Today, digitalization is a key factor for businesses to enhance growth and gain advantages and insight in their operations. Both in planning operations and understanding customers the digitalization processes today have key roles, and companies are spending more and more resources in this fields to gain critical insights and enhance growth. The fast-food industry is no exception where restaurants need to be highly flexible and agile in their work. With this, there exists an immense demand for knowledge and insights to help restaurants plan their daily operations and there is a great need for organizations to continuously adapt new technological solutions into their existing processes. Well implemented Machine Learning solutions in combination with feature engineering are likely to bring value into the existing processes. Sales forecasting, which is the main field of study in this thesis work, has a vital role in planning of fast food restaurant's operations, both for budgeting purposes, but also for staffing purposes. The word fast food describes itself. With this comes a commitment to provide high quality food and rapid service to the customers. Understaffing can risk violating either quality of the food or service while overstaffing leads to low overall productivity. Generating highly reliable sales forecasts are thus vital to maximize profits and minimize operational risk. SARIMA, XGBoost and Random Forest were evaluated on training data consisting of sales numbers, business hours and categorical variables describing date and month. These models worked as base learners where sales predictions from a specific dataset were used as training data for a Support Vector Regression model (SVR). A stacking approach to this type of project shows sufficient results with a significant gain in prediction accuracy for all investigated restaurants on a 6-week aggregated timeline compared to the existing solution. / Digitalisering har idag en nyckelroll för att skapa tillväxt och insikter för företag, dessa insikter ger fördelar både inom planering och i förståelsen om deras kunder. Det här är ett område som företag lägger mer och mer resurser på för att skapa större förståelse om sin verksamhet och på så sätt öka tillväxten. Snabbmatsindustrin är inget undantag då restauranger behöver en hög grad av flexibilitet i sina arbetssätt för att möta kundbehovet. Det här skapar en stor efterfrågan av kunskap och insikter för att hjälpa dem i planeringen av deras dagliga arbete och det finns ett stort behov från företagen att kontinuerligt implementera nya tekniska lösningar i befintliga processer. Med väl implementerade maskininlärningslösningar i kombination med att skapa mer informativa variabler från befintlig data kan aktörer skapa mervärde till redan existerande processer. Försäljningsprognostisering, som är huvudområdet för den här studien, har en viktig roll för verksamhetsplaneringen inom snabbmatsindustrin, både inom budgetering och bemanning. Namnet snabbmat beskriver sig själv, med det följer ett löfte gentemot kunden att tillhandahålla hög kvalitet på maten samt att kunna tillhandahålla snabb service. Underbemanning kan riskera att bryta någon av dessa löften, antingen i undermålig kvalitet på maten eller att inte kunna leverera snabb service. Överbemanning riskerar i stället att leda till ineffektivitet i användandet av resurser. Att generera högst tillförlitliga prognoser är därför avgörande för att kunna maximera vinsten och minimera operativ risk. SARIMA, XGBoost och Random Forest utvärderades på ett träningsset bestående av försäljningssiffror, timme på dygnet och kategoriska variabler som beskriver dag och månad. Dessa modeller fungerar som basmodeller vars prediktioner från ett specifikt testset används som träningsdata till en Stödvektorsreggresionsmodell (SVR). Att använda stapling av maskininlärningsmodeller till den här typen av problem visade tillfredställande resultat där det påvisades en signifikant förbättring i prediktionssäkerhet under en 6 veckors aggregerad period gentemot den redan existerande modellen.

Hydropower is an important part of renewable power production in Sweden. The voltage stability of the already existing hydropower needs to be improved. One way to do this is by improving the control system that damp terminal voltage oscillations. If the oscillations in the power system are not damped it could lead to lower power outputs or in the worst case a blackout. This thesis focuses on the automatic voltage regulator (AVR) system with a proportional, integral, derivative (PID) controller. The PID controller’s parameters are optimized to dampen the terminal voltage instability in a generator. The aim is to develop a machine learning model that predicts the optimal gain parameters for a PID controller. The model is using the tuned gains from the Ziegler-Nichols (Z-N) method and the amplifier gain as inputs and gives the optimal gains as output. A linearized model of an AVR system, based on transfer functions was developed in a MATLAB script. This model was used to simulate the behaviours of an AVR system when a change in load occurs. The Z-N method and the genetic algorithm (GA) with different settings and fitness functions were used to tune a PID controller. The best performing method is GA with the fitness function developed by Zwe-Lee Gaing (ZL).  The best performing settings are: roulette selection, adapt feasible mutation, and arithmetic crossover. The GA (ZL) was used in the development of a machine learning model. Two different models were developed and tested: the support vector regression (SVR) and the gaussian process regression (GPR). The data that was used to train the models were generated by changing the transfer functions’ time constants 4096 times. At each step, the Z-N, and the GA (ZL) were run. The GPR model is shown to be the superior model with a lower root mean square error (RMSE) and a higher ratio of variation (R^2). The RMSE for GPR is 0.1091, 0.0815, 0.0717 and the R^2 is 87 %, 59 %, and 86%. The result shows that the developed model has capabilities to optimize the PID controller gains of any AVR-system without knowing the characteristics of the components.

A key challenge for maximizing the world’s food supply is crop yield prediction. In this study, three machine models are used to predict the fresh weight (yield) of lettuce plants that are grown inside indoor farms hydroponically using the vertical farming infrastructure, namely, support vector regressor (SVR), random forest regressor (RFR), and deep neural network (DNN).The climate data, nutrient data, and plant growth data are passed as input to train the models to understand the growth pattern based on the available features. The study of evaluation metrics majorly covers Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared, and Adjusted R-squared values.The results of the project have shown that the Random Forest with all the features is the best model having the best results with the least cross-validated MAE score and good cross-validated Adjusted R-squared value considering that the error of the prediction is minimal. This is followed by the DNN model with minor differences in the resulting values. The Support Vector Regressor (SVR) model gave a very poor performance with a huge error value that cannot be afforded in this scenario. In this study, we have also compared various evaluating metrics mentioned above and considered the cross-validated MAE and cross-validated Adjusted R-squared metrics. According to our study, MAE had the lowest error value, which is less sensitive to the outliers and adjusted R-squared value helps to understand the variance of the target variable with the predictor variable and adjust the metric to prevent the issues of overfitting.

This paper investigates correlation between energy consumption 24 hours ahead and features used for predicting energy consumption. The features originate from three categories: weather, time and previous energy. The correlations are calculated using Pearson correlation and mutual information. This resulted in the highest correlated features being those representing previous energy consumption, followed by temperature and month. Two identical feature sets containing all attributes1 were obtained by ranking the features according to correlation. Three feature sets were created manually. The first set contained seven attributes representing previous energy consumption over the course of seven days prior to the day of prediction. The second set consisted of weather and time attributes. The third set consisted of all attributes from the first and second set. These sets were then compared on different machine learning models. It was found the set containing all attributes and the set containing previous energy attributes yielded the best performance for each machine learning model. 1In this report, the words ”attribute” and ”feature” are used interchangeably. / I denna rapport undersöks korrelation och betydelsen av olika attribut för att förutspå energiförbrukning 24 timmar framåt. Attributen härstammar från tre kategorier: väder, tid och tidigare energiförbrukning. Korrelationerna tas fram genom att utföra Pearson Correlation och Mutual Information. Detta resulterade i att de högst korrelerade attributen var de som representerar tidigare energiförbrukning, följt av temperatur och månad. Två identiska attributmängder erhölls genom att ranka attributen över korrelation. Tre attributmängder skapades manuellt. Den första mängden innehåll sju attribut som representerade tidigare energiförbrukning, en för varje dag, sju dagar innan datumet för prognosen av energiförbrukning. Den andra mängden bestod av väderoch tidsattribut. Den tredje mängden bestod av alla attribut från den första och andra mängden. Dessa mängder jämfördes sedan med hjälp av olika maskininlärningsmodeller. Resultaten visade att mängden med alla attribut och den med tidigare energiförbrukning gav bäst resultat för samtliga modeller.

Campylobacter jejuni é a espécie bacteriana mais comumente relacionada como causa de gastroenterite em humanos em vários países. Porém, o isolamento e o estudo de C. jejuni não são muito frequentes no Brasil, o que dificulta avaliar a dimensão dessa bactéria como causadora de doença em humanos e animais, bem como, determinar o impacto de sua presença em alimentos e no meio-ambiente. O objetivo desse trabalho foi avaliar a diversidade genética por cinco diferentes técnicas de tipagem molecular, o potencial patogênico pela pesquisa de 16 genes de virulência por PCR e o perfil de resistência pela concentração inibitória mínima por Etest® frente a quatro antimicrobianos e pela análise in silico de genes de resistência e pontos de mutação de linhagens de C. jejuni isoladas no Brasil. Foram estudadas 121 linhagens de C. jejuni isoladas de humanos (51), animais (35), alimentos (33) e ambiente (02) nos estados de Minas Gerais, São Paulo, Rio de Janeiro e Rio Grande do Sul, no período de 1996 a 2016. Todas as linhagens apresentaram os genes flaA, flhA, iamA, docA, ciaB, cdtA, cdtB, cdtC, racR, dnaJ, pldA, cadF, sodB e csrA. O gene wlaN foi detectado em 15 linhagens, e uma linhagem apresentou o gene virB11. Dentre as 121 linhagens estudadas, 68 linhagens foram resistentes a pelo menos um dos antimicrobianos testados. A resistência à ciprofloxacina, doxiciclina, tetraciclina e eritromicina foi observada em 43,8%, 34,7%, 34,7% e 4,9% das linhagens, respectivamente. O dendrograma de similaridade genética de Pulsed field gel electrophoresis (PFGE) agrupou as 121 linhagens estudadas em três grupos com similaridade genômica de 46,9% entre eles. Apesar da alta diversidade genômica entre as linhagens estudadas, algumas linhagens isoladas de diferentes fontes, locais e anos, apresentaram uma similaridade genotípica acima de 80% entre elas e, foram agrupadas em 21 subgrupos. Pelas sequências da SVR do gene flaA as linhagens estudadas foram agrupadas em dois grupos com linhagens isoladas de fontes clínicas e não clínicas e de humanos e animais com similaridade acima de 80,9 % entre elas e tipadas em 40 SVR-flaA alelos, sendo os alelos 57, 49 e 45 os mais frequentemente detectados. A análise do locus CRISPR por HRMA tipou as linhagens de C. jejuni em 23 diferentes variantes sendo que algumas variantes continham linhagens de origem clínica e não clínica e de humanos e animais. A árvore de SNPs gerada a partir dos dados do sequenciamento do genoma completo alocou as 116 linhagens sequenciadas em dois principais grupos. O grupo SNP-A agrupou 97 linhagens e o grupo SNP-B agrupou 19 linhagens, com linhagens de fontes clínicas e não clínicas e de humanos e animais, respectivamente. A técnica de Multilocus sequence typing (MLST) tipou as 116 linhagens de C. jejuni em 46 STs, e não foi observada a predominância de um ST. O índice de discriminação das metodologias de análise de SNPs no genoma completo, PFGE, MLST, sequenciamento das SVR do gene flaA e análise do locus CRISPR por HRMA foi 1,0, 0,982, 0,941, 0,939 e 0,874, respectivamente. Na análise in silico de genes de resistência e pontos de mutação, 95 linhagens apresentaram ao menos um gene de resistência ou ponto de mutação conhecido, sendo que a porcentagem de correlação entre os resultados de resistência fenotípicos e genotípicos foi maior que 66,7%; 94,6% e 96,8% para eritromicina, tetraciclina e ciprofloxacina, respectivamente. Conclui-se que a alta frequência da maioria dos genes de virulência pesquisados evidenciou o potencial patogênico das linhagens de C. jejuni estudadas. A resistência a antimicrobianos de primeira escolha utilizados para o tratamento da campylobacteriose encontrada nas linhagens estudadas é preocupante, podendo levar à falha terapêutica quando o tratamento é necessário. Os resultados obtidos pelas metodologias de tipagem molecular realizadas sugerem que uma possível contaminação possa ter ocorrido entre fontes clínicas e não clínicas e entre humanos e animais, ao longo de 20 anos no Brasil. Pelo índice de discriminação, foi observado que as metodologias de análise de SNPs no genoma completo e PFGE, em comparação com as outras técnicas de tipagem, foram as mais eficientes em discriminar as linhagens de C. jejuni do presente estudo. / Campylobacter jejuni is the most commonly bacterial species related as a cause of gastroenteritis in humans in several countries. However, the isolation and the study of C. jejuni have not been very frequently in Brazil, which makes it difficult to evaluate the involvement of this bacterium as a cause of diseases in humans and animals, as well as to determine the impact of its presence in food and the environment. The aim of this study was to evaluate the genetic diversity by five different molecular typing techniques, the pathogenic potential by searching for the presence of 16 virulence genes by PCR and the resistance profile by the minimum inhibitory concentration by Etest® against four antibiotics and by the in silico analyses of resistance genes and mutation points of C. jejuni strains isolated in Brazil. A total of 121 C. jejuni strains isolated from humans (51), animals (35), food (33) and the environment (02) in the States of Minas Gerais, Sao Paulo, Rio de Janeiro and Rio Grande do Sul, between 1996 to 2016 were studied. All strains presented the genes flaA, flhA, iamA, docA, ciaB, cdtA, cdtB, cdtC, racR, dnaJ, pldA, cadF, sodB and csrA. The wlaN gene was detected in 15 strains, and one strain presented the virB11 gene. Among the 121 strains studied, 68 strains were resistant to at least one of the antibiotics tested. Resistance to ciprofloxacin, doxycycline, tetracycline and erythromycin was observed in 43.8%, 34.7%, 34.7% and 4.9% of the strains, respectively. The Pulsed field gel electrophoresis (PFGE) dendrogram of genetic similarity clustered the 121 strains studied in three groups with a genomic similarity of 46.9% among them. Despite the high genomic diversity among the strains studied, some strains isolated from different sources, places and years, presented a genotypic similarity above 80% among them and were grouped into 21 subgroups. By flaA-SVR sequencing the strains studied were clustered into two groups with strains isolated from clinical and non-clinical sources and from humans and animals with a similarity above 80.9% among them and typed in 40 flaA-SVR alleles, being the alleles 57, 49 and 45 the most frequently detected. The analysis of the CRISPR locus by HRMA typed the C. jejuni strains in 23 different variants, with some variants containing strains from clinical and non-clinical origin and from humans and animals. The SNP tree generated from the whole genome sequencing data grouped the 116 strains sequenced into two major groups. SNP-A grouped 97 strains and SNP-B grouped 19 strains, with strains from clinical and non-clinical sources and from humans and animals, respectively. Multilocus sequence typing (MLST) technique typed the 116 C. jejuni strains in 46 STs, and it was not observed a predominant ST. The discrimination index of the analysis of SNPs in the whole genome, PFGE, MLST, flaA-SVR sequencing and analysis of the CRISPR locus by HRMA was 1.0, 0.982, 0.941, 0.939 and 0.874, respectively. In the in silico analyses of resistance genes and mutation points, 95 strains showed at least one resistance gene or known mutation point, and the percentage of correlation between phenotypic and genotypic resistance results was greater than 66.7%; 94.6% and 96.8% for erythromycin, tetracycline and ciprofloxacin, respectively. In conclusion, the high frequency of the majority of the virulence genes studied highlighted the pathogenic potential of the C. jejuni strains studied. Resistance to antimicrobials of first choice used for the treatment of campylobacteriosis found in the strains studied is worrying and may lead to therapeutic failure when treatment is required. The results obtained by the molecular typing methodologies performed suggest that a possible contamination may have occurred between clinical and non-clinical sources and between humans and animals over 20 years in Brazil. By the discrimination index, it was observed that the methodologies of analysis of SNPs in the whole genome and PFGE, in comparison to the other typing techniques, were the most efficients in discriminating the C. jejuni strains of the present study.

Dans cette recherche, nous tentons d'évaluer la pertinence d'une approche de simulation inverse des facteurs physiques d'ambiances dans le processus de conception en architecture et en aménagement urbain. Dans cette perspective, un outil de simulation inverse est développé et interfacé en sur-couche du logiciel de CAO AutoCAD largement utilisé dans les agences d'architectures. Il agrége les méthodes développées au Cerma ces dernières années sur la simulation inverse, de l'ensoleillement d'une part, et de la visibilité d'autre part. Dans le projet architectural ou urbain, la simulation directe solaire ou visuelle permet l'analyse d'une situation à un instant donné ou pour un point de vue donné a posteriori (après la conception d'un projet), tandis que notre démarche inverse consiste à cadrer la génération de solutions architecturales à partir des intentions d'ambiances du concepteur, et ce pour des périodes solaires et des zones de contraintes définies au début d'un projet. Les modélisations inverses de volumes de contraintes solaires et visuelles – ensembles de solutions à une contrainte donnée – ou d'uniques solutions d'ouvertures ou d'écrans sont des réponses optimales aux problèmes spatio-temporels de l'ensoleillement et de la visibilité. Ces volumes englobent l'ensemble des rayons solaires ou visuels joignant une base de contrainte (une zone à ensoleiller ou à protéger du soleil, ou un ensemble de positions potentielles d'un observateur) à une cible de contrainte (période solaire sur la "voûte solaire" ou cible visuelle du type monument, repère...). Ces volumes de contraintes sont aisément manipulables dans le modeleur géométrique. Comme les autres entités qui composent une scène numérique, il est possible de leur faire subir des opérations booléennes, des sections, des translations... Dans un premier temps, nous présentons un état de l'art de cette recherche sur les différents outils et méthodes de simulation inverse 2D puis 3D de l'ensoleillement et de la visibilité. Dans un second temps, nous développons et présentons l'outil SVR ainsi que ses applications. Enfin, nous livrons un état de l'art de quelques observations et méthodes d'observation des concepteurs à l'œuvre et nous évaluons notre logiciel par l'observation des raisonnements et comportements de onze architectes et étudiants en architecture concevant avec notre outil durant des phases d'esquisses et d'avant-projet. Pour cette évaluation, nous mettons en œuvre un protocole d'observation simultané ("think aloud protocol").

No description available.

This work focuses on scientific area called Music Information Retrieval, more precisely it’s subdivision focusing on the recognition of emotions in music called Music Emotion Recognition. The beginning of the work deals with general overview and definition of MER, categorization of individual methods and offers a comprehensive view of this discipline. The thesis also concentrates on the selection and description of suitable parameters for the recognition of emotions, using tools openSMILE and MIRtoolbox. A freely available DEAM database was used to obtain the set of music recordings and their subjective emotional annotations. The practical part deals with the design of a static dimensional regression evaluation system for numerical prediction of musical emotions in music recordings, more precisely their position in the AV emotional space. The thesis publishes and comments on the results obtained by individual analysis of the significance of individual parameters and for the overall analysis of the prediction of the proposed model.

Hydropower is an important energy source since it is fossil-free, renewable, and controllable. Characteristics that become especially important as the reliance on intermittent energy sources increases. However, the dams for the hydropower plants are also associated with large risks as a dam failure could have fatal consequences. Dams are therefore monitored by several sensors, to follow and evaluate any changes in the dam. One of the most important dam surveillance measurements is seepage since it can examine internal erosion. Seepage is affected by several different parameters such as reservoir water level, temperature, and precipitation. Studies also indicate the existence of a time lag between the reservoir water level and the seepage flow, meaning that when there is a change in the reservoir level there is a delay before these changes are reflected in the seepage behaviour. Recent years have seen increased use of AI in dam monitoring, enabling more dynamic warning systems.  This master’s thesis aims to develop a model for dynamic warning signals by predicting seepage using reservoir water level, temperature, and precipitation. Furthermore, a snowmelt variable was introduced to account for the impact of increased water flows during the spring season. The occurrence of a time lag and its possible influence on the model’s performance is also examined. To predict the seepage, three models with different complexity are used – linear regression, support vector regression, and long short-term memory. To investigate the time lag, the linear regression and support vector regression models incorporate a static time lag by shifting the reservoir water level data up to 14 days. The time lag was further investigated using the long short-term memory model as well.  The results show that reservoir water level, temperature, and the snowmelt variable are the combination of input parameters that generate the best results for all three models. Although a one-day time lag between reservoir water level and seepage slightly improved the predictions, the exact duration and nature of the time lag remain unclear. The more complex models (support vector regression and long short-term memory) generated better predictions than the linear regression but performed similarly when evaluated based on the dynamic warning signals. Therefore, linear regression is deemed a suitable model for dynamic warning signals by seepage prediction.

Ambient temperature poses a significant challenge to the performance of mobile phones, impacting their internal thermal flow and increasing the likelihood of overheating, leading to a compromised user experience. The knowledge about the ambient temperature in mobile phones is crucial as it assists engineers in correlating external factors with internal factors that might affect the mobile's performance under various conditions. Notably, these devices lack dedicated sensors to measure ambient temperature independently, underscoring the need for innovative solutions to estimate it accurately.      In response to this challenge, our research investigates the feasibility of estimating ambient temperature using machine-learning algorithms based on data from internal thermal sensors in Sony mobile phones.  Through comprehensive data collection and analysis, custom datasets were constructed to simulate different use-case scenarios, including CPU workloads, camera operation, and GPU tasks. These scenarios introduced varying levels of thermal disturbance, providing a robust basis for evaluating model performance. Feature engineering played a pivotal role in ensuring that the models could effectively interpret the internal thermal dynamics and correlate them with the ambient temperature. The results demonstrate that while simpler models like Linear Regression offer computational efficiency, they fall short in scenarios with complex thermal patterns. In contrast, deep learning models, particularly those incorporating time series analysis, showed superior accuracy and robustness. The Attention-LSTM model, in particular, excelled in generalizing across diverse and novel thermal conditions, although its complexity poses challenges for on-device deployment. This research underscores the importance of selecting appropriate sensors and incorporating a wide range of training scenarios to enhance model performance. It also highlights the potential of advanced machine learning techniques in providing advance solutions for ambient temperature estimation, thereby contributing to more effective thermal management in mobile devices.