Predicting events based on available data is an effective way to protect human lives. Issuing health alert based on prediction of environmental pollution, executing timely evacuation of people from vulnerable areas based on prediction of natural disasters are the application areas of sensor data stream where accurate and timely prediction is crucial to safeguard people and assets. Thus, prediction accuracy plays a significant role to take precautionary measures and minimize the extent of damage. Belief rule-based Expert System (BRBES) is a rule-driven approach to perform accurate prediction based on knowledge base and inference engine. It outperforms other such knowledge-driven approaches, such as, fuzzy logic, Bayesian probability theory in terms of dealing with uncertainties. On the other hand, Deep Learning is a data-driven approach which belongs to Artificial Intelligence (AI) domain. Deep Learning discovers hidden data pattern by performing analytics on huge amount of data. Thus, Deep Learning is also an effective way to predict events based on available data, such as, historical data and sensor data streams. Integration of Deep Learning with BRBES can improve prediction accuracy further as one can address the inefficiency of the other to bring down error gap. We have taken air pollution prediction as the application area of our proposed integrated approach. Our combined approach has shown higher accuracy than relying only on BRBES and only on Deep Learning. / <p>This is a Master Thesis Report as part of degree requirement of Erasmus Mundus Joint Master Degree (EMJMD) in Pervasive Computing and Communications for Sustainable Development (PERCCOM).</p>

Welcome to the Supplementum issue of the International Journal of Homiletics. The articles in this volume are edited, peer-reviewed versions of keynote lectures and papers presented at the Societas Homiletica Conference on August 3rd – 8th 2018, at The Divinity School of Duke University, North Carolina, USA. The theme of the conference was “Fearing God in a Fear-Filled World? Homiletical Explorations” – a topic that resonated with homileticians from all over the world and engendered rich reflections and discussions during the conference. In what follows are four keynote lectures, a keynote response and six papers discussing the theme of fear from theological perspectives of South Africa, Brazil, Australia, Germany, the Netherlands, Sweden, and the United States.

The process of energy consumption and monitoring of a buildingis time-consuming. Therefore, an feasible approach for using trans-fer learning is presented to decrease the necessary time to extract re-quired large dataset. The technique applies a bidirectional long shortterm memory recurrent neural network using sequence to sequenceprediction. The idea involves a training phase that extracts informa-tion and patterns of a building that is presented with a reasonablysized dataset. The validation phase uses a dataset that is not sufficientin size. This dataset was acquired through a related paper, the resultscan therefore be validated accordingly. The conducted experimentsinclude four cases that involve different strategies in training and val-idation phases and percentages of fine-tuning. Our proposed modelgenerated better scores in terms of prediction performance comparedto the related paper.

This study investigated the validity of measures that were hypothesized to account for significant variance in English reading ability. During kindergarten, 63 bilingual Hispanic children completed letter identification, English and Spanish phonological awareness, rapid automatized naming, and sentence repetition static assessment tasks. They also completed a dynamic assessment nonsense-word decoding task that yielded pretest to posttest gain score, response to decoding strategy, and temporally related working memory information. One week prior to kindergarten, information was gathered regarding socioeconomic status, preschool attendance, English and Spanish language dominance, and language ability. At the end of first grade, the same children completed word identification, decoding, and reading fluency tasks designed to represent the narrow view of reading. Reliability, content relevancy, construct validity, and predictive evidence of validity were examined. The letter identification task, the English-only and Spanish-only tasks, and a composite of the participants' best English and Spanish scores accounted for significant variance in first-grade word-level reading. However, the Spanish and BLS static measures did not account for significant, unique variance over and above English-only static measures, and the English-only static measures did not account for significant, unique variance over and above the letter identification static measure. The dynamic assessment measure pertaining to the response to reading strategy instruction accounted for equivalent variance in first-grade word-level reading when compared to a combination of letter identification and BLS static measures. The dynamic assessment measure yielded the highest classification accuracy, with sensitivity and specificity at or above 80% for all three formative criterion reading measures, including 100% sensitivity for two out of the three first-grade measures. The dynamic assessment of reading strategy surfaced as a parsimonious, valid means of predicting first-grade word-level reading ability for Hispanic, bilingual children. When compared to multiple English, Spanish, and BLS static measures, the dynamic measure accounted for equivalent variance in the majority of first-grade reading measures and had superior classification accuracy.

No description available.

Idag finns mängder av företag i olika branscher, stora som små, som vill förutsäga sin försäljning. Det kan bland annat bero på att de vill veta hur stort antal produkter de skall köpa in eller tillverka, och även vilka produkter som bör investeras i över andra. Vilka varor som är bra att investera i på kort sikt och vilka som är bra på lång sikt. Tidigare har detta gjorts med intuition och statistik, de flesta vet att skidjackor inte säljer så bra på sommaren, eller att strandprylar inte säljer bra under vintern. Det här är ett simpelt exempel, men hur blir det när komplexiteten ökar, och det finns ett stort antal produkter och butiker? Med hjälp av maskininlärning kan ett sånt här problem hanteras. En maskininlärningsalgoritm appliceras på en tidsserie, som är en datamängd med ett antal ordnade observationer vid olika tidpunkter under en viss tidsperiod. I den här studiens fall är detta försäljning av olika produkter som säljs i olika butiker och försäljningen ska prediceras på månadsbasis. Tidsserien som behandlas är ett dataset från Kaggle.com som kallas för “Predict Future Sales”. Algoritmerna som används i för den här studien för att hantera detta tidsserieproblem är XGBoost, MLP och MLR. XGBoost, MLR och MLP har i tidigare forskning gett bra resultat på liknande problem, där bland annat bilförsäljning, tillgänglighet och efterfrågan på taxibilar och bitcoin-priser legat i fokus. Samtliga algoritmer presterade bra utifrån de evalueringsmått som användes för studierna, och den här studien använder samma evalueringsmått. Algoritmernas prestation beskrivs enligt så kallade evalueringsmått, dessa är R², MAE, RMSE och MSE. Det är dessa mått som används i resultat- och diskussionskapitlen för att beskriva hur väl algoritmerna presterar. Den huvudsakliga forskningsfrågan för studien lyder därför enligt följande: Vilken av algoritmerna MLP, XGBoost och MLR kommer att prestera bäst enligt R², MAE, RMSE och MSE på tidsserien “Predict Future Sales”. Tidsserien behandlas med ett känt tillvägagångssätt inom området som kallas CRISP-DM, där metodens olika steg följs. Dessa steg innebär bland annat dataförståelse, dataförberedelse och modellering. Denna metod är vad som i slutändan leder till resultatet, där resultatet från de olika modellerna som skapats genom CRISP-DM presenteras. I slutändan var det MLP som fick bäst resultat enligt mätvärdena, följt av MLR och XGBoost. MLP fick en RMSE på 0.863, MLR på 1.233 och XGBoost på 1.262 / Today, there are a lot of companies in different industries, large and small, that want to predict their sales. This may be due, among other things, to the fact that they want to know how many products they should buy or manufacture, and also which products should be invested in over others. In the past, this has been done with intuition and statistics. Most people know that ski jackets do not sell so well in the summer, or that beach products do not sell well during the winter. This is a simple example, but what happens when complexity increases, and there are a large number of products and stores? With the help of machine learning, a problem like this can be managed easier. A machine learning algorithm is applied to a time series, which is a set of data with several ordered observations at different times during a certain time period. In the case of this study, it is the sales of different products sold in different stores, and sales are to be predicted on a monthly basis. The time series in question is a dataset from Kaggle.com called "Predict Future Sales". The algorithms used in this study to handle this time series problem are XGBoost, MLP and MLR. XGBoost, MLR and MLP. These have in previous research performed well on similar problems, where, among other things, car sales, availability and demand for taxis and bitcoin prices were in focus. All algorithms performed well based on the evaluation metrics used by the studies, and this study uses the same evaluation metrics. The algorithms' performances are described according to so-called evaluation metrics, these are R², MAE, RMSE and MSE. These measures are used in the results and discussion chapters to describe how well the algorithms perform. The main research question for the study is therefore as follows: Which of the algorithms MLP, XGBoost and MLR will perform best according to R², MAE, RMSE and MSE on the time series "Predict Future Sales". The time series is treated with a known approach called CRISP-DM, where the methods are followed in different steps. These steps include, among other things, data understanding, data preparation and modeling. This method is what ultimately leads to the results, where the results from the various models created by CRISP-DM are presented. In the end, it was the MLP algorithm that got the best results according to the measured values, followed by MLR and XGBoost. MLP got an RMSE of 0.863, MLR of 1,233 and XGBoost of 1,262

Terminaison de la transcription. Rho se fixe aux transcrits naissants au niveau d’un site Rut (Rhoutilization) libre à partir duquel il transloque le long de l’ARN (5’→3’) de façon ATP-dépendante pour rattraper le complexe d’élongation de la transcription et induire la dissociation de celui-ci. Il est généralement admis que les sites de fixation de Rho présentent une richesse en Cytosines et une pauvreté en Guanines, ainsi qu’une relative pauvreté en structures secondaires. Les études génomiques ou transcriptomiques n’ont pas dégagé d’éléments consensus ou de règles permettant de prédire les sites de terminaison Rho-dépendants. En combinant approches biochimiques et bioinformatiques, j’ai tenté de comprendre les mécanismes par lesquels Rho reconnait les transcrits.J’ai identifié un ensemble de déterminants de séquence qui, pris ensemble, possèdent un bon pouvoir prédictif et que j’ai utilisé pour construire le premier modèle computationnel capable de prédire la terminaison Rho-dépendante à l’échelle des génomes d’E. coli et Salmonella. J’ai caractérisé in vitro certains de ces terminateurs, en particulier dans les régions 5’UTR, avec l’espoir qu’ils soient impliqués dans des mécanismes de régulation conditionnelle. J’ai identifié des candidats dont l’activité pourrait être sous le contrôle de facteurs comme des petits ARN non codants (sRNA) ou latempérature. J’ai également développé une méthode fluorogénique pour détecter facilement la terminaison Rho-dépendante in vitro et ai commencé à adapter l’approche CLIP-seq à l’étude du transcriptome Rho-dépendant chez Salmonella. Collectivement, mes travaux offrent de nouveaux outils d’analyse et de prédiction de la terminaison Rho-dépendante, une meilleure cartographie des sites d’action de Rho chez E. coli et Salmonella, ainsi que de nouvelles pistes d’étude du rôle de Rhodans l’expression conditionnelle du génome. / Transcripts at a free Rut (Rho-utilization) site from which Rho moves along the RNA in an ATP dependentfashion to catch up with and dissociate the transcription elongation complex. It is generally believed that the Rut sites are, respectively, rich and poor in Cytosines and Guanines as well as relatively poor in secondary structures. Studies at the genomic or transcriptomic scale have notrevealed any stronger consensus features or rules for predicting potential Rho-dependent termination sites. By combining biochemical and bioinformatics approaches, I have explored the mechanisms by which Rho recognizes transcripts to induce transcription termination. I have identified a complex set of sequence determinants which, taken together, have good predictive power and which I used to build the first computational model able to predict Rho-dependent termination at the scale of Escherichiacoli and Salmonella genomes. I have characterized in vitro some of these terminators, particularly in 5'UTRs, with the hope that they will be involved in conditional regulatory mechanisms. I have identified several candidates whose activity may be under the control of factors such as small non-coding RNAs(sRNA) or temperature. I have also developed a fluorogenic method to easily detect Rho-dependent termination in vitro and have begun to adapt the CLIP-seq approach to the study of the Rhodependent transcriptome in Salmonella. Collectively, my work offers new tools for the analysis and prediction of Rho-dependent termination, a better mapping of the sites of probable Rho action in E.coli and Salmonella, as well as several lines of investigation of the role of Rho in the conditional expression of bacterial genomes.

A determinação do tempo de vida útil dos alimentos é importante, pois garante que estes estejam adequados para o consumo se ingeridos dentro do período estipulado. Os alimentos que apresentam vida curta têm seu tempo de vida útil determinado por estudos não acelerados, os quais demandam métodos multivariados de análise para uma boa predição. Considerando isso, este estudo objetiva: propor um método estatístico multivariado capaz de predizer o tempo de vida útil de alimentos, em estudos não acerados; avaliar sua estabilidade e sensibilidade frente a perturbações provocadas nas variáveis de entrada, utilizando técnicas de simulação bootstrap; apresentar o método SheNon para dados experimentais por meio da construção de contrastes dos tempos preditos dos tratamentos de interesse e compará-los com uma diferença mínima significativa (DMS) obtida empiricamente por meio do método bootstrap. Com os resultados provenientes deste estudo constatou-se que o método proposto mostra-se promissor e estável para a predição do tempo de vida útil de alimentos em estudos não acelerados. O método mostrou-se sensível ao número de tempos (tamanho da amostra) em que o alimento foi observado. Verificou-se, também, bom desempenho na análise de dados experimentais, uma vez que após predição do tempo de vida útil para cada tratamento considerado, pode-se inferir sobre a igualdade dos tempos de vida de diferentes tratamentos. / Consumers are increasingly demanding about the quality of food and expectation that this quality is maintained at high level during the period between purchase and consumption. These expectations are a consequence not only of the requirement that the food should stay safe, but also the need to minimize the unwanted changes in their sensory qualities. Considering food safety and consumer demands this study aims to propose a multivariate statistical method to predict the shelf life of time not accelerated studies, the method SheNon. The development of multivariate method for predicting the shelf life of a food, considering all attributes and their natures describes a new concept of data analysis for estimating the degradation mechanisms that govern food and determines the time period in which these foods retain their characteristics within acceptable levels. The proposed method allows to include microbiological, physical, chemical and sensory attributes, which leads to a more accurate prediction of shelf life of food. The method SheNon features easy interpretation, its main advantages include the ability to combine information from different natures and can be generalized to data with experimental structure. The method SheNon was applied to eggplants minimally processed predicting a lifetime of around 9.6 days.

在此篇論文之前, 已經有許多學者指出在金融市場奔盤之前的價格波動與熱物理學中的臨界現象有所類似. 其價格會呈現Power law的形式迅速加速上升, 同時伴隨著log-periodic震盪. 藉由first-order Landau expansion和second-order Landau expansion, 我們使用了50個隨機樣本, 分別從五個不同的指數來驗證其正確性. 結果發現該模型很難運用在高波動的市場, 但是對於中級波動的市場卻有不錯的預測能力, 比方說S&P500與Nikkei 225指數. / Before this paper, many scholars indicated that market price movement before a crash is similar to critical phenomena. It can be described by a power law acceleration of the market price decorated with log-periodic oscillations. By first-order Landau expansion and second-order Landau expansion, we use 50 random samples from each of 5 different indices to test the model. It is hard to adapt Landau expansion to high volatility indices, but fit pretty well for medium volatility indices, such as S&P 500 and Nikkei 225.

Prior research on the ability of financial ratios to predict bankruptcies has shown a significant difference between the companies that went into bankruptcy and those that survived. This paper investigates whether there is a difference in the prediction ability of financial ratios during the last financial crisis compared to relatively normal macroeconomic environments in which most previous studies have been conducted. We use univariate analysis to compare companies that went into bankruptcy during 2010 and 2011 with companies that remained active. Our dataset consists of 51 failed companies that are matched with 102 companies that remained active. All companies were Swedish limited companies with more than 50 employees and the comparison is made with 26 financial ratios. Our result indicates that financial ratios were better tools to predict bankruptcy during the crisis than during more stable macroeconomic conditions. In total 24 of the analyzed financial ratios differed significantly between the two populations and many of them showed significance earlier prior to the bankruptcy than in comparable studies.