Every year, criminals launder billions of dollars acquired from serious felonies (e.g., terrorism, drug smuggling, or human trafficking), harming countless people and economies. Cryptocurrencies, in particular, have developed as a haven for money laundering activity. Machine Learning can be used to detect these illicit patterns. However, labels are so scarce that traditional supervised algorithms are inapplicable. Here, we address money laundering detection assuming minimal access to labels. First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset. Then, we show that our proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5% of the labels. This solution mimics a typical real-life situation in which a limited number of labels can be acquired through manual annotation by experts.

Inflammatory skin diseases, including psoriasis and atopic dermatitis, affect around one quarter to one third of the world population. Systemic cyclosporine A, an immunosuppressant agent, is included in the current therapeutic armamentarium of these diseases. Despite being highly effective, it is associated with several side effects, and its topical administration is limited by its high molecular weight and poor water solubility. To overcome these limitations, cyclosporine A was incorporated into solid lipid nanoparticles obtained from Softisan® 649, a commonly used cosmetic ingredient, aiming to develop a vehicle for application to the skin. The nanoparticles presented sizes of around 200 nm, low polydispersity, negative surface charge, and stability when stored for 8 weeks at room temperature or 4 °C. An effective incorporation of 88% of cyclosporine A within the nanoparticles was observed, without affecting its morphology. After the freeze-drying process, the Softisan® 649-based nanoparticles formed an oleogel. Skin permeation studies using pig ear as a model revealed low permeation of the applied cyclosporine A in the freeze-dried form of the nanoparticles in relation to free drug and the freshly prepared nanoparticles. About 1.0 mg of cyclosporine A was delivered to the skin with reduced transdermal permeation. These results confirm local delivery of cyclosporine A, indicating its promising topical administration.

Every year, criminals launder billions of dollars acquired from serious felonies (e.g., terrorism, drug smuggling, or human trafficking) harming countless people and economies. Cryptocurrencies, in particular, have developed as a haven for money laundering activity. Machine Learning can be used to detect these illicit patterns. However, labels are so scarce that traditional supervised algorithms are inapplicable. Here, we address money laundering detection assuming minimal access to labels. First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset. Then, we show that our proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5% of the labels. This solution mimics a typical real-life situation in which a limited number of labels can be acquired through manual annotation by experts.

Driving behaviour has a great impact on road safety. A popular way of analysing driving behaviour is to move the focus to the manoeuvres as they give useful information about the driver who is performing them. In this paper, we investigate a new way of identifying manoeuvres from vehicle telematics data, through motif detection in time-series. We implement a modified version of the Extended Motif Discovery (EMD) algorithm, a classical variable-length motif detection algorithm for time-series and we applied it to the UAH-DriveSet, a publicly available naturalistic driving dataset. After a systematic exploration of the extracted motifs, we were able to conclude that the EMD algorithm was not only capable of extracting simple manoeuvres such as accelerations, brakes and curves, but also more complex manoeuvres, such as lane changes and overtaking manoeuvres, which validates motif discovery as a worthwhile line for future research.

No abstract

No abstract

No abstract

No abstract