Construção de um classificador automático de severidade de bugs para sistemas open source

Software bug analysis is one of the most important activities in Software Quality. The rapid and correct implementation of the necessary repair influence both developers, who must leave the fully functioning software, and users, who need to perform their daily tasks. In this context, if there is an incorrect classification of bugs, there may be unwanted situations. One of the main factors to be assigned bugs in the act of its initial report is severity, which lives up to the urgency of correcting that problem. In this scenario, we identified in datasets with data extracted from five open source systems (Apache, Eclipse, Kernel, Mozilla and Open Office), that there is an irregular distribution of bugs with respect to existing severities, which is an early sign of misclassification. In the dataset analyzed, exists a rate of about 85% bugs being ranked with normal severity. Therefore, this classification rate can have a negative influence on software development context, where the misclassified bug can be allocated to a developer with little experience to solve it and thus the correction of the same may take longer, or even generate a incorrect implementation. Several studies in the literature have disregarded the normal bugs, working only with the portion of bugs considered severe or not severe initially. This work aimed to investigate this portion of the data, with the purpose of identifying whether the normal severity reflects the real impact and urgency, to investigate if there are bugs (initially classified as normal) that could be classified with other severity, and to assess if there are impacts for developers in this context. For this, an automatic classifier was developed, which was based on three algorithms (Näive Bayes, Max Ent and Winnow) to assess if normal severity is correct for the bugs categorized initially with this severity. The algorithms presented accuracy of about 80%, and showed that between 21% and 36% of the bugs should have been classified differently (depending on the algorithm), which represents somewhere between 70,000 and 130,000 bugs of the dataset.

Reação de genótipos de cafeeiro à Hemileia vastatrix e à Cercospora coffeicola

Coffee plants were introduced in Brazil in the Northern State of Para around 1727. Two major diseases have affected coffee trees in the country. One is rust, caused by fungus Hemileia vastatrix and accountable for production losses up to 50%. The other one is Cercospora leaf spot, caused by fungus Cercospora coffeicola endemic to all Brazilian coffee farms and, therefore, economically critical due to production losses both in the plant nursery and in the field. Availability of resistant varieties has been a constant challenge for breeders. Research programs play an important role in the search for new resistant and/or tolerant genotypes, since over time plants can become susceptible to new, genetically variable races of pathogens. This study aimed to evaluate the incidence and severity of such diseases, the resistance of different coffee genotypes to H. vastatrix and C. coffeicola pathogens, as well as the productivity of said genotypes in dense planting system. The experimental design consisted of randomized blocks, with twelve genotypes (treatments) and two replications (blocks). SISVAR® program was used to analyze data and compare them building on Scott-Knott test and Tukey’s test with a probability of 5%. Disease incidence and severity percentage were assessed for both Cercospora leaf spot and rust. Means were used to calculate the area under the disease progress curve (AUDPC) of both diseases. As to rust, the most resistant genotypes were H586-6, IBC 12, and H556-7 H567-6. As to Cercospora leaf spot and productivity, no statistical differences were found across genotypes. The dense planting system did not impair plant development, but favored disease evolution given the microclimate it produces.

Escala diagramática e influência de sistemas de produção na ocorrência do crestamento gomoso da melancia

CHAPTER 1 - The gummy stem blight, caused by the fungus D. bryoniae, is a disease commonly found in watermelon cultivated in several countries. In Brazil, there are numerous studies related to the disease, but there are not uniform methods for quantifying of disease severity in the field. Thus, we developed a diagrammatic scale based on scanned photos of watermelon leaves infected with D. bryoniae. The scale developed showed levels of 0; 10; 20; 45; 65 and 90% of severity. The scale validation was divided into two parts: initially, 10 evaluators (half with experienced and other half without experience) estimated the disease severity based on the initial observation of 100 photos of watermelon leaves with symptoms of the disease at different severity levels. Before, the same evaluators estimated the disease severity with the support of the scale prepared from the Quant program. Data were analyzed using linear regression and were obtained angular, linear, and correlation coefficients. Based on these data, we determined the accuracy and precision of the evaluations. The correlation coefficients (R2) ranged from 0.88 - 0.97 for the experienced evaluators and from 0.55 - 0.95 for the inexperienced evaluators. The average angular coefficient (A) for inexperienced evaluators was 20.42 and 8.61 with and without the support of diagrammatic scale, respectively. Experienced evaluators showed values of average linear coefficient of 5.30 and 1.68 with and without the support of diagrammatic scale, respectively. The absolute errors analysis indicated that the use of diagrammatic scale contributed to minimize the flaws in the severity levels estimation. The diagrammatic scale proposed shown adequate for gummy stem blight severity evaluation in watermelon. CHAPTER 2 - The gummy stem blight (Didymella bryoniae) is a disease that affects the productivity of watermelon leading to losses over 40%. This study aimed to evaluate the efficiency of different production systems in control of gummy stem blight in watermelon for to establish efficient methods to combat the disease. There were applied the following treatments: conventional tillage (T1), integrated management (T2) and organic management (T3). In T1 and T2 were applied mineral fertilization and T3 was used bovine manure. There was application of fungicides and insecticides in commercial dose in T1 and T2, being after soil chemical analysis in T2. Disease severity was assessed by grading scale. The experimental design was randomized blocks. The severity of gummy stem blight has increased substantially during the fruit formation. Watermelon plants grown with integrated management (T2) showed lower levels of disease severity, while plants in organic management (T3) exhibited higher levels of severity. We conclude that management based on judicious accompaniments in field represents best way to achieve the phytosanitary aspect adequate for cultivation of watermelon in Tocantins.

Fungicidas protetores no manejo da ferrugem da soja, processos fisiológicos e produtividade da cultura

Currently, the management recommendations for asian soybean rust (ASR) has been based on the application of protective fungicides mixed with triazoles and stronilurins. Thus, this study aimed at assessing whether the increased productivity provided by the application of protective fungicides is due solely to the fungicidal action of the product or some physiological changes in the plant and which the latter would be. The experiment was conducted from March to July 2015 at the experimental station of Udi Research and Development in Uberlândia-MG, with the cultivar 97Y07 RR. The experimental design chosen for this study was comprised of a randomized block with four replications and 16 treatments: check, fluxapyroxad + pyraclostrobin (116.55 + 58.45 g ha-1), azoxystrobin + benzovindiflupir (90 + 45 g ha-1), trifloxystrobin + prothioconazole (60 + 70 g ha-1), tebuconazole + picoxystrobin (100 + 60 g ha-1), picoxystrobin + cyproconazole (60 + 24 g ha-1), mancozeb (1125 g ha-1), azoxistrobina + tebuconazole + difenoconazole (60 + 75 + 120 g ha-1), azoxystrobin + tebuconazole + difenoconazole + chlorothalonil ( 60 + 120 + 75 + 1440 g ha-1), and mistures fluxapyroxad + pyraclostrobin + mancozeb, azoxystrobin + benzovindiflupir + mancozeb, trifloxystrobin + prothioconazole + mancozeb, tebuconazole + picoxystrobin + mancozeb, picoxystrobin + cyproconazole + mancozeb, azoxystrobin + tebuconazole + difenoconazole + mancozeb, and azoxystrobin + benzovindiflupir + chlorothalonil, from the aforesaid doses. The first application of the treatments occurred in R1, in the absence of symptoms. The number of applications, intervals and the use of adjuvants were performed according to the recommendations by manufacturers. The variables analyzed were: disease severity, concentration of chlorophylls and carotenoids, photosynthetic rate (A), transpiration rate (E), stomatal conductance (gs), internal carbon concentration (Ci), instantaneous efficiency in water use (A/E), intrinsic water use efficiency (A/gs), and carboxylation efficiency (A/C). With these data collected, this study set to date the progress curve of each variable (AUPC). At the end of the crop cycle, the average of pods per plant was quantified, grain per pod, productivity and weight of 1,000 grains. It was concluded that: the addition of mancozeb to fluxapyroxad + pyraclostrobin, azoxystrobin + benzovindiflupir, trifloxystrobin + prothioconazole and tebuconazole + picoxystrobin potentiated the ASR control; adding mancozebe to the mixture azoxystrobin + benzovindiflupir provided better control of the disease compared to the addition of chlorothalonil; mancozeb amounts to AUPC concentration of photosynthetic pigments and when added to axozystrobin + tebuconazole + difenoconazole, increases the AUPC for total chlorophyll concentration, as well as when chlorothalonil was added; mancozeb added to the mix fluxapyroxad + pyraclostrobin raised the AUPC for A/Ci and A/gs, increasing the W1,000G and crop productivity; the addition of protectors similarly reflected on the productivity of culture.

Alterações fisiológicas causadas por fungicidas em soja infectada naturalmente por oídio

Soybean crop is substantially important for both Brazilian and international markets. A relevant disease that affects soybeans is powdery mildew, caused by fungus Erysiphe diffusa. The objective of this master’s thesis was to analyze physiological changes produced by fungicides in two greenhouse-grown soybean genotypes (i.e., Anta 8500 RR and BRS Santa Cruz RR) naturally infected with powdery mildew. A complete randomized block design was used with six replications in a 2x5 factorial arrangement. Treatments consisted of applications of Azoxystrobin, Biofac (fermented solution of Penicillium sp.), Carbendazim or Picoxystrobin fungicides, and a Control (no fungicide application). Three applications were performed in the experimental period, and each eventually represented a period of data collection. Gas exchanges, chlorophyll content, fluorescence of chlorophyll a and disease severity were measured twice a week. Dry grain mass production was measured at the end of the experiment. Areas under progression curve of variables were submitted to both ANOVA and Tukey’s test at 5% significance. Treatments Azoxystrobin, Biofac and Picoxystrobin had higher photosynthetic rates than Control in the second period, with genotype Anta having higher rate than Santa Cruz. Biofac had higher transpiration rate than Control in the second period, while Biofac and Picoxystrobin had higher figures in Santa Cruz in the third period. Carbendazim had greater stomatal conductance in Anta, whilst Azoxystrobin, Biofac and Picoxystrobin had greater values than Carbendazim in Santa Cruz. Biofac and Picoxystrobin had greater intercellular CO2 concentration in Santa Cruz. Azoxystrobin and Picoxystrobin had greater instantaneous water use efficiency than Control, with Anta being more efficient than Santa Cruz. Biofac and Picoxystrobin had greater intrinsic water use efficiency in Anta, while Carbendazim increased efficiency in Santa Cruz. Azoxystrobin, Biofac and Picoxystrobin had greater carboxylation efficiency than Control in the second period, with Anta being more efficient than Santa Cruz. Azoxystrobin and Biofac had greater contents of chlorophylls a, b and a+b than Control in the second period. Azoxystrobin had greater effective quantum yield than Control and Picoxystrobin. All treatments faced increasing disease severity over time, with Anta being less resistant than Santa Cruz. As for production, data showed that: (1) Santa Cruz was more productive than Anta, having the greatest dry grain mass with Carbendazim, and (2) Anta’s lower disease severity did not translate into higher productions. In conclusion, strobilurins (Azoxystrobin and Picoxystrobin) and Biofac performed similarly as to their physiological effects on soybeans; however, these effects did not lead to increased dry grain mass by the end of the experiment.