Natural health products (NHPs) are attractive due to the public’s perception that they are natural and safe but there is wide variety of risks associated with these products. Post-market surveillance is the key to control hazards produced from NHPs. A set of activities are involved in post-market surveillance designed to assure the safety, efficacy and quality of products after being launched into the market. Although post-market surveillance is an efficient tool to preserve the safety of users from adverse reactions of NHPs but there are various challenges associated with performing post-market surveillance specifically for NHPs. This research project is focused on defining a framework for performing post-market surveillance for NHPs and on identifying best practices in its application. An international comparative analysis was undertaken to formulate best practices by reviewing existing frameworks for post-market surveillance of NHPs in Australia, Germany, New Zealand, United Kingdom and United States. Evidence-based best practices are compared with the Canadian post-market surveillance framework to identify key gaps in the Canadian system. Recommendations are provided for bridging each gap, and making the Canadian NHPs surveillance system, strong according to the international standards of best practices.

Natural health products (NHPs) are attractive due to the public’s perception that they are natural and safe but there is wide variety of risks associated with these products. Post-market surveillance is the key to control hazards produced from NHPs. A set of activities are involved in post-market surveillance designed to assure the safety, efficacy and quality of products after being launched into the market. Although post-market surveillance is an efficient tool to preserve the safety of users from adverse reactions of NHPs but there are various challenges associated with performing post-market surveillance specifically for NHPs. This research project is focused on defining a framework for performing post-market surveillance for NHPs and on identifying best practices in its application. An international comparative analysis was undertaken to formulate best practices by reviewing existing frameworks for post-market surveillance of NHPs in Australia, Germany, New Zealand, United Kingdom and United States. Evidence-based best practices are compared with the Canadian post-market surveillance framework to identify key gaps in the Canadian system. Recommendations are provided for bridging each gap, and making the Canadian NHPs surveillance system, strong according to the international standards of best practices.

Enterprise systems are built for companies and used by the employees to complete work tasks. Focus on userdriven designs for consumer technology has led to expectations of user-friendly designs. Enterprise technology tends, however, to be more technology-driven rather than user-driven, creating unmatched expectations and mismatch between end-user and company objectives. This is why it is necessary to also consider enterprise systems from a user-driven perspective. Therefore, this study addresses user-driven enterprise designs through the Implicit Interaction Framework using a market surveillance system (MSS) as a case study. Practical design implementations and insights were gained through Research through Design (RtD), which were obtained from a survey to validate potential problems, mapping activities using the framework to gain design insights, and prototyped wireframes expressed through narrative video scenarios and evaluated with UX professionals to identify design directions. Three design directions were identified: Recall: Actions for Reminding, Collaboration: Anticipation of Intention, and Disruption: Supporting Ongoing State-Shifting. Control comes at the cost of disruption or risking wrongful actions, context of implicitness creates a trade-off between cognitive load and risk of errors, and lastly UX professionals might have to balance competing objectives in a situation where they collide. Furthermore, the Implicit Interaction Framework can guide enterprise UX designers and researchers to understand the interplay and interactions occurring between system and end-user. However, it is a translation where the complexity of enterprise systems is in some respects difficult to demonstrate, where better end-user experiences through implicit interactions should not be assumed. / Företagssystem är byggda för företag och används av de anställda för att slutföra arbetsuppgifter. Fokus på användardriven design inom konsumentteknik har lett till förväntningar på användarvänliga designer. Företagssystem tenderar dock att vara mer teknologidriven snarare än användardriven, vilket skapar oöverträffade förväntningar och oöverensstämmelse mellan slutanvändarnas och företagets mål. Det är därför nödvändigt att också betrakta företagssystem från ett användardrivet perspektiv. Därför behandlar den här studien användardrivna företagsdesigner genom ramverket ”Implicit Interaction Framework” där ett marknadsövervakningssystem ”market surveillance system” (MSS) används som fallstudie. Praktiska designimplementeringar och insikter nåddes genom Research through Design (RtD), som erhölls från en enkät för att validera potentiella problem, kartläggningsaktiviteter för att få designinsikter, och prototyper framhävda genom videoscenarier med berättarröst och som utvärderas med UX-yrkesverksamma personer för att identifiera designriktningar. Tre designriktningar identifierades: Komma ihåg: Åtgärder för att Påminna, Samverkan: Förväntan på Avsikt, och Avbrott: Stöd för Pågående Tillståndsändring. Kontroll har sitt pris genom avbrott eller risk för felaktiga handlingar, sammanhanget för implicititet skapar en avvägning mellan kognitiv belastning och risk för fel, och slutligen UX-yrkesverksamma kan behöva balansera konkurrerande mål i en situation där de kolliderar. Dessutom kan Implicit Interaction Framework vägleda UX-designers och forskare för att förstå samspelet och interaktionerna mellan system och slutanvändare. Det är dock en översättning där komplexiteten i företagssystem i vissa avseenden är svår att demonstrera, där bättre slutanvändarupplevelser genom implicita interaktioner inte bör antas.

Financial markets are now undergoing exponential growth in data, as high-frequency trading is widespread. The need for effective market surveillance is, therefore, become more prominent. Domain experts in exchanges, trading participants, and regulators must provide evidence in their market surveillance investigation. Still, the increased number of participants and its transaction leads to a complicated task that needs to be analyzed more resource-efficient. One way of performing market surveillance is through an at-a- glance view, which can systematically and timely handle this data. Dashboards are today the widely adopted tool for processing large amounts of data in the financial sector. This study seeks to enhance the user experience of a market surveillance system developed with information visualization of participants’ statistical measures. The research was carried out in an industrial setting and followed the case study paradigm. The user research produced a list of expected tasks, translating into design requirements by reflecting on related research on effective dashboard design for interactive high-dimensional data exploration. The design requirements formed the design elements embedded into the low- and high-fidelity prototypes development. During prototype development, the participants’ statistical measures shown as the predefined dimensions on the dashboard were selected using feature selection methods correlate to their number of alerts. User evaluation of the final high-fidelity prototype suggests that interactive high-dimensional data exploration using parallel coordinates plots could improve the market surveillance process. The gap of effectiveness and efficiency scores between first-time users and experts and the feedback from both users show a steep learning curve in visual exploration. / Finansmarknaderna genomgår nu en exponentiell tillväxt i data, eftersom högfrekvent handel ar utbredd. Behovet av effektiv marknadsövervakning har därför blivit mer framträdande. Domänexperter inom utbyten, handelsdeltagare och tillsynsmyndigheter måste tillhandahålla bevis i sin marknadsövervakningsutredning. Anda leder det okade antalet deltagare och dess transaktion till en komplicerad uppgift som behöver analyseras mer resurseffektivt. Ett satt att utföra marknadsövervakning ar genom en översiktsverk som systematiskt och i tid kan hantera dessa uppgifter. Dashboards ar idag det allmänt använda verk tyget for att bearbeta stora mängder data inom finanssektorn. Denna studie syftar till att förbättra användarupplevelsen av ett marknadsövervakningssystem utvecklat med informationsvisualisering av deltagarnas statistiska matt. Forskningen utfördes i en industriell miljö och följde fallstudieparadigmet. Användarundersökningen producerade en lista över förväntade uppgifter som översattes till designkrav genom att reflektera över relaterad forskning om effektiv instrumentbrädesdesign for interaktiv högdimensionell datautforskning. Konstruktionskraven bildade designelementen inbäddade i utvecklingen av prototyper med lag och hög trohet. Under prototyputvecklingen valdes deltagarnas statistiska matt som visade som de fördefinierade dimensionerna på instrumentpanelen med hjälp av funktionsvalsmetoder som korrelerar med deras antal varningar. Användarutvärdering av den slutliga högtroh prototypen antyder att interaktiv högdimensionell data utforskning med parallella koordinatdiagram kan förbättra marknadsövervakningsprocessen. Gapet mellan effektivitets- och effektivitetsresultat mellan förstagångsanvändare och experter och feedback från bada an vandare visar en brant inlärningskurva i visuell utforskning.

Medical devices are used to diagnose, treat, or prevent a disease or abnormal physical condition without any chemical action in the body. They can also result in unintended incidents and other errors. This thesis was divided into three chapters: i) a systematic review on the recognition, reporting and resolution of incidents related to medical devices and other health technologies; ii) telephone interviews with physicians and registered nurses (RNs) to solicit information on the resolution, reporting and resolution of medical device-related incidents based on their professional experience; and iii) a case study to review the continuous quality improvement (CQI) data retrieved from the wireless smart infusion pump system at The Ottawa Hospital (TOH) and to propose a CQI data analysis process. The systematic review included 30 studies on factors that influence the recognition, reporting and resolution of incidents in hospitals and interventions to improve patient safety. Central themes that emerged for incident reporting were personal attitudes, awareness and perception of incident reporting systems, organizational culture, and feedback to healthcare professionals. In our telephone interviews, physicians and RNs attributed incident recognition to devices not operating based on the manufacturer’s instructions, and to the hospital staff’s knowledge of and professional experience with the use of the medical device, and clinical manifestations of patients. Suggestions to improve medical device safety surveillance centered on education and training to ensure that the staff is able to use the medical device properly and know what would be considered an error, and how to report these errors. The results of the systematic review and interviews helped to inform the design of a medical device surveillance framework in a hospital setting. Our case study assessed the Dose Error Reduction Software compliance and frequency of soft and hard limit alerts with wireless smart infusion pump systems over a one year period. A CQI data analysis process to monitor the performance of wireless smart infusion pumps is proposed. The findings of this doctoral thesis can contribute to the development of a medical device surveillance system that would help to improve health care delivery and patient safety in a health care institution.

Deep learning methods have the ability to accurately predict and interpret what data represents. However, the decision making of a deep learning model is not comprehensible for humans. This is a problem for sectors like market surveillance which needs clarity in the decision making of the used algorithms. This thesis aimed to investigate how a deep learning model can be constructed to make the decision making of the model humanly comprehensible, and to investigate the potential impact on classification performance. A literature study was performed and publicly available explanation methods were collected. The explanation methods LIME, SHAP, model distillation and SHAP TreeExplainer were implemented and evaluated on a ResNet trained on three different time-series datasets. A decision tree was used as the student model for model distillation, where it was trained with both soft and hard labels. A survey was conducted to evaluate if the explanation method could increase comprehensibility. The results were that all methods could improve comprehensibility for people with experience in machine learning. However, none of the methods could provide full comprehensibility and clarity of the decision making. The model distillation reduced the performance compared to the ResNet model and did not improve the performance of the student model. / Djupinlärningsmetoder har egenskapen att förutspå och tolka betydelsen av data. Däremot så är djupinlärningsmetoders beslut inte förståeliga för människor. Det är ett problem för sektorer som marknadsövervakning som behöver klarhet i beslutsprocessen för använda algoritmer. Målet för den här uppsatsen är att undersöka hur en djupinlärningsmodell kan bli konstruerad för att göra den begriplig för en människa, och att undersöka eventuella påverkan av klassificeringsprestandan. En litteraturstudie genomfördes och publikt tillgängliga förklaringsmetoder samlades. Förklaringsmetoderna LIME, SHAP, modelldestillering och SHAP TreeExplainer blev implementerade och utvärderade med en ResNet modell tränad med tre olika dataset. Ett beslutsträd användes som studentmodell för modelldestillering och den blev tränad på båda mjuka och hårda etiketter. En undersökning genomfördes för att utvärdera om förklaringsmodellerna kan förbättra förståelsen av modellens beslut. Resultatet var att alla metoder kan förbättra förståelsen för personer med förkunskaper inom maskininlärning. Däremot så kunde ingen av metoderna ge full förståelse och insyn på hur beslutsprocessen fungerade. Modelldestilleringen minskade prestandan jämfört med ResNet modellen och förbättrade inte prestandan för studentmodellen.

The increasing complexity of trading strategies, when combined with machine learning models, forces market surveillance corporations to develop increasingly sophisticated methods for recognizing potential misuse. One strategy is to employ traders’ weapons against themselves, namely machine learning. However, the data utilized in market surveillance is highly sensitive, what may be available for machine learning is limited. In this thesis, we examine how federated learning for time series data can be used to identify potential market abuse while maintaining client privacy and data security. We are interested in developing a time-series-specific neural network employing federated learning. We demonstrate that when this strategy is used, the performance of detecting potential market abuse is comparable to that of the standard data centralized approach. Specifically, a non-federated model, a federated model, and a federated model with extra data privacy and security protection are evaluated and compared. Each model utilize an LSTM autoencoder to identify market abuse. The results demonstrate that a federated model’s performance in detecting possible market abuse is comparable to that of a non-federated model. Moreover, a federated approach with extra data privacy and security experienced a slight performance loss but is still a competitive model in comparison to the other models. Although this approach results in increased privacy and security, there is a limit to how much privacy and security can be ensured, as excessive privacy led to extremely poor performance. Federated learning offers the ability to increase data privacy and security with little performance decrease. / Den ökande komplexiteten handelsstrategier, i kombination med maskininlärning modeller, tvingar marknadsövervakning företag att utveckla allt mer sofistikerade metoder för att identifiera potentiellt marknadsmissbruk. En strategi är att använda handlarnas vapen mot sig själva, nämligen maskininlärning. Däremot, data som används inom marknadsövervakning är mycket känslig och vad som kan finnas tillgängligt för maskininlärning är begränsat.I den här studien undersöker vi hur federerat lärande för tidsseriedata kan användas till att identifiera potentiellt marknadsmissbruk samtidigt som klienternas integritet och datasäkerhet bibehålls. Vi är intresserade av att utveckla ett tidsserie-specifikt neuralt nätverk med hjälp av federated inlärning. Vi visar att när denna strategi används är prestanda för att upptäcka potentiellt marknadsmissbruk jämförbart med det för den vanliga data-centraliserade metoden. Specifikt, en icke-federerad modell, en federerad modell och en federerad modell med extra dataintegritet och säkerhet utvärderas och jämförs. Varje modell använder en LSTM-Autoencoder för att identifiera marknadsmissbruk. Resultaten visar att en federerad modells prestanda när det gäller att upptäcka eventuellt marknadsmissbruk är jämförbar med en icke-federerad modell. Dessutom, ett federerat tillvägagångssätt med extra dataintegritet upplevde en liten prestandaförlust men är fortfarande en konkurrenskraftig modell i jämförelse med andra modeller. Även om detta tillvägagångssätt resulterar i ökad integritet och säkerhet, finns det en gräns för hur mycket som kan säkerställas. Federated learning möjliggör ökad datasekretess och säkerhet med liten prestandasänkning.

This master thesis explores the effectiveness of interpolating a larger generic speech recognition model with smaller domain-specific models to enable transcription of domain-specific conversations. The study uses a corpus within the financial domain collected from the web and processed by abstracting named entities such as financial instruments, numbers, as well as names of people and companies. By substituting each named entity with a tag representing the entity type in the domain-specific corpus, each named entity can be replaced during the hypothesis search by words added to the systems pronunciation dictionary. Thus making instruments and other domain-specific terms a matter of extension by configuration.  A proof-of-concept automatic speech recognition system with the ability to transcribe and extract named entities within the constantly changing domain of voice trading was created. The system achieved a 25.08 Word Error Rate and 0.9091 F1-score using stochastic and neural net based language models. The best configuration proved to be a combination of both stochastic and neural net based domain-specific models interpolated with a generic model. This shows that even though the models were trained using the same corpus, different models learned different aspects of the material. The study was deemed successful by the authors as the Word Error Rate was improved by model interpolation and all but one named entities were found in the test recordings by all configurations. By adjusting the amount of influence the domain-specific models had against the generic model, the results improved the transcription accuracy at the cost of named entity recognition, and vice versa. Ultimately, the choice of configuration depends on the business case and the importance of named entity recognition versus accurate transcriptions.

Machine Learning (ML) is the current trend that most industries opt for to improve their business and operations. ML has also been adopted in the financial markets, where well-funded financial institutions employ the latest ML algorithms to gain an advantage on the market. The darker side of ML is the potential emergence of complex algorithmic trading schemes that are abusive and manipulative. Because of this, it is inevitable that ML will be applied to financial market surveillance in order to detect these abusive and manipulative trading strategies. Ideally, an accurate ML detection model would be developed with data from many financial institutions or trading venues. However, such ML models require vast quantities of data, which poses a problem in market surveillance where data is sensitive or limited. Data sharing between companies or countries is typically accompanied by legal and privacy concerns. By training ML models on distributed datasets, Federated Learning (FL) overcomes these issues by eliminating the need to centralise sensitive data. This thesis aimed to address these ML related issues in market surveillance by implementing and evaluating a FL model. FL enables a group of independent data-holding clients with the same intention to build a shared ML model collaboratively without compromising private data. In this work, a ML model is initially deployed in a centralised data setting and trained to detect the manipulative trading scheme known as spoofing. The LSTM-Autoencoder was the model chosen method for this task. The same model is also implemented in a federated setting but with decentralised data, using the FL framework FEDn. Another FL framework, Flower, is also employed to evaluate the performance of FEDn. Experiments were conducted comparing the FL models to the conventional centralised learning model, as well as comparing the two frameworks to each other. The results showed that under certain circumstances, the FL models performed better than the centralised model in detecting spoofing. FEDn was equivalent to Flower in terms of detection performance. In addition, the results indicated that Flower was marginally faster than FEDn. It is assumed that variations in the experimental setup and stochasticity account for the performance disparity.

<p>The Ethiopia Commodity Exchange (ECX), like many other data intensive organizations, is having difficulties making full use of the vast amounts of data that it collects. This MSc thesis identifies areas within the organization where concepts from the academic fields of information visualization and visual analytics can be applied to address this issue.Software solutions are designed and implemented in two areas with the purpose of evaluating the approach and to demonstrate to potential users, developers and managers what can be achieved using this method. A number of presentation methods are proposed for the ECX website, which previously contained no graphing functionality for market data, to make it easier for users to find trends, patterns and outliers in prices and trade volumes of commodieties traded at the exchange. A software application is also developed to support the ECX market surveillance team by drastically improving its capabilities of investigating complex trader relationships.Finally, as ECX lacked previous experiences with visualization, one software developer was trained in computer graphics and involved in the work, to enable continued maintenance and future development of new visualization solutions within the organization.</p>