In the last few years, computer-based classification has been introduced as an additional tool to improve the clinical diagnosis of the erythemato-squamous diseases. The objectives of this study are: to demonstrate the importance of computer-based classification algorithms which have only clinical features as input in helping the physician to differentiate between psoriasis and non-psoriasis diseases and, to introduce these Machine Learning algorithms as a first stage in developing an expert system for the diagnosis and severity assessment of psoriasis lesions. From the erythemato-squamous diseases dataset taken from UCI (University of California, Irvine) machine repository, only the first ten clinical features are used as input for six state-of-theart classification algorithms. The accuracy obtained using this set of algorithms is above 93%. The results obtained led to the development of a mobile/desktop medical application that can help the physician in differentiating psoriasis lesions from other erythemato-squamous lesions using only clinical features.

No abstract

No abstract

Within the Internet of Things (IoT) paradigm, an everyday object can be transformed into a smart object, able to sense, interpret and react to the environment. IoT is bringing new ways of communicating between people and things (objects) to reach common goals, bringing a high impact on everydaylife. The aim of this paper is to present how people with psoriasis and their doctors can benefit from the IoT advantages. There is presented a proposed system for surveillance and treatment plan for patients suffering from psoriasis using assisted IoT and Computer Vision technologies.

This paper presents a new method for determining the voice quality of a VoIP carrier at a given time. The current methods rely on the voice stream analysis, their main drawback being the large computational power required and the cost for licenses. The method presented in this paper analyses the time difference between successive calls from the same source number to the same destination number, and identifies a connection between this calling pattern and the voice quality of a VoIP carrier. The advantage of this method relies in its low computational power requirement, as the voice stream analysis is no longer required. Bayesian networks are built to infer the exact a posteriori probability of poor voice quality. A case study was performed on a prepaid long distance carrier and the results show that a large percent (above 50%) of the customer complaints can be identified using this method.