Tagging Accuracy Research Articles

Evaluating the energy consumption of the RFID tag collision resolution protocols

RFID technology acts as a bridge to connect the physical world with the digital space, and RFID system is pervading our daily life in the last few years. The energy consumed by the reader and a tag in resolving the collisions caused by multiple tags is a key issue that affects life time of mobile reader and active tags, as well as the identification accuracy of passive tags. In this paper, the energy consumed by the reader and a tag in resolving the tag collision is examined for the commonly used RFID tag collision resolution protocols, including the frame slotted ALOHA based and the binary query tree based protocols. Numeric evaluation is also performed and the result verifies that regarding to energy consumption, the dynamic frame slotted ALOHA protocol for the Class-1 RFID system performs best among the frame slotted ALOHA protocols, and the modified binary query tree protocol also performs better than the standard binary query tree protocols.

A New Model for Automatic Sentence Segmentation

Context Overlapping Model (COM) is presented in this article for the task of Automatic Sentence Segmentation (ASS). Comparing with HMM, COM expands observation from single word to n-gram unit and there is an overlapping part between the neighboring units. Due to the co-occurrence constraint and transition constraint, COM model reduces the search space and improves tagging accuracy. We treated ASS as a task of sequence labeling and applied 2-gram COM to it. The experiment results show that the overall correct rate of the open test is as high as 90.11%, which is significantly higher than the baseline model (second order HMM), which is 85.16%.

Semi-Automatic Tagging of Photo Albums via Exemplar Selection and Tag Inference

As one of the emerging Web 2.0 activities, tagging becomes a popular approach to manage personal media data, such as photo albums. A dilemma in tagging behavior is the users' manual efforts and the tagging accuracy: exhaustively tagging all photos in an album is labor-intensive and time-consuming, and simply entering tags for the whole album leads to unsatisfying results. In this paper, we propose a semi-automatic tagging scheme that aims to facilitate users in photo album tagging. The scheme is able to achieve a good trade-off between manual efforts and tagging accuracy as well as to adjust tagging performance according to the user's customization. For a given album, it first selects a set of representative exemplars for manual tagging via a temporally consistent affinity propagation algorithm, and the tags of the rest of the photos are automatically inferred. Then a constrained affinity propagation algorithm is applied to select a new set of exemplars for manual tagging in an incremental manner, based on which the performance of the tag inference in the previous round can be estimated. If the results are not satisfying enough, a further round of exemplar selection and tag inference will be implemented. This process repeats until satisfactory tagging results are achieved, and users can also stop the process at any time. Experimental results on real-world Flickr photo albums have demonstrated the effectiveness and usefulness of the proposed scheme.

Determining the three-dimensional read accuracy of an RFID tag using a power scaling factor

It is beneficial in RFID applications to know where a tag can be successfully powered in a three-dimensional space. The research presented gives a method for efficient calculation of the powering volume of an RFID tag computationally facilitated by a newly developed power scaling factor. The method, when used in conjunction with the three-dimensional interrogator and tag antenna gains, can provide insight into the powering capability of the tag. Additionally, the power-scaling factor provides a new figure of merit that can be used to compare performance of RFID tags.

Testing the Accuracy of Text Deconstruction using PTree tool.

Our research project is currently to develop an Automatic Concept Relation Extraction (ACRE) System which automatically extracts concepts and their relationships across texts in all domains of knowledge. Concept Relational Tree (CRT) is one of the text analyzer applications used in the ACRE System to automatically extract concepts and their relationships in a document. To check on the correctness of the extraction of concepts and their relationships, the PTree is designed to reconstruct the text by reverse input. In this paper we present the PTree tool to test the accuracy of the automatic tagging and tree structure created by CRT from texts. The PTree tool is implemented from Java Universal Network/ Graph Framework (JUNG) libraries. This tool provides a few functions to allow for flexibility in drawing parse trees for concept relationships. Due to its flexibility and dynamic features, PTree can be further extended for use in the deconstruction of highly complex texts.

Mongolian part-of-speech tagging approach based on conditional random fields

It is necessary to tag both stem and affix in the Mongolian part of speech tagging in order to save lots of syntax and semantic information of affix and to reduce the size of Mongolian dictionary.This paper presented a new approach of Mongolian part of speech tagging based on CRF.To take advantage of the ability of using arbitrary features as input in CRF the system exploited not only the contexts of words but also new statistical features adopted for mutual influence between the morphemes.The system was tested in the 38000 part-of-speech dataset provided by Inner Mongolia University.The closed test results show that POS tagging accuracy of the testing set reaches 96.65% outperforming the HMM-based model.

Founder population-specific HapMap panel increases power in GWA studies through improved imputation accuracy and CNV tagging

The combining of genome-wide association (GWA) data across populations represents a major challenge for massive global meta-analyses. Genotype imputation using densely genotyped reference samples facilitates the combination of data across different genotyping platforms. HapMap data is typically used as a reference for single nucleotide polymorphism (SNP) imputation and tagging copy number polymorphisms (CNPs). However, the advantage of having population-specific reference panels for founder populations has not been evaluated. We looked at the properties and impact of adding 81 individuals from a founder population to HapMap3 reference data on imputation quality, CNP tagging, and power to detect association in simulations and in an independent cohort of 2138 individuals. The gain in SNP imputation accuracy was highest among low-frequency markers (minor allele frequency [MAF] < 5%), for which adding the population-specific samples to the reference set increased the median R(2) between imputed and genotyped SNPs from 0.90 to 0.94. Accuracy also increased in regions with high recombination rates. Similarly, a reference set with population-specific extension facilitated the identification of better tag-SNPs for a subset of CNPs; for 4% of CNPs the R(2) between SNP genotypes and CNP intensity in the independent population cohort was at least twice as high as without the extension. We conclude that even a relatively small population-specific reference set yields considerable benefits in SNP imputation, CNP tagging accuracy, and the power to detect associations in founder populations and population isolates in particular.

P2PDocTagger

As the amount of user generated content grows, personal information management has become a challenging problem. Several information management approaches, such as desktop search, document organization and (collaborative) document tagging have been proposed to address this, however they are either inappropriate or inefficient. Automated collaborative document tagging approaches mitigate the problems of manual tagging, but they are usually based on centralized settings which are plagued by problems such as scalability, privacy, etc. To resolve these issues, we present P2PDocTagger, an automated and distributed document tagging system based on classification in P2P networks. P2P-DocTagger minimizes the efforts of individual peers and reduces computation and communication cost while providing high tagging accuracy, and eases of document organization/retrieval. In addition, we provide a realistic and flexible simulation toolkit -- P2PDMT, to facilitate the development and testing of P2P data mining algorithms.

Persian POS tagging using probabilistic morphological analysis

Part of speech (POS) tagging as a fundamental task in natural language processing (NLP) has attracted many research efforts and many taggers are developed with different approaches to reach high performance and accuracy. In many complex applications of NLP, tagged corpora are among essential resources and designing an algorithm to create or enrich these resources is of high importance. Handling unknown words is a challenge in POS tagging which usually decreases the performance of taggers. This paper presents a POS tagger for Persian. It exploits a hybrid approach which is a combination of statistical and rule-based methods to tag Persian sentences. The proposed tagger uses a novel probabilistic morphological analysis to tag unknown words. As a secondary result of this research a knowledge base of Persian morphological rules with their probabilities is built according to a corpus. Experimental results show that our method improves the tagging performance and accuracy.

Combining lexical, syntactic and prosodic cues for improved online dialog act tagging

Prosody is an important cue for identifying dialog acts. In this paper, we show that modeling the sequence of acoustic–prosodic values as n -gram features with a maximum entropy model for dialog act (DA) tagging can perform better than conventional approaches that use coarse representation of the prosodic contour through summative statistics of the prosodic contour. The proposed scheme for exploiting prosody results in an absolute improvement of 8.7% over the use of most other widely used representations of acoustic correlates of prosody. The proposed scheme is discriminative and exploits context in the form of lexical, syntactic and prosodic cues from preceding discourse segments. Such a decoding scheme facilitates online DA tagging and offers robustness in the decoding process, unlike greedy decoding schemes that can potentially propagate errors. Our approach is different from traditional DA systems that use the entire conversation for offline dialog act decoding with the aid of a discourse model. In contrast, we use only static features and approximate the previous dialog act tags in terms of lexical, syntactic and prosodic information extracted from previous utterances. Experiments on the Switchboard-DAMSL corpus, using only lexical, syntactic and prosodic cues from three previous utterances, yield a DA tagging accuracy of 72% compared to the best case scenario with accurate knowledge of previous DA tags (oracle), which results in 74% accuracy.

Minimum tag error for discriminative training of conditional random fields

This paper proposes a new criterion called minimum tag error (MTE) for discriminative training of conditional random fields (CRFs). The new criterion, which is a smoothed approximation to the sentence labeling error, aims to maximize an average of transcription tagging accuracies of all possible sentences, weighted by their probabilities. Corpora from the second international Chinese word segmentation bakeoff (Bakeoff 2005) are used to test the effectiveness of this new training criterion. The experimental results have demonstrated that the proposed minimum tag error criterion can reliably improve the initial performance of supervised conditional random fields. In particular, the recall rate of out-of-vocabulary words ( R oov) is significantly improved compared with that obtained using standard conditional random fields. Furthermore, the new training method has the advantage of robustness to segmentation across all datasets.

Dimensionality of dialogue act tagsets

This article compares one-dimensional and multi-dimensional dialogue act tagsets used for automatic labeling of utterances. The influence of tagset dimensionality on tagging accuracy is first discussed theoretically, then based on empirical data from human and automatic annotations of large scale resources, using four existing tagsets: damsl, swbd-damsl, icsi-mrda and maltus. The Dominant Function Approximation proposes that automatic dialogue act taggers could focus initially on finding the main dialogue function of each utterance, which is empirically acceptable and has significant practical relevance.

High dose dobutamine stress gradient echo imagíng and tagging at 3 T in patients with suspected coronary artery disease

1) to evaluate the feasibility and accuracy of standard GRE and myocardial tagging for detection of obstructive CAD in a high dose dobutamine stress protocol and

Improving Morphosyntactic Tagging of Slovene Language through Meta-tagging

Part-of-speech (PoS) or, better, morphosyntactic tagging is the process of assigning morphosyntactic categories to words in a text, an important pre-processing step for most human language technology applications. PoS-tagging of Slovene texts is a challenging task since the size of the tagset is over one thousand tags (as opposed to English, where the size is typically around sixty) and the state-of-the-art tagging accuracy is still below levels desired. The paper describes an experiment aimed at improving tagging accuracy for Slovene, by combining the outputs of two taggers – a proprietary rule-based tagger developed by the Amebis HLT company, and TnT, a tri-gram HMM tagger, trained on a handannotated corpus of Slovene. The two taggers have comparable accuracy, but there are many cases where, if the predictions of the two taggers differ, one of the two does assign the correct tag. We investigate training a classifier on top of the outputs of both taggers that predicts which of the two taggers is correct. We experiment with selecting different classification algorithms and constructing different feature sets for training and show that some cases yield a meta-tagger with a significant increase in accuracy compared to that of either tagger in isolation.

Looking Under the Hood of Stochastic Machine Learning Algorithms for Parts of Speech Tagging

Abstract : A variety of Natural Language Processing and Information Extraction tasks, such as question answering and named entity recognition, can benefit from precise knowledge about a words? syntactic category or Part of Speech (POS) "Church, 1988; Rabiner, 1989; Stolz, Tannenbaum, & Carstensen, 1965". POS taggers are widely used to assign a single best POS to every word in text data, with stochastic approaches achieving accuracy rates of up to 96% to 97% (Jurafsky & Martin, 2000). When building a POS tagger, human beings needs to make a set of choices about design decisions, some of which significantly impact the accuracy and other performance aspects of the resulting engine. However, documentations of POS taggers often leave these choices and decisions implicit. In this paper we provide an overview on some of these decisions and empirically determine their impact on POS tagging accuracy. The gained insights can be a valuable contribution for people who want to design, implement, modify, fine-tune, integrate, or responsibly use a POS tagger. We considered the results presented herein in building and integrating a POS tagger into AutoMap, a tool that facilitates relation extraction from texts, as a stand-alone feature as well as an auxiliary feature for other tasks.

Tagging Icelandic text: an experiment with integrations and combinations of taggers

We use integrations and combinations of taggers to improve the tagging accuracy of Icelandic text. The accuracy of the best performing integrated tagger, which consists of our linguistic rule-based tagger for initial disambiguation and a trigram tagger for full disambiguation, is 91.80%. Combining five different taggers, using simple voting, results in 93.34% accuracy. By adding two linguistically motivated rules to the combined tagger, we obtain an accuracy of 93.48%. This method reduces the error rate by 20.5%, with respect to the best performing tagger in the combination pool.

Large-scale production of SAGE libraries from microdissected tissues, flow-sorted cells, and cell lines

We describe the details of a serial analysis of gene expression (SAGE) library construction and analysis platform that has enabled the generation of >298 high-quality SAGE libraries and >30 million SAGE tags primarily from sub-microgram amounts of total RNA purified from samples acquired by microdissection. Several RNA isolation methods were used to handle the diversity of samples processed, and various measures were applied to minimize ditag PCR carryover contamination. Modifications in the SAGE protocol resulted in improved cloning and DNA sequencing efficiencies. Bioinformatic measures to automatically assess DNA sequencing results were implemented to analyze the integrity of ditag structure, linker or cross-species ditag contamination, and yield of high-quality tags per sequence read. Our analysis of singleton tag errors resulted in a method for correcting such errors to statistically determine tag accuracy. From the libraries generated, we produced an essentially complete mapping of reliable 21-base-pair tags to the mouse reference genome sequence for a meta-library of approximately 5 million tags. Our analyses led us to reject the commonly held notion that duplicate ditags are artifacts. Rather than the usual practice of discarding such tags, we conclude that they should be retained to avoid introducing bias into the results and thereby maintain the quantitative nature of the data, which is a major theoretical advantage of SAGE as a tool for global transcriptional profiling.

Classification of juvenile flatfishes to estuarine and coastal habitats based on the elemental composition of otoliths

The elemental composition of otoliths from juvenile English sole Pleuronectes vetulus and speckled sanddab Citharichthys stigmaeus living in estuaries and sandy coastal habitats were compared to determine if a chemical habitat tag existed that could be used to differentiate fish living in the alternative juvenile habitats. Juveniles of both species were collected from seven estuaries and 11 coastal sites along 500 km of the central California coast. Collections occurred in three years: 1998, 1999 and 2000. The chemical composition of the otoliths was analyzed using solution-based inductively coupled plasma mass spectrometry. The multi-elemental composition (Sr, Li, Ba, Mn) of otoliths from estuarine and coastal fish differed significantly for all models (global, region and years models) examined in this study. For each species, discriminant function analysis (DFA) for the global model, which pooled juveniles collected from three regions over multiple years, classified fish into estuarine and coastal groups with close to 80% accuracy. The two main elements in the discriminant models, Sr and Li, differed consistently between habitats; Sr was higher and Li was lower in estuarine fish. Classification success was modestly improved by generating separate discriminant functions for each region (regions model) because of some regional differences in Sr and Li concentrations. Classification success also was improved in some cases by generating separate discriminant functions for each year (years model) because Ba and Mn differed between habitats in only some years. Despite this variability in the concentration of elements in some regions and years, a chemical habitat tag was present in each species that could be used to discriminate coastal and estuarine juveniles over a large geographic area and over three years with very different oceanographic conditions (e.g., El Niño, La Niña). In addition, I found that English sole and speckled sanddab had striking similarities in their chemical habitat tags and that, in some cases, one species could be used as a proxy to classify juveniles of the other species without compromising the accuracy of the habitat tag. The ability to use a proxy classification model would significantly reduce the number of juvenile fish that would need to be collected and analyzed in order to classify members of an ecologically similar species. The chemical habitat tags found in this study appears to be promising tools for identifying fish that have lived in alternative juvenile habitats and, ultimately, the proportional contribution of estuarine and coastal habitats to the central California populations of English sole and speckled sanddab.

Peptide Sequence Tags for Fast Database Search in Mass-Spectrometry

Filtration techniques in the form of rapid elimination of candidate sequences while retaining the true one are key ingredients of database searches in genomics. Although SEQUEST and Mascot perform a conceptually similar task to the tool BLAST, the key algorithmic idea of BLAST (filtration) was never implemented in these tools. As a result MS/MS protein identification tools are becoming too time-consuming for many applications including search for post-translationally modified peptides. Moreover, matching millions of spectra against all known proteins will soon make these tools too slow in the same way that "genome vs genome" comparisons instantly made BLAST too slow. We describe the development of filters for MS/MS database searches that dramatically reduce the running time and effectively remove the bottlenecks in searching the huge space of protein modifications. Our approach, based on a probability model for determining the accuracy of sequence tags, achieves superior results compared to GutenTag, a popular tag generation algorithm. Our tag generating algorithm along with our de novo sequencing algorithm PepNovo can be accessed via the URL http://peptide.ucsd.edu/.

Accuracy of geolocation estimates for flying seabirds

Geolocation (Global Location Sensing or GLS logging) using archival light-recording tags offers considerable potential for tracking animal movements, yet few studies of flying seabirds have exploited this technology. Our study evaluated its effectiveness for determining foraging ranges of black-browed albatrosses Thalassarche melanophrys fitted simultaneously with GLS loggers and satellite-transmitters (Platform Terminal Transmitters, PTTs). After some preliminary validation, the position of an albatross could be determined by geolocation with a mean error +/- SD of 186 +/- 114 km (SDs of 1.66degrees and 1.82degrees of latitude and longitude, respectively). Errors from identical static loggers were lower (mean +/- SD of 85 +/- 47 km, with overall SDs of 0.61degrees and 0.99degrees of latitude and longitude, respectively) and less variable, with the difference attributable to variation in sensor orientation, intermittent shading by plumage, and the difficulty of correcting for extensive, potentially non-linear movements of flying birds. Iterative smoothing reduced both the mean error and the inflation of kernel ranges derived from GLS data, but over-smoothing contracted the extremes of the range. This reduced the overlap with radial cores apparent in the control data, and should be avoided for multinuclear GLS fix distributions. The accuracy of GLS tags is more than adequate for tracking migration and breeding-season foraging ranges of pelagic species, and for identifying broad-scale habitat preferences, overlap and potential conflict with commercial fisheries.