Decentralization of the electric grid can increase resiliency (during natural disasters) and can reduce T&D energy losses and emissions. Microgrids and DERs can enable this to happen. It is important to optimally control microgrids and DERs to extract the greatest economic, environmental and resiliency benefits. This is enabled by robust forecasting to optimally control loads and energy sources. An integral part of microgrid control is power side and load side demand forecasting. In this thesis, we look at the ability of a powerful neural network algorithm to forecast the load side demand for a microgrid using the UMass campus as the test bed. UMass has its own power plant producing 16 MW of power. In addition to this, Solar panels totaling 5.5MW and lithium ion battery bank of 1.32 MW/4 MWh are also available. An LSTM recurrent neural network is used for demand forecasting. In addition to a fully trained LSTM network, multi linear regression model, ARIMA and ANN model are also tested to compare the performance. In addition to the Short Term Load Forecasting, the peak prediction accuracy of the model was also tested to run a battery discharge algorithm to shave peak demand for the microgrid. This will result in demand cost savings for the facility. Finally, the fully trained neural network was deployed on a raspberry pi computer.

<div>Textual emotion classification is a task in affective AI that branches from sentiment analysis and focuses on identifying emotions expressed in a given text excerpt. </div><div>It has a wide variety of applications that improve human-computer interactions, particularly to empower computers to understand subjective human language better. </div><div>Significant research has been done on this task, but very little of that research leverages one of the most emotion-bearing symbols we have used in modern communication: Emojis.</div><div>In this thesis, we propose several transformer-based models for emotion classification that processes emojis as input tokens and leverages pretrained models and uses them</div><div>, a model that processes Emojis as textual inputs and leverages DeepMoji to generate affective feature vectors used as reference when aggregating different modalities of text encoding. </div><div>To evaluate ReferEmo, we experimented on the SemEval 2018 and GoEmotions datasets, two benchmark datasets for emotion classification, and achieved competitive performance compared to state-of-the-art models tested on these datasets. Notably, our model performs better on the underrepresented classes of each dataset.</div>

This thesis wants to explore the forecasting potential of the multi-factor models to predict excess returns of the aggregated portfolio of the European stock mar- ket. These factors provided by Fama and French and Carhart are well-known in the field of asset pricing, we also add several financial and macroeconomic factors according to the literature. We establish a benchmark model of ARIMA and we compare the forecasting errors of OLS and the LSTM neural networks. Both models take the lagged excess returns and the inputs. We measure the performance with the root mean square error and mean absolute error. The results suggest that neural networks are in this particular task capable of bet- ter predictions given the same input as OLS but their forecasting error is not significantly lower according to the Diebold-Mariano test. JEL Classification C45, C53, C61, E37, G11, G15 Keywords Stocks, European market, Neural networks, LSTM, Factor Models, Fama-French, Predic- tions, RMSE Title Does LSTM neural network improve factor mod- els' predictions of the European stock market?

Language modeling is a very broad field and has been used for various purposes for a long period of time to make the lives of people easier. Language modeling is also used for text prediction for mobile keyboards to make the user experience smooth. Tobii has been working since 2001 for users who are suffering from ALS (Amyotrophic Lateral Sclerosis). In this disease, users are unable to talk, walk or chew due to the weakening of voluntary muscles and this gets worse day by day. Tobii has designed an Eye Tracker solution for people suffering from ALS to do their tasks more conveniently. They also developed a keyboard for talking which is controlled by an Eye Tracker device. Users can write sentences using the keyboard and then convey them to other people by conversion of this keyboard written text to speech. Therefore, the thesis is related to predicting the text on the initial input of the keyboard to make the user experience fast, easy and less hectic. This thesis project was conducted at Tobii Dynavox with the objective to build a language model which is an automatic, fast, and efficient approach to predict the text for the given input of text. It explores the way to predict sentences by using deep learning models on the initial text input from users and predict the text by taking into consideration user-specific writing style. The model developed in the thesis could be used by Tobii Dynavox for the end-users to predict the text. Part of the objective is also to find out which is the better approach for the implementation of the language models. The results show that federated learning is performing better than centralized machine learning. After analysing the results, it can also be said that Gated Recurrent Units (GRU) will be a good choice for our models because these models show better results for accuracy and take less training and response times.

Natural language processing and text classification are topics of much discussion among researchers of machine learning. Contributions in the form of new methods and models are presented on a yearly basis. However, less focus is aimed at comparing models, especially comparing models that are less complex to state-of-the-art models. This paper compares a Random Forest with a Long-Short Term Memory neural network for the task of classifying sentences as questions or non-questions, without considering punctuation. The models were trained and optimized on chat data from a Swedish insurance company, as well as user comments data on articles from a newspaper. The results showed that the LSTM model performed better than the Random Forest. However, the difference was small and therefore Random Forest could still be a preferable alternative in some use cases due to its simplicity and its ability to handle noisy data. The models’ performances were not dramatically improved after hyper parameter optimization. A literature study was also conducted aimed at exploring how customer service can be automated using a chatbot and what features and functionality should be prioritized by management during such an implementation. The findings of the study showed that a data driven design should be used, where features are derived based on the specific needs and customers of the organization. However, three features were general enough to be presented the personality of the bot, its trustworthiness and in what stage of the value chain the chatbot is implemented. / Språkteknologi och textklassificering är vetenskapliga områden som tillägnats mycket uppmärksamhet av forskare inom maskininlärning. Nya metoder och modeller presenteras årligen, men mindre fokus riktas på att jämföra modeller av olika karaktär. Den här uppsatsen jämför Random Forest med ett Long Short-Term Memory neuralt nätverk genom att undersöka hur väl modellerna klassificerar meningar som frågor eller icke-frågor, utan att ta hänsyn till skiljetecken. Modellerna tränades och optimerades på användardata från ett svenskt försäkringsbolag, samt kommentarer från nyhetsartiklar. Resultaten visade att LSTM-modellen presterade bättre än Random Forest. Skillnaden var dock liten, vilket innebär att Random Forest fortfarande kan vara ett bättre alternativ i vissa situationer tack vare dess enkelhet. Modellernas prestanda förbättrades inte avsevärt efter hyperparameteroptimering. En litteraturstudie genomfördes även med målsättning att undersöka hur arbetsuppgifter inom kundsupport kan automatiseras genom införandet av en chatbot, samt vilka funktioner som bör prioriteras av ledningen inför en sådan implementation. Resultaten av studien visade att en data-driven approach var att föredra, där funktionaliteten bestämdes av användarnas och organisationens specifika behov. Tre funktioner var dock tillräckligt generella för att presenteras personligheten av chatboten, dess trovärdighet och i vilket steg av värdekedjan den implementeras.

Machine learning models as tools for predicting time series have in recent years proven to perform exceptionally well. With financial time series in the form of stock indices being inherently complex and subject to noise and volatility, the prediction of stock market movements has proven to be especially difficult throughout extensive research. The objective of this study is to thoroughly analyze the LSTM architecture for neural networks and its performance when applied to the S&amp;P 500 stock index. The main research question revolves around quantifying the impact of varying the number of time steps in the LSTM model on predictive performance when applied to the S&amp;P 500 index. The data used in the model is of high reliability downloaded from the Bloomberg Terminal, where the closing price has been used as feature in the model. Other constituents of the model have been based in previous research, where satisfactory results have been reached. The results indicate that among the evaluated time steps, ten steps provided the superior performance. However, the impact of varying time steps is not all too significant for the overall performance of the model. Finally, the implications of the results for the field of research present themselves as good basis for future research, where parameters are varied and fine-tuned in pursuit of optimal performance. / Maskininlärningsmodeller som redskap för att förutspå tidsserier har de senaste åren visat sig prestera exceptionellt bra. Vad gäller finansiella tidsserier i formen av aktieindex, som har en inneboende komplexitet, och är föremål för störningar och volatilitet, har förutsägelse av aktiemarknadsrörelser visat sig vara särskilt svårt igenom omfattande forskning. Målet med denna studie är att grundligt undersöka LSTM-arkitekturen för neurala nätverk och dess prestanda när den appliceras på aktieindexet S&amp;P 500. Huvudfrågan kretsar kring att kvantifiera inverkan som varierande av antal tidssteg i LTSM-modellen har på prediktivprestanda när den appliceras på aktieindexet S&amp;P 500. Data som använts i modellen är av hög pålitlighet, nedladdad frånBloomberg-terminalen, där stängningskurs har använts som feature i modellen. Andra beståndsdelar av modellen har baserats i tidigare forskning, där tillfredsställande resultat har uppnåtts. Resultaten indikerar att bland de testade tidsstegen så producerartio tidssteg bäst resultat. Dock verkar inte påverkan av antalet tidssteg vara särskilt signifikant för modellens övergripandeprestanda. Slutligen så presenterar sig implikationerna av resultaten för forskningsområdet som god grund för framtida forskning, där parametrar kan varieras och finjusteras i strävan efter optimal prestanda.

With more aircraft in the air than ever before, there is a need for automating the surveillance of the airspace. It is widely known that aircraft with different intentions fly in different flight patterns. Support systems for finding different flight patterns are therefore needed. In this thesis, we investigate the possibility of detecting circular flight patterns using deep learning models. The basis for detection is ADS-B data which is continuously transmitted by aircraft containing information related to the aircraft status. Two deep learning models are constructed to solve the binary classification problem of detecting circular flight patterns. The first model is a Long Short-Term Memory (LSTM) model and utilizes techniques such as sliding window and bidirectional LSTM layers to solve the given task. The second model is a Convolutional Neural Network (CNN) and utilizes transfer learning. For the CNN model, the trajectory data is converted into image representations which are fed into a pre-trained model with a custom final dense layer. While ADS-B is openly available, finding specific flight patterns and producing a labeled data set of that pattern is hard and time-consuming. The data set is therefore expanded using other sources of data. Two additional sources of trajectory data are added to the data set; radar and simulated data. Training a model on data of a different distribution than the model is being evaluated on can be problematic and introduces a new source of error known as training-validation mismatch. One of the main goals of this thesis is to be able to quantify the size of this error to decide if using data from other sources is a viable option. The results show that the CNN model outperforms the LSTM model and achieves an accuracy of 98.2%. The results also show that there is a cost, in terms of accuracy, associated with not only training on ADS-B data. For the CNN model that cost was a 1-4% loss in accuracy depending on the training data used. The corresponding cost for the LSTM model was 2-10%.

The previous research available to predict travel speed is wide and has been extensively studied. What currently is missing from the previous work is to estimate the travel speed when different non-recurrent events occur, such as car accidents and road maintenance work. This research implements a machine learning model to predict the average speed on a road segment with and without road accidents. The model would assist in (1) planning the most efficient route which could reduce CO2 emissions and travel time (2) the drivers in traffic could get an estimate of when the traffic will open up again (3) the authorities could take safety measures if drivers are expected to be stuck for too long. In our work, we conducted a review to determine some of the optimal machine learning models to predict on time series data. What we found by comparing GRU (Gated Recurrent Unit) and LSTM (Long Short Term Memory) on travel speed data over a road in Sweden provided by the Swedish Transport Administration, is that there is no major difference in performance between the LSTM and GRU algorithms to predict the average travel speed. We also study the impact of using weather, date and accident related parameters on the model’s predictions. What we found is that we obtained much better results when including the weather data. Furthermore, the inclusion of road events vaguely hints that it could improve performance, but can not be verified due to the low number of road accidents in our dataset.

<p>High-throughput phenotyping has emerged as a powerful approach to expedite crop breeding programs. Modern remote sensing systems, including manned aircraft, unmanned aerial vehicles (UAVs), and terrestrial platforms equipped with multiple sensors, such as RGB cameras, multispectral, hyperspectral, and infrared thermal sensors, as well as light detection and ranging (LiDAR) scanners are now widely used technologies in advancing high throughput phenotyping. These systems can collect high spatial, spectral, and temporal resolution data on various phenotypic traits, such as plant height, canopy cover, and leaf area. Enhancing the capability of utilizing such remote sensing data for automated phenotyping is crucial in advancing crop breeding. This dissertation focuses on developing deep learning and transfer learning methodologies for crop phenotyping using multi-modality remote sensing and environmental data. The techniques address two main areas: multi-temporal/across-field biomass prediction and multi-scale remote sensing data fusion.</p> <p><br></p> <p>Biomass is a plant characteristic that strongly correlates with biofuel production, but is also influenced by genetic and environmental factors. Previous studies have shown that deep learning-based models are effective in predicting end-of-season biomass for a single year and field. This dissertation includes development of transfer learning methodologies for multiyear,</p> <p>across-field biomass prediction. Feature importance analysis was performed to identify and remove redundant features. The proposed model can incorporate high-dimensional genetic marker data, along with other features representing phenotypic information, environmental conditions, or management practices. It can also predict end-of-season biomass using mid-season remote sensing and environmental data to provide early rankings. The framework was evaluated using experimental trials conducted from 2017 to 2021 at the Agronomy Center for Research and Education (ACRE) at Purdue University. The proposed transfer learning techniques effectively selected the most informative training samples in the target domain, resulting in significant improvements in end-of-season yield prediction and ranking. Furthermore, the importance of input remote sensing features was assessed at different growth stages.</p> <p><br></p> <p>Remote sensing technology enables multi-scale, multi-temporal data acquisition. However, to fully exploit the potential of the acquired data, data fusion techniques that leverage the strengths of different sensors and platforms are necessary. In this dissertation, a generative adversarial network (GAN) based multiscale RGB-guided model and domain adaptation framework were developed to enhance the spatial resolution of multispectral images. The model was trained on limited high spatial resolution images from a wheel-based platform and then applied to low spatial resolution images acquired by UAV and airborne platforms.</p> <p>The strategy was tested in two distinct scenarios, sorghum plant breeding, and urban areas, to evaluate its effectiveness.</p>

Automatically detecting anomalies in text is of great interest for surveillance entities as vast amounts of data can be analysed to find suspicious activity. In this thesis, three distinct machine learning algorithms are evaluated as a chat message classifier is being implemented for the purpose of market surveillance. Naive Bayes and Support Vector Machine belong to the statistical class of machine learning algorithms being evaluated in this thesis and both require feature selection, a side objective of the thesis is thus to find a suitable feature selection technique to ensure mentioned algorithms achieve high performance. Long Short-Term Memory network is the deep learning algorithm being evaluated in the thesis, rather than depend on feature selection, the deep neural network will be evaluated as it is trained using word embeddings. Each of the algorithms achieved high performance but the findings ofthe thesis suggest Naive Bayes algorithm in conjunction with a feature counting feature selection technique is the most suitable choice for this particular learning problem. / Att automatiskt kunna upptäcka anomalier i text har stora implikationer för företag och myndigheter som övervakar olika sorters kommunikation. I detta examensarbete utvärderas tre olika maskininlärningsalgoritmer för chattmeddelandeklassifikation i ett marknadsövervakningsystem. Naive Bayes och Support Vector Machine tillhör båda den statistiska klassen av maskininlärningsalgoritmer som utvärderas i studien och bådar kräver selektion av vilka särdrag i texten som ska användas i algoritmen. Ett sekundärt mål med studien är således att hitta en passande selektionsteknik för att de statistiska algoritmerna ska prestera så bra som möjligt. Long Short-Term Memory Network är djupinlärningsalgoritmen som utvärderas i studien. Istället för att använda en selektionsteknik kommer djupinlärningsalgoritmen nyttja ordvektorer för att representera text. Resultaten visar att alla utvärderade algoritmer kan nå hög prestanda för ändamålet, i synnerhet Naive Bayes tillsammans med termfrekvensselektion.