An unsupervised approach to generating generic summaries of documents

We present an optimization-based unsupervised approach to automatic document summarization. In the proposed approach, text summarization is modeled as a Boolean programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. The approach proposed in this paper is applicable to both tasks: single- and multi-document summarization. In both tasks, documents are split into sentences in preprocessing. We select some salient sentences from document(s) to generate a summary. Finally, the summary is generated by threading all the selected sentences in the order that they appear in the original document(s). We implemented our model on multi-document summarization task. When comparing our methods to several existing summarization methods on an open DUC2005 and DUC2007 data sets, we found that our method improves the summarization results significantly. This is because, first, when extracting summary sentences, this method not only focuses on the relevance scores of sentences to the whole sentence collection, but also the topic representative of sentences. Second, when generating a summary, this method also deals with the problem of repetition of information. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-SU4 metrics. In this paper, we also demonstrate that the summarization result depends on the similarity measure. Results of the experiment showed that combination of symmetric and asymmetric similarity measures yields better result than their use separately.     

Sensor network design based on system-wide reliability criteria. Part I: Objectives

Reliability based criteria are quite popular for optimal sensor network design. We present a modified definition of system reliability for sensor network design for two applications: reliable estimation of variables in a steady state linear flow process, and reliable fault detection and diagnosis for any process. Unlike the weakest-link based definition of system reliability in the literature, the proposed definition considers the entire system and is consistent with the reliability concept used in classical reliability literature. For each application, dual approaches for defining system reliability are proposed, and their analogy with the reliability problem in the classical reliability literature is established. Using examples and stochastic simulations, the advantage of using the proposed system reliability in contrast to the existing definition is illustrated. Part II of this series of articles presents methods for efficient generation of the system reliability function and its use in optimization-based approaches for designing optimal sensor networks.     

Comparative evaluation of different statistical tools for the prediction of uniaxial compressive strength of rocks

In this study, uniaxial compressive strength (UCS), unit weight (UW), Brazilian tensile strength (BTS), Schmidt hardness (SHH), Shore hardness (SSH), point load index (Is₅₀) and P-wave velocity (V_p) properties were determined. To predict the UCS, simple regression (SRA), multiple regression (MRA), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and genetic expression programming (GEP) have been utilized. The obtained UCS values were compared with the actual UCS values with the help of various graphs. Datasets were modeled using different methods and compared with each other. In the study where the performance indice PI_at was used to determine the best performing method, MRA method is the most successful method with a small difference. It is concluded that the mean PI_at equal to 2.46 for testing dataset suggests the superiority of the MRA, while these values are 2.44, 2.33, and 2.22 for GEP, ANFIS, and ANN techniques, respectively. The results pointed out that the MRA can be used for predicting UCS of rocks with higher capacity in comparison with others. According to the performance index assessment, the weakest model among the nine model is P7, while the most successful models are P2, P9, and P8, respectively.     

Crossing the Border: From Keto- to Imine Reduction in Short-Chain Dehydrogenases/Reductases

The family of NAD(P)H-dependent short-chain dehydrogenases/reductases (SDRs) comprises numerous biocatalysts capable of C=O or C=C reduction. The highly homologous noroxomaritidine reductase (NR) from Narcissus sp. aff. pseudonarcissus and Zt_SDR from Zephyranthes treatiae, however, are SDRs with an extended imine substrate scope. Comparison with a similar SDR from Asparagus officinalis (Ao_SDR) exhibiting keto-reducing activity, yet negligible imine-reducing capability, and mining the Short-Chain Dehydrogenase/Reductase Engineering Database indicated that NR and Zt_SDR possess a unique active-site composition among SDRs. Adapting the active site of Ao_SDR accordingly improved its imine-reducing capability. By applying the same strategy, an unrelated SDR from Methylobacterium sp. 77 (M77_SDR) with distinct keto-reducing activity was engineered into a promiscuous enzyme with imine-reducing activity, thereby confirming that the ability to reduce imines can be rationally introduced into members of the “classical” SDR enzyme family. Thus, members of the SDR family could be a promising starting point for protein approaches to generate new imine-reducing enzymes.     

Genetic algorithm and self organizing map based fuzzy hybrid intelligent method for color image segmentation

The grouping of pixels based on some similarity criteria is called image segmentation. In this paper the problem of color image segmentation is considered as a clustering problem and a fixed length genetic algorithm (GA) is used to handle it. The effectiveness of GA depends on the objective function (fitness function) and the initialization of the population. A new objective function is proposed to evaluate the quality of the segmentation and the fitness of a chromosome. In fixed length genetic algorithm the chromosomes have same length, which is normally set by the user. Here, a self organizing map (SOM) is used to determine the number of segments in order to set the length of a chromosome automatically. An opposition based strategy is adopted for the initialization of the population in order to diversify the search process. In some cases the proposed method makes the small regions of an image as separate segments, which leads to noisy segmentation. A simple ad hoc mechanism is devised to refine the noisy segmentation. The qualitative and quantitative results show that the proposed method performs better than the state-of-the-art methods.     

Genetic diversity by AFLP analysis within Jatropha curcas L. populations in the State of São Paulo,Brazil

The genetic diversity of 5 populations of Jatropha curcas L. (Euphorbiaceae), a species cultivated in tropical countries and used in biodiesel production, was analyzed by amplified fragment length polymorphism (AFLP). Plants from distinct populations found in the State of São Paulo, Brazil, had their genetic diversity characterized by using three primer combinations. The number of polymorphic bands obtained reached 184 and the base pair length of bands ranged from 75 to 350, with average PIC values of 0.418. Accessions from the Aguas de Santa Barbara population presented the highest percentage of polymorphic loci (89.76%), followed by the populations of Catanduva (84.24%), Jales (80.98%), Jurucê (78.80%) and Taquaritinga (70.65%). Plants collected from the populations of Taquaritinga and Jales presented the smallest and highest genetic diversities, respectively, measured by using both Nei's genetic variability index (h = 0.2242 and 0.2973) and Shannon's index (I = 0.3359 and 0.4319). The results obtained indicated that 73.1% of genetic variability corresponds to intrapopulational variation and 26.8% to variation among populations. The clustering dendrogram using Jacquard showed four clusters. Three clusters with low genetic diversity grouped most of individuals collected in distinct regions (63.3% JU, 47.0% JA and 82.5% TA) and the fourth with the higher genetic diversity was composed with basically individuals collected in CA and AS, but it also had samples collected in JU, JA and TA, where it is possible to select individuals to be included in breeding programs.     

Two-step pyrolytic engineering to form porous nitrogen-rich carbons with a 3D network structure for Zn-air battery oxygen reduction electrocatalysis

It is of great urgency to design inexpensive and high-performance oxygen reduction reaction (ORR) electrocatalysts derived from biowastes as substitutes for Pt-based materials in electrochemical energy-conversion devices. Here we propose a strategy to synthesize three-dimensional (3D) porous nitrogen-doped network carbons to catalyze the ORR from two-step pyrolysis engineering of biowaste scale combined with the use of a ZnCl₂ activator and a FeCl₂ promotor. Electrochemical tests show that the synthesized network carbons have exhibited comparable ORR catalytic activity with a half-wave potential (~0.85 V vs. RHE) and outstanding cyclical stability in comparison to the Pt/C catalyst. Beyond that, a high electron transfer number (~3.8) and a low peroxide yield (<7.6%) can be obtained, indicating a four-electron reaction pathway. The maximum power density is ~68 mW cm^?2, but continuous discharge curves (at a constant potential of ~1.30 V) for 12 h are not obviously declined in Zn-air battery tests using synthesized network carbons as the cathodic catalyst. The formation of 3D porous structures with high BET surface area can effectively expose the surface catalytic sites and promote mass transportation to boost the ORR activity. This work may open a new idea to prepare porous carbon-based catalysts for some important reactions in new energy devices.     

Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.     

A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

The potential of energy flexibility of space heating and cooling in Portugal

This study assesses the potential of energy flexibility of space heating and cooling for a typical household under different geographical conditions in Portugal. The proposed approach modifies the demand through the optimization of the thermostat settings using a genetic algorithm to reduce either operational costs or interaction with the grid. The results show that the used energy flexibility indicator expresses the available potential and that flexibility depends on several factors, namely: i) thermal inertia of the archetypical household; ii) the time of use electricity tariffs; iii) users’ comfort boundaries; and iv) the geographical location of the houses.