Detection,localisation and tracking of pallets using machine learning techniques and 2D range data

The problem of autonomous transportation in industrial scenarios is receiving a renewed interest due to the way it can revolutionise internal logistics, especially in unstructured environments. This paper presents a novel architecture allowing a robot to detect, localise, and track (possibly multiple) pallets using machine learning techniques based on an on-board 2D laser rangefinder only. The architecture is composed of two main components: the first stage is a pallet detector employing a Faster Region-Based Convolutional Neural Network (Faster R-CNN) detector cascaded with a CNN-based classifier; the second stage is a Kalman filter for localising and tracking detected pallets, which we also use to defer commitment to a pallet detected in the first stage until sufficient confidence has been acquired via a sequential data acquisition process. For fine-tuning the CNNs, the architecture has been systematically evaluated using a real-world dataset containing 340 labelled 2D scans, which have been made freely available in an online repository. Detection performance has been assessed on the basis of the average accuracy over k-fold cross-validation, and it scored 99.58% in our tests. Concerning pallet localisation and tracking, experiments have been performed in a scenario where the robot is approaching the pallet to fork. Although data have been originally acquired by considering only one pallet as per specification of the use case we consider, artificial data have been generated as well to mimic the presence of multiple pallets in the robot workspace. Our experimental results confirm that the system is capable of identifying, localising and tracking pallets with a high success rate while being robust to false positives.

     

Photoinduced Self‐Assembled Nanostructures and Permanent Polaron Formation in Regioregular Poly(3‐hexylthiophene)

Solution processing of conjugated polymers into ordered self‐assembled precursors has attracted great interest in the past years owing to the ability to manipulate their structural and physical properties. Regioregular poly(3‐hexylthiophene) (P3HT) has become the benchmark polymer in this scenario, where ordered lamellar structures significantly improve carrier mobility of the thin films due to increased crystallinity, extended intrachain conjugation, and ordered interchain π‐stacking. Here, a new photoinduced approach is presented for the generation of highly ordered P3HT aggregate structures that is amenable to the use of visible light to control the aggregate formation. Strong intra‐ and interchain interactions in the solution precursors allow for permanent formation of localized and delocalized polarons that are stable for months. Spin‐coated thin films are found to preserve, in part, the morphological and physical properties of the aggregated P3HT solution precursors with high degree of crystallinity and short π‐stack interchain distances.     

Algebraic integer architecture with minimum adder count for the 2-D Daubechies 4-tap filters banks

A multiplierless architecture based on algebraic integer representation for computing the Daubechies 4-tap wavelet transform for 1-D/2-D signal processing is proposed. This architecture improves on previous designs in a sense that it minimizes the number of parallel 2-input adder circuits. The algorithm was achieved using numerical optimization based o exhaustive search over the algebraic integer representation. The proposed architecture furnishes exact computation up to the final reconstruction step, which is the operation that maps the exactly computed filtered results from algebraic integer representation to fixed-point. Compared to Madishetty et al. (IEEE Trans Circuits Syst I (Accepted, In Press), 2012a), this architecture shows a reduction of \(10\cdot n-3\) adder circuits, where \(n\) is the number of wavelet decomposition levels. Standard \(512\times 512\) images Mandrill, Lena, and Cameraman were submitted to digital realizations of both proposed algebraic integer based as well as fixed-point schemes, leading to quantifiable comparisons. The design is physically implemented for a 4-level 2-D decomposition using a Xilinx Virtex-6 vcx240t-1ff1156 FPGA device operating at up to a maximum clock frequency of 263.15 MHz. The FPGA implementation is tested using hardware co-simulation using an ML605 board with clock of 100 MHz. A 45 nm CMOS synthesis shows improved clock frequency of better than 500 MHz for a supply voltage of 1.1 V.     

Identification and analysis of isothiocyanates and new acylated anthocyanins in the juice of Raphanus sativus cv. Sango sprouts

The freeze-dried sprouts’ juice of Raphanus sativus (L.) cv. Sango was prepared and analysed for the first time. HPLC analysis of total isothiocyanates, after protein displacement, resulted in 77.8 ± 3.0 μmol/g of dry juice while GC–MS analysis of hexane and acetone extracts showed E- and Z-raphasatin (8.9 and 0.11 μmol/g, respectively) and sulforaphene (11.7 μmol/g), summing up to 20.7 ± 1.7 μmol/g of free isothiocyanates. Sprouts’ juice contained an unprecedented wealth of anthocyanins and a new fractionation methodology allowed us to isolate 34 mg/g of acylated anthocyanins (28.3 ± 1.9 μmol/g), belonging selectively to the cyanidin family. Analysis was performed by HPLC–PDA–ESI–MSⁿ and extended to deacylated anthocyanins and aglycones, obtained, respectively, by alkaline and acid hydrolysis. This study identified 70 anthocyanins, 19 of which have never been described before and 32 of which are reported here in R. sativus for the first time. Sango radish sprouts are exceptional dietary sources of heath-promoting micronutrients.     

Quantification of soluble solids in reconstituted açaí (Euterpe oleracea Mart.) pulp using near‐infrared spectroscopy

Açaí consumption is increasing worldwide because of the growing recognition of its nutritional and therapeutic properties. This product is classified based on its soluble solids content (SS), but the determination of SS in pulp is time consuming, tedious and not suitable for modern food processing plants. As near‐infrared (NIR) systems have been implemented to measure various quality attributes of food products, the objective of this study was to evaluate the feasibility of NIR diffuse reflectance spectroscopy to quantify the SS content of açaí pulp. Partial least squares (PLS) regression models were constructed to predict the SS. An optimum PLS model required one latent variable [principal component (PC)1 = 97%] with a root‐mean‐square error of calibration (RMSEC) of 1.06% for the calibration data set and the root‐mean‐square error of prediction (RMSEP) of 1.03% for internal cross‐validation. External validation using an independent data set showed good performance (RMSEP = 1.33% and Rp² = 0.82). NIR spectroscopy is a reliable method with which to determine SS in açaí pulp and thereby to classify açaí pulp according to established minimum quality standards.     

Effect ofSolanum Glycoalkaloids on Potato Aphid,Macrosiphum euphorbiae

Macrosiphum euphorbiae, also known as the potato aphid, is a potato virus vector, associated with decreased tuber production. Feeding, toxicity, and reproductive effects of the major potato glycoalkaloids (α-chaconine and α-solanine), their common aglycone (solanidine), and a nonpotato glycoalkaloid (α-tomatine) and its aglycone (tomatidine) onM. euphorbiae were studied. As expected, neither α-chaconine nor α-solanine had a strong lethal effect on the aphid, but α-chaconine stimulated feeding at low concentrations. Both aglycones were deterrent and lethal at high concentrations and, like α-chaconine and α-tomatine, they delayed the appearance and decreased the number of nymphs.     

Correction to Lombardo and Foschi (2003).

Reports an error in the original article by G. P. Lombardo and R. Foschi (History of Psychology, 2003, 2, 123-142). In the reference list, several works by Pierre Janet were identified as being Paul Janet. The correct references are provided, where Paul Janet is identified by the initial P. and Pierre Janet is identified by the initials P. M. F.. (The following abstract of this article originally appeared in record 2003-03729-003.) Since the 1920s, the road to the acknowledgment of personality psychology as a field of scientific psychology that has individuality as its object began with the founding of the discipline by Gordon W. Allport. Historians of psychology have made serious attempts to reconstruct the cultural, political, institutional, and chronological beginnings of this field in America in the 20th century. In this literature, however, an important European tradition of psychological studies of personality that developed in France in the 2nd half of the 19th century has been overlooked. The aim of this article is to cast some light on this unexplored tradition of psychological personality studies and to discuss its influence on the development of the scientific study of personality in the United States. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The ParTriCluster Algorithm for Gene Expression Analysis

Analyzing gene expression patterns is becoming a highly relevant task in the Bioinformatics area. This analysis makes it possible to determine the behavior patterns of genes under various conditions, a fundamental information for treating diseases, among other applications. A recent advance in this area is the Tricluster algorithm, which is the first algorithm capable of determining 3D clusters (genes × samples × timestamps), that is, groups of genes that behave similarly across samples and timestamps. However, even though biological experiments collect an increasing amount of data to be analyzed and correlated, the triclustering problem remains a bottleneck due to its NP-Completeness, so its parallelization seems to be an essential step towards obtaining feasible solutions. In this work we propose and evaluate the implementation of a parallel version of the Tricluster algorithm using the filter-labeled-stream paradigm supported by the Anthill parallel programming environment. The results show that our parallelization scales well with the data size, being able to handle severe load imbalances that are inherent to the problem. Further more, the parallelization strategy is applicable to any depth-first searches.     

Analytical Electromagnetic Solution for Bragg Mirrors With Graded Interfaces and Guidelines for Enhanced Reflectivity

Bragg mirrors, the key element of vertical-cavity surface-emitting lasers, always present graded interfaces when current is pumped through them, so as to reduce their series resistance and related heating problems. We present here an analytical solution for the electromagnetic fields in graded Bragg mirrors. It allows to generate reference reflection and transmission coefficients that are compared with those obtained by the staircase approximation method. Graded mirrors are then analyzed in detail and it is shown that, with an optimized design, higher reflectivity than in the abrupt scheme can be achieved