Trading spaces : on the lore and limitations of latent semantic analysis

Two decades after its inception, Latent Semantic Analysis(LSA) has become part and parcel of every modern introduction to Information Retrieval. For any tool that matures so quickly, it is important to check its lore and limitations, or else stagnation will set in. We focus here on the three main aspects of LSA that are well accepted, and the gist of which can be summarized as follows: (1) that LSA recovers latent semantic factors underlying the document space, (2) that such can be accomplished through lossy compression of the document space by eliminating lexical noise, and (3) that the latter can best be achieved by Singular Value Decomposition. For each aspect we performed experiments analogous to those reported in the LSA literature and compared the evidence brought to bear in each case. On the negative side, we show that the above claims about LSA are much more limited than commonly believed. Even a simple example may show that LSA does not recover the optimal semantic factors as intended in the pedagogical example used in many LSA publications. Additionally, and remarkably deviating from LSA lore, LSA does not scale up well: the larger the document space, the more unlikely that LSA recovers an optimal set of semantic factors. On the positive side, we describe new algorithms to replace LSA (and more recent alternatives as pLSA, LDA, and kernel methods) by trading its l2 space for an l1 space, thereby guaranteeing an optimal set of semantic factors. These algorithms seem to salvage the spirit of LSA as we think it was initially conceived.

Intraurban rail access : Policy implications of five revealed perspectives from a Q-sorting exercise in three Australian cities

This project advances current understanding of intra-urban rail passengers and their travel experiences in order to help rail industry leaders tailor policy approaches to fit specific, relevant segments of their target population. Using a Q sorting technique and cluster analysis, our preliminary research identified five perspectives occurring in a small sample of rail passengers, who varied in their frequency and location of rail travel as well as certain socio-demographic characteristics. Revealed perspectives (named to capture the gist of their content) included: ‘Rail Travel is About the Destination, Not the Journey’; ‘Despite Challenges, Public Transport is Still the Best Option’; ‘Rail Travel is Fine’; ‘Rail Travel? So Far, So Good’; and ‘Bad Taste for Rail Travel’. This paper discusses each of the perspectives in detail, and considers them in terms of tailored policy implications. An overarching finding from this study is that improving railway travel ‘access’ requires attention to physical, psychological, financial, and social facets of accessibility. For example, designing waiting areas to be more socially functional and comfortable has the potential to increase ridership by addressing social forms of access, decreasing perceived wait times, and making time at the station feel like time well spent. Even at this preliminary stage, the Q sorting technique promises to provide a valuable, holistic albeit fine-grained analysis of passenger attitudes and experiences that will assist industry efforts to increase ridership.

Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Intraurban rail access : policy implications of five revealed perspectives from a Q-sorting exercise in three Australian cities

This project advances the current understanding of intraurban rail passengers and their travel experiences to help rail industry leaders tailor policy approaches to fit specific, relevant segments of their target population. Using a Q-sorting technique and cluster analysis, preliminary research identified five perspectives occurring in a small sample of rail passengers who varied in their frequency and location of rail travel as well as certain sociodemographic characteristics. Revealed perspectives (named to capture the gist of their content) included "Rail travel is about the destination, not the journey"; "Despite challenges, public transport is still the best option"; "Rail travel is fine"; "Rail travel? So far, so good"; and "Bad taste for rail travel." This paper discusses each of the perspectives in detail and considers them in relation to tailored policy implications. An overarching finding from this study is that improving railway travel access requires attention to physical, psychological, financial, and social facets of accessibility. For example, designing waiting areas to be more socially functional and comfortable has the potential to increase ridership by addressing social forms of access, decreasing perceived wait times, and making time at the station feel like time well spent. Even at this preliminary stage, the Q-sorting technique promises to provide a valuable, holistic, albeit fine-grained, analysis of passenger attitudes and experiences that will assist industry efforts in increasing ridership.

Superpixel-based appearance change prediction for long-term navigation across seasons

Changing environments pose a serious problem to current robotic systems aiming at long term operation under varying seasons or local weather conditions. This paper is built on our previous work where we propose to learn to predict the changes in an environment. Our key insight is that the occurring scene changes are in part systematic, repeatable and therefore predictable. The goal of our work is to support existing approaches to place recognition by learning how the visual appearance of an environment changes over time and by using this learned knowledge to predict its appearance under different environmental conditions. We describe the general idea of appearance change prediction (ACP) and investigate properties of our novel implementation based on vocabularies of superpixels (SP-ACP). Our previous work showed that the proposed approach significantly improves the performance of SeqSLAM and BRIEF-Gist for place recognition on a subset of the Nordland dataset under extremely different environmental conditions in summer and winter. This paper deepens the understanding of the proposed SP-ACP system and evaluates the influence of its parameters. We present the results of a large-scale experiment on the complete 10 h Nordland dataset and appearance change predictions between different combinations of seasons.