Search results for: XBG classifier

Authors: T. Thein, S. Kalyar Myo

Abstract:

Human uses visual information for understanding the speech contents in noisy conditions or in situations where the audio signal is not available. The primary advantage of visual information is that it is not affected by the acoustic noise and cross talk among speakers. Using visual information from the lip movements can improve the accuracy and robustness of automatic speech recognition. However, a major challenge with most automatic lip reading system is to find a robust and efficient method for extracting the linguistically relevant speech information from a lip image sequence. This is a difficult task due to variation caused by different speakers, illumination, camera setting and the inherent low luminance and chrominance contrast between lip and non-lip region. Several researchers have been developing methods to overcome these problems; the one is lip reading. Moreover, it is well known that visual information about speech through lip reading is very useful for human speech recognition system. Lip reading is the technique of a comprehensive understanding of underlying speech by processing on the movement of lips. Therefore, lip reading system is one of the different supportive technologies for hearing impaired or elderly people, and it is an active research area. The need for lip reading system is ever increasing for every language. This research aims to develop a visual teaching method system for the hearing impaired persons in Myanmar, how to pronounce words precisely by identifying the features of lip movement. The proposed research will work a lip reading system for Myanmar Consonants, one syllable consonants (င (Nga)၊ ည (Nya)၊ မ (Ma)၊ လ (La)၊ ၀ (Wa)၊ သ (Tha)၊ ဟ (Ha)၊ အ (Ah) ) and two syllable consonants ( က(Ka Gyi)၊ ခ (Kha Gway)၊ ဂ (Ga Nge)၊ ဃ (Ga Gyi)၊ စ (Sa Lone)၊ ဆ (Sa Lain)၊ ဇ (Za Gwe) ၊ ဒ (Da Dway)၊ ဏ (Na Gyi)၊ န (Na Nge)၊ ပ (Pa Saug)၊ ဘ (Ba Gone)၊ ရ (Ya Gaug)၊ ဠ (La Gyi) ). In the proposed system, there are three subsystems, the first one is the lip localization system, which localizes the lips in the digital inputs. The next one is the feature extraction system, which extracts features of lip movement suitable for visual speech recognition. And the final one is the classification system. In the proposed research, Two Dimensional Discrete Cosine Transform (2D-DCT) and Linear Discriminant Analysis (LDA) with Active Contour Model (ACM) will be used for lip movement features extraction. Support Vector Machine (SVM) classifier is used for finding class parameter and class number in training set and testing set. Then, experiments will be carried out for the recognition accuracy of Myanmar consonants using the only visual information on lip movements which are useful for visual speech of Myanmar languages. The result will show the effectiveness of the lip movement recognition for Myanmar Consonants. This system will help the hearing impaired persons to use as the language learning application. This system can also be useful for normal hearing persons in noisy environments or conditions where they can find out what was said by other people without hearing voice.

Keywords: feature extraction, lip reading, lip localization, Active Contour Model (ACM), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Two Dimensional Discrete Cosine Transform (2D-DCT)

Procedia PDF Downloads 259

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 104

Authors: Sofia Papadimitriou

Abstract:

INTRODUCTION: The differential diagnosis between acute viral and bacterial infections is an important cost-effectiveness parameter at the stage of the treatment process in order to achieve the maximum benefits in therapeutic intervention by combining the minimum cost to ensure the proper use of antibiotics.The discovery of sensitive and robust molecular diagnostic tests in response to the role of the host in infections has enhanced the accurate diagnosis and differentiation of infections. METHOD: The study used a sample of six independent blood samples (total=756) which are associated with human proteins-proteins, each of which at the transcription stage expresses a different response in the host network between viral and bacterial infections.Τhe individual blood samples are subjected to a sequence of computer filters that identify a gene panel corresponding to an autonomous diagnostic score. The data set and the correspondence of the gene panel to the diagnostic patents a new Bangalore -Viral Bacterial (BL-VB). FINDING: We use a biomarker based on the blood of 10 genes(Panel-VB) that are an important prognostic value for the detection of viruses from bacterial infections with a weighted average AUROC of 0.97(95% CL:0.96-0.99) in eleven independent samples (sets n=898). We discovered a base with a patient score (VB 10 ) according to the table, which is a significant diagnostic value with a weighted average of AUROC 0.94(95% CL: 0.91-0.98) in 2996 patient samples from 56 public sets of data from 19 different countries. We also studied VB 10 in a new cohort of South India (BL-VB,n=56) and found 97% accuracy in confirmed cases of viral and bacterial infections. We found that VB 10 (a)accurately identifies the type of infection even in unspecified cases negative to the culture (b) shows its clinical condition recovery and (c) applies to all age groups, covering a wide range of acute bacterial and viral infectious, including non-specific pathogens. We applied our VB 10 rating to publicly available COVID 19 data and found that our rating diagnosed viral infection in patient samples. RESULTS: Τhe results of the study showed the diagnostic power of the biomarker VB 10 as a diagnostic test for the accurate diagnosis of acute infections in recovery conditions. We look forward to helping you make clinical decisions about prescribing antibiotics and integrating them into your policies management of antibiotic stewardship efforts. CONCLUSIONS: Overall, we are developing a new property of the RNA-based biomarker and a new blood test to differentiate between viral and bacterial infections to assist a physician in designing the optimal treatment regimen to contribute to the proper use of antibiotics and reduce the burden on antimicrobial resistance, AMR.

Keywords: acute infections, antimicrobial resistance, biomarker, blood transcriptome, systems biology, classifier diagnostic score

Procedia PDF Downloads 127

Authors: Sandra Smieszek, Jonathan Haines

Abstract:

Introduction: Numerous research efforts have focused on searching for ‘longevity genes’. However, attempting to decipher the genetic component of the longevous phenotype have resulted in limited success and the mechanisms governing longevity remain to be explained. We conducted a genome-wide homozygosity analysis (GWHA) of the founder population of the Amish community in central Ohio. While genome-wide association studies using unrelated individuals have revealed many interesting longevity associated variants, these variants are typically of small effect and cannot explain the observed patterns of heritability for this complex trait. The Amish provide a large cohort of extended kinships allowing for in depth analysis via family-based approach excellent population due to its. Heritability of longevity increases with age with significant genetic contribution being seen in individuals living beyond 60 years of age. In our present analysis we show that the heritability of longevity is estimated to be increasing with age particularly on the paternal side. Methods: The present analysis integrated both phenotypic and genotypic data and led to the discovery of a series of variants, distinct for stratified populations across ages and distinct for paternal and maternal cohorts. Specifically 5437 subjects were analyzed and a subset of 893 successfully genotyped individuals was used to assess CHIP heritability. We have conducted the homozygosity analysis to examine if homozygosity is associated with increased risk of living beyond 90. We analyzed AMISH cohort genotyped for 614,957 SNPs. Results: We delineated 10 significant regions of homozygosity (ROH) specific for the age group of interest (>90). Of particular interest was ROH on chromosome 13, P < 0.0001. The lead SNPs rs7318486 and rs9645914 point to COL4A2 and our lead SNP. COL25A1 encodes one of the six subunits of type IV collagen, the C-terminal portion of the protein, known as canstatin, is an inhibitor of angiogenesis and tumor growth. COL4A2 mutations have been reported with a broader spectrum of cerebrovascular, renal, ophthalmological, cardiac, and muscular abnormalities. The second region of interest points to IRS2. Furthermore we built a classifier using the obtained SNPs from the significant ROH region with 0.945 AUC giving ability to discriminate between those living beyond to 90 years of age and beyond. Conclusion: In conclusion our results suggest that a history of longevity does indeed contribute to increasing the odds of individual longevity. Preliminary results are consistent with conjecture that heritability of longevity is substantial when we start looking at oldest fifth and smaller percentiles of survival specifically in males. We will validate all the candidate variants in independent cohorts of centenarians, to test whether they are robustly associated with human longevity. The identified regions of interest via ROH analysis could be of profound importance for the understanding of genetic underpinnings of longevity.

Keywords: regions of homozygosity, longevity, SNP, Amish

Procedia PDF Downloads 206

Authors: Ran Goldblatt, Nicholas Jones, Jennifer Mannix, Brad Bottoms

Abstract:

Accurate, complete, and up-to-date geospatial information is the foundation of successful disaster management. When the 2010 Haiti Earthquake struck, accurate and timely information on the distribution of critical infrastructure was essential for the disaster response community for effective search and rescue operations. Existing geospatial datasets such as Google Maps did not have comprehensive coverage of these features. In the days following the earthquake, many organizations released high-resolution satellite imagery, catalyzing a worldwide effort to map Haiti and support the recovery operations. Of these organizations, OpenStreetMap (OSM), a collaborative project to create a free editable map of the world, used the imagery to support volunteers to digitize roads, buildings, and other features, creating the most detailed map of Haiti in existence in just a few weeks. However, large portions of the island are still not fully covered by OSM. There is an increasing need for a tool to automatically identify which areas in Haiti, as well as in other countries vulnerable to disasters, that are not fully mapped. The objective of this project is to leverage different types of remote sensing measurements, together with machine learning approaches, in order to identify geographical areas where OSM coverage of building footprints is incomplete. Several remote sensing measures and derived products were assessed as potential predictors of OSM building footprints coverage, including: intensity of light emitted at night (based on VIIRS measurements), spectral indices derived from Sentinel-2 satellite (normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), soil-adjusted vegetation index (SAVI), urban index (UI)), surface texture (based on Sentinel-1 SAR measurements)), elevation and slope. Additional remote sensing derived products, such as Hansen Global Forest Change, DLR`s Global Urban Footprint (GUF), and World Settlement Footprint (WSF), were also evaluated as predictors, as well as OSM street and road network (including junctions). Using a supervised classification with a random forest classifier resulted in the prediction of 89% of the variation of OSM building footprint area in a given cell. These predictions allowed for the identification of cells that are predicted to be covered but are actually not mapped yet. With these results, this methodology could be adapted to any location to assist with preparing for future disastrous events and assure that essential geospatial information is available to support the response and recovery efforts during and following major disasters.

Keywords: disaster management, Haiti, machine learning, OpenStreetMap, remote sensing

Procedia PDF Downloads 98

Authors: Soyon Kim, Edward Kim

Abstract:

In order to retrieve information from the massive stream of songs in the music industry, music search by title, lyrics, artist, mood, and genre has become more important. Despite the subjectivity and controversy over the definition of music genres across different nations and cultures, automatic genre classification systems that facilitate the process of music categorization have been developed. Manual genre selection by music producers is being provided as statistical data for designing automatic genre classification systems. In this paper, an automatic music genre classification system utilizing non-negative matrix factorization (NMF) is proposed. Short-term characteristics of the music signal can be captured based on the timbre features such as mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), octave-based spectral contrast (OSC), and octave band sum (OBS). Long-term time-varying characteristics of the music signal can be summarized with (1) the statistical features such as mean, variance, minimum, and maximum of the timbre features and (2) the modulation spectrum features such as spectral flatness measure, spectral crest measure, spectral peak, spectral valley, and spectral contrast of the timbre features. Not only these conventional basic long-term feature vectors, but also NMF based feature vectors are proposed to be used together for genre classification. In the training stage, NMF basis vectors were extracted for each genre class. The NMF features were calculated in the log spectral magnitude domain (NMF-LSM) as well as in the basic feature vector domain (NMF-BFV). For NMF-LSM, an entire full band spectrum was used. However, for NMF-BFV, only low band spectrum was used since high frequency modulation spectrum of the basic feature vectors did not contain important information for genre classification. In the test stage, using the set of pre-trained NMF basis vectors, the genre classification system extracted the NMF weighting values of each genre as the NMF feature vectors. A support vector machine (SVM) was used as a classifier. The GTZAN multi-genre music database was used for training and testing. It is composed of 10 genres and 100 songs for each genre. To increase the reliability of the experiments, 10-fold cross validation was used. For a given input song, an extracted NMF-LSM feature vector was composed of 10 weighting values that corresponded to the classification probabilities for 10 genres. An NMF-BFV feature vector also had a dimensionality of 10. Combined with the basic long-term features such as statistical features and modulation spectrum features, the NMF features provided the increased accuracy with a slight increase in feature dimensionality. The conventional basic features by themselves yielded 84.0% accuracy, but the basic features with NMF-LSM and NMF-BFV provided 85.1% and 84.2% accuracy, respectively. The basic features required dimensionality of 460, but NMF-LSM and NMF-BFV required dimensionalities of 10 and 10, respectively. Combining the basic features, NMF-LSM and NMF-BFV together with the SVM with a radial basis function (RBF) kernel produced the significantly higher classification accuracy of 88.3% with a feature dimensionality of 480.

Keywords: mel-frequency cepstral coefficient (MFCC), music genre classification, non-negative matrix factorization (NMF), support vector machine (SVM)

Procedia PDF Downloads 265

Authors: Akbar Gharbali, Ali Abbasian Ardekani, Afshin Mohammadi

Abstract:

Introduction: Thyroid nodules have an incidence of 33-68% in the general population. More than 5-15% of these nodules are malignant. Early detection and treatment of thyroid nodules increase the cure rate and provide optimal treatment. Between the medical imaging methods, Ultrasound is the chosen imaging technique for assessment of thyroid nodules. The confirming of the diagnosis usually demands repeated fine-needle aspiration biopsy (FNAB). So, current management has morbidity and non-zero mortality. Objective: To explore diagnostic potential of automatic texture analysis (TA) methods in differentiation benign and malignant thyroid nodules by ultrasound imaging in order to help for reliable diagnosis and monitoring of the thyroid nodules in their early stages with no need biopsy. Material and Methods: The thyroid US image database consists of 70 patients (26 benign and 44 malignant) which were reported by Radiologist and proven by the biopsy. Two slices per patient were loaded in Mazda Software version 4.6 for automatic texture analysis. Regions of interests (ROIs) were defined within the abnormal part of the thyroid nodules ultrasound images. Gray levels within an ROI normalized according to three normalization schemes: N1: default or original gray levels, N2: +/- 3 Sigma or dynamic intensity limited to µ+/- 3σ, and N3: present intensity limited to 1% - 99%. Up to 270 multiscale texture features parameters per ROIs per each normalization schemes were computed from well-known statistical methods employed in Mazda software. From the statistical point of view, all calculated texture features parameters are not useful for texture analysis. So, the features based on maximum Fisher coefficient and the minimum probability of classification error and average correlation coefficients (POE+ACC) eliminated to 10 best and most effective features per normalization schemes. We analyze this feature under two standardization states (standard (S) and non-standard (NS)) with Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-Linear Discriminant Analysis (NDA). The 1NN classifier was performed to distinguish between benign and malignant tumors. The confusion matrix and Receiver operating characteristic (ROC) curve analysis were used for the formulation of more reliable criteria of the performance of employed texture analysis methods. Results: The results demonstrated the influence of the normalization schemes and reduction methods on the effectiveness of the obtained features as a descriptor on discrimination power and classification results. The selected subset features under 1%-99% normalization, POE+ACC reduction and NDA texture analysis yielded a high discrimination performance with the area under the ROC curve (Az) of 0.9722, in distinguishing Benign from Malignant Thyroid Nodules which correspond to sensitivity of 94.45%, specificity of 100%, and accuracy of 97.14%. Conclusions: Our results indicate computer-aided diagnosis is a reliable method, and can provide useful information to help radiologists in the detection and classification of benign and malignant thyroid nodules.

Keywords: ultrasound imaging, thyroid nodules, computer aided diagnosis, texture analysis, PCA, LDA, NDA

Procedia PDF Downloads 256

Authors: Jie Lin, Yiwen Pan, Li Zhang, Zhangyong Xia

Abstract:

Atherosclerosis is a chronic inflammatory disease characterized by the accumulation of lipids, immune cells, and extracellular matrix in the arterial walls. This pathological process can lead to the formation of plaques that can obstruct blood flow and trigger various cardiovascular diseases such as heart attack and stroke. The underlying molecular mechanisms still remain unclear, although many studies revealed the dysfunction of endothelial cells, recruitment and activation of monocytes and macrophages, and the production of pro-inflammatory cytokines and chemokines in atherosclerosis. This study aimed to identify hub genes involved in the progression of atherosclerosis and to analyze their biological function in silico, thereby enhancing our understanding of the disease’s molecular mechanisms. Through the analysis of microarray data, we examined the gene expression in media and neo-intima from plaques, as well as distant macroscopically intact tissue, across a cohort of 32 hypertensive patients. Initially, 112 differentially expressed genes (DEGs) were identified. Subsequent immune infiltration analysis indicated a predominant presence of 27 immune cell types in the atherosclerosis group, particularly noting an increase in monocytes and macrophages. In the Weighted gene co-expression network analysis (WGCNA), 10 modules with a minimum of 30 genes were defined as key modules, with blue, dark, Oliver green and sky-blue modules being the most significant. These modules corresponded respectively to monocyte, activated B cell, and activated CD4 T cell gene patterns, revealing a strong morphological-genetic correlation. From these three gene patterns (modules morphology), a total of 2509 key genes (Gene Significance >0.2, module membership>0.8) were extracted. Six hub genes (CD36, DPP4, HMOX1, PLA2G7, PLN2, and ACADL) were then identified by intersecting 2509 key genes, 102 DEGs with lipid-related genes from the Genecard database. The bio-functional analysis of six hub genes was estimated by a robust classifier with an area under the curve (AUC) of 0.873 in the ROC plot, indicating excellent efficacy in differentiating between the disease and control group. Moreover, PCA visualization demonstrated clear separation between the groups based on these six hub genes, suggesting their potential utility as classification features in predictive models. Protein-protein interaction (PPI) analysis highlighted DPP4 as the most interconnected gene. Within the constructed key gene-drug network, 462 drugs were predicted, with ursodeoxycholic acid (UDCA) being identified as a potential therapeutic agent for modulating DPP4 expression. In summary, our study identified critical hub genes implicated in the progression of atherosclerosis through comprehensive bioinformatic analyses. These findings not only advance our understanding of the disease but also pave the way for applying similar analytical frameworks and predictive models to other diseases, thereby broadening the potential for clinical applications and therapeutic discoveries.

Keywords: atherosclerosis, hub genes, drug prediction, bioinformatics

Procedia PDF Downloads 28

Authors: Safaa M. Hassan; Safwat S. Gabr, Mohamed F. Sadek

Abstract:

This study is proposed for the lithological and iron oxides detection in the old mine areas of El-Bahariya Depression, Western Desert, using ASTER and Landsat-8 remote sensing data. Four old iron ore occurrences, namely; El-Gedida, El-Haraa, Ghurabi, and Nasir mine areas found in the El-Bahariya area. This study aims to find new high potential areas for iron mineralization around El-Baharyia depression. Image processing methods such as principle component analysis (PCA) and band ratios (b4/b5, b5/b6, b6/b7, and 4/2, 6/7, band 6) images were used for lithological identification/mapping that includes the iron content in the investigated area. ASTER and Landsat-8 visible and short-wave infrared data found to help mapping the ferruginous sandstones, iron oxides as well as the clay minerals in and around the old mines area of El-Bahariya depression. Landsat-8 band ratio and the principle component of this study showed well distribution of the lithological units, especially ferruginous sandstones and iron zones (hematite and limonite) along with detection of probable high potential areas for iron mineralization which can be used in the future and proved the ability of Landsat-8 and ASTER data in mapping these features. Minimum Noise Fraction (MNF), Mixture Tuned Matched Filtering (MTMF), pixel purity index methods as well as Spectral Ange Mapper classifier algorithm have been successfully discriminated the hematite and limonite content within the iron zones in the study area. Various ASTER image spectra and ASD field spectra of hematite and limonite and the surrounding rocks are compared and found to be consistent in terms of the presence of absorption features at range from 1.95 to 2.3 μm for hematite and limonite. Pixel purity index algorithm and two sub-pixel spectral methods, namely Mixture Tuned Matched Filtering (MTMF) and matched filtering (MF) methods, are applied to ASTER bands to delineate iron oxides (hematite and limonite) rich zones within the rock units. The results are validated in the field by comparing image spectra of spectrally anomalous zone with the USGS resampled laboratory spectra of hematite and limonite samples using ASD measurements. A number of iron oxides rich zones in addition to the main surface exposures of the El-Gadidah Mine, are confirmed in the field. The proposed method is a successful application of spectral mapping of iron oxides deposits in the exposed rock units (i.e., ferruginous sandstone) and present approach of both ASTER and ASD hyperspectral data processing can be used to delineate iron-rich zones occurring within similar geological provinces in any parts of the world.

Keywords: Landsat-8, ASTER, lithological mapping, iron exploration, western desert

Procedia PDF Downloads 114

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 37

Authors: Alexandre Leclerc, Christian Gout, Carole Le Guyader, Pierre Besset, Carlos Miranda, Olivier Gibaru

Abstract:

In this work, we address the challenges faced by human operators in visually inspecting production lines in factories, especially in automotive manufacturing involving numerous checkpoints to be handled every minute for extended hours. This tedious and error-prone process calls for a solution, and we propose an AI-powered assistant to achieve this goal. The objective is to design a system that can efficiently perform visual inspections on moving items and assemblies, in a structured manner, such as on conveyors and production lines. The system task is to visually verify specific part conformity for each assembly or class of assembly. For instance, in an automotive assembly line, the assistant may need to check the presence of headlights and ensure proper rim mounting. To meet these requirements, the assistant must detect the passage of relevant assemblies and perform anomaly detection on relevent parts. Notably, the system copes with the a prior knowledge deficit challenge of which assemblies and parts the users will choose for inspection. Therefore, it needs to be versatile enough to work across a wide range of industrial use cases. By incorporating these considerations, the proposed AI-powered assistant aims to reduce the difficulty, tedium and unreliability of human visual checks on production lines. Constraints specific to the industrial sector underpin the proposal: • Easy and fast setup (< 1 hour). • Strong hardware constraints on GPU power and memory. • Short inference time (< 100 ms). The proposed approach involves leveraging recent advances in mathematical models and computer science tools complying with the above requirements. It can be summarized as follows: 1) Implementing state-of-the-art deep neural networks trained on vast and diverse datasets (known as foundation models) to assist with annotation, facilitating rapid preparation for detector training. 2) Utilizing the latest models capable of handling object detection and instance segmentation tasks to track the objects needing analysis. Result refinement is then achieved through trajectory analysis of the examined areas. 3) Incorporating a pre-trained classifier and fine-tuning it using detector-acquired data. 4) Inferring the classification model on the detections obtained from the trackers to warn the operator quickly when necessary. Furthermore, we subjected these methods to continuous testing in real industrial environments to ensure their practical applicability and effectiveness.

Keywords: anomaly detection, computer vision, deep learning, image and video processing, image segmentation, industrial inspection, production line

Procedia PDF Downloads 52

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 102

Authors: Kenneth A. Rostowsky, Alexander S. Maher, Nahian F. Chowdhury, Andrei Irimia

Abstract:

The clinical significance of cerebral microbleeds (CMBs) due to mild traumatic brain injury (mTBI) remains unclear. Here we use magnetic resonance imaging (MRI), diffusion tensor imaging (DTI) and connectomic analysis to investigate the statistical association between mTBI-related CMBs, post-TBI changes to the human connectome and neurological/cognitive deficits. This study was undertaken in agreement with US federal law (45 CFR 46) and was approved by the Institutional Review Board (IRB) of the University of Southern California (USC). Two groups, one consisting of 26 (13 females) mTBI victims and another comprising 26 (13 females) healthy control (HC) volunteers were recruited through IRB-approved procedures. The acute Glasgow Coma Scale (GCS) score was available for each mTBI victim (mean µ = 13.2; standard deviation σ = 0.4). Each HC volunteer was assigned a GCS of 15 to indicate the absence of head trauma at the time of enrollment in our study. Volunteers in the HC and mTBI groups were matched according to their sex and age (HC: µ = 67.2 years, σ = 5.62 years; mTBI: µ = 66.8 years, σ = 5.93 years). MRI [including T1- and T2-weighted volumes, gradient recalled echo (GRE)/susceptibility weighted imaging (SWI)] and gradient echo (GE) DWI volumes were acquired using the same MRI scanner type (Trio TIM, Siemens Corp.). Skull-stripping and eddy current correction were implemented. DWI volumes were processed in TrackVis (http://trackvis.org) and 3D Slicer (http://www.slicer.org). Tensors were fit to DWI data to perform DTI, and tractography streamlines were then reconstructed using deterministic tractography. A voxel classifier was used to identify image features as CMB candidates using Microbleed Anatomic Rating Scale (MARS) guidelines. For each peri-lesional DTI streamline bundle, the null hypothesis was formulated as the statement that there was no neurological or cognitive deficit associated with between-scan differences in the mean FA of DTI streamlines within each bundle. The statistical significance of each hypothesis test was calculated at the α = 0.05 level, subject to the family-wise error rate (FWER) correction for multiple comparisons. Results: In HC volunteers, the along-track analysis failed to identify statistically significant differences in the mean FA of DTI streamline bundles. In the mTBI group, significant differences in the mean FA of peri-lesional streamline bundles were found in 21 out of 26 volunteers. In those volunteers where significant differences had been found, these differences were associated with an average of ~47% of all identified CMBs (σ = 21%). In 12 out of the 21 volunteers exhibiting significant FA changes, cognitive functions (memory acquisition and retrieval, top-down control of attention, planning, judgment, cognitive aspects of decision-making) were found to have deteriorated over the six months following injury (r = -0.32, p < 0.001). Our preliminary results suggest that acute post-TBI CMBs may be associated with cognitive decline in some mTBI patients. Future research should attempt to identify mTBI patients at high risk for cognitive sequelae.

Keywords: traumatic brain injury, magnetic resonance imaging, diffusion tensor imaging, connectomics

Procedia PDF Downloads 146

Authors: Panagiota Katsikouli, William Hamilton Byrne, Thomas Gammeltoft-Hansen, Tijs Slaats

Abstract:

An individual who demonstrates a well-founded fear of persecution or faces real risk of being subjected to torture is eligible for asylum. In Danish law, the exact legal thresholds reflect those established by international conventions, notably the 1951 Refugee Convention and the 1950 European Convention for Human Rights. These international treaties, however, remain largely silent when it comes to how states should assess asylum claims. As a result, national authorities are typically left to determine an individual’s legal eligibility on a narrow basis consisting of an oral testimony, which may itself be hampered by several factors, including imprecise language interpretation, insecurity or lacking trust towards the authorities among applicants. The leaky ground, on which authorities must assess their subjective perceptions of asylum applicants' credibility, questions whether, in all cases, adjudicators make the correct decision. Moreover, the subjective element in these assessments raises questions on whether individual asylum cases could be afflicted by implicit biases or stereotyping amongst adjudicators. In fact, recent studies have uncovered significant correlations between decision outcomes and the experience and gender of the assigned judge, as well as correlations between asylum outcomes and entirely external events such as weather and political elections. In this study, we analyze a publicly available dataset containing approximately 8,000 summaries of asylum cases, initially rejected, and re-tried by the Refugee Appeals Board (RAB) in Denmark. First, we look for variations in the recognition rates, with regards to a number of applicants’ features: their country of origin/nationality, their identified gender, their identified religion, their ethnicity, whether torture was mentioned in their case and if so, whether it was supported or not, and the year the applicant entered Denmark. In order to extract those features from the text summaries, as well as the final decision of the RAB, we applied natural language processing and regular expressions, adjusting for the Danish language. We observed interesting variations in recognition rates related to the applicants’ country of origin, ethnicity, year of entry and the support or not of torture claims, whenever those were made in the case. The appearance (or not) of significant variations in the recognition rates, does not necessarily imply (or not) bias in the decision-making progress. None of the considered features, with the exception maybe of the torture claims, should be decisive factors for an asylum seeker’s fate. We therefore investigate whether the decision can be predicted on the basis of these features, and consequently, whether biases are likely to exist in the decisionmaking progress. We employed a number of machine learning classifiers, and found that when using the applicant’s country of origin, religion, ethnicity and year of entry with a random forest classifier, or a decision tree, the prediction accuracy is as high as 82% and 85% respectively. tentially predictive properties with regards to the outcome of an asylum case. Our analysis and findings call for further investigation on the predictability of the outcome, on a larger dataset of 17,000 cases, which is undergoing.

Keywords: asylum adjudications, automated decision-making, machine learning, text mining

Procedia PDF Downloads 65

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 28

Authors: Alena Nesterenko, Svetlana Petrikova

Abstract:

Research evaluation is one of the most important elements of self-regulation and development of researchers as it is impartial and independent process of assessment. The method of expert evaluations as a scientific instrument solving complicated non-formalized problems is firstly a scientifically sound way to conduct the assessment which maximum effectiveness of work at every step and secondly the usage of quantitative methods for evaluation, assessment of expert opinion and collective processing of the results. These two features distinguish the method of expert evaluations from long-known expertise widespread in many areas of knowledge. Different typical problems require different types of expert evaluations methods. Several issues which arise with these methods are experts’ selection, management of assessment procedure, proceeding of the results and remuneration for the experts. To address these issues an on-line system was created with the primary purpose of development of a versatile application for many workgroups with matching approaches to scientific work management. Online documentation assessment and statistics system allows: - To realize within one platform independent activities of different workgroups (e.g. expert officers, managers). - To establish different workspaces for corresponding workgroups where custom users database can be created according to particular needs. - To form for each workgroup required output documents. - To configure information gathering for each workgroup (forms of assessment, tests, inventories). - To create and operate personal databases of remote users. - To set up automatic notification through e-mail. The next stage is development of quantitative and qualitative criteria to form a database of experts. The inventory was made so that the experts may not only submit their personal data, place of work and scientific degree but also keywords according to their expertise, academic interests, ORCID, Researcher ID, SPIN-code RSCI, Scopus AuthorID, knowledge of languages, primary scientific publications. For each project, competition assessments are processed in accordance to ordering party demands in forms of apprised inventories, commentaries (50-250 characters) and overall review (1500 characters) in which expert states the absence of conflict of interest. Evaluation is conducted as follows: as applications are added to database expert officer selects experts, generally, two persons per application. Experts are selected according to the keywords; this method proved to be good unlike the OECD classifier. The last stage: the choice of the experts is approved by the supervisor, the e-mails are sent to the experts with invitation to assess the project. An expert supervisor is controlling experts writing reports for all formalities to be in place (time-frame, propriety, correspondence). If the difference in assessment exceeds four points, the third evaluation is appointed. As the expert finishes work on his expert opinion, system shows contract marked ‘new’, managers commence with the contract and the expert gets e-mail that the contract is formed and ready to be signed. All formalities are concluded and the expert gets remuneration for his work. The specificity of interaction of the examination officer with other experts will be presented in the report.

Keywords: expertise, management of research evaluation, method of expert evaluations, research evaluation

Procedia PDF Downloads 181

Authors: Thilini M. Yatanwala

Abstract:

CCTV (Closed-Circuit-Television) Surveillance System is being used in public places over decades and a large variety of data is being produced every moment. However, most of the CCTV data is stored in isolation without having integrity. As a result, identification of the behavior of suspicious people along with their location has become strenuous. This research was conducted to acquire more accurate and reliable timely information from the CCTV video records. The implemented system can identify human objects in public places based on outfit colors. Inter-process communication technologies were used to implement the CCTV camera network to track people in the premises. The research was conducted in three stages and in the first stage human objects were filtered from other movable objects available in public places. In the second stage people were uniquely identified based on their outfit colors and in the third stage an individual was continuously tracked in the CCTV network. A face detection algorithm was implemented using cascade classifier based on the training model to detect human objects. HAAR feature based two-dimensional convolution operator was introduced to identify features of the human face such as region of eyes, region of nose and bridge of the nose based on darkness and lightness of facial area. In the second stage outfit colors of human objects were analyzed by dividing the area into upper left, upper right, lower left, lower right of the body. Mean color, mod color and standard deviation of each area were extracted as crucial factors to uniquely identify human object using histogram based approach. Color based measurements were written in to XML files and separate directories were maintained to store XML files related to each camera according to time stamp. As the third stage of the approach, inter-process communication techniques were used to implement an acknowledgement based CCTV camera network to continuously track individuals in a network of cameras. Real time analysis of XML files generated in each camera can determine the path of individual to monitor full activity sequence. Higher efficiency was achieved by sending and receiving acknowledgments only among adjacent cameras. Suspicious incidents such as a person staying in a sensitive area for a longer period or a person disappeared from the camera coverage can be detected in this approach. The system was tested for 150 people with the accuracy level of 82%. However, this approach was unable to produce expected results in the presence of group of people wearing similar type of outfits. This approach can be applied to any existing camera network without changing the physical arrangement of CCTV cameras. The study of human identification and suspicious incident detection using outfit color analysis can achieve higher level of accuracy and the project will be continued by integrating motion and gait feature analysis techniques to derive more information from CCTV videos.

Keywords: CCTV surveillance, human detection and identification, image processing, inter-process communication, security, suspicious detection

Procedia PDF Downloads 149

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of the flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on the spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts, as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with an attention mechanism. In previous works on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work, with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on the presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: machine learning, classification and regression, gene circuit design, bidirectional transformers

Procedia PDF Downloads 32