Structural Data Acquisition Using Sensor Network

The development cost of any civil infrastructure is very high; during its life span, the civil structure undergoes a lot of physical loads and environmental effects which damage the structure. Failing to identify this damage at an early stage may result in severe property loss and may become a potential threat to people and the environment. Thus, there is a need to develop effective damage detection techniques to ensure the safety and integrity of the structure. One of the Structural Health Monitoring methods to evaluate a structure is by using statistical analysis. In this study, a civil structure measuring 8 feet in length, 3 feet in diameter, embedded with thermocouple sensors at 4 different levels is analyzed under controlled and variable conditions. With the help of statistical analysis, possible damage to the structure was analyzed. The analysis could detect the structural defects at various levels of the structure.

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Thanks to the advanced technologies and social networks that allow the data to be widely shared among the Internet, there is an explosion of pervasive multimedia data, generating high demands of multimedia services and applications in various areas for people to easily access and manage multimedia data. Towards such demands, multimedia big data analysis has become an emerging hot topic in both industry and academia, which ranges from basic infrastructure, management, search, and mining to security, privacy, and applications. Within the scope of this dissertation, a multimedia big data analysis framework is proposed for semantic information management and retrieval with a focus on rare event detection in videos. The proposed framework is able to explore hidden semantic feature groups in multimedia data and incorporate temporal semantics, especially for video event detection. First, a hierarchical semantic data representation is presented to alleviate the semantic gap issue, and the Hidden Coherent Feature Group (HCFG) analysis method is proposed to capture the correlation between features and separate the original feature set into semantic groups, seamlessly integrating multimedia data in multiple modalities. Next, an Importance Factor based Temporal Multiple Correspondence Analysis (i.e., IF-TMCA) approach is presented for effective event detection. Specifically, the HCFG algorithm is integrated with the Hierarchical Information Gain Analysis (HIGA) method to generate the Importance Factor (IF) for producing the initial detection results. Then, the TMCA algorithm is proposed to efficiently incorporate temporal semantics for re-ranking and improving the final performance. At last, a sampling-based ensemble learning mechanism is applied to further accommodate the imbalanced datasets. In addition to the multimedia semantic representation and class imbalance problems, lack of organization is another critical issue for multimedia big data analysis. In this framework, an affinity propagation-based summarization method is also proposed to transform the unorganized data into a better structure with clean and well-organized information. The whole framework has been thoroughly evaluated across multiple domains, such as soccer goal event detection and disaster information management.

Power spectrum model of visual masking: simulations and empirical data

In the study of the spatial characteristics of the visual channels, the power spectrum model of visual masking is one of the most widely used. When the task is to detect a signal masked by visual noise, this classical model assumes that the signal and the noise are previously processed by a bank of linear channels and that the power of the signal at threshold is proportional to the power of the noise passing through the visual channel that mediates detection. The model also assumes that this visual channel will have the highest ratio of signal power to noise power at its output. According to this, there are masking conditions where the highest signal-to-noise ratio (SNR) occurs in a channel centered in a spatial frequency different from the spatial frequency of the signal (off-frequency looking). Under these conditions the channel mediating detection could vary with the type of noise used in the masking experiment and this could affect the estimation of the shape and the bandwidth of the visual channels. It is generally believed that notched noise, white noise and double bandpass noise prevent off-frequency looking, and high-pass, low-pass and bandpass noises can promote it independently of the channel's shape. In this study, by means of a procedure that finds the channel that maximizes the SNR at its output, we performed numerical simulations using the power spectrum model to study the characteristics of masking caused by six types of one-dimensional noise (white, high-pass, low-pass, bandpass, notched, and double bandpass) for two types of channel's shape (symmetric and asymmetric). Our simulations confirm that (1) high-pass, low-pass, and bandpass noises do not prevent the off-frequency looking, (2) white noise satisfactorily prevents the off-frequency looking independently of the shape and bandwidth of the visual channel, and interestingly we proved for the first time that (3) notched and double bandpass noises prevent off-frequency looking only when the noise cutoffs around the spatial frequency of the signal match the shape of the visual channel (symmetric or asymmetric) involved in the detection. In order to test the explanatory power of the model with empirical data, we performed six visual masking experiments. We show that this model, with only two free parameters, fits the empirical masking data with high precision. Finally, we provide equations of the power spectrum model for six masking noises used in the simulations and in the experiments.

Utility of a panviral microarray for detection of swine respiratory viruses in clinical samples

Several factors have recently converged, elevating the need for highly parallel diagnostic platforms that have the ability to detect many known, novel, and emerging pathogenic agents simultaneously. Panviral DNA microarrays represent the most robust approach for massively parallel viral surveillance and detection. The Virochip is a panviral DNA microarray that is capable of detecting all known viruses, as well as novel viruses related to known viral families, in a single assay and has been used to successfully identify known and novel viral agents in clinical human specimens. However, the usefulness and the sensitivity of the Virochip platform have not been tested on a set of clinical veterinary specimens with the high degree of genetic variance that is frequently observed with swine virus field isolates. In this report, we investigate the utility and sensitivity of the Virochip to positively detect swine viruses in both cell culture-derived samples and clinical swine samples. The Virochip successfully detected porcine reproductive and respiratory syndrome virus (PRRSV) in serum containing 6.10 × 10(2) viral copies per microliter and influenza A virus in lung lavage fluid containing 2.08 × 10(6) viral copies per microliter. The Virochip also successfully detected porcine circovirus type 2 (PCV2) in serum containing 2.50 × 10(8) viral copies per microliter and porcine respiratory coronavirus (PRCV) in turbinate tissue homogenate. Collectively, the data in this report demonstrate that the Virochip can successfully detect pathogenic viruses frequently found in swine in a variety of solid and liquid specimens, such as turbinate tissue homogenate and lung lavage fluid, as well as antemortem samples, such as serum.

Proposal to minimize the difficulty of recording abortion data in sheep

Background: The most frequent viral diseases which can cause abortion in sheep are Blue tongue, Border disease virus, Cache Valley fever and Schmallenberg virus. The diagnosis of abortion, namely virus-induced represents a challenge to field clinicians, since clinical signs presented by the dam are discrete, non-specific and variable (Agerhom et al., 2015). On the other hand, while some foetuses reveal characteristic and visible malformations, others do not reveal any lesions. In face of it, definitive diagnosis requires an appropriate history collection, as well as sending fresh samples, namely abortion material, foetus, placenta and umbilical cord, to a specialty laboratory, to obtain a precise diagnosis. Objectives: The authors suggest a registration method of all mandatory data, in order to further assist the diagnosis of viral diseases at the laboratories, including the most frequent congenital malformations reported in sheep abortions. Methods: Abortion samples of suspected viral origin were collected and all data were registered, in worktables optimized for this purpose. Results: The authors document, using macroscopic figures lesions of malformations in abortions, emphasizing the frequency and the importance of documenting each case, proposing practical and effective worktables to assist the fieldwork. Conclusions: Field clinician’s awareness of the importance of early detection of viral diseases causing abortion outbreaks stimulates a proper data collection for each case of abortion, in order to contribute to a precise diagnosis and posterior consistent epidemiological studies, which may allow diminishing of economic losses.

Detection and Grading of Prostate Cancer in Temporal Enhanced Ultrasound using Convolutional Neural Networks

Prostate cancer is the most common non-dermatological cancer amongst men in the developed world. The current definitive diagnosis is core needle biopsy guided by transrectal ultrasound. However, this method suffers from low sensitivity and specificity in detecting cancer. Recently, a new ultrasound based tissue typing approach has been proposed, known as temporal enhanced ultrasound (TeUS). In this approach, a set of temporal ultrasound frames is collected from a stationary tissue location without any intentional mechanical excitation. The main aim of this thesis is to implement a deep learning-based solution for prostate cancer detection and grading using TeUS data. In the proposed solution, convolutional neural networks are trained to extract high-level features from time domain TeUS data in temporally and spatially adjacent frames in nine in vivo prostatectomy cases. This approach avoids information loss due to feature extraction and also improves cancer detection rate. The output likelihoods of two TeUS arrangements are then combined to form our novel decision support system. This deep learning-based approach results in the area under the receiver operating characteristic curve (AUC) of 0.80 and 0.73 for prostate cancer detection and grading, respectively, in leave-one-patient-out cross-validation. Recently, multi-parametric magnetic resonance imaging (mp-MRI) has been utilized to improve detection rate of aggressive prostate cancer. In this thesis, for the first time, we present the fusion of mp-MRI and TeUS for characterization of prostate cancer to compensates the deficiencies of each image modalities and improve cancer detection rate. The results obtained using TeUS are fused with those attained using consolidated mp-MRI maps from multiple MR modalities and cancer delineations on those by multiple clinicians. The proposed fusion approach yields the AUC of 0.86 in prostate cancer detection. The outcomes of this thesis emphasize the viable potential of TeUS as a tissue typing method. Employing this ultrasound-based intervention, which is non-invasive and inexpensive, can be a valuable and practical addition to enhance the current prostate cancer detection.

Mixed genotype Hepatitis C virus infections: incidence in Scotland and methods for detection

The diagnosis of mixed genotype hepatitis C virus (HCV) infection is rare and information on incidence in the UK, where genotypes 1a and 3 are the most prevalent, is sparse. Considerable variations in the efficacies of direct-acting antivirals (DAAs) for the HCV genotypes have been documented and the ability of DAAs to treat mixed genotype HCV infections remains unclear, with the possibility that genotype switching may occur. In order to estimate the prevalence of mixed genotype 1a/3 infections in Scotland, a cohort of 512 samples was compiled and then screened using a genotype-specific nested PCR assay. Mixed genotype 1a/3 infections were found in 3.8% of samples tested, with a significantly higher prevalence rate of 6.7% (p<0.05) observed in individuals diagnosed with genotype 3 infections than genotype 1a (0.8%). An analysis of the samples using genotypic-specific qPCR assays found that in two-thirds of samples tested, the minor strain contributed <1% of the total viral load. The potential of deep sequencing methods for the diagnosis of mixed genotype infections was assessed using two pan-genotypic PCR assays compatible with the Illumina MiSeq platform that were developed targeting the E1-E2 and NS5B regions of the virus. The E1-E2 assay detected 75% of the mixed genotype infections, proving to be more sensitive than the NS5B assay which identified only 25% of the mixed infections. Studies of sequence data and linked patient records also identified significantly more neurological disorders in genotype 3 patients. Evidence of distinctive dinucleotide expression within the genotypes was also uncovered. Taken together these findings raise interesting questions about the evolutionary history of the virus and indicate that there is still more to understand about the different genotypes. In an era where clinical medicine is frequently more personalised, the development of diagnostic methods for HCV providing increased patient stratification is increasingly important. This project has shown that sequence-based genotyping methods can be highly discriminatory and informative, and their use should be encouraged in diagnostic laboratories. Mixed genotype infections were challenging to identify and current deep sequencing methods were not as sensitive or cost-effective as Sanger-based approaches in this study. More research is needed to evaluate the clinical prognosis of patients with mixed genotype infection and to develop clinical guidelines on their treatment.

Screening a Case Base for Stroke Disease Detection

Stroke stands for one of the most frequent causes of death, without distinguishing age or genders. Despite representing an expressive mortality fig-ure, the disease also causes long-term disabilities with a huge recovery time, which goes in parallel with costs. However, stroke and health diseases may also be prevented considering illness evidence. Therefore, the present work will start with the development of a decision support system to assess stroke risk, centered on a formal framework based on Logic Programming for knowledge rep-resentation and reasoning, complemented with a Case Based Reasoning (CBR) approach to computing. Indeed, and in order to target practically the CBR cycle, a normalization and an optimization phases were introduced, and clustering methods were used, then reducing the search space and enhancing the cases re-trieval one. On the other hand, and aiming at an improvement of the CBR theo-retical basis, the predicates` attributes were normalized to the interval 0…1, and the extensions of the predicates that match the universe of discourse were re-written, and set not only in terms of an evaluation of its Quality-of-Information (QoI), but also in terms of an assessment of a Degree-of-Confidence (DoC), a measure of one`s confidence that they fit into a given interval, taking into account their domains, i.e., each predicate attribute will be given in terms of a pair (QoI, DoC), a simple and elegant way to represent data or knowledge of the type incomplete, self-contradictory, or even unknown.

A Case Based Methodology for Problem Solving aiming at Knee Osteoarthritis Detection

Knee osteoarthritis is the most common type of arthritis and a major cause of impaired mobility and disability for the ageing populations. Therefore, due to the increasing prevalence of the malady, it is expected that clinical and scientific practices had to be set in order to detect the problem in its early stages. Thus, this work will be focused on the improvement of methodologies for problem solving aiming at the development of Artificial Intelligence based decision support system to detect knee osteoarthritis. The framework is built on top of a Logic Programming approach to Knowledge Representation and Reasoning, complemented with a Case Based approach to computing that caters for the handling of incomplete, unknown, or even self-contradictory information.

Detecting outliers and asserting consistency in agriculture ground truth information by using temporal VI data from modis.

Collecting ground truth data is an important step to be accomplished before performing a supervised classification. However, its quality depends on human, financial and time ressources. It is then important to apply a validation process to assess the reliability of the acquired data. In this study, agricultural infomation was collected in the Brazilian Amazonian State of Mato Grosso in order to map crop expansion based on MODIS EVI temporal profiles. The field work was carried out through interviews for the years 2005-2006 and 2006-2007. This work presents a methodology to validate the training data quality and determine the optimal sample to be used according to the classifier employed. The technique is based on the detection of outlier pixels for each class and is carried out by computing Mahalanobis distances for each pixel. The higher the distance, the further the pixel is from the class centre. Preliminary observations through variation coefficent validate the efficiency of the technique to detect outliers. Then, various subsamples are defined by applying different thresholds to exclude outlier pixels from the classification process. The classification results prove the robustness of the Maximum Likelihood and Spectral Angle Mapper classifiers. Indeed, those classifiers were insensitive to outlier exclusion. On the contrary, the decision tree classifier showed better results when deleting 7.5% of pixels in the training data. The technique managed to detect outliers for all classes. In this study, few outliers were present in the training data, so that the classification quality was not deeply affected by the outliers.

Characterization of the volatile profile of Brazilian Merlot wines through comprehensive two dimensional gas chromatography time-of-flight mass spectrometric detection.

Wine aroma is an important characteristic and may be related to certain specific parameters, such as raw material and production process. The complexity of Merlot wine aroma was considered suitable for comprehensive two-dimensional gas chromatography (GCGC), as this technique offers superior performance when compared to one-dimensional gas chromatography (1D-GC). The profile of volatile compounds of Merlot wine was, for the first time, qualitatively analyzed by HS-SPME-GCxGC with a time-of-flight mass spectrometric detector (TOFMS), resulting in 179 compounds tentatively identified by comparison of experimental GCxGC retention indices and mass spectra with literature 1D-GC data and 155 compounds tentatively identified only by mass spectra comparison. A set of GCGC experimental retention indices was also, for the first time, presented for a specific inverse set of columns. Esters were present in higher number (94), followed by alcohols (80), ketones (29), acids (29), aldehydes (23), terpenes (23), lactones (16), furans (14), sulfur compounds (9), phenols (7), pyrroles (5), C13-norisoprenoids (3), and pyrans (2). GCxGC/TOFMS parameters were improved and optimal conditions were: a polar (polyethylene glycol)/medium polar (50% phenyl 50% dimethyl arylene siloxane) column set, oven temperature offset of 10ºC, 7 s as modulation period and 1.4 s of hot pulse duration. Co-elutions came up to 138 compounds in 1D and some of them were resolved in 2D. Among the coeluted compounds, thirty-three volatiles co-eluted in both 1D and 2D and their tentative identification was possible only due to spectral deconvolution. Some compounds that might have important contribution to aroma notes were included in these superimposed peaks. Structurally organized distribution of compounds in the 2D space was observed for esters, aldehydes and ketones, alcohols, thiols, lactones, acids and also inside subgroups, as occurred with esters and alcohols. The Fischer Ratio was useful for establishing the analytes responsible for the main differences between Merlot and non-Merlot wines. Differentiation among Merlot wines and wines of other grape varieties were mainly perceived through the following components: ethyl dodecanoate, 1-hexanol, ethyl nonanoate, ethyl hexanoate, ethyl decanoate, dehydro-2-methyl-3(2H)thiophenone, 3-methyl butanoic acid, ethyl tetradecanoate, methyl octanoate, 1,4 butanediol, and 6-methyloctan-1-ol.

Genome-wide detection of CNVs and their association with meat tenderness in Nelore cattle.

Brazil is one of the largest beef producers and exporters in the world with the Nelore breed representing the vast majority of Brazilian cattle (Bos taurus indicus). Despite the great adaptability of the Nelore breed to tropical climate, meat tenderness (MT) remains to be improved. Several factors including genetic composition can influence MT. In this article, we report a genome-wide analysis of copy number variation (CNV) inferred from Illumina1 High Density SNP-chip data for a Nelore population of 723 males. We detected >2,600 CNV regions (CNVRs) representing 6.5% of the genome. Comparing our results with previous studies revealed an overlap in 1400 CNVRs (>50%). A total of 1,155 CNVRs (43.6%) overlapped 2,750 genes. They were enriched for processes involving guanosine triphosphate (GTP), previously reported to influence skeletal muscle physiology and morphology. Nelore CNVRs also overlapped QTLs for MT reported in other breeds (8.9%, 236 CNVRs) and from a previous study with this population (4.1%, 109 CNVRs). Two CNVRs were also proximal to glutathione metabolism genes that were previously associated with MT. Genome-wide association study of CN state with estimated breeding values derived from meat shear force identified 6 regions, including a region on BTA3 that contains genes of the cAMP and cGMP pathway. Ten CNVRs that overlapped regions associated with MT were successfully validated by qPCR. Our results represent the first comprehensive CNV study in Bos taurus indicus cattle and identify regions in which copy number changes are potentially of importance for the MT phenotype.

Deep Learning Architectures for time of arrival detection in Acoustic Emissions Monitoring

Acoustic Emission (AE) monitoring can be used to detect the presence of damage as well as determine its location in Structural Health Monitoring (SHM) applications. Information on the time difference of the signal generated by the damage event arriving at different sensors is essential in performing localization. This makes the time of arrival (ToA) an important piece of information to retrieve from the AE signal. Generally, this is determined using statistical methods such as the Akaike Information Criterion (AIC) which is particularly prone to errors in the presence of noise. And given that the structures of interest are surrounded with harsh environments, a way to accurately estimate the arrival time in such noisy scenarios is of particular interest. In this work, two new methods are presented to estimate the arrival times of AE signals which are based on Machine Learning. Inspired by great results in the field, two models are presented which are Deep Learning models - a subset of machine learning. They are based on Convolutional Neural Network (CNN) and Capsule Neural Network (CapsNet). The primary advantage of such models is that they do not require the user to pre-define selected features but only require raw data to be given and the models establish non-linear relationships between the inputs and outputs. The performance of the models is evaluated using AE signals generated by a custom ray-tracing algorithm by propagating them on an aluminium plate and compared to AIC. It was found that the relative error in estimation on the test set was < 5% for the models compared to around 45% of AIC. The testing process was further continued by preparing an experimental setup and acquiring real AE signals to test on. Similar performances were observed where the two models not only outperform AIC by more than a magnitude in their average errors but also they were shown to be a lot more robust as compared to AIC which fails in the presence of noise.

Automatic detection of the inferior alveolar nerve in CT scans with CenterNet

The inferior alveolar nerve (IAN) lies within the mandibular canal, named inferior alveolar canal in literature. The detection of this nerve is important during maxillofacial surgeries or for creating dental implants. The poor quality of cone-beam computed tomography (CBCT) and computed tomography (CT) scans and/or bone gaps within the mandible increase the difficulty of this task, posing a challenge to human experts who are going to manually detect it and resulting in a time-consuming task.Therefore this thesis investigates two methods to automatically detect the IAN: a non-data driven technique and a deep-learning method. The latter tracks the IAN position at each frame leveraging detections obtained with the deep neural network CenterNet, fined-tuned for our task, and temporal and spatial information.

Model-Based validation of Driver Drowsiness Detection System for ADAS

The work described in this Master’s Degree thesis was born after the collaboration with the company Maserati S.p.a, an Italian luxury car maker with its headquarters located in Modena, in the heart of the Italian Motor Valley, where I worked as a stagiaire in the Virtual Engineering team between September 2021 and February 2022. This work proposes the validation using real-world ECUs of a Driver Drowsiness Detection (DDD) system prototype based on different detection methods with the goal to overcome input signal losses and system failures. Detection methods of different categories have been chosen from literature and merged with the goal of utilizing the benefits of each of them, overcoming their limitations and limiting as much as possible their degree of intrusiveness to prevent any kind of driving distraction: an image processing-based technique for human physical signals detection as well as methods based on driver-vehicle interaction are used. A Driver-In-the-Loop simulator is used to gather real data on which a Machine Learning-based algorithm will be trained and validated. These data come from the tests that the company conducts in its daily activities so confidential information about the simulator and the drivers will be omitted. Although the impact of the proposed system is not remarkable and there is still work to do in all its elements, the results indicate the main advantages of the system in terms of robustness against subsystem failures and signal losses.