Breast lesion detection employing state of the art microwave systems provide a safe, non-ionizing technique that can differentiate healthy and non-healthy tissues by exploiting their dielectric properties. In this paper, a microwave apparatus for breast lesion detection is used to accumulate clinical data from subjects undergoing breast examinations at the Department of Diagnostic Imaging, Perugia Hospital, Perugia, Italy. This paper presents the first ever clinical demonstration and comparison of a microwave ultra-wideband (UWB) device augmented by machine learning with subjects who are simultaneously undergoing conventional breast examinations. Non-ionizing microwave signals are transmitted through the breast tissue and the scattering parameters (S-parameter) are received via a dedicated moving transmitting and receiving antenna set-up. The output of a parallel radiologist study for the same subjects, performed using conventional techniques, is taken to pre-process microwave data and create suitable data for the machine intelligence system. These data are used to train and investigate several suitable supervised machine learning algorithms nearest neighbour (NN), multi-layer perceptron (MLP) neural network, and support vector machine (SVM) to create an intelligent classification system towards supporting clinicians to recognise breasts with lesions. The results are rigorously analysed, validated through statistical measurements, and found the quadratic kernel of SVM can classify the breast data with 98% accuracy.

Due to the increased awareness of issues ranging from green initiatives, sustainability, and occupant well-being, buildings are becoming smarter, but with smart requirements come increasing complexity and monitoring, ultimately carried out by humans. Building heating ventilation and air-conditioning (HVAC) units are one of the major units that consume large percentages of a building’s energy, for example through their involvement in space heating and cooling, the greatest energy consumption in buildings. By monitoring such components effectively, the entire energy demand in buildings can be substantially decreased. Due to the complex nature of building management systems (BMS), many simultaneous anomalous behaviour warnings are not manageable in a timely manner; thus, many energy related problems are left unmanaged, which causes unnecessary energy wastage and deteriorates equipment’s lifespan. This study proposes a machine learning based multi-level automatic fault detection system (MLe-AFD) focusing on remote HVAC fan coil unit (FCU) behaviour analysis. The proposed method employs sequential two-stage clustering to identify the abnormal behaviour of FCU. The model’s performance is validated by implementing well-known statistical measures and further cross-validated via expert building engineering knowledge. The method was experimented on a commercial building based in central London, U.K., as a case study and allows remotely identifying three types of FCU faults appropriately and informing building management staff proactively when they occur; this way, the energy expenditure can be further optimized.

Modernisation and retrofitting of older buildings has created a drive to install Building Energy Management Systems (BEMS) that can assist building managers in paving the way for smarter energy use and indirectly, using appropriate methods, occupant comfort understanding. BEMS may discover problems that can inform managers of building maintenance and energy wastage issues and indirectly , via repetitive data patterns appreciate user comfort requirements. The main focus of this paper is to describe a method to detect faulty Heating, Ventilation and AirConditioning (HVAC) Terminal Unit (TU) and diagnose them in an automatic and remote manner. For this purpose, a typical big-data framework has been constructed to process the very large volume of data. A novel feature extraction method encouraged by Proportional Integral Derivative (PID) controller has been proposed to describe events from multidimensional TU data streams. These features are further used to categorise different TU behaviours using unsupervised data-driven strategy and supervised learning is applied to diagnose faults. X-means clustering has been performed to group diverse TU behaviours which are experimented on daily, weekly, monthly and randomly selected dataset. Subsequently, Multi-Class Support Vector Machine (MC-SVM) has been employed based on categorical information to generate an automated fault detection and diagnosis system towards making the building smarter. The clustering and classification results further compared with wellknown and established algorithms and validated through statistical measurements.

The collection of digital images is growing at ever-increasing rate which rises the interest of mining the embedded information. The appropriate representation of an image is inconceivable by a single feature. Thus, the research addresses that point for content based image retrieval (CBIR) by fusing parametric color and shape features with nonparametric texture feature. The color moments, and moment invariants which are parametric methods and applied to describe color distribution and shapes of an image. The nonparametric ranklet transformation is performed to narrate the texture features. Experimentally these parametric and nonparametric features are integrated to propose a robust and effective algorithm. The proposed work is compared with seven existing techniques by determining statistical metrics across five image databases. Finally, a hypothesis test is carried out to establish the significance of the proposed work which, infers evaluated precision and recall values are true and accepted for the all image database.

Abstract-An indoor positioning system (IPS) is a technology employed to locate objects and people within a building scenario using signal processing or other sensory information. Ultra Wide Band (UWB) is a versatile wireless technology that can be employed as an IPS and has shown very good performances. UWB can be used in many scenarios and its effectiveness in through wall detection along with its excellent resolution for person localization is one of the best applications of IR-UWB. The main objective of this work is to propose a concept for intelligent radar systems employing UWB augmented by machine learning approaches to not only localize but understand the location of a person or target within a building. Although suitably developed UWB is excellent for obtaining localizing data it does not automatically understand what that location effectively means or where it is thus further methods are required to create meaningful data for end user appreciation. Learning from the huge amount of UWB signal data through Multi Class Support Vector Machine (MC-SVM) architecture enables a truly evolving scheme to both localize targets and identify them in a useful way. Statistical analysis of the experimental results supports the proposed algorithm.