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. / The full-text of this article will be released for public view at the end of the publisher embargo on 27 Dec 2024.

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.

This report details the design of a garbage collection (GC) module, which introduces modern GC features to the domain of embedded implementations. The described design supports weak references and feeds reference queues. Its architecture allows multiple concurrent application cores operating as mutators on the shared memory managed by the GC module. The garbage collection is exact and fully concurrent so as to enable the uninterrupted computational progress of the mutators. It combines a distributed root marking with a centralized heap scan of the managed memory. It features a novel mark-and-copy GC strategy on a segmented memory, which thereby overcomes both the tremendous space overhead of two-space copying and the compaction race of mark-and-compact approaches. The proposed GC architecture has been practically implemented and proven using the embedded bytecode processor SHAP as a sample testbed. The synthesis results for settings up to three SHAP mutator cores are given and online functional measurements are presented. Basic performance dependencies on the system configuration are evaluated.

This thesis consists of the research on linkage-based fingertips for prosthetic hands. These fingertips consists of small polycentric mechanisms attached to what would be the pulp in normal anatomical fingers. These mechanisms allow the prosthetic hand to conform to the shape of objects during grasp. The goal of these prosthetic fingertips is to maximize the functionality of the hand while minimizing the number of inputs that the user has to control. The stability of the fingertip mechanisms is analyzed using the principle of virtual work. From this analysis we are able to show that the fingertip mechanism is stable for a large range of rotation of the link and for a large range of directions on which the force is applied, and that the mechanism is indifferent to the magnitude of the force applied to it (assuming that the force does not damage/deform the mechanism). To assess if the four-bar mechanisms (fingertips) improve the grasping capabilities in robotics and prosthetics, tests were performed on prosthetic hands and robot grippers with and without the fingertips. Comparisons were made using the Southampton Hand Assessment Procedure (SHAP) protocol, which tests the differences and measures the functionality of particular types of grasp, such as power, spherical, lateral, tripod, tip and extension. In the human testing, the overall Index of Functionality (IOF) of the Hosmer hook is 66.65 and 66.21 for the hook with the fingertips. The hook with the fingertips had a better IOF in the spherical and power prehensile pattern. When the IOF is calculated for the tasks that the fingertips were used, in 10 of 11 of the tasks, the IOF is higher than using the Hosmer hook. In the robotic gripper testing, the Index of Functionality was not be calculated because the time to perform the tasks depended more on the robotic control system than on the physical characteristics of the gripper.

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.