Justin Lloyd's Thinkering

Today I read a paper titled “Face Recognition using Principal Component Analysis and Log-Gabor Filters”

The abstract is:
In this article we propose a novel face recognition method based on Principal Component Analysis (PCA) and Log-Gabor filters.

The main advantages of the proposed method are its simple implementation, training, and very high recognition accuracy.

For recognition experiments we used 5151 face images of 1311 persons from different sets of the FERET and AR databases that allow to analyze how recognition accuracy is affected by the change of facial expressions, illumination, and aging.

Recognition experiments with the FERET database (containing photographs of 1196 persons) showed that our method can achieve maximal 97-98% first one recognition rate and 0.3-0.4% Equal Error Rate.

The experiments also showed that the accuracy of our method is less affected by eye location errors and used image normalization method than of traditional PCA -based recognition method.

Today I read a paper titled “Quantum random walks – an introductory overview”

The abstract is:
This article aims to provide an introductory survey on quantum random walks.

Starting from a physical effect to illustrate the main ideas we will introduce quantum random walks, review some of their properties and outline their striking differences to classical walks.

We will touch upon both physical effects and computer science applications, introducing some of the main concepts and language of present day quantum information science in this context.

We will mention recent developments in this new area and outline some open questions.

Today I read a paper titled “Speech Synthesis with Neural Networks”

The abstract is:
Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech.

This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural network to control the timing of the generated speech.

The neural network system requires less memory than a concatenation system, and performed well in tests comparing it to commercial systems using other technologies.

Today I read a paper titled “Text-To-Speech Conversion with Neural Networks: A Recurrent TDNN Approach”

The abstract is:
This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system.

The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries.

Recurrent data input also helps smooth the output parameter tracks.

Independent testing has demonstrated that the voice quality produced by this system compares favorably with speech from existing commercial text-to-speech systems.

Today I read a paper titled “Re-Finding Found Things: An Exploratory Study of How Users Re-Find Information”

The abstract is:
The problem of how people find information is studied extensively; however, the problem of how people organize, re-use, and re-find information that they have found is not as well understood.

Recently, several projects have conducted in-situ studies to explore how people re-find and re-use information.

Here, we present results and observations from a controlled, laboratory study of refinding information found on the web.

Our study was conducted as a collaborative exercise with pairs of participants.

One participant acted as a retriever, helping the other participant re-find information by telephone.

This design allowed us to gain insight into the strategies that users employed to re-find information, and into how domain artifacts and contextual information were used to aid the re-finding process.

We also introduced the ability for users to add their own explicitly artifacts in the form of making annotations on the web pages they viewed.

We observe that re-finding often occurs as a two stage, iterative process in which users first attempt to locate an information source (search), and once found, begin a process to find the specific information being sought (browse).

Our findings are consistent with research on waypoints; orienteering approaches to re-finding; and navigation of electronic spaces.

Furthermore, we observed that annotations were utilized extensively, indicating that explicitly added context by the user can play an important role in re-finding.

Today I read a paper titled “Probabilistic Search for Object Segmentation and Recognition”

The abstract is:
The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework.

Object models are formulated as generative models for range data of the scene.

A new statistical criterion, the truncated object probability, is introduced to infer an optimal sequence of object hypotheses to be evaluated for their match to the data.

The truncated probability is partly determined by prior knowledge of the objects and partly learned from data.

Some experiments on sequence quality and object segmentation and recognition from stereo data are presented.

The article recovers classic concepts from object recognition (grouping, geometric hashing, alignment) from the probabilistic perspective and adds insight into the optimal ordering of object hypotheses for evaluation.

Moreover, it introduces point-relation densities, a key component of the truncated probability, as statistical models of local surface shape.

Today I read a paper titled “Learning unification-based grammars using the Spoken English Corpus”

The abstract is:
This paper describes a grammar learning system that combines model-based and data-driven learning within a single framework.

Our results from learning grammars using the Spoken English Corpus (SEC) suggest that combined model-based and data-driven learning can produce a more plausible grammar than is the case when using either learning style isolation..

Today I read a paper titled “A New Computational Framework For 2D Shape-Enclosing Contours”

The abstract is:
In this paper, a new framework for one-dimensional contour extraction from discrete two-dimensional data sets is presented.

Contour extraction is important in many scientific fields such as digital image processing, computer vision, pattern recognition, etc.

This novel framework includes (but is not limited to) algorithms for dilated contour extraction, contour displacement, shape skeleton extraction, contour continuation, shape feature based contour refinement and contour simplification.

Many of the new techniques depend strongly on the application of a Delaunay tessellation.

In order to demonstrate the versatility of this novel toolbox approach, the contour extraction techniques presented here are applied to scientific problems in material science, biology and heavy ion physics.

Today I read a paper titled “Collaborative Storage Management In Sensor Networks”

The abstract is:
In this paper, we consider a class of sensor networks where the data is not required in real-time by an observer; for example, a sensor network monitoring a scientific phenomenon for later play back and analysis.

In such networks, the data must be stored in the network.

Thus, in addition to battery power, storage is a primary resource: the useful lifetime of the network is constrained by its ability to store the generated data samples.

We explore the use of collaborative storage technique to efficiently manage data in storage constrained sensor networks.

The proposed collaborative storage technique takes advantage of spatial correlation among the data collected by nearby sensors to significantly reduce the size of the data near the data sources.

We show that the proposed approach provides significant savings in the size of the stored data vs.

local buffering, allowing the network to run for a longer time without running out of storage space and reducing the amount of data that will eventually be relayed to the observer.

In addition, collaborative storage performs load balancing of the available storage space if data generation rates are not uniform across sensors (as would be the case in an event driven sensor network), or if the available storage varies across the network.

Today I read a paper titled “Specifying Intonation from Context for Speech Synthesis”

The abstract is:
This paper presents a theory and a computational implementation for generating prosodically appropriate synthetic speech in response to database queries.

Proper distinctions of contrast and emphasis are expressed in an intonation contour that is synthesized by rule under the control of a grammar, a discourse model, and a knowledge base.

The theory is based on Combinatory Categorial Grammar, a formalism which easily integrates the notions of syntactic constituency, semantics, prosodic phrasing and information structure.

Results from our current implementation demonstrate the system’s ability to generate a variety of intonational possibilities for a given sentence depending on the discourse context..

Today I read a paper titled “On the Cell-based Complexity of Recognition of Bounded Configurations by Finite Dynamic Cellular Automata”

The abstract is:
This paper studies complexity of recognition of classes of bounded configurations by a generalization of conventional cellular automata (CA) — finite dynamic cellular automata (FDCA).

Inspired by the CA-based models of biological and computer vision, this study attempts to derive the properties of a complexity measure and of the classes of input configurations that make it beneficial to realize the recognition via a two-layered automaton as compared to a one-layered automaton.

A formalized model of an image pattern recognition task is utilized to demonstrate that the derived conditions can be satisfied for a non-empty set of practical problems.

Today I read a paper titled “Distributed Selfish Load Balancing”

The abstract is:
Suppose that a set of $m$ tasks are to be shared as equally as possible amongst a set of $n$ resources.

A game-theoretic mechanism to find a suitable allocation is to associate each task with a “selfish agent”, and require each agent to select a resource, with the cost of a resource being the number of agents to select it.

Agents would then be expected to migrate from overloaded to underloaded resources, until the allocation becomes balanced.

Recent work has studied the question of how this can take place within a distributed setting in which agents migrate selfishly without any centralized control.

In this paper we discuss a natural protocol for the agents which combines the following desirable features: It can be implemented in a strongly distributed setting, uses no central control, and has good convergence properties.

For $m\gg n$, the system becomes approximately balanced (an $\epsilon$-Nash equilibrium) in expected time $O(\log\log m)$.

We show using a martingale technique that the process converges to a perfectly balanced allocation in expected time $O(\log\log m+n^4)$.

We also give a lower bound of $\Omega(\max\{\log\log m,n\})$ for the convergence time.

Today I read a paper titled “Topic Identification in Discourse”

The abstract is:
This paper proposes a corpus-based language model for topic identification.

We analyze the association of noun-noun and noun-verb pairs in LOB Corpus.

The word association norms are based on three factors: 1) word importance, 2) pair co-occurrence, and 3) distance.

They are trained on the paragraph and sentence levels for noun-noun and noun-verb pairs, respectively.

Under the topic coherence postulation, the nouns that have the strongest connectivities with the other nouns and verbs in the discourse form the preferred topic set.

The collocational semantics then is used to identify the topics from paragraphs and to discuss the topic shift phenomenon among paragraphs..

Today I read a paper titled “Analytical formulations of Peer-to-Peer Connection Efficiency”

The abstract is:
Use of Peer-to-Peer (P2P) service networks introduces a new communication paradigm because peers are both clients and servers and so each peer may provide/request services to/from other peers.

Empirical studies of P2P networks have been undertaken and reveal useful characteristics.

However there is to date little analytical work to describe P2P networks with respect to their communication paradigm and their interconnections.

This paper provides an analytical formulation and optimisation of peer connection efficiency, in terms of minimising the fraction of wasted connection time.

Peer connection efficiency is analysed for both a uni- and multi-connected peer.

Given this fundamental optimisation, the paper optimises the number of connections that peers should make use of as a function of network load, in terms of minimising the total queue size that requests in the P2P network experience.

The results of this paper provide a basis for engineering high performance P2P interconnection networks.

The optimisations are useful for reducing bandwidth and power consumption, e.g.

in the case of peers being mobile devices with a limited power supply.

Also these results could be used to determine when a (virtual) circuit should be switched to support a connection.