Multi-source composite kernels for urban image classification

This letter presents advanced classification methods for very high resolution images. Efficient multisource information, both spectral and spatial, is exploited through the use of composite kernels in support vector machines. Weighted summations of kernels accounting for separate sources of spectral and spatial information are analyzed and compared to classical approaches such as pure spectral classification or stacked approaches using all the features in a single vector. Model selection problems are addressed, as well as the importance of the different kernels in the weighted summation.

UPLC-TOF-MS for plant metabolomics: a sequential approach for wound marker analysis in Arabidopsis thaliana.

The model plant Arabidopsis thaliana was studied for the search of new metabolites involved in wound signalling. Diverse LC approaches were considered in terms of efficiency and analysis time and a 7-min gradient on a UPLC-TOF-MS system with a short column was chosen for metabolite fingerprinting. This screening step was designed to allow the comparison of a high number of samples over a wide range of time points after stress induction in positive and negative ionisation modes. Thanks to data treatment, clear discrimination was obtained, providing lists of potential stress-induced ions. In a second step, the fingerprinting conditions were transferred to longer column, providing a higher peak capacity able to demonstrate the presence of isomers among the highlighted compounds.

The glasses of the transept's rosette of the Cathedral of Tarragona: characterization, classification and decay.

The glasses of the rosette forming the main window of the transept of the Gothic Cathedral of Tarragona have been characterised by means of SEM/EDS, XRD, FTIR and electronic microprobe. The multivariate statistical treatment of these data allow to establish a classification of the samples forming groups having an historical significance and reflecting ancient restorations. Furthermore, the decay patterns and mechanisms have been determined and the weathering by-products characterised. It has been demonstrated a clear influence of the bioactivity in the decay of these glasses, which activity is partially controlled by the chemical composition of the glasses.

The glasses of the transept's rosette of the Cathedral of Tarragona: characterization, classification and decay.

The glasses of the rosette forming the main window of the transept of the Gothic Cathedral of Tarragona have been characterised by means of SEM/EDS, XRD, FTIR and electronic microprobe. The multivariate statistical treatment of these data allow to establish a classification of the samples forming groups having an historical significance and reflecting ancient restorations. Furthermore, the decay patterns and mechanisms have been determined and the weathering by-products characterised. It has been demonstrated a clear influence of the bioactivity in the decay of these glasses, which activity is partially controlled by the chemical composition of the glasses.

Iowa Roads and Streets Functional Classification Manual, 1970

This manual provides a set of procedural rules and regulations for use in functionally classifying all roads and streets in Iowa according to the character of service they are intended to provide. Functional classification is a requirement of House File 394 (Functional Highway Classification Bill) enacted by the 63rd General Assembly of the Iowa Legislature. Functional classification is defined in this Bill as: "The grouping of roads and streets into systems according to the character of service they will be expected to provide, and the assignment of jurisdiction over each class to the governmental unit having primary interest in each type of service."

Iowa Roads and Streets Functional Classification Manual, 1975

This manual provides a set of procedural rules and regulations for use in functionally classifying all roads and streets in Iowa according to the character of service they are intended to provide. Functional classification is a requirement of the 1973 Code of Iowa (Chapter 306) as amended by Senate File 1062 enacted by the 2nd session of the 65th General Assembly of Iowa. Functional classification is defined as the grouping of roads and streets into systems according to the character of service they will be expected to provide, and the assignment of jurisdiction over each class to the governmental unit having primary interest in each type of service. Stated objectives of the legislation are: "Functional classification will serve the legislator by providing an equitable basis for determination of proper source of tax support and providing for the assignment of financial resources to the governmental unit having responsibility for each class of service. Functional classification promotes the ability of the administrator to effectively prepare and carry out long range programs which reflect the transportation needs of the public." All roads and streets in legal existence will be classified. Instructions are also included in this manual for a continuous reporting to the Highway Commission of changes in classification and/or jurisdiction resulting from new construction, corporation line changes, relocations, and deletions. This continuous updating of records is absolutely essential for modern day transportation planning as it is the only possible way to monitor the status of existing road systems, and consequently determine adequacy and needs with accuracy.

Characterization and multivariate classification of grapes and wines of two Cabernet Sauvignon clones

The objective of this work was to assess and characterize two clones, 169 and 685, of Cabernet Sauvignon grapes and to evaluate the wine produced from these grapes. The experiment was carried out in São Joaquim, SC, Brazil, during the 2009 harvest season. During grape ripening, the evolution of physical-chemical properties, phenolic compounds, organic acids, and anthocyanins was evaluated. During grape harvest, yield components were determined for each clone. Individual and total phenolics, individual and total anthocyanins, and antioxidant activity were evaluated for wine. The clones were also assessed regarding the duration of their phenological cycle. During ripening, the evolution of phenolic compounds and of physical-chemical parameters was similar for both clones; however, during harvest, significant differences were observed regarding yield, number of bunches per plant and berries per bunch, leaf area, and organic acid, polyphenol, and anthocyanin content. The wines produced from these clones showed significant differences regarding chemical composition. The clones showed similar phenological cycle and responses to bioclimatic parameters. Principal component analysis shows that clone 685 is strongly correlated with color characteristics, mainly monomeric anthocyanins, while clone 169 is correlated with individual phenolic compounds.

Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images.

This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.

Approximate polytope ensemble for one-class classification

In this work, a new one-class classification ensemble strategy called approximate polytope ensemble is presented. The main contribution of the paper is threefold. First, the geometrical concept of convex hull is used to define the boundary of the target class defining the problem. Expansions and contractions of this geometrical structure are introduced in order to avoid over-fitting. Second, the decision whether a point belongs to the convex hull model in high dimensional spaces is approximated by means of random projections and an ensemble decision process. Finally, a tiling strategy is proposed in order to model non-convex structures. Experimental results show that the proposed strategy is significantly better than state of the art one-class classification methods on over 200 datasets.

Mixed spectral-structural classification of very high resolution images with summation kernels

In this paper, mixed spectral-structural kernel machines are proposed for the classification of very-high resolution images. The simultaneous use of multispectral and structural features (computed using morphological filters) allows a significant increase in classification accuracy of remote sensing images. Subsequently, weighted summation kernel support vector machines are proposed and applied in order to take into account the multiscale nature of the scene considered. Such classifiers use the Mercer property of kernel matrices to compute a new kernel matrix accounting simultaneously for two scale parameters. Tests on a Zurich QuickBird image show the relevance of the proposed method : using the mixed spectral-structural features, the classification accuracy increases of about 5%, achieving a Kappa index of 0.97. The multikernel approach proposed provide an overall accuracy of 98.90% with related Kappa index of 0.985.

Land use/cover classification in the Brazilian Amazon using satellite images

Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation‑based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi‑resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Among the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, have the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical‑based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

Concurrent or sequential adjuvant letrozole and radiotherapy after conservative surgery for early-stage breast cancer (CO-HO-RT): a phase 2 randomised trial.

BACKGROUND: Letrozole radiosensitises breast cancer cells in vitro. In clinical settings, no data exist for the combination of letrozole and radiotherapy. We assessed concurrent and sequential radiotherapy and letrozole in the adjuvant setting. METHODS: This phase 2 randomised trial was undertaken in two centres in France and one in Switzerland between Jan 12, 2005, and Feb 21, 2007. 150 postmenopausal women with early-stage breast cancer were randomly assigned after conserving surgery to either concurrent radiotherapy and letrozole (n=75) or sequential radiotherapy and letrozole (n=75). Randomisation was open label with a minimisation technique, stratified by investigational centres, chemotherapy (yes vs no), radiation boost (yes vs no), and value of radiation-induced lymphocyte apoptosis (< or = 16% vs >16%). Whole breast was irradiated to a total dose of 50 Gy in 25 fractions over 5 weeks. In the case of supraclavicular and internal mammary node irradiation, the dose was 44-50 Gy. Letrozole was administered orally once daily at a dose of 2.5 mg for 5 years (beginning 3 weeks pre-radiotherapy in the concomitant group, and 3 weeks post-radiotherapy in the sequential group). The primary endpoint was the occurrence of acute (during and within 6 weeks of radiotherapy) and late (within 2 years) radiation-induced grade 2 or worse toxic effects of the skin. Analyses were by intention to treat. This study is registered with ClinicalTrials.gov, number NCT00208273. FINDINGS: All patients were analysed apart from one in the concurrent group who withdrew consent before any treatment. During radiotherapy and within the first 12 weeks after radiotherapy, 31 patients in the concurrent group and 31 in the sequential group had any grade 2 or worse skin-related toxicity. The most common skin-related adverse event was dermatitis: four patients in the concurrent group and six in the sequential group had grade 3 acute skin dermatitis during radiotherapy. At a median follow-up of 26 months (range 3-40), two patients in each group had grade 2 or worse late effects (both radiation-induced subcutaneous fibrosis). INTERPRETATION: Letrozole can be safely delivered shortly after surgery and concomitantly with radiotherapy. Long-term follow-up is needed to investigate cardiac side-effects and cancer-specific outcomes. FUNDING: Novartis Oncology France.

Effect of repetitive arm cycling following botulinum toxin injection for poststroke spasticity: evidence from FMRI.

BACKGROUND AND OBJECTIVE: Investigations were performed to establish if repetitive arm cycling training enhances the antispastic effect of intramuscular botulinum toxin (BTX) injections in postischemic spastic hemiparesis. Effects on cerebral activation were evaluated by functional magnetic resonance imaging (fMRI). METHODS: Eight chronic spastic hemisyndrome patients (49 ± 10 years) after middle cerebral artery infarction (5.5 ± 2.7 years) were investigated. BTX was injected into the affected arm twice, 6 months apart. Spasticity was assessed using the Ashworth Scale and range of motion before and 3 months after BTX injections. Images were analyzed using Brain Voyager QX 1.8, and fMRI signal changes were corrected for multiple comparisons. RESULTS: During passive movements of affected and nonaffected hands, fMRI activity was increased bilaterally in the sensorimotor cortex (MISI), secondary somatosensory areas (SII), and supplementary motor area predominantly in the contralesional hemisphere, compared with the rest. Following repetitive arm cycling, fMRI activity increased further in MISI of the lesioned hemisphere and SII of the contralesional hemisphere. For patients with residual motor activity, treatment-related fMRI activity increases were associated with reduced spasticity; in completely plegic patients, there was no fMRI activity change in SII but increased spasticity after training. CONCLUSION: Increased activity in SII of the contralesional hemisphere and in MISI of the lesioned hemisphere reflect a treatment-induced effect in the paretic arm. It is hypothesized that the increased BOLD activity results from increased afferent information related to the antispastic BTX effect reinforced by training.

JPEG standard uniform quantization error modeling with applications to sequential and progressive operation modes

In this paper we propose a method for computing JPEG quantization matrices for a given mean square error or PSNR. Then, we employ our method to compute JPEG standard progressive operation mode definition scripts using a quantization approach. Therefore, it is no longer necessary to use a trial and error procedure to obtain a desired PSNR and/or definition script, reducing cost. Firstly, we establish a relationship between a Laplacian source and its uniform quantization error. We apply this model to the coefficients obtained in the discrete cosine transform stage of the JPEG standard. Then, an image may be compressed using the JPEG standard under a global MSE (or PSNR) constraint and a set of local constraints determined by the JPEG standard and visual criteria. Secondly, we study the JPEG standard progressive operation mode from a quantization based approach. A relationship between the measured image quality at a given stage of the coding process and a quantization matrix is found. Thus, the definition script construction problem can be reduced to a quantization problem. Simulations show that our method generates better quantization matrices than the classical method based on scaling the JPEG default quantization matrix. The estimation of PSNR has usually an error smaller than 1 dB. This figure decreases for high PSNR values. Definition scripts may be generated avoiding an excessive number of stages and removing small stages that do not contribute during the decoding process with a noticeable image quality improvement.

Concurrent or Sequential Adjuvant Letrozole and Radiotherapy after Conservative Surgery for Early-stage Breast Cancer: Long-term Results of the Cohort Phase 2 Randomized Trial

Purpose/Objective(s): Letrozole radiosensitizes breast cancer cells in vitro. In clinical settings, no data exist for the combination of letrozole and radiotherapy. We assessed concurrent and sequential radiotherapy and letrozole in the adjuvant setting.Materials/Methods: The present study is registered with ClinicalTrials.gov, number NCT00208273. This Phase 2 randomized trial was undertaken in two centers in France and one in Switzerland between January 12, 2005, and February 21, 2007. One hundred fifty postmenopausal women with early-stage breast cancer were randomly assigned after conserving surgery to either concurrent radiotherapy and letrozole (n = 75) or sequential radiotherapy and letrozole (n = 75). Randomization was open label with a minimization technique, stratified by investigational centers, chemotherapy (yes vs. no), radiation boost (yes vs. no), and value of radiation-induced lymphocyte apoptosis (#16% vs. .16%). The whole breast was irradiated to a total dose of 50 Gy in 25 fractions over 5 weeks. In the case of supraclavicular and internal mammary node irradiation, the dose was 44 - 50 Gy. Letrozole was administered orally once daily at a dose of 2 - 5 mg for 5 years (beginning 3 weeks pre-radiotherapy in the concomitant group, and 3 weeks postradiotherapy in the sequential group). The primary endpoint was the occurrence of acute (during and within 6 weeks of radiotherapy) and late (within 2 years) radiation-induced Grade 2 or worse toxic effects of the skin and lung (functional pulmonary test and lung CT-scan). Analyses were by intention-to-treat. The long-term follow-up after 2 years was only performed in Montpellier (n = 121) and evaluated skin toxicity (clinical examination every 6 months), lung fibrosis (one CT-scan yearly), cosmetic outcome.Results: All patients were analyzed apart from 1 in the concurrent group who withdrew consent before any treatment.Within the first 2 years (n = 149), no lung toxicity was identified by CT scan and no modification from baseline was noted by the lung diffusion capacity test. Two patients in each group had Grade 2 or worse late effects (both radiation-induced subcutaneous fibrosis [RISF]). After 2 years (n = 121), and with a median follow-up of 50 months (38-62), 2 patients (1 in each arm) presented a Grade 3 RISF. No lung toxicity was identified by CT scan. Cosmetic results (photographies) and quality of life was good to excellent. All patients who had Grade 3 subcutaneous fibrosis had an RILA value of 16% or less, irrespective of the sequence with letrozole.Conclusions:With long-term follow-up, letrozole can be safely delivered shortly after surgery and concomitantly with radiotherapy.