This report presents the SHAP platform consisting of its microarchitecture and its implementation of the Java Virtual Machine (JVM). Like quite a few other embedded implementations of the Java platform, the SHAP microarchitecture relies on an instruction set architecture based on Java bytecode. Unlike them, it, however, features a design with well-encapsulated components autonomously managing their duties on rather high abstraction levels. Thus, permanent runtime duties are transferred from the central computing core to concurrently working components so that it can actually spent a larger fraction of time executing application code. The degree of parallelity between the application and the runtime implementation is increased. Currently, the stack and heap management including the automatic garbage collection are implemented this way. After detailing the design of the microarchitecture, the SHAP implementation of the Java Virtual Machine is described. A major focus is laid on the presentation of the layout and the use of the runtime data structures representing the various language abstractions provided by Java. Also, the boot sequence starting the JVM is described.

Abstract This paper introduces a new embedded Java multi-core architecture which shows a significantly better performance for a large number of cores than the related projects JopCMP and jamuth IP multi-core. The cores gain fast access to the shared heap by a fullduplex bus with pipelined transactions. Each core is equipped with local on-chip memory for the Java operand stack and the method cache to further reduce the memory bandwidth requirements. As opposed to the related projects, synchronization is supported on a per object-basis instead of a single lock. Load balancing is implemented in Java and requires no additional hardware. The multi-port memory manager includes an exact and fully concurrent garbage collector for automatic memory management. The design can be synthesized for a variable number of parallel cores and shows a linear increase in chip-space. Three different benchmarks demonstrate the very good scalability of our architecture. Due to limited chip-space on our evaluation platform, the core count could not be increased further than 8. But, we expect a smooth performance decrease.

Accurate forecasts are vital in multiple areas of economic, scientific, commercial, and industrial activity. There are few previous studies on using forecasting methods for predicting serious events. This thesis set out to investigate two things, firstly whether machine learning models could be applied to the objective of forecasting serious events. Secondly, if the models could be made interpretable. Given these objectives, the approach was to formulate two forecasting tasks for the models and then use the Python framework SHAP to make them interpretable. The first task was to predict if a serious event will happen in the coming eight hours. The second task was to forecast how many serious events that will happen in the coming six hours. GBDT and LSTM models were implemented, evaluated, and compared on both tasks. Given the problem complexity of forecasting, the results match those of previous related research. On the classification task, the best performing model achieved an accuracy of 71.6%, and on the regression task, it missed by less than 1 on average. / Exakta prognoser är viktiga inom flera områden av ekonomisk, vetenskaplig, kommersiell och industriell verksamhet. Det finns få tidigare studier där man använt prognosmetoder för att förutsäga allvarliga händelser. Denna avhandling syftar till att undersöka två saker, för det första om maskininlärningsmodeller kan användas för att förutse allvarliga händelser. För det andra, om modellerna kunde göras tolkbara. Med tanke på dessa mål var metoden att formulera två prognosuppgifter för modellerna och sedan använda Python-ramverket SHAP för att göra dem tolkbara. Den första uppgiften var att förutsäga om en allvarlig händelse kommer att ske under de kommande åtta timmarna. Den andra uppgiften var att förutse hur många allvarliga händelser som kommer att hända under de kommande sex timmarna. GBDT- och LSTM-modeller implementerades, utvärderades och jämfördes för båda uppgifterna. Med tanke på problemkomplexiteten i att förutspå framtiden matchar resultaten de från tidigare relaterad forskning. På klassificeringsuppgiften uppnådde den bäst presterande modellen en träffsäkerhet på 71,6%, och på regressionsuppgiften missade den i genomsnitt med mindre än 1 i antal förutspådda allvarliga händelser.

Yes / Reviews and ratings of consumers towards a product impact consumer decision-making and their perceptions. Such information is key in measuring consumer satisfaction and net promoter scores. However, when the reviewed products are refurbished, consumer reviews become more important because information influences consumer behaviour and attitude toward looped products. This research explores the decision-influencing attributes of consumers while purchasing refurbished goods using quantitative and qualitative methods. Online after-sales 1986 laptop customers’ review and rating data in the public domain were analysed to reveal the decision-influencing attributes and their impact on potential consumers. The study envisions assisting the operations of sellers in the refurbished market by strengthening their businesses' value proposition and stimulating reverse logistics entrepreneurs to use the opportunity. Review data containing lifecycle valuation of old laptops induced feature extraction by machine learning applications. It is beneficial to sellers in the refurbished product segment. It provides information to strengthen their value proposition and is informative to entrepreneurs wanting to enter the segment. Based on the text analysis of consumer reviews, the study's results show that price, brand, design, performance, services, and utility influence consumers. The frequency analysis technique was used to extract attributes, followed by content analysis and feature selection using SHapley Additive exPlanations (SHAP) for exploring correlations between features and star ratings. Lastly, multinomial logistic regression was used to validate the generated model. The results show that brand, design, price, and utility are the most prominent attributes influencing consumers' decision-making with positive sentiments. In contrast, performance and services often generate neutral and negative sentiments.

This report presents the SHAP platform consisting of its microarchitecture and its implementation of the Java Virtual Machine (JVM). Like quite a few other embedded implementations of the Java platform, the SHAP microarchitecture relies on an instruction set architecture based on Java bytecode. Unlike them, it, however, features a design with well-encapsulated components autonomously managing their duties on rather high abstraction levels. Thus, permanent runtime duties are transferred from the central computing core to concurrently working components so that it can actually spent a larger fraction of time executing application code. The degree of parallelity between the application and the runtime implementation is increased. Currently, the stack and heap management including the automatic garbage collection are implemented this way. After detailing the design of the microarchitecture, the SHAP implementation of the Java Virtual Machine is described. A major focus is laid on the presentation of the layout and the use of the runtime data structures representing the various language abstractions provided by Java. Also, the boot sequence starting the JVM is described.

The increasing complexity of Artificial Intelligence (AI) models is accompanied by an increase in difficulty in interpreting model predictions. This thesis work provides insights and understanding of the differences and similarities between explainability methods for AI models. Opening up black-box models is important, especially if AI is applied in sensitive domains such as to, e.g., aid medical professionals. In recent years, the use of Transformer-based artificial neural network architectures such as Bidirectional Encoder Representations from Transformers (BERT) has become common in the field of Natural Language Processing (NLP), showing human-level performance on tasks such as sentiment classification and question answering. In addition, a growing portion of research within eXplainable AI (XAI) has shown success in using explainability methods to output auxiliary explanations at inference time together with predictions made by these complex models. When scoping the different methods, there is a distinction to be made whether the explanations emerge as part of the prediction process or subsequently via a separate model. These two categories of explainability methods are referred to as self-explaining and post-hoc, respectively. The goal of this work is to evaluate, analyze and compare these two categories of methods for assisting BERT models with explanations in the context of sentiment classification. A comparative analysis was therefore conducted in order to investigate quantitative and qualitative differences. To measure the quality of explanations, the Intersection Over Union (IOU) and Precision-Recall Area Under the Curve (PR-AUC) scores were used together with Explainable NLP (ExNLP) datasets, containing human annotated explanations. Apart from discussing benefits, drawbacks and assumptions of the different methods, results of the work indicated that the self-explaining method proved more successful in some instances while the post-hoc method performed better in others. Given the subjective nature of explanation quality, however, this work should be extended in several proposed directions, in order to fully capture the nuances of the explainability methods. / Parallellt med den ökande komplexiteten hos modeller med artificiell intelligens (AI) följer en ökad svårighet att tolka förutsägelser som modellerna gör. Detta examensarbete fokuserar på skillnader och likheter mellan förklaringsmetoder för AI-modeller. Att skapa mer transparens kring modellerna är viktigt, speciellt om AI ska appliceras i känsliga områden som t.ex. inom hälso- och sjukvård. Under de senaste åren har användningen av Transformer-baserade artificiella neurala nätverk som Bidirectional Encoder Representations from Transformers (BERT) blivit vanligt inom Natural Language Processing (NLP). Resultaten som modellerna når på uppgifter såsom sentimentklassificering och svar på frågor är på en mänsklig nivå. En växande del av forskningen inom eXplainable AI (XAI) har dessutom kunnat visa stora framsteg inom användandet av förklaringsmetoder, för att bistå förutsägelserna som dessa komplexa modeller gör med förklaringar. I kategoriseringar av metoderna särskiljs det ofta mellan huruvida förklaringarna uppstår som en del av förutsägelsen, tillsammans med modellen eller om de skapas efteråt via en separat modell. Dessa två kategorier av förklaringsmetoder kallas självförklarande och post-hoc. Målet med detta arbete är att utvärdera, analysera och jämföra dessa två kategorier av metoder som används för att hjälpa BERT-modeller med förklaringar i samband med sentimentklassificering av text. En jämförande analys genomfördes därför för att undersöka kvantitativa och kvalitativa skillnader. För att mäta kvaliteten på förklaringar användes Intersection Over Union (IOU) och Precision-Recall Area Under the Curve (PR-AUC) tillsammans med dataset skräddarsydda för just Explainable NLP (ExNLP) innehållande mänskligt annoterade förklaringar. Förutom att diskutera fördelar, nackdelar och antaganden med de olika metoderna, pekade resultaten på att den självförklarande metoden presterade bättre i vissa fall medan post-hoc-metoden presterade bättre i andra. Med tanke på hur kvaliteten av förklaringar till stor del handlar om en subjektiv bedömning bör dock detta arbete utvidgas i flera riktningar – föreslagna i detta arbete – för att fånga alla nyanser av förklaringsmetoderna.

The overprescription of antibiotics has resulted in bacteria resistance, which is considered a global threat to global health. Deciding if antibiotics should be prescribed or not from individual visits of patients’ medical records in Swedish can be considered a text classification task, one of the applications of Natural Language Processing (NLP). However, medical experts and patients can not trust a model if explanations for its decision are not provided. In this work, multilingual and monolingual Transformer models are evaluated for the medical classification task. Furthermore, local explanations are obtained with SHapley Additive exPlanations and Integrated Gradients to compare the models’ predictions and evaluate the explainability methods. Finally, the local explanations are also aggregated to obtain global explanations and understand the features that contributed the most to the prediction of each class. / Felaktig utskrivning av antibiotika har resulterat i ökad antibiotikaresistens, vilket anses vara ett globalt hot mot global hälsa. Att avgöra om antibiotika ska ordineras eller inte från patientjournaler på svenska kan betraktas som ett textklassificeringproblem, en av tillämpningarna av Natural Language Processing (NLP). Men medicinska experter och patienter kan inte lita på en modell om förklaringar till modellens beslut inte ges. I detta arbete utvärderades flerspråkiga och enspråkiga Transformersmodeller för medisinska textklassificeringproblemet. Dessutom erhölls lokala förklaringar med SHapley Additive exPlanations och Integrated gradients för att jämföra modellernas förutsägelser och utvärdera metodernas förklarbarhet. Slutligen aggregerades de lokala förklaringarna för att få globala förklaringar och förstå de ord som bidrog mest till modellens förutsägelse för varje klass.

[pt] Somente no século XXI, o mundo enfrentou os impactos devastadores de três doenças respiratórias agudas: a Síndrome Respiratória do Oriente Médio(MERS), a Síndrome Respiratória Aguda Grave (SARS) e a COVID-19, que evoluiu para uma pandemia. Essas doenças não apenas causaram um grande número de mortes, mas também prejudicaram a economia das regiões afetadas. Em particular, os países da região da América Latina e Caribe (LAC)enfrentaram desafios adicionais, devido a maiores desigualdades sociais, acesso limitado a serviços de saúde e condições de vida precárias. Portanto, é imperativo compreender os efeitos das ações de mitigação para orientar as ações no sentido de mitigar os impactos sanitários e socioeconômicos, se (ou quando)surgirem novas doenças respiratórias agudas, especialmente nestes países. Foi realizado um estudo retrospectivo para modelar a dinâmica da variação da mortalidade por COVID-19 em países da LAC e analisar sua associação com estratégias de vacinação, medidas de contenção, restrições de mobilidade e fatores socioeconômicos. A metodologia do estudo aplicou técnicas de clustering que revelaram dois agrupamentos distintos com base em características socio-demográficas, seguidos pela aplicação do XGBoost para modelar a dinâmica de variação de mortes nos países de cada cluster, ao longo do tempo. Por fim, foi aplicada a técnica de SHAP Values para compreender as associações entre mortalidade e fatores como vacinação, medidas de contenção e restrições de mobilidade. Além disso, foi realizado um painel com especialistas para avaliar a relevância e efetividade dos resultados encontrados. O estudo fornece evidências de que o suporte econômico e a conclusão do esquema de vacinação foram especialmente relevantes para reduzir a mortalidade por COVID-19.Foi possível detectar dois grupos distintos de países, onde um grupo pode ter características de maior vulnerabilidade do que o outro grupo. As intervenções mais importantes para entender a mortalidade por COVID-19 variaram em dois períodos distintos da pandemia: pré-vacinação e pós-vacinação. No período pré-vacinação, as medidas de contenção foram as intervenções mais importantes para a mortalidade nos países menos vulneráveis, enquanto para os países mais vulneráveis, foram as variações na mobilidade populacional. No período pós-vacinação, a cobertura vacinal foi a intervenção mais importante para a mortalidade nos países menos vulneráveis, enquanto os países mais vulneráveis foram mais impactados pelas medidas de contenção. / [en] In the 21st century alone, the world has faced the devastating impacts of three acute respiratory diseases: Middle East Respiratory Syndrome (MERS), Severe Acute Respiratory Syndrome (SARS), and COVID-19, which evolved into a pandemic. These diseases have not only caused a large number of deaths but have also damaged the economies of the affected regions. In particular, countries in the Latin American and Caribbean (LAC) region have faced additional challenges due to greater social inequalities, limited access to health services, and precarious living conditions. Therefore, it is imperative to understand the effects of mitigation actions to guide actions to mitigate the health and socioeconomic impacts if (or when) new acute respiratory diseases emerge, especially in these countries. A retrospective study was conducted to model the dynamics of variation in COVID-19 mortality in LAC countries and analyze its association with vaccination strategies, containment measures, mobility restrictions, and socioeconomic factors. The study methodology applied clustering techniques that revealed two distinct clusters based on sociodemographic characteristics, followed by the application of XGBoost to model the dynamics of variation in deaths in the countries of each cluster, over time. Finally, the SHAP Values technique was applied to understand the associations between mortality and factors such as vaccination, containment measures and mobility restrictions. In addition, a panel of experts was held to assess the relevance and effectiveness of the results found. The study provides evidence that economic support and the completion of the vaccination scheme were especially relevant in reducing COVID-19 mortality. It was possible to detect two distinct groups of countries, where one group may have characteristics of greater vulnerability than the other group. The most important interventions for understanding COVID-19 mortality varied in two distinct periods of the pandemic: pre-vaccination and post-vaccination. In the pre-vaccination period, containment measures were the most important interventions for mortality in the least vulnerable countries, while for the most vulnerable countries, they were variations in population mobility. In the post-vaccination period, vaccination coverage was the most important intervention for mortality in the least vulnerable countries, while the most vulnerable countries were more impacted by containment measures.

Denna undersökning utvärderar tillvägagångssätt inom "Explainable Artificial Intelligence" (XAI), särskilt "Local Interpretable Model Agnostic Explanations" (LIME) och 'Shapley Additive Explanations' (SHAP), genom att implementera dem i maskininlärningsmodeller som används inom cybersäkerhetens brandväggssystem. Prioriteten är att förbättra förståelsen av flervals klassificerings uppgift inom brandvägg hantering. I takt med att dagens AI-system utvecklas, sprids och tar en större roll i kritiska beslutsprocesser, blir transparens och förståelighet alltmer avgörande. Denna studie demonstrerar genom detaljerad analys och metodisk experimentell utvärdering hur SHAP och LIME belyser effekten av olika egenskaper på modellens prognoser, vilket i sin tur ökar tilliten till beslut som drivs av AI. Resultaten visar, hur funktioner såsom "Elapsed Time (sec)”, ”Network Address Translation” (NAT) källa och "Destination ports" ansenlig påverkar modellens resultat, vilket demonstreras genom analys av SHAP-värden. Dessutom erbjuder LIME detaljerade insikter i den lokala beslutsprocessen, vilket förbättrar vår förståelse av modellens beteende på individuell nivå. Studiet betonar betydelsen av XAI för att minska klyftan mellan AI operativa mekanismer och användarens förståelse, vilket är avgörande för felsökning samt för att säkerställa rättvisa, ansvar och etisk integritet i AI-implementeringar. Detta gör studiens implikationer betydande, då den ger en grund för framtida forskning om transparens i AI-system inom olika sektorer. / This study evaluates the explainable artificial intelligence (XAI) methods, specifically Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), by applying them to machine learning models used in cybersecurity firewall systems and focusing on multi-class classification tasks within firewall management to improve their interpretability. As today's AI systems become more advanced, widespread, and involved in critical decision-making, transparency and interpretability have become essential. Through accurate analysis and systematic experimental evaluation, this study illustrates how SHAP and LIME clarify the impact of various features on model predictions, thereby leading to trust in AI-driven decisions. The results indicate that features such as Elapsed Time (sec), Network Address Translation (NAT) source, and Destination ports markedly affect model outcomes, as demonstrated by SHAP value analysis. Additionally, LIME offers detailed insights into the local decision making process, enhancing our understanding of model behavior at the individual level. The research underlines the importance of XAI in reducing the gap between AI operational mechanisms and user understanding, which is critical for debugging, and ensuring fairness, responsibility, and ethical integrity in AI implementations. This makes the implications of this study substantial, providing a basis for future research into the transparency of AI systems across different sectors.

Для решения проблемы низкой точности, слабой адаптивности и плохой интерпретируемости существующих моделей прогнозирования опасности схода грязевых потоков предлагается новый метод прогнозирования. В качестве примера рассматриваются 159 точек бедствий в бассейне реки Нуцзян в Китае. Выбраны 15 факторов влияния, и с использованием метода комбинированного взвешивания тремя сторонами проводится оценка опасности точек риска схода грязевых потоков. Затем для прогнозирования опасности схода грязевых потоков используется модель CNN-BiGRU-Attention. Для оптимизации гиперпараметров применяется улучшенный алгоритм KOA (IKOA). В конечном итоге для повышения интерпретируемости результатов прогнозирования модели введена рамка SHAP. Результаты показывают, что по сравнению с 13 текущими наиболее часто используемыми моделями прогнозирования, модель IKOA-CNN-BiGRU-Attention демонстрирует наилучшие результаты прогнозирования. / To address the issues of low accuracy, poor adaptability, and weak interpretability in existing models for predicting debris flow hazards, a new prediction method is proposed. Using 159 disaster points in the Nujiang River Basin in China as a case study, 15 influencing factors are selected, and a tripartite combined weighting method is used to evaluate the risk levels of debris flow points. Subsequently, the CNN-BiGRU-Attention model is used to predict the hazard of debris flows. The improved KOA algorithm (IKOA) is employed for hyperparameter optimization. Finally, the SHAP framework is introduced to enhance the interpretability of the model's prediction results. The results show that compared to the 13 currently commonly used prediction models, the IKOA-CNN-BiGRU-Attention model exhibits the best predictive performance.