescence upon interacting with CT-DNA suggesting possible luminescence-based sensing applications for these complexes. Complexes 1-3 show moderate cleavage of supercoiled (SC) DNA to its nicked circular (NC) form on exposure to UV-A light of 312 nm involving formation of singlet oxygen (O-1(2)) and hydroxyl radicals (cOH) in type-II and photoredox pathways. Eu(III) and Tb(III) complexes exhibit remarkable photocytotoxicity with human cervical cancer cell line (HeLa) (IC50 = 20.7-28.5 mM) while remaining essentially noncytotoxic up to 150 mM in the dark. Complexes are nontoxic in nature thus suitable for designing cellular imaging agents. Fluorescence microscopy data reveal primarily cytosolic localization of the Eu(III) and Tb(III) complexes in HeLa cells.