Evidence of syntactic working memory usage in MEG data

While reading times are often used to measure working memory load, frequency effects (such as surprisal or n-gram frequencies) also have strong confounding effects on reading times. This work uses a naturalistic audio corpus with magnetoencephalographic (MEG) annotations to measure working memory load during sentence processing. Alpha oscillations in posterior regions of the brain have been found to correlate with working memory load in non-linguistic tasks (Jensen et al., 2002), and the present study extends these findings to working memory load caused by syntactic center embeddings. Moreover, this work finds that frequency effects in naturally-occurring stimuli do not significantly contribute to neural oscillations in any frequency band, which suggests that many modeling claims could be tested on this sort of data even without controlling for frequency effects.

Memory Usage Inference for Object-Oriented Programs

We present a type-based approach to statically derive symbolic closed-form formulae that characterize the bounds of heap memory usages of programs written in object-oriented languages. Given a program with size and alias annotations, our inference system will compute the amount of memory required by the methods to execute successfully as well as the amount of memory released when methods return. The obtained analysis results are useful for networked devices with limited computational resources as well as embedded software.

Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

Mesh traversal and sorting for efficient memory usage in scientific codes

Applications that operate on meshes are very popular in High Performance Computing (HPC) environments. In the past, many techniques have been developed in order to optimize the memory accesses for these datasets. Different loop transformations and domain decompositions are com- monly used for structured meshes. However, unstructured grids are more challenging. The memory accesses, based on the mesh connectivity, do not map well to the usual lin- ear memory model. This work presents a method to improve the memory performance which is suitable for HPC codes that operate on meshes. We develop a method to adjust the sequence in which the data are used inside the algorithm, by means of traversing and sorting the mesh. This sorted mesh can be transferred sequentially to the lower memory levels and allows for minimum data transfer requirements. The method also reduces the lower memory requirements dra- matically: up to 63% of the L1 cache misses are removed in a traditional cache system. We have obtained speedups of up to 2.58 on memory operations as measured in a general- purpose CPU. An improvement is also observed with se- quential access memories, where we have observed reduc- tions of up to 99% in the required low-level memory size.

Memory Cost Analysis for OpenFlow Multiple Table Lookup

Multiple Table Lookup architectures in Software Defined Networking (SDN) open the door for exciting new network applications. The development of the OpenFlow protocol supported the SDN paradigm. However, the first version of the OpenFlow protocol specified a single table lookup model with the associated constraints in flow entry numbers and search capabilities. With the introduction of multiple table lookup in OpenFlow v1.1, flexible and efficient search to support SDN application innovation became possible. However, implementation of multiple table lookup in hardware to meet high performance requirements is non-trivial. One possible approach involves the use of multi-dimensional lookup algorithms. A high lookup performance can be achieved by using embedded memory for flow entry storage. A detailed study of OpenFlow flow filters for multi-dimensional lookup is presented in this paper. Based on a proposed multiple table lookup architecture, the memory consumption and update performance using parallel single field searches are evaluated. The results demonstrate an efficient multi-table lookup implementation with minimum memory usage.

Darjeeling, a Java compatible virtual machine for microcontrollers

The Java programming language enjoys widespread popularity on platforms ranging from servers to mobile phones. While efforts have been made to run Java on microcontroller platforms, there is currently no feature-rich, open source virtual machine available. In this paper we present Darjeeling, a system comprising offline tools and a memory efficient runtime. The offline post-compiler tool analyzes, links and consolidates Java class files into loadable modules. The runtime implements a modified Java VM that supports multithreading and is designed specifically to operate in constrained execution environments such as wireless sensor network nodes. Darjeeling improves upon existing work by supporting inheritance, threads, garbage collection, and loadable modules while keeping memory usage to a minimum. We have demonstrated Java running on AVR128 and MSP430 micro-controllers at speeds of up to 70,000 JVM instructions per second.

Scalability of encryption techniques for electronic health record (EHR) retrieval

Electronic Health Record (EHR) retrieval processes are complex demanding Information Technology (IT) resources exponentially in particular memory usage. Database-as-a-service (DAS) model approach is proposed to meet the scalability factor of EHR retrieval processes. A simulation study using ranged of EHR records with DAS model was presented. The bucket-indexing model incorporated partitioning fields and bloom filters in a Singleton design pattern were used to implement custom database encryption system. It effectively provided faster responses in the range query compared to different types of queries used such as aggregation queries among the DAS, built-in encryption and the plain-text DBMS. The study also presented with constraints around the approach should consider for other practical applications.

Capping computation time and storage requirements for appearance-based localization with CAT-SLAM

Appearance-based localization is increasingly used for loop closure detection in metric SLAM systems. Since it relies only upon the appearance-based similarity between images from two locations, it can perform loop closure regardless of accumulated metric error. However, the computation time and memory requirements of current appearance-based methods scale linearly not only with the size of the environment but also with the operation time of the platform. These properties impose severe restrictions on longterm autonomy for mobile robots, as loop closure performance will inevitably degrade with increased operation time. We present a set of improvements to the appearance-based SLAM algorithm CAT-SLAM to constrain computation scaling and memory usage with minimal degradation in performance over time. The appearance-based comparison stage is accelerated by exploiting properties of the particle observation update, and nodes in the continuous trajectory map are removed according to minimal information loss criteria. We demonstrate constant time and space loop closure detection in a large urban environment with recall performance exceeding FAB-MAP by a factor of 3 at 100% precision, and investigate the minimum computational and memory requirements for maintaining mapping performance.

Fast tessellated solid navigation in GEANT4

Navigation through tessellated solids in GEANT4 can degrade computational performance, especially if the tessellated solid is large and is comprised of many facets. Redefining a tessellated solid as a mesh of tetrahedra is common in other computational techniques such as finite element analysis as computations need only consider local tetrahedrons rather than the tessellated solid as a whole. Here within we describe a technique that allows for automatic tetrahedral meshing of tessellated solids in GEANT4 and the subsequent loading of these meshes as assembly volumes; loading nested tessellated solids and tetrahedral meshes is also examined. As the technique makes the geometry suitable for automatic optimisation using smartvoxels, navigation through a simple tessellated volume has been found to be more than two orders of magnitude faster than that through the equivalent tessellated solid. Speed increases of more than two orders of magnitude were also observed for a more complex tessellated solid with voids and concavities. The technique was benchmarked for geometry load time, simulation run time and memory usage. Source code enabling the described functionality in GEANT4 has been made freely available on the Internet.

Decentralized detector generation in cooperative intrusion detection system

We consider Cooperative Intrusion Detection System (CIDS) which is a distributed AIS-based (Artificial Immune System) IDS where nodes collaborate over a peer-to-peer overlay network. The AIS uses the negative selection algorithm for the selection of detectors (e.g., vectors of features such as CPU utilization, memory usage and network activity). For better detection performance, selection of all possible detectors for a node is desirable but it may not be feasible due to storage and computational overheads. Limiting the number of detectors on the other hand comes with the danger of missing attacks. We present a scheme for the controlled and decentralized division of detector sets where each IDS is assigned to a region of the feature space. We investigate the trade-off between scalability and robustness of detector sets. We address the problem of self-organization in CIDS so that each node generates a distinct set of the detectors to maximize the coverage of the feature space while pairs of nodes exchange their detector sets to provide a controlled level of redundancy. Our contribution is twofold. First, we use Symmetric Balanced Incomplete Block Design, Generalized Quadrangles and Ramanujan Expander Graph based deterministic techniques from combinatorial design theory and graph theory to decide how many and which detectors are exchanged between which pair of IDS nodes. Second, we use a classical epidemic model (SIR model) to show how properties from deterministic techniques can help us to reduce the attack spread rate.

The ranking based constrained document clustering method and its application to social event detection

With the growing size and variety of social media files on the web, it’s becoming critical to efficiently organize them into clusters for further processing. This paper presents a novel scalable constrained document clustering method that harnesses the power of search engines capable of dealing with large text data. Instead of calculating distance between the documents and all of the clusters’ centroids, a neighborhood of best cluster candidates is chosen using a document ranking scheme. To make the method faster and less memory dependable, the in-memory and in-database processing are combined in a semi-incremental manner. This method has been extensively tested in the social event detection application. Empirical analysis shows that the proposed method is efficient both in computation and memory usage while producing notable accuracy.

Scalable Context-Sensitive Points-To Analysis Using Multi-Dimensional Bloom Filters

Context-sensitive points-to analysis is critical for several program optimizations. However, as the number of contexts grows exponentially, storage requirements for the analysis increase tremendously for large programs, making the analysis non-scalable. We propose a scalable flow-insensitive context-sensitive inclusion-based points-to analysis that uses a specially designed multi-dimensional bloom filter to store the points-to information. Two key observations motivate our proposal: (i) points-to information (between pointer-object and between pointer-pointer) is sparse, and (ii) moving from an exact to an approximate representation of points-to information only leads to reduced precision without affecting correctness of the (may-points-to) analysis. By using an approximate representation a multi-dimensional bloom filter can significantly reduce the memory requirements with a probabilistic bound on loss in precision. Experimental evaluation on SPEC 2000 benchmarks and two large open source programs reveals that with an average storage requirement of 4MB, our approach achieves almost the same precision (98.6%) as the exact implementation. By increasing the average memory to 27MB, it achieves precision upto 99.7% for these benchmarks. Using Mod/Ref analysis as the client, we find that the client analysis is not affected that often even when there is some loss of precision in the points-to representation. We find that the NoModRef percentage is within 2% of the exact analysis while requiring 4MB (maximum 15MB) memory and less than 4 minutes on average for the points-to analysis. Another major advantage of our technique is that it allows to trade off precision for memory usage of the analysis.

RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

Human action recognition in H.264/AVC compressed domain using meta-cognitive radial basis function network

In this paper, we propose a H.264/AVC compressed domain human action recognition system with projection based metacognitive learning classifier (PBL-McRBFN). The features are extracted from the quantization parameters and the motion vectors of the compressed video stream for a time window and used as input to the classifier. Since compressed domain analysis is done with noisy, sparse compression parameters, it is a huge challenge to achieve performance comparable to pixel domain analysis. On the positive side, compressed domain allows rapid analysis of videos compared to pixel level analysis. The classification results are analyzed for different values of Group of Pictures (GOP) parameter, time window including full videos. The functional relationship between the features and action labels are established using PBL-McRBFN with a cognitive and meta-cognitive component. The cognitive component is a radial basis function, while the meta-cognitive component employs self-regulation to achieve better performance in subject independent action recognition task. The proposed approach is faster and shows comparable performance with respect to the state-of-the-art pixel domain counterparts. It employs partial decoding, which rules out the complexity of full decoding, and minimizes computational load and memory usage. This results in reduced hardware utilization and increased speed of classification. The results are compared with two benchmark datasets and show more than 90% accuracy using the PBL-McRBFN. The performance for various GOP parameters and group of frames are obtained with twenty random trials and compared with other well-known classifiers in machine learning literature. (C) 2015 Elsevier B.V. All rights reserved.

Compressed domain human action recognition in H.264/AVC video streams

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of the proposed work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85 % accuracy. The proposed algorithm classifies actions with speed (> 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms.