Jana Trojanova

Fault Diagnosis of Air Handling Units

Abstract This paper presents an improved method for fault detection and diagnostics (FDD) of air handling units (AHUs). The fault detection module defines observable states of the AHU, where each state depends on current values of sensor data and control signals. The fault diagnostic module maps the observable states to the faults and then applies the cumulative sum chart (CUSUM) to define the size and development of each fault in time. The FDD method was tested on real datasets and its results were confirmed by the building technician. Finally, the method is compared with the standard APAR (AHU performance assessment rules) method developed by Schein et al.

From Symptoms to Faults: Temporal Reasoning Methods

Complex systems composed of many components can operate in an inappropriate way. Information about the system is obtained in time, gradually. The assessment of casualties in such situation has challenged many researchers. The present paper provides a new compact methodology for diagnostics of faults form measurements: Space of measurements is divided into symptoms. Each symptom is able to admit some faults as possible and exclude some as impossible. This concept is based on fuzzy logic approach and provides an efficient alternative to usual probabilistic oriented methodologies. These relations between symptoms and faults are stated in the mapping table as logical rules. The diagnosis information is gathered online and aggregated on the side of symptoms or on the side of faults. This paper provides and compares a set of different methods for transformation of measured information into truth rates for each fault.

Multi-object tracking of pedestrian driven by context

The characteristics like density of objects, their contrast with respect to surrounding background, their occlusion level and many more describe the context of the scene. The variation of the context represents ambiguous task to be solved by tracker. In this paper we present a new long term tracking framework boosted by context around each tracklet. The framework works by first learning the database of optimal tracker parameters for various context offline. During the testing, the context surrounding each tracklet is extracted and match against database to select best tracker parameters. The tracker parameters are tuned for each tracklet in the scene to highlight its discrimination with respect to surrounding context rather than tuning the parameters for whole scene. The proposed framework is trained on 9 public video sequences and tested on 3 unseen sets. It outperforms the state-of-art pedestrian trackers in scenarios of motion changes, appearance changes and occlusion of objects.

Active Shape Model and linear predictors for face association refinement

This paper summarizes results of face association experiments on real low resolution data from airport and the Labeled faces in the Wild (LFW) database. The objective of experiments is to evaluate different face alignment methods and their contribution to face association as such. The first alignment method used is Sequential Learnable Linear Predictor (SLLiP), originally developed for object tracking. The second method is well known face alignment method Active Shape Model (ASM). Both methods are compared versus face association without alignment. In case of high resolution LFW database the ASM rapidly increases the association results, on the other hand for real low resolution airport data the SLLiP method brought more improvement than ASM.