Search results for: discriminator

Authors: Fahad Alhussein, Huaping Liu

Abstract:

This paper compares the multipath mitigation performance of code correlation reference waveform receivers with variable and fixed window width, for binary offset carrier and multiplexed binary offset carrier signals typically used in global navigation satellite systems. In the variable window width method, such width is iteratively reduced until the distortion on the discriminator with multipath is eliminated. This distortion is measured as the Euclidean distance between the actual discriminator (obtained with the incoming signal), and the local discriminator (generated with a local copy of the signal). The variable window width have shown better performance compared to the fixed window width. In particular, the former yields zero error for all delays for the BOC and MBOC signals considered, while the latter gives rather large nonzero errors for small delays in all cases. Due to its computational simplicity, the variable window width method is perfectly suitable for implementation in low-cost receivers.

Keywords: correlation reference waveform receivers, binary offset carrier, multiplexed binary offset carrier, global navigation satellite systems

Procedia PDF Downloads 92

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 232

Authors: Jovana Nikolov, Natasa Todorovic, Ivana Stojkovic

Abstract:

Monitoring of 222Rn in drinking or surface waters, as well as in groundwater has been performed in connection with geological, hydrogeological and hydrological surveys and health hazard studies. Liquid scintillation counting (LSC) is often preferred analytical method for 222Rn measurements in waters because it allows multiple-sample automatic analysis. LSC method implies mixing of water samples with organic scintillation cocktail, which triggers radon diffusion from the aqueous into organic phase for which it has a much greater affinity, eliminating possibility of radon emanation in that manner. Two direct LSC methods that assume different sample composition have been presented, optimized and evaluated in this study. One-phase method assumed direct mixing of 10 ml sample with 10 ml of emulsifying cocktail (Ultima Gold AB scintillation cocktail is used). Two-phase method involved usage of water-immiscible cocktails (in this study High Efficiency Mineral Oil Scintillator, Opti-Fluor O and Ultima Gold F are used). Calibration samples were prepared with aqueous 226Ra standard in glass 20 ml vials and counted on ultra-low background spectrometer Quantulus 1220TM equipped with PSA (Pulse Shape Analysis) circuit which discriminates alpha/beta spectra. Since calibration procedure is carried out with 226Ra standard, which has both alpha and beta progenies, it is clear that PSA discriminator has vital importance in order to provide reliable and precise spectra separation. Consequentially, calibration procedure was done through investigation of PSA discriminator level influence on 222Rn efficiency detection, using 226Ra calibration standard in wide range of activity concentrations. Evaluation of presented methods was based on obtained efficiency detections and achieved Minimal Detectable Activity (MDA). Comparison of presented methods, accuracy and precision as well as different scintillation cocktail’s performance was considered from results of measurements of 226Ra spiked water samples with known activity and environmental samples.

Keywords: 222Rn in water, Quantulus1220TM, scintillation cocktail, PSA parameter

Procedia PDF Downloads 169

Authors: Dongjoo Kim, Chang-Sik Son, Won-Seok Kang

Abstract:

Adequate sleep affects various parts of one’s overall physical and mental life. As one of the methods in determining the appropriate amount of sleep, this research presents a heart rate based sleep quality index. In order to evaluate sleep quality using the heart rate, sleep data from 280 subjects taken over one month are used. Their sleep data are categorized by a three-part heart rate range. After categorizing, some features are extracted, and the statistical significances are verified for these features. The results show that some features of this sleep quality index model have statistical significance. Thus, this heart rate based sleep quality index may be a useful discriminator of sleep.

Keywords: sleep, sleep quality, heart rate, statistical analysis

Procedia PDF Downloads 305

Authors: Jindong Gu, Matthias Schubert, Volker Tresp

Abstract:

In many outlier detection tasks, only training data belonging to one class, i.e., the positive class, is available. The task is then to predict a new data point as belonging either to the positive class or to the negative class, in which case the data point is considered an outlier. For this task, we propose a novel corrupted Generative Adversarial Network (CorGAN). In the adversarial process of training CorGAN, the Generator generates outlier samples for the negative class, and the Discriminator is trained to distinguish the positive training data from the generated negative data. The proposed framework is evaluated using an image dataset and a real-world network intrusion dataset. Our outlier-detection method achieves state-of-the-art performance on both tasks.

Keywords: one-class classification, outlier detection, generative adversary networks, semi-supervised learning

Procedia PDF Downloads 119

Authors: Sharun Akter Khushbu

Abstract:

‘SOS’ addresses text summary such as feasibility study and allows more comprehensive methods on text of language resources. Resources language has been exploited by the importance of text documental procedure. Throughout this key idea will come out a machine interpreter called an SOS that has built an argumentative as an employed model is LSTM-CNN(long short-term memory- recurrent neural network). Summarization of Bengali text formulated by the information of latent structure instead of brief input string counting as text. Text summarization is the proper utilization of optimal solutions being time reduction, and easy interpretation whenever human-generated summary and machine targeted summary remain similar and without degrading the semantic summarization quality. According to the problem affirmation key idea has advanced an algorithm with the method of encoder and decoder describing a sequential structure that is rigorously connected with actual predicted and meaningful output. Regarding the seq2seq approach aimed in the future with high semantic summarization similarity on behalf of the large data samples that are also enlisted by the method. Thus, the SOS method assigns a discriminator over Bengali text documents where encoded input sequences such as summary and decoded the targeted summary of gist will be an error-free machine.

Keywords: LSTM-CNN, NN, SOS, text summarization

Procedia PDF Downloads 36

Authors: Zhang Shuqi, Liu Dan

Abstract:

For the problems in intelligent network anomaly traffic detection models, such as low detection accuracy caused by the lack of training samples, poor effect with small sample attack detection, a classification model enhancement method, F-ACGAN(Flow Auxiliary Classifier Generative Adversarial Network) which introduces generative adversarial network and adversarial training, is proposed to solve these problems. Generating adversarial data with category labels could enhance the training effect and improve classification accuracy and model robustness. FACGAN consists of three steps: feature preprocess, which includes data type conversion, dimensionality reduction and normalization, etc.; A generative adversarial network model with feature learning ability is designed, and the sample generation effect of the model is improved through adversarial iterations between generator and discriminator. The adversarial disturbance factor of the gradient direction of the classification model is added to improve the diversity and antagonism of generated data and to promote the model to learn from adversarial classification features. The experiment of constructing a classification model with the UNSW-NB15 dataset shows that with the enhancement of FACGAN on the basic model, the classification accuracy has improved by 8.09%, and the score of F1 has improved by 6.94%.

Keywords: data imbalance, GAN, ACGAN, anomaly detection, adversarial training, data augmentation

Procedia PDF Downloads 72

Authors: Rongbo Shen, Jianhua Yao, Kezhou Yan, Kuan Tian, Cheng Jiang, Ke Zhou

Abstract:

This study proposes a generative adversarial networks (GAN) framework to perform synthetic sampling in feature space, i.e., feature augmentation, to address the class imbalance problem in medical image analysis. A feature extraction network is first trained to convert images into feature space. Then the GAN framework incorporates adversarial learning to train a feature generator for the minority class through playing a minimax game with a discriminator. The feature generator then generates features for minority class from arbitrary latent distributions to balance the data between the majority class and the minority class. Additionally, a data cleaning technique, i.e., Tomek link, is employed to clean up undesirable conflicting features introduced from the feature augmentation and thus establish well-defined class clusters for the training. The experiment section evaluates the proposed method on two medical image analysis tasks, i.e., mass classification on mammogram and cancer metastasis classification on histopathological images. Experimental results suggest that the proposed method obtains superior or comparable performance over the state-of-the-art counterparts. Compared to all counterparts, our proposed method improves more than 1.5 percentage of accuracy.

Keywords: class imbalance, synthetic sampling, feature augmentation, generative adversarial networks, data cleaning

Procedia PDF Downloads 100

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 93

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 49

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 107

Authors: Pirta Palola, Richard Bailey, Lisa Wedding

Abstract:

Societies and economies worldwide fundamentally depend on natural capital. Alarmingly, natural capital assets are quickly depreciating, posing an existential challenge for humanity. The development of robust natural capital accounting systems is essential for transitioning towards sustainable economic systems and ensuring sound management of capital assets. However, the accurate, equitable and comprehensive estimation of natural capital asset stocks and their accounting values still faces multiple challenges. In particular, the representation of socio-cultural values held by groups or communities has arguably been limited, as to date, the valuation of natural capital assets has primarily been based on monetary valuation methods and assumptions of individual rationality. People relate to and value the natural environment in multiple ways, and no single valuation method can provide a sufficiently comprehensive image of the range of values associated with the environment. Indeed, calls have been made to improve the representation of multiple types of value (instrumental, intrinsic, and relational) and diverse ontological and epistemological perspectives in environmental valuation. This study addresses this need by establishing a novel valuation framework, Environmental Value Functions (EVF), that allows for the integration of multiple types of value in natural capital accounting systems. The EVF framework is based on the estimation and application of value functions, each of which describes the relationship between the value and quantity (or quality) of an ecosystem component of interest. In this framework, values are estimated in terms of change relative to the current level instead of calculating absolute values. Furthermore, EVF was developed to also support non-marginalist conceptualizations of value: it is likely that some environmental values cannot be conceptualized in terms of marginal changes. For example, ecological resilience value may, in some cases, be best understood as a binary: it either exists (1) or is lost (0). In such cases, a logistic value function may be used as the discriminator. Uncertainty in the value function parameterization can be considered through, for example, Monte Carlo sampling analysis. The use of EVF is illustrated with two conceptual examples. For the first time, EVF offers a clear framework and concrete methodology for the representation of multiple types of value in natural capital accounting systems, simultaneously enabling 1) the complementary use and integration of multiple valuation methods (monetary and non-monetary); 2) the synthesis of information from diverse knowledge systems; 3) the recognition of value incommensurability; 4) marginalist and non-marginalist value analysis. Furthermore, with this advancement, the coupling of EVF and ecosystem modeling can offer novel insights to the study of spatial-temporal dynamics in natural capital asset values. For example, value time series can be produced, allowing for the prediction and analysis of volatility, long-term trends, and temporal trade-offs. This approach can provide essential information to help guide the transition to a sustainable economy.

Keywords: economics of biodiversity, environmental valuation, natural capital, value function

Procedia PDF Downloads 156

Authors: Joyjit Dey, Souvik Sen

Abstract:

Middle Permian Barakar formation is the major economic coal bearing unit of vast east-west trending Damodar Valley basin of Gondwana coalfield. Primary sedimentary structures were studied from the core holes, which represent majorly four facies groups: sandstone dominated facies, sandstone-shale heterolith facies, shale facies and coal facies. Total eight major coal seams have been identified with the bottom most seam being the thickest. Laterally, continuous coal seams were deposited in the calm and quiet environment of extensive floodplain swamps. Channel sinuosity and lateral channel migration/avulsion results in lateral facies heterogeneity and coal splitting. Geophysical well logs (Gamma-Resistivity-Density logs) have been used to establish the vertical and lateral correlation of various litho units field-wide, which reveals the predominance of repetitive fining upwards cycles. Well log data being a permanent record, offers a strong foundation for generating log based property evaluation and helps in characterization of depositional units in terms of lateral and vertical heterogeneity. Low gamma, high resistivity, low density is the typical coal seam signatures in geophysical logs. Here, we have used a density cutoff of 1.6 g/cc as a primary discriminator of coal and the same has been employed to compute various coal assay parameters, which are ash, fixed carbon, moisture, volatile content, cleat porosity, vitrinite reflectance (VRo%), which were calibrated with the laboratory based measurements. The study shows ash content and VRo% increase from west to east (towards basin margin), while fixed carbon, moisture and volatile content increase towards west, depicting increased coal quality westwards. Seam wise cleat porosity decreases from east to west, this would be an effect of overburden, as overburden pressure increases westward with the deepening of basin causing more sediment packet deposited on the western side of the study area. Coal is a porous, viscoelastic material in which velocity and strain both change nonlinearly with stress, especially for stress applied perpendicular to the bedding plane. Usually, the coal seam has a high velocity contrast relative to its neighboring layers. Despite extensive discussion of the maceral and chemical properties of coal, its elastic characteristics have received comparatively little attention. The measurement of the elastic constants of coal presents many difficulties: sample-to-sample inhomogeneity and fragility and velocity dependence on stress, orientation, humidity, and chemical content. In this study, a conclusive empirical equation VS= 0.80VP-0.86 has been used to model shear velocity from compression velocity. Also the same has been used to compute various geomechanical moduli. Geomech analyses yield a Poisson ratio of 0.348 against coals. Average bulk modulus value is 3.97 GPA, while average shear modulus and Young’s modulus values are coming out as 1.34 and 3.59 GPA respectively. These middle Permian Barakar coals show an average 23.84 MPA uniaxial compressive strength (UCS) with 4.97 MPA cohesive strength and 0.46 as friction coefficient. The output values of log based proximate parameters and geomechanical moduli suggest a medium volatile Bituminous grade for the studied coal seams, which is found in the laboratory based core study as well.

Keywords: core analysis, coal characterization, geophysical log, geo-mechanical moduli

Procedia PDF Downloads 189