Search

In recent years, Internet of Things has being used in several fields of modern life. The possibility of having an interconnection between all the related objects through data opens up a world of research in different fields. Among these fields, IoT technology is considered to make a significant impact in casting industry and the whole casting process. Moreover, the casting industry is an exceptionally critical field since it directly provides elements to other industries. Therefore, castings are subjected to a series of very rigorous quality controls which must be validated by the entire manufacturing process. Considering that the casting process has to be interconnected in order to foresee the state of the each piece before it is produced, it is vitally important that all sub-processes feed back into the system to learn from errors. In this work, we presented a new methodology for the detection and categorization of the imperfections on the surface of the castings. Among these defects, we particularly focused on inclusions, cold laps and misruns. To this end, we first compared several features extracted from the obtained images in order to highlight the regions of the casting that may be affected. And then, we applied several machine-learning techniques to classify the regions. The final results were carried to the starting point of the process to use them in the models to predict the quality of new castings.

As a result of our research work, we present a demo app that showcases the different interaction techniques that can be implemented using OpenUIX; a novel HCI model that provides the logical mechanisms to easily design Spatial User Interfaces. Thanks to this solution, interaction designers can define widget behaviors that not only take into consideration the physical surroundings of the end users, but also their general context (including their psychological state and any disability they might have). An approach that greatly facilitates the creation and sharing of user experiences adapted to the actual needs and desires of the users (therefore liberating designers from the responsibility of creating responsive and accessible versions of their user interfaces).

Knowing what potential clients want, is the most important issue for companies. The current situation of social communication is generating a lot of information about users, such as favourite sites, food, politic tendencies, hopes or needs. This information has an incalculable value for marketing interests but, unfortunately, it is not trivial to process it. One way to obtain this information without disturbing the users is to store their searches, used words on the Internet and clicked items, to construct specific profiles. But, the problem with these techniques is that they do not retrieve current information about the targeted user because they gather information that may or may not be up to date. In light of this background, we propose a methodology to obtain up to date information about user's interests, likes and needs by analysing users conversations in social networks and instant messaging systems to generate personalised and interesting advertisement with better impact and higher success rates.

Spam has become an important problem for computer security because it is a channel for the spreading of threats such as computer viruses, worms and phishing. Currently, more than 85% of received emails are spam. Historical approaches to combat these messages, including simple techniques such as sender blacklisting or the use of email signatures, are no longer completely reliable. Many solutions utilise machine-learning approaches trained using statistical representations of the terms that usually appear in the emails. However, these methods require a time-consuming training step with labelled data. Dealing with the situation where the availability of labelled training instances is limited slows down the progress of filtering systems and offers advantages to spammers. In a previous work, we presented the first spam filtering method based on anomaly detection that reduces the necessity of labelling spam messages and only employs the representation of legitimate emails. We showed that this method achieved high accuracy rates detecting spam while maintaining a low false positive rate and reducing the effort produced by labelling spam. In this paper, we enhance that system applying a data reduction algorithm to the labelled dataset, finding similarities among legitimate emails and grouping them to form consistent clusters that reduce the amount of needed comparisons. We show that this improvement reduces drastically the processing time, while maintaining detection and false positive rates stable.

Malware is any software designed to harm computers. Commercial anti-virus are based on signature scanning, which is a technique effective only when the malicious executables have been previously analysed and identified. Malware writers employ several techniques in order to hide their actual behaviour. Executable packing consists in encrypting or hiding the real payload of the executable. Generic unpacking techniques do not depend on the packer used, as they execute the binary within an isolated environment (namely `sandbox') to gather the real code of the packed executable. However, this approach is slow and, therefore, a filter step is required to determine when an executable has been packed. To this end, supervised machine learning approaches trained with static features from the executables have been proposed. Notwithstanding, supervised learning methods need the identification and labelling of a high number of packed and not packed executables. In this paper, we propose a new method for packed executable detection that adopts a collective learning approach to reduce the labelling requirements of completely supervised approaches. We performed an empirical validation demonstrating that the system maintains a high accuracy rate while the labelling efforts are lower than when using supervised learning.