This paper deals with the vulnerability of machine learning models to adversarial examples and its implication for robustness and generalization properties. We propose an evolutionary algorithm that can generate adversarial examples for any machine learning model in the black-box attack scenario. This way, we can find adversarial examples without access to model's parameters, only by querying the model at hand. We have tested a range of machine learning models including deep and shallow neural networks. Our experiments have shown that the vulnerability to adversarial examples is not only the problem of deep networks, but it spreads through various machine learning architectures. Rather, it depends on the type of computational units. Local units, such as Gaussian kernels, are less vulnerable to adversarial examples.
- MeSH
- Algorithms MeSH
- Humans MeSH
- Neural Networks, Computer * MeSH
- Supervised Machine Learning * trends MeSH
- Pattern Recognition, Automated methods trends MeSH
- Machine Learning trends MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands 〈 3 , 8 〉 and 〈 8 , 15 〉 Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.
- MeSH
- Accelerometry methods MeSH
- Algorithms MeSH
- Bayes Theorem MeSH
- Exercise MeSH
- Bicycling * MeSH
- Fitness Trackers * MeSH
- Humans MeSH
- Cell Phone instrumentation MeSH
- Neural Networks, Computer MeSH
- Signal Processing, Computer-Assisted MeSH
- Motion MeSH
- Reproducibility of Results MeSH
- Pattern Recognition, Automated MeSH
- Software MeSH
- Heart Rate * MeSH
- Models, Statistical MeSH
- Support Vector Machine MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
With a rapidly-growing amount of biomedical information available only in textual form, there is considerable interest in applying NLP techniques to extract such information from the biomedical literature. Much of the research has paid special attention to extracting information about biomedical named entities. In this paper, we conducted a survey on biomedical named entity recognition and normalization, focusing on gene mention recognition and normalization. We believe this can help researchers to find work of their interest and interpret their own research.
BACKGROUND AND OBJECTIVE: We present a fully automatic system based on learning approaches, which aims to localization and identification (labeling) of vertebrae in 3D computed tomography (CT) scans of possibly incomplete spines in patients with bone metastases and vertebral compressions. METHODS: The framework combines a set of 3D algorithms for i) spine detection using a convolution neural network (CNN) ii) spinal cord tracking based on combination of a CNN and a novel growing sphere method with a population optimization, iii) intervertebral discs localization using a novel approach of spatially variant filtering of intensity profiles and iv) vertebra labeling using a CNN-based classification combined with global dynamic optimization. RESULTS: The proposed algorithm has been validated in testing databases, including also a publicly available dataset. The mean error of intervertebral discs localization is 4.4 mm, and for vertebra labeling, the average rate of correctly identified vertebrae is 87.1%, which can be considered a good result with respect to the large share of highly distorted spines and incomplete spine scans. CONCLUSIONS: The proposed framework, which combines several advanced methods including also three CNNs, works fully automatically even with incomplete spine scans and with distorted pathological cases. The achieved results allow including the presented algorithms as the first phase to the fully automated computer-aided diagnosis (CAD) system for automatic spine-bone lesion analysis in oncological patients.
- MeSH
- Algorithms MeSH
- Databases, Factual MeSH
- Diagnosis, Computer-Assisted MeSH
- Humans MeSH
- Neoplasm Metastasis MeSH
- Intervertebral Disc diagnostic imaging pathology MeSH
- Bone Neoplasms diagnostic imaging pathology MeSH
- Spinal Diseases diagnostic imaging MeSH
- Neural Networks, Computer MeSH
- Spine diagnostic imaging pathology MeSH
- Tomography, X-Ray Computed * MeSH
- Image Processing, Computer-Assisted MeSH
- Reproducibility of Results MeSH
- Pattern Recognition, Automated MeSH
- Software MeSH
- Imaging, Three-Dimensional methods MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
The microvascular pattern in the histological section, i.e. the point-pattern composed of capillaries perpendicular to the plane of section, contains information about the three-dimensional structure of the capillary network. Histological processing is followed by the shrinkage of tissue of uncertain magnitude. In order to obtain relevant information, the scale-independent analysis is necessary. We used an approach based on the Minkowski cover of measured set. The true fractal dimension of the point pattern is obviously of zero, but the artificial result of the algorithm can be related to the complexity of shape. We fitted the log-log plot by the modified rounded ramp function and the slope of the oblique part was used as the fractal based descriptor. We demonstrated on histological samples of the heart that this fractal-based parameter has the property of scale and rotation invariance.
The microvascular pattern in the histological section, i.e. the point-pattern composed of capillaries perpendicular to the plane of section, contains information about the three-dimensional structure of the capillary network. Histological processing is followed by the shrinkage of tissue of uncertain magnitude. In order to obtain relevant information, the scale-independent analysis is necessary. We used an approach based on the Minkowski cover of measured set. The true fractal dimension of the point pattern is obviously of zero, but the artificial result of the algorithm can be related to the complexity of shape. We fitted the log-log plot by the modified rounded ramp function and the slope of the oblique part was used as the fractal based descriptor. We demonstrated on histological samples of the heart that this fractal-based parameter has the property of scale and rotation invariance.
- MeSH
- Fractals MeSH
- Histological Techniques * MeSH
- Image Interpretation, Computer-Assisted * MeSH
- Humans MeSH
- Pattern Recognition, Automated MeSH
- Check Tag
- Humans MeSH
- Publication type
- Research Support, Non-U.S. Gov't MeSH
Lung cancer is the leading cause of cancer death in men and women. The prognostic value of survival after lung cancer surgery has an important role in decision-making for surgeons and patients. The combination of clinical features and CT scan information for diagnosis, treatment and survival of patients with lung cancer increases the accuracy of prediction using machine learning. Therefore, creating a computer intelligent method with low error and high accuracy to predict survival is an important challenge, and it is beneficial for decreasing mortality from lung cancer, and for planning treatment. In this work, we implemented a deep stacked sparse auto-encoder (DSSAE) approach on a thoracic surgery data set for 470 patients, and our results contributing to deep learning based on 16 features were more precise than other suggested techniques for predicting post-operative survival expectancy in thoracic lung cancer surgery. The proposed method achieved a sensitivity of 94%, specificity of 82.86% and g-mean of 88.25%.
- MeSH
- Survival Analysis MeSH
- Deep Learning MeSH
- Thoracic Surgical Procedures methods MeSH
- Humans MeSH
- Lung Neoplasms * diagnostic imaging surgery pathology MeSH
- Postoperative Complications mortality prevention & control MeSH
- Surgical Clearance MeSH
- Prognosis MeSH
- Supervised Machine Learning MeSH
- Pattern Recognition, Automated MeSH
- Check Tag
- Humans MeSH
This article presents a steganographic method StegoNN based on neural networks. The method is able to identify a photomontage from presented signed images. Unlike other academic approaches using neural networks primarily as classifiers, the StegoNN method uses the characteristics of neural networks to create suitable attributes which are then necessary for subsequent detection of modified photographs. This also results in a fact that if an image is signed by this technique, the detection of modifications does not need any external data (database of non-modified originals) and the quality of the signature in various parts of the image also serves to identify modified (corrupted) parts of the image. The experimental study was performed on photographs from CoMoFoD Database and its results were compared with other approaches using this database based on standard metrics. The performed study showed the ability of the StegoNN method to detect corrupted parts of an image and to mark places which have been most probably image-manipulated. The usage of this method is suitable for reportage photography, but in general, for all cases where verification (provability) of authenticity and veracity of the presented image are required.
Machine learning (ML) is a growing field that provides tools for automatic pattern recognition. The neuroimaging community currently tries to take advantage of ML in order to develop an auxiliary diagnostic tool for schizophrenia diagnostics. In this letter, we present a classification framework based on features extracted from magnetic resonance imaging (MRI) data using two automatic whole-brain morphometry methods: voxel-based (VBM) and deformation-based morphometry (DBM). The framework employs a random subspace ensemble-based artificial neural network classifier-in particular, a multilayer perceptron (MLP). The framework was tested on data from first-episode schizophrenia patients and healthy controls. The experiments differed in terms of feature extraction methods, using VBM, DBM, and a combination of both morphometry methods. Thus, features of different types were available for model adaptation. As we expected, the combination of features increased the MLP classification accuracy up to 73.12%-an improvement of 5% versus MLP-based only on VBM or DBM features. To further verify the findings, other comparisons using support vector machines in place of MLPs were made within the framework. However, it cannot be concluded that any classifier was better than another.
- MeSH
- Diagnosis, Computer-Assisted methods MeSH
- Humans MeSH
- Magnetic Resonance Imaging * methods MeSH
- Brain diagnostic imaging MeSH
- Neural Networks, Computer * MeSH
- Pattern Recognition, Automated methods MeSH
- Schizophrenia diagnostic imaging MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
We present the ROCA (ROad Curvature Analyst) software, in the form of an ESRI ArcGIS Toolbox, intended for vector line data processing. The software segments road network data into tangents and horizontal curves. Horizontal curve radii and azimuth of tangents are then automatically computed. Simultaneously, additional frequently used road section characteristics are calculated, such as the sinuosity of a road section (detour ratio), the number of turns along an individual road section and the average cumulative angle for a road section. The identification of curves is based on the naïve Bayes classifier and users are allowed to prepare their own training data files. We applied ROCA software to secondary roads within the Czech road network (9,980 km). The data processing took less than ten minutes. Approximately 43% of the road network in question consists of 42,752 horizontal curves. The ROCA software outperforms other existing automatic methods by 26% with respect to the percentage of correctly identified curves. The segmented secondary roads within the Czech road network can be viewed on the roca.cdvgis.cz/czechia web-map application. We combined data on road geometry with road crashes database to develop the crash modification factors for horizontal curves with various radii. We determined that horizontal curves with radii of 50 m are approximately 3.7 times more hazardous than horizontal curves with radii accounting for 1000 m. ROCA software can be freely downloaded for noncommercial use from https://roca.cdvinfo.cz/ website.
- MeSH
- Automobiles standards MeSH
- Safety MeSH
- Accidents, Traffic prevention & control MeSH
- Geographic Information Systems MeSH
- Humans MeSH
- Self-Help Devices * MeSH
- Automobile Driving * standards MeSH
- Rotation * MeSH
- Pattern Recognition, Automated methods MeSH
- Software * standards MeSH
- Environment Design MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
Examination of the common carotid artery (CCA) based on an ultrasound video sequence is an effective method for detecting cardiovascular diseases. Here, we propose a video processing method for the automated geometric analysis of CCA transverse sections. By explicitly compensating the parasitic phenomena of global movement and feature drift, our method enables a reliable and accurate estimation of the movement of the arterial wall based on ultrasound sequences of arbitrary length and in situations where state-of-the-art methods fail or are very inaccurate. The method uses a modified Viola-Jones detector and the Hough transform to localize the artery in the image. Then it identifies dominant scatterers, also known as interest points (IPs), whose positions are tracked by means of the pyramidal Lucas-Kanade method. Robustness to global movement and feature drift is achieved by a detection of global movement and subsequent IP re-initialization, as well as an adaptive removal and addition of IPs. The performance of the proposed method is evaluated using simulated and real ultrasound video sequences. Using the Harris detector for IP detection, we obtained an overall root-mean-square error, averaged over all the simulated sequences, of 2.16 ± 1.18 px. The computational complexity of our method is compatible with real-time operation; the runtime is about 30-70 ms/frame for sequences with a spatial resolution of up to 490 × 490 px. We expect that in future clinical practice, our method will be instrumental for non-invasive early-stage diagnosis of atherosclerosis and other cardiovascular diseases.
- MeSH
- Carotid Arteries diagnostic imaging MeSH
- Image Interpretation, Computer-Assisted methods MeSH
- Humans MeSH
- Image Processing, Computer-Assisted methods MeSH
- Reproducibility of Results MeSH
- Pattern Recognition, Automated methods MeSH
- Sensitivity and Specificity MeSH
- Ultrasonography methods MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
