Limited Memory Environment Research Articles

Tiny Asymmetric Feature Normalized Network for Person Re-Identification System

Person re-identification (ReID) identifies object IDs in a multicamera environment based on local tracking of city surveillance cameras in public places. This method can improve the performance by learning various features using a convolutional neural network. However, ReID methods are limited in terms of application in practical surveillance environments as the ReID model is trained on public datasets and lacks the ability to generalize images acquired using other cameras. Moreover, although various methods to improve the ReID performance have been proposed, most existing studies did not evaluate ReID performances according to the number of parameters, i.e., ReID models that can be used in a limited memory environment were not considered. In this study, we propose a Tiny Asymmetric Feature Normalized Network, which can be generalized to test atasets acquired in real surveillance environments considering various scale features and can be operated with a limited number of parameters. Moreover, the Gwangju Institute of Science and Technology Practical Person ReID (GPP-reID) dataset, which was used to evaluate the performance of the ReID model, has been distributed and made available to enable applications in real-world surveillance environments. Our proposed method achieved mean average precision (mAP), Rank-1 values of 86.2, 94.7 and 74.8, 85.9 on the Market1501 and Duke Multitracking Multicamera ReID datasets, respectively. In addition, mAP and Rank-1 values of 44.2 and 64.1, respectively, were achieved on the cross-validated, new benchmark dataset, GPP-reID, using a network with one-tenth the number of parameters as the 50-layer residual network.

CDDM: Concept Drift Detection Model for Data Stream

<p>Data stream is the huge amount of data generated in various fields, including financial processes, social media activities, Internet of Things applications, and many others. Such data cannot be processed through traditional data mining algorithms due to several constraints, including limited memory, data speed, and dynamic environment. Concept Drift is known as the main constraint of data stream mining, mainly in the classification task. It refers to the change in the data stream underlining distribution over time. Thus, it results in accuracy deterioration of classification models and wrong predictions. Spam emails, consumer behavior changes, and adversary activates, are examples of Concept Drift. In this paper, a Concept Drift detection model is introduced, Concept Drift Detection Model (CDDM). It monitors the accuracy of the classification model over a sliding window, assuming the decline in accuracy indicates a drift occurrence. A modification over CDDM is a weighted version of the CDDM as W-CDDM.</p><p>Both models have evaluated against two real datasets and four artificial datasets. The experimental results of abrupt drift show that CDDM, W-CDDM outperforms the other models in the dataset of 100K and 1M instances, respectively. Regarding gradual drift, the W-CDDM overtook the rest in terms of accuracy, run time, and detection delays in the dataset of 100 K instances. While in the dataset of 1M instances, CDDM has got the highest accuracy using the NB classifier. Moreover, W-CDDM achieves the highest accuracy on real datasets.</p>

Algorithms for spatial collocation pattern mining in a limited memory environment: a summary of results

Rapid growth of spatial datasets requires methods to find (semi-)automatically spatial knowledge from these sets. Spatial collocation patterns represent subsets of spatial features whose instances are frequently located together in a spatial neighborhood. In recent years, efficient methods for collocation discovery have been developed, however, none of them assume limited size of the operational memory or limited access to memory with short access times. Such restrictions are especially important in the context of the large size of the data structures required for efficient identification of collocation instances. In this work we present and compare three algorithms for collocation pattern mining in a limited memory environment. The first algorithm is based on the well-known joinless method introduced by Shekhar and Yoo. The second and third algorithms are inspired by a tree structure (iCPI-tree) presented by Wang et al. In our experimental evaluation, we have compared the efficiency of the algorithms, both on synthetic and real world datasets.

Effectively and Efficiently Mining Frequent Patterns from Dense Graph Streams on Disk

In this paper, we focus on dense graph streams, which can be generated in various applications ranging from sensor networks to social networks, from bio-informatics to chemical informatics. We also investigate the problem of effectively and efficiently mining frequent patterns from such streaming data, in the targeted case of dealing with limited memory environments so that disk support is required. This setting occurs frequently (e.g., in mobile applications/systems) and is gaining momentum even in advanced computational settings where social networks are the main representative. Inspired by this problem, we propose (i) a specialized data structure called DSMatrix, which captures important data from dense graph streams onto the disk directly and (ii) stream mining algorithms that make use of such structure in order to mine frequent patterns effectively and efficiently. Experimental results clearly confirm the benefits of our approach.

FEATURE SELECTION FOR OPTIMIZATION OF WAVELET PACKET DECOMPOSITION IN RELIABILITY ANALYSIS OF SYSTEMS

One of the most important types of signal found in the area of machine condition monitoring/prognostic health monitoring (MCM/PHM) is the vibration signal, a type of waveform. Many time-frequency domain techniques have been proposed to interpret such signals, including wavelet packet decomposition (WPD). Previous work has shown how to extend the WPD algorithm to operate on streaming signals, but the number of output variables becomes exponential in the number of levels of decomposition, hindering data mining in limited-memory environments. Feature selection techniques, well understood in other areas of data mining, can be used to greatly reduce the number of output variables and speed up the machine learning algorithms. This paper presents a case study comparing two versions of WPD both with and without feature selection, demonstrating that removing most of the features produced by the WPD does not impair its performance within the context of MCM/PHM.

Real-time ambient occlusion and halos with Summed Area Tables

Volume models often show high depth complexity. This poses difficulties to the observer in judging the spatial relationships accurately. Illustrators usually use certain techniques such as improving the shading through shadows, halos, or edge darkening in order to enhance depth perception of certain structures. Both effects are difficult to generate in real-time for volumetric models. Either they may have an important impact in rendering time, or they require precomputation that prevents changing the transfer function interactively, as it determines the occlusions. In this paper we present two methods for the fast generation of ambient occlusion on volumetric models. The first is a screen-space approach that does not require any precomputed data structure. The second is a view independent method that stores volumetric information in the form of a Summed Area Table of the density values, and thus, allows the interactive change of transfer functions on demand, although at the expense of memory space. Despite the fact that similar quality results are obtained with both approaches, the 3D version is more suitable for objects with discontinuous structures such as a vessels tree or the intestines, and it yields better framerates. The screen-space version is more suitable in limited GPU memory environments because it does not need extra 3D texture storage. As an extra result, our screen-space technique also allows for the computation of view dependent, interactively configurable halos using the same data structure. We have also implemented both methods using CUDA and have analyzed their efficiency.

Madre: the Memory-Aware Data Redistribution Engine

We report on the development of a new computational framework for efficiently carrying out parallel data redistribution in a limited memory environment. This new library, MADRE (Memory-Aware Data Redistribution Engine), is an open-source, C/MPI-based toolkit designed for quick and easy integration into application codes that have demanding data migration needs. At the same time, MADRE exposes a lower-level application programming interface that greatly facilitates the development and incorporation of new algorithms into the MADRE framework, thus serving as a potential organizing entity for continued research in this area. Finally, we develop, describe, and test in detail several new parallel redistribution algorithms that are incorporated into the MADRE distribution.

Analysis of the solution phase of a parallel multifrontal approach

We study the forward and backward substitution phases of a sparse multifrontal factorization. These phases are often neglected in papers on sparse direct factorization but, in many applications, they can be the bottleneck so it is crucial to implement them efficiently. In this work, we assume that the factors have been written on disk during the factorization phase, and we discuss the design of an efficient solution phase. We will look at the issues involved when we are solving the sparse systems on parallel computers and will consider in particular their solution in a limited memory environment when out-of-core working is required. Two different approaches are presented to read data from the disk, with a discussion on the advantages and the drawbacks of each. We present some experiments on realistic test problems using an out-of-core version of a sparse multifrontal code called MUltifrontal Massively Parallel Solver (MUMPS).

Algorithm 734: A Fortran 90 code for unconstrained nonlinear minimization

This paper describes a Fortran 90 implementation of ACM Transactions on Mathematical Software Algorithm 630, a minimization algorithm designed for use in a limited-memory environment. It includes implementation of the Buckley-LeNir method, Nocedal's limited memory algorithm, and an experimental limited-memory implementation of a factored update due to Powell, as well as a fairly standard quasi-Newton implementation due originally to Shanno. This algorithm uses a number of the new features of Fortran 90 to offer capabilities that were not formerly available.