Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

IoT Based Pain Management using Physiological Parameters

The continuous technology evaluation is benefiting our lives to a great extent. The evolution of Internet of things and deployment of wireless sensor networks is making it possible to have more connectivity between people and devices used extensively in our daily lives. Almost every discipline of daily life including health sector, transportation, agriculture etc. is benefiting from these technologies. There is a great potential of research and refinement of health sector as the current system is very often dependent on manual evaluations conducted by the clinicians. There is no automatic system for patient health monitoring and assessment which results to incomplete and less reliable heath information. Internet of things has a great potential to benefit health care applications by automated and remote assessment, monitoring and identification of diseases. Acute pain is the main cause of people visiting to hospitals. An automatic pain detection system based on internet of things with wireless devices can make the assessment and redemption significantly more efficient. The contribution of this research work is proposing pain assessment method based on physiological parameters. The physiological parameters chosen for this study are heart rate, electrocardiography, breathing rate and galvanic skin response. As a first step, the relation between these physiological parameters and acute pain experienced by the test persons is evaluated. The electrocardiography data collected from the test persons is analyzed to extract interbeat intervals. This evaluation clearly demonstrates specific patterns and trends in these parameters as a consequence of pain. This parametric behavior is then used to assess and identify the pain intensity by implementing machine learning algorithms. Support vector machines are used for classifying these parameters influenced by different pain intensities and classification results are achieved. The classification results with good accuracy rates between two and three levels of pain intensities shows clear indication of pain and the feasibility of this pain assessment method. An improved approach on the basis of this research work can be implemented by using both physiological parameters and electromyography data of facial muscles for classification.

Parameter Identification in a Tuberculosis Model for Cameroon

A deterministic model of tuberculosis in Cameroon is designed and analyzed with respect to its transmission dynamics. The model includes lack of access to treatment and weak diagnosis capacity as well as both frequency-and density-dependent transmissions. It is shown that the model is mathematically well-posed and epidemiologically reasonable. Solutions are non-negative and bounded whenever the initial values are non-negative. A sensitivity analysis of model parameters is performed and the most sensitive ones are identified by means of a state-of-the-art Gauss-Newton method. In particular, parameters representing the proportion of individuals having access to medical facilities are seen to have a large impact on the dynamics of the disease. The model predicts that a gradual increase of these parameters could significantly reduce the disease burden on the population within the next 15 years.

Dynamic-Data Driven Real-Time Identification for Electric Power Systems

Power system engineers face a double challenge: to operate electric power systems within narrow stability and security margins, and to maintain high reliability. There is an acute need to better understand the dynamic nature of power systems in order to be prepared for critical situations as they arise. Innovative measurement tools, such as phasor measurement units, can capture not only the slow variation of the voltages and currents but also the underlying oscillations in a power system. Such dynamic data accessibility provides us a strong motivation and a useful tool to explore dynamic-data driven applications in power systems. To fulfill this goal, this dissertation focuses on the following three areas: Developing accurate dynamic load models and updating variable parameters based on the measurement data, applying advanced nonlinear filtering concepts and technologies to real-time identification of power system models, and addressing computational issues by implementing the balanced truncation method. By obtaining more realistic system models, together with timely updated parameters and stochastic influence consideration, we can have an accurate portrait of the ongoing phenomena in an electrical power system. Hence we can further improve state estimation, stability analysis and real-time operation.

Identification, diversity and distribution patterns of fish larvae in Khark & Kharko Coralline Islands ecosystem – Persian Gulf, by GIS method

Khark & Kharko Islands are the last Northern point for fringing coral reefs in Iranian side of the Persian Gulf. These Coralline habitats are the Protected Area and Wildlife Refugees with the total area of 2400 ha which located in the territory of Bushehr Province. This research carried out during 2006-2007 with monthly sampling from 12 stations, which selected around Islands and inshore waters with maximum depth of 20 meter. Sampling was conducted using by Bongo-Net plankton sampler with 500μ of mesh size. Totally, 1808 specimen from 45 family fish larvae was identified in studied area, including: 21 coralline fish larva families and 24 shore fish larvae such as pelagic and demersal fishes which some of them known as indicator, sentinel or endemic species for coral reef ecosystems. The results was shown that coral reef diversity in coral reefs (Khark & Kharko Islands) is more than other habitats such as estuary and river mouth, creeks, mangrove forest sites, and off shore water of the Persian Gulf and Oman Sea Iranian side. Among Identified families, Clupeidae, Blenniidae, Sillaginidae, Atherinidae and Tripterygiidae; with more abundance were dominant families in studied area. The pick of fish larvae abundance family were estimated in spring. There were significant differences between seasonally abundance and sub areas, but there were not significant differences in diversity indexes between Khark and Kharko stations with coastal stations (p< 0.05). The mean abundance of fish larvae were estimated 18.7083 larvae under 10m² of sea surface, and the mean diversity indexes and evenness were estimated 0.7135 and 0.565342 consequently, that was showed the area is under ecological stress for fish larvae, and wasn’t stable. Therefore, from the ecological point of view, only some of the fish larvae groups as like Clupeidae were dominant. Thus, they were the main cause of the fish larvae abundance change in studied area. Due to geographical location of Khark and Kharko Islands and among the environmental parameters, Its seems that the condition of sea current is the main cause for present or absent and distribution patterns of fish larvae in area. Abundance of fish larvae in west of Islands was higher than eastern parts in the spring. But this condition will be reversed in eastern part of Island and several coastal stations, so that the Islands surrounding clock wise current to cause fish larvae distribution patterns.

The possible identification and introduction of metallothionein in Persian Sturgeon (Acipenser persicus)

Due to anthropogenic activities, toxic metals still represent a threat for various marine organisms. Metallothionein (MT) and cadmium concentration in gills, liver, and kidney tissues and cadmium partitioning in soluble (cytosol) and insoluble fractions of mentioned tissues of Persian sturgeon (Acipenser persicus) were determined following exposure to sub-lethal levels of waterborne cadmium (Cd) (50, 400 and 1000 μg L-1) after 1, 2, 4 and 14 days. The increases of MT from background levels in comparison to controls were 4.6-, 3-, and 2.8-fold for kidney, liver, and gills, respectively after 14 days. The matallothionein concentration in liver was in the range of 56.89-168.44 μgL-1 and for kidney and gills, 39.78-189.30 and 28.15-91.20 μgL-1, respectively. The results showed that MT level change in the kidney is time and concentration dependent. Also, cortisol measurement revealed elevation at the day 1 of exposure and that followed by MT increase in the liver. Cd concentrations in the cytosol of experimental tissues were measured and the results indicated that Cd levels in the cytosol of liver, kidney, and gills increased 240.71-, 32.05-, and 40.16-fold, respectively 14 days after exposure to 1000 μgL-1 Cd. The accumulation of Cd in cytosol of tissues is in the order of liver > gills > kidney. Spearman correlation coefficients showed the MT content in kidney is correlated with Cd concentration, the value of which is more than in liver and gills. Thus, kidney can be considered as a tissue indicator in Acipenser persicus for waterborne Cd contamination. Also, tissue metal accumulations (gills, liver, kidney and muscle) in Persian sturgeon (Acipenser persicus) were compared following exposure to sublethal levels of waterborne Cd (50, 400 and 1000 μg L-1) after periods of 1, 2, 4 and 14 days. Meanwhile, the trends of Cd concentration increase in different tissues during the exposure periods and concentrations were modelled as equations. The obtained results indicate that at the end of 4 and 14 days of exposure, total tissue cadmium concentration followed the pattern: liver> gill> kidney> muscle. Calculation of bioconcentration factor (BCF) after 14 days exposure showed that at low and high concentrations, highest BCFs were found in kidney and liver, respectively. According to the results, the accumulation capacity of muscle was the lowest at all exposure concentrations. The hematological parameters including osmolarity, total protein, cortisol and glucose of plasma were measured, too. Total protein of plasma was in the range of 416.90-1068.10 mg dl-1 plasma.Total protein decreased not significantly (P≥0.05) after exposure to Cd. Cortisol increased after 1 day exposure that followed by significant (P≤0.05) elevation of glucose. The range of cortisol was very vast and it was determined between 0.03 to 16.21 ng mL-1. The content of plasma osmolarity was in the range of 282.33-294.20 mOsmol L-1.Osmolarity of treated fish plasma showed no significant decrease (P≥0.05). Total protein in gills, liver, and kidney showed that at high concentrations of metal, protein content decreased significantly (P≤0.05) in the liver after 4 and 14 days exposure. Thus, total protein of liver and glucose of plasma can be used as general biomarkers of exposure to Cd. Also, the metallothionein and cadmium were measured in gills, kidney and liver of 8 wild Persian sturgeon caught in coast of Guilan Province. According to the results, the concentration of metallothionein was in the range of 45.87-154.66 microgram per liter with the maximum and minimum concentrations in liver and gills, respectively. The trend of cadmium concentration in cytosol of tissues was: liver> kidney> gills. The results of Spearman correlation test showed that there was a significant positive correlation between metallothionein and cadmium in cytosol of liver (r2= 0.850, p≤ 0.01). In the kidney, the correlation between cadmium and metallothionein was significantly positive (r2= 0.731, p≥ 0.05). But there was not such significant correlation in the gills (p≥ 0.05).

Soft computing based parameter identification in pavements and geomechanical systems

Accurate estimation of road pavement geometry and layer material properties through the use of proper nondestructive testing and sensor technologies is essential for evaluating pavement’s structural condition and determining options for maintenance and rehabilitation. For these purposes, pavement deflection basins produced by the nondestructive Falling Weight Deflectometer (FWD) test data are commonly used. The nondestructive FWD test drops weights on the pavement to simulate traffic loads and measures the created pavement deflection basins. Backcalculation of pavement geometry and layer properties using FWD deflections is a difficult inverse problem, and the solution with conventional mathematical methods is often challenging due to the ill-posed nature of the problem. In this dissertation, a hybrid algorithm was developed to seek robust and fast solutions to this inverse problem. The algorithm is based on soft computing techniques, mainly Artificial Neural Networks (ANNs) and Genetic Algorithms (GAs) as well as the use of numerical analysis techniques to properly simulate the geomechanical system. A widely used pavement layered analysis program ILLI-PAVE was employed in the analyses of flexible pavements of various pavement types; including full-depth asphalt and conventional flexible pavements, were built on either lime stabilized soils or untreated subgrade. Nonlinear properties of the subgrade soil and the base course aggregate as transportation geomaterials were also considered. A computer program, Soft Computing Based System Identifier or SOFTSYS, was developed. In SOFTSYS, ANNs were used as surrogate models to provide faster solutions of the nonlinear finite element program ILLI-PAVE. The deflections obtained from FWD tests in the field were matched with the predictions obtained from the numerical simulations to develop SOFTSYS models. The solution to the inverse problem for multi-layered pavements is computationally hard to achieve and is often not feasible due to field variability and quality of the collected data. The primary difficulty in the analysis arises from the substantial increase in the degree of non-uniqueness of the mapping from the pavement layer parameters to the FWD deflections. The insensitivity of some layer properties lowered SOFTSYS model performances. Still, SOFTSYS models were shown to work effectively with the synthetic data obtained from ILLI-PAVE finite element solutions. In general, SOFTSYS solutions very closely matched the ILLI-PAVE mechanistic pavement analysis results. For SOFTSYS validation, field collected FWD data were successfully used to predict pavement layer thicknesses and layer moduli of in-service flexible pavements. Some of the very promising SOFTSYS results indicated average absolute errors on the order of 2%, 7%, and 4% for the Hot Mix Asphalt (HMA) thickness estimation of full-depth asphalt pavements, full-depth pavements on lime stabilized soils and conventional flexible pavements, respectively. The field validations of SOFTSYS data also produced meaningful results. The thickness data obtained from Ground Penetrating Radar testing matched reasonably well with predictions from SOFTSYS models. The differences observed in the HMA and lime stabilized soil layer thicknesses observed were attributed to deflection data variability from FWD tests. The backcalculated asphalt concrete layer thickness results matched better in the case of full-depth asphalt flexible pavements built on lime stabilized soils compared to conventional flexible pavements. Overall, SOFTSYS was capable of producing reliable thickness estimates despite the variability of field constructed asphalt layer thicknesses.

Multi-objective optimization of material model parameters of an adhesive layer by using SPEA2

The usage of multi material structures in industry, especially in the automotive industry are increasing. To overcome the difficulties in joining these structures, adhesives have several benefits over traditional joining methods. Therefore, accurate simulations of the entire process of fracture including the adhesive layer is crucial. In this paper, material parameters of a previously developed meso mechanical finite element (FE) model of a thin adhesive layer are optimized using the Strength Pareto Evolutionary Algorithm (SPEA2). Objective functions are defined as the error between experimental data and simulation data. The experimental data is provided by previously performed experiments where an adhesive layer was loaded in monotonically increasing peel and shear. Two objective functions are dependent on 9 model parameters (decision variables) in total and are evaluated by running two FEsimulations, one is loading the adhesive layer in peel and the other in shear. The original study converted the two objective functions into one function that resulted in one optimal solution. In this study, however, a Pareto frontis obtained by employing the SPEA2 algorithm. Thus, more insight into the material model, objective functions, optimal solutions and decision space is acquired using the Pareto front. We compare the results and show good agreement with the experimental data.

On The Use of Genetic Algorithms for Parameter Identification in Anaerobic Digestion Modelling

Anaerobic digestion (AD) of wastewater is a very interesting option for waste valorization, energy production and environment protection. It is a complex, naturally occurring process that can take place inside bioreactors. The capability of predicting the operation of such bioreactors is important to optimize the design and the operation conditions of the reactors, which, in part, justifies the numerous AD models presently available. The existing AD models are not universal, have to be inferred from prior knowledge and rely on existing experimental data. Among the tasks involved in the process of developing a dynamical model for AD, the estimation of parameters is one of the most challenging. This paper presents the identifiability analysis of a nonlinear dynamical model for a batch reactor. Particular attention is given to the structural identifiability of the model, which considers the uniqueness of the estimated parameters. To perform this analysis, the GenSSI toolbox was used. The estimation of the model parameters is achieved with genetic algorithms (GA) which have already been used in the context of AD modelling, although not commonly. The paper discusses its advantages and disadvantages.

Texture for Script identification

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.