Abstract
Transformer buildings are at the heart of the effective operation of distribution systems, and heating problems of transformers under severe operational conditions are among the main factors affecting the lifetime, efficiency, technical losses, etc., of such important power system assets. It is crucial that the inside temperature of transformer buildings is higher than the outside temperature due to the operation of the transformer and the effect of ambient conditions. This issue may cause several problems such as additional transformer aging, losses, and moisture. The main purpose of this study is to decrease the inside temperature of transformer buildings; in other words, to prevent the inside temperature from being higher than the outside temperature. To realize this, it is recommended to apply a combined heat reduction technique by covering the outer surface with a reflective surface and use a low-emitting material on the inner surface. The relevant results of the practical evidence in this manner are presented in detail at a distribution system in Turkey with different climate and loading conditions in the summertime.

Abstract
Training firefighters using Virtual Reality (VR) technology brings several benefits over traditional training methods including the reduction of costs and risks. The ability of causing the same level of stress as a real situation so that firefighters can learn how to deal with stress was investigated. An experiment aiming to study the influence that additional stimuli (heat, weight, smell and using personal protective equipment-PPE) have on user's stress level while performing a Virtual Environment (VE) designed to train firefighters was developed. Participants' stress and Heart Rate Variability (HRV) were obtained from electrocardiograms recorded during the experiment. The results suggest that wearing the PPE has the largest impact on user's stress level. The results also showed that HRV was able to evidence differences between two phases of the experiment, which suggests that it can be used to monitor users' quantified reaction to VEs.

Abstract

Abstract
The high asymmetry of international termination rates, where calls are charged with higher values, are fertile ground for the appearance of frauds in Telecom Companies. In this paper, we present three different and complementary solutions for a real problem called Interconnect Bypass Fraud. This problem is one of the most common in the telecommunication domain and can be detected by the occurrence of abnormal behaviours from specific numbers. Our goal is to detect as soon as possible numbers with abnormal behaviours, e.g. bursts of calls, repetitions and mirror behaviours. Based on this assumption, we propose: (i) the adoption of a new fast forgetting technique that works together with the Lossy Counting algorithm; (ii) the proposal of a single pass hierarchical heavy hitter algorithm that also contains a forgetting technique; and (iii) the application of the HyperLogLog sketches for each phone number. We used the heavy hitters to detect abnormal behaviours, e.g. burst of calls, repetition and mirror. The hierarchical heavy hitters algorithm is used to detect the numbers that make calls for a huge set of destinations and destination numbers that receives a huge set of calls to provoke a denial of service. Additionally, to detect the cardinality of destination numbers of each origin number we use the HyperLogLog algorithm. The results shows that these three approaches combined complements the techniques used by the telecom company and make the fraud task more difficult.

Abstract
Users tend to search over the Internet to get the most updated news when an event occurs. Search engines should then be capable of effectively retrieving relevant documents for event-related queries. As the previous studies have shown, different retrieval models are needed for different types of events. Therefore, the first step for improving effectiveness is identifying the event-related queries and determining their types. In this paper, we propose a novel model based on deep neural networks to classify event-related queries into four categories: periodic, aperiodic, one-time-only, and non-event. The proposed model combines recurrent neural networks (by feeding two LSTM layers with query frequencies) and visual recognition models (by transforming time-series data from a 1D signal to a 2D image - later passed to a CNN model) for effective query type estimation. Worth noting is that our method uses only the time-series data of query frequencies, without the need to resort to any external sources such as contextual data, which makes it language and domain-independent with regards to the query issued. For evaluation, we build upon the previous datasets on event-related queries to create a new dataset that fits the purpose of our experiments. The obtained results show that our proposed model can achieve an F1-score of 0.87.

Abstract
Rehabilitation is an important recovery process from dysfunctions that improves the patient's activities of daily living. On the other hand, collaborative robotic applications, where humans and machines can share the same space, are increasing once it allows splitting a task between the accuracy of a robot and the ability and flexibility of a human. This paper describes an innovative approach that uses a collaborative robot to support the rehabilitation of the upper limb of patients, complemented by an intelligent system that learns and adapts its behaviour according to the patient's performance during the therapy. This intelligent system implements the reinforcement learning algorithm, which makes the system robust and independent of the path of motion. The validation of the proposed approach uses a UR3 collaborative robot training in a real environment. The main control is the resistance force that the robot is able to do against the movement performed by the human arm.