Search

Non-technical losses (NTL) identification has been paramount in the last years. However, it is not straightforward to obtain labelled datasets to perform a supervised NTL recognition task. In this paper, the optimum-path forest (OPF) clustering algorithm has been employed to identify irregular and regular profiles of commercial and industrial consumers obtained from a Brazilian electrical power company. Additionally, a model for the problem of NTL recognition as an anomaly detection task has been proposed when there are little or no information about irregular consumers. For such purpose, two new approaches based on the OPF framework have been introduced and compared against the well-known k -means, Gaussian mixture model, Birch, affinity propagation and one-class support vector machines. The experimental results have shown the robustness of OPF for both unsupervised NTL recognition and anomaly detection problems. In short, the main contributions of this paper are fourfold: (i) to employ unsupervised OPF for non-technical losses detection, (ii) to model the problem of NTL as being an anomaly detection task, (iii) to employ unsupervised OPF to estimate the parameters of the Gaussian distributions, and (iv) to present an anomaly detection approach based on unsupervised optimum-path forest. [ABSTRACT FROM AUTHOR]

The data about high students' failure rates in introductory programming courses have been alarming many educators, raising a number of important questions regarding prediction aspects. In this paper, we present a comparative study on the effectiveness of educational data mining techniques to early predict students likely to fail in introductory programming courses. Although several works have analyzed these techniques to identify students' academic failures, our study differs from existing ones as follows: (i) we investigate the effectiveness of such techniques to identify students likely to fail at early enough stage for action to be taken to reduce the failure rate; (ii) we analyse the impact of data preprocessing and algorithms fine-tuning tasks, on the effectiveness of the mentioned techniques. In our study we evaluated the effectiveness of four prediction techniques on two different and independent data sources on introductory programming courses available from a Brazilian Public University: one comes from distance education and the other from on-campus. The results showed that the techniques analyzed in our study are able to early identify students likely to fail, the effectiveness of some of these techniques is improved after applying the data preprocessing and/or algorithms fine-tuning, and the support vector machine technique outperforms the other ones in a statistically significant way. [ABSTRACT FROM AUTHOR]

In the framework of forensic anthropology osteometric techniques are generally preferred over visual examinations due to a higher level of reproducibility and repeatability; qualities that are crucial within a legal context. The use of osteometric methods has been further reinforced by incorporating statistically-based algorithms and large reference samples in a variety of user-friendly software applications. However, the continued increase in admixture of human populations have made the use of osteometric methods for estimation of ancestry much more complex, which confounds one of major requirements of ancestry assessment - intra-population homogeneity. The present paper tests the accuracy of ancestry and sex assessment using four identification software tools, specifically FORDISC 2.0, FORDISC 3.1.293, COLIPR 1.5.2 and 3D-ID 1.0. Software accuracy was tested in a sample of 174 documented human crania of Brazilian origin composed of different ancestral groups (i.e., European Brazilians, Afro-Brazilians, and Japanese Brazilians and of admixed ancestry). The results show that regardless of the software algorithm employed and composition of the reference database, all methods were able to allocate approximately 50% of Brazilian specimens to an appropriate major reference group. Of the three ancestral groups, Afro-Brazilians were especially prone to misclassification. Japanese Brazilians, by contrast, were shown to be relatively easily recognizable as being of Asian descent but at the same time showed a strong affinity towards Hispanic crania, in particularly when the classification based on FDB was carried out in FORDISC. For crania of admixed origin all of the algorithms showed a considerable higher rate of inconsistency with a tendency for misclassification into Asian and American Hispanic groups. Sex assessments revealed an overall modest to poor reliability (60-71% of correctly classified specimens) using the tested software programs with unbalanced individual rates for males and females. The highest and atypically balanced rate of classification for sex assessment was provided by COLIPR software, which reached 78% of correctly assessed crania. [ABSTRACT FROM AUTHOR]

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system — a cascade-based operation scenario. For this, we propose a new mathematical modeling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multi-objective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out. • An efficient Multi-objective Evolutionary Swarm Hybrid algorithm is proposed. • Development of a nonlinear model to operational control of Hydro-power plants. • Hydro-power plant data regression obtains the maximum efficiency of the power units. • Efficiency energy goals achieved an increasing the profit in the energy production. [ABSTRACT FROM AUTHOR]

• A semi-analytical model was proposed to retrieve Chl- a using satellite imagery. • The model was based on the inherent optical properties (IOPs). • Chl- a distribution was mapped in inland waters from oligo-to-hypereutrophic status. • The model error was higher for hypereutrophic waters. • The model can be used operationally for long-term monitoring of the trophic status. Previous studies have shown the challenges in using a single model to estimate chlorophyll- a concentration (Chl- a) in water bodies with widely differing characteristics. A single model based on remote sensing to map the Chl- a distribution across the entire Tietê River Cascade System (TRCS) serves as a cost and time-efficient alternative to the conventional monitoring by providing trophic status over space and time. The Tietê River contains one of the largest cascade reservoir systems in the world, which sustains important ecological and socio-economic activities in the São Paulo State, Brazil. Surplus nutrients in water draining its surrounding catchments have been the main cause of eutrophication in the reservoirs of the TRCS. To assess the trophic state of the reservoirs, Chl- a has been regularly monitored by sampling points. However, they are limited by operational costs and dependent on weather conditions. Moreover, the current sampling method only produces point-based measurements. In this paper, we calibrate remote sensing images based on the absorption coefficient to map the spatial distribution patterns of Chl- a levels in the reservoirs. Mapping is done by estimating the Chl- a concentration. The absorption coefficients were retrieved from OLI/Landsat images using the Quasi-Analytical Algorithm (QAA). The total absorption (a t) in 482 nm and 655 nm retrieved by QAA presented NRMSE of 17% and 18.5%, respectively. Both a t (482 and 655 nm) were used in the model calibration and presented a satisfactory result covering all data ranges, with R2 of 0.646 and NRMSE of 15.3%. The proposed model in this study to retrieve Chl- a maps with relatively high accuracy can be incorporated into the operational monitoring system of the TRCS at a low cost that can provide timely information for reservoir managers to carry out necessary actions. This may include mitigating environmental impacts caused by sudden algae blooms. [ABSTRACT FROM AUTHOR]