Interval lung cancers (ILC) that are diagnosed before the next scheduled screening usually are more advanced stage (stage III/IV non-small cell lung cancer) or are small cell cancer and have a poorer prognosis than prevalent cancers. The challenge is how to predict who will develop future cancer when the lungs are "visually normal" on CT at the last scheduled screening round. We aim to use an AI model based on the radiomics approach to identify sub-visual changes in the lungs before future cancer develops.

Pneumoconiosis is a group of occupational lung diseases induced by mineral dust inhalation and subsequent lung tissue reactions. It can eventually cause irreparable lung damage, as well as gradual and permanent physical impairments. It has affected millions of workers in hazardous industries throughout the world, and it is a leading cause of occupational death. It is difficult to diagnose early pneumoconiosis because of the low sensitivity of chest radiographs, the wide variation in interpretation between and among readers, and the scarcity of B-readers, which all add to the difficulty in diagnosing these occupational illnesses. In recent years, deep machine learning algorithms have been extremely successful at classifying and localising abnormality of medical images. In this study, we proposed an ensemble learning approach to improve pneumoconiosis detection in chest X-rays (CXRs) using nine machine learning classifiers and multi-dimensional deep features extracted using CheXNet-121 architecture. There were eight evaluation metrics utilised for each high-level feature set of the associated cross-validation datasets in order to compare the ensemble performance and state-of-the-art techniques from the literature that used the same cross-validation datasets. It is observed that integrated ensemble learning exhibits promising results (92.68% accuracy, 85.66% Matthews correlation coefficient (MCC), and 0.9302 area under the precision–recall (PR) curve), compared to individual CheXNet-121 and other state-of-the-art techniques. Finally, Grad-CAM was used to visualise the learned behaviour of individual dense blocks within CheXNet-121 and their ensembles into three-color channels of CXRs. We compared the Grad-CAM-indicated ROI to the ground-truth ROI using the intersection of the union (IOU) and average-precision (AP) values for each classifier and their ensemble. Through the visualisation of the Grad-CAM within the blue channel, the average IOU passed more than 90% of the pneumoconiosis detection in chest radiographs.

Globally, coal remains one of the natural resources that provide power to the world. Thousands of people are involved in coal collection, processing, and transportation. Particulate coal dust is produced during these processes, which can crush the lung structure of workers and cause pneumoconiosis. There is no automated system for detecting and monitoring diseases in coal miners, except for specialist radiologists. This paper proposes ensemble learning techniques for detecting pneumoconiosis disease in chest X-ray radiographs (CXRs) using multiple deep learning models. Three ensemble learning techniques (simple averaging, multi-weighted averaging, and majority voting (MVOT)) were proposed to investigate performances using randomised cross-folds and leave-one-out cross-validations datasets. Five statistical measurements were used to compare the outcomes of the three investigations on the proposed integrated approach with state-of-the-art approaches from the literature for the same dataset. In the second investigation, the statistical combination was marginally enhanced in the ensemble of multi-weighted averaging on a robust model, CheXNet. However, in the third investigation, the same model elevated accuracies from 87.80 to 90.2%. The investigated results helped us identify a robust deep learning model and ensemble framework that outperformed others, achieving an accuracy of 91.50% in the automated detection of pneumoconiosis.

Computer-aided diagnostic (CAD) systems can assist radiologists in detecting coal workers' pneumoconiosis (CWP) in their chest X-rays. Early diagnosis of the CWP can significantly improve workers' survival rate. The development of the CAD systems will reduce risk in the workplace and improve the quality of chest screening for CWP diseases. This systematic literature review (SLR) amis to categorise and summarise the feature extraction and detection approaches of computer-based analysis in CWP using chest X-ray radiographs (CXR). We conducted the SLR method through 11 databases that focus on science, engineering, medicine, health, and clinical studies. The proposed SLR identified and compared 40 articles from the last 5 decades, covering three main categories of computer-based CWP detection: classical handcrafted features-based image analysis, traditional machine learning, and deep learning-based methods. Limitations of this review and future improvement of the review are also discussed.

Pneumoconiosis is an incurable respiratory disease caused by long-term inhalation of respirable dust. Due to small pneumoconiosis incidence and restrictions on sharing of patient data, the number of available pneumoconiosis X-rays is insufficient, which introduces significant challenges for training deep learning models. In this paper, we use both real and synthetic pneumoconiosis radiographs to train a cascaded machine learning framework for the automated detection of pneumoconiosis, including a machine learning based pixel classifier for lung field segmentation, and Cycle-Consistent Adversarial Networks (CycleGAN) for generating abundant lung field images for training, and a Convolutional Neural Network (CNN) based image classier. Experiments are conducted to compare the classification results from several state-of-the-art machine learning models and ours. Our proposed model outperforms the others and achieves an overall classification accuracy of 90.24%, a specificity of 88.46% and an excellent sensitivity of 93.33% for detecting pneumoconiosis.

Black Lung (BL) is an incurable respiratory disease caused by long term inhalation of respirable coal dust. Confidentiality restrictions and disease incidence limit the availability of BL datasets, which presents significant challenges in the training of deep learning (DL) models. This paper presents the implementations and detailed performance comparison of seven DL models for BL detection with small datasets. The models include VGG16, VGG19, InceptionV3, Xception, ResNet50, DenseNet121 and CheXNet. A small BL dataset of real and synthetic images was used to train the seven deep learning models. Segmented lung X-ray images, with and without BL, were used as training images to establish a benchmark. To increase the number of images required for training a deep learning system the training data set was augmented, using a Cycle-Consistent Adversarial Networks (CycleGAN) and the Keras Image Data Generator, to generate additional augmented and synthetic radiographs. The effects of different dropout nodes as a blocking factor was also investigated on all seven models. The best sensitivity (Normal Prediction Rate), specificity (BL prediction Rate), error rate (ERR or incorrect prediction rate), accuracy (1-ERR), as well as total execution time for binary classification for each model, with and without augmentation, was compared for optimal BL detection. On average, the CheXNet model gave the best performance of all seven DL models.

The widespread human-robot interaction is increasing progressively as robots have made the life of everyone easy-going and comfortable. In this work, we have analysed the behaviour and characteristics of various types of robots.

Early detection of pneumoconiosis in X-Rays has been a challenging task that leads to high inter- and intra-reader variability. Motivated by the success of deep learning in general and medical image classification, this paper proposes an approach to automatically detect pneumoconiosis using a deep feature based binary classifier. The features are extracted from X-rays using deep transfer learning, comprising both low and high-level feature sets. For this, a CNN model pre-trained with a transfer learning from a CheXNet model was initially used to extract deep features from the X-Ray images, then the deep features were mapped to higher-dimensional feature spaces for classification using Support Vector Machine (SVM) and CNN based feature aggregation methods. In order to cross validate the proposed method, the training and testing images were randomly split into three folds before each experiment. Nine evaluation metrics were employed to compare the performance of the proposed method and state-of-the-art methods from the literature that used the same datasets. The experimental results show that the proposed framework outperformed others, achieving an accuracy of 92.68% in the automated detection of pneumoconiosis.

Coal Worker Pneumoconiosis (CWP), commonly called Black Lung (BL), is an incurable respiratory disease caused by long-term inhalation of respirable dust. Privacy restrictions and disease incidence placed limits on the available BL datasets, which introduces significant challenges for training deep learning (DL) models. Recently, transfer learning has been seen as an efficient DL method for automatic disease detection with small datasets. This paper investigates BL detection in chest X-rays using transfer DL knowledge from a CheXNet model on a small dataset. A training image set of real, segmented lung X-ray images, with and without BL, was used as a benchmark for detection accuracy. The training data set was then augmented using a Cycle-Consistent Adversarial Networks (CycleGAN) and Keras Image Data Generator, to generate training data with real, augmented and synthetic CWP radiographs to the CheXNet model (with and without pre-trained weights). The effects of different dropout nodes as a blocking factor was also investigated. The accuracy, sensitivity (recall or true positive rate), specificity (true negative rate) and error rate (ERR or incorrect prediction rate) using 3-fold cross-validation experiments was compared for each transfer learning experiment. The total execution time for binary classification of our model also measured. While no definitive conclusion could be reached regarding the effect of dropout rates, results indicated an improvement of classification accuracy from transfer learning.

Scantlings of researches have been conversed in the literature for the identification of fingerprint. Gender identification from fingerprints is an important step in forensic anthropology in order to identify the gender of a criminal and minimize the list of suspects search. In this paper, gender identification is carried out by using Wavelet Transform, Pixels calculation and Binary Transform. Right thumb impression of each sample of the internal database of 200 male samples and 200 female samples of good quality are selected. This identification is portrayed in the result and discussion section.

Handwritten signatures are considered as the most natural method of authenticating a person’s identity. Human signatures can be handled as an image and used in a scanned document is a promising facility for many banking and insurance related business activities. The signatures of the same person vary with time, age of the person and also because of the emotional state of a person. This paper present an off-line human signature recognition system based on histogram analysis. The main steps of constructing a signature recognition system are discussed and experiments on the values of cumulative distribution function (CDF).The off-line signature recognition and verification is implemented using MATLAB. © 2016 Elixir all rights reserved. Elixir Inform. Tech. 94 (2016) 40429-40433 Information Technology Available online at www.elixirpublishers.com (Elixir International Journal)

Abstract : This is a study on motorbike safety by analyzing various factors of a motorbike such as road condition, braking, various weathers and many more. In this paper we have tried to develop the motorcycle safety system by analyzing the causes of accidents and motorcycle dynamics. For doing these we have explained some factors and relate the dynamics of a motorcycle with safety facts. Some Simple mathematical calculations and formulas can be used to reduce the risk of various kinds of motorcycle accident which are considered as major. By analyzing these by mathematics and physics, we have found some points which can be used to reduce the probability of a motorcycle crashes and for saving lives caused by motorcycle crashes.

This study addresses some mathematical and statistical techniques of medical image compression and their computational implementation. Fundamental theories have been presented, applied and illustrated with examples. To make the report as self-contained as possible, key terminologies have been defined and some classical results and theorems are stated, in the most part, without proof. Some algorithms and techniques of image processing have been described and substantiated with experimentation using MATLAB. Medical image compression is necessary for huge database storage in Medical Centers and medical data transfer for the purpose of diagnosis. Wavelet transforms present one such approach for the purpose of compression. The same has been explored in study with respect to wide variety of medical images. In this approach, the redundancy of the medical image and DWT coefficients are reduced through thresholding and further through Huffman encoding. In this study our main goal is to compare different types of wavelets for medical image compression. Finally, implementation of the above-mentioned concepts is illustrated.

Abstract. Electrocardiogram (ECG) plays a vital role in heart disease diagnosis. Usually ECG signals are affected by various noises. Several r searchers have done their works to conform the purity of ECG signals. In this work, th e discrete wavelet transform (DWT) based wavelet denoising have implemented using diff erent thresholding techniques to remove the sources of noises from the original sign als. Four thresholding techniques (‘Rigrsure’, ‘Heursure’, ‘Sqtwolog’ and ‘Minimaxi’) and three wavelet functions (‘db20’, ’sym20’ and ‘coif5’) have been used in this work to de-noise the original ECG signals. The significant reduction of above considered noise s has been shown by the experimental result. It also retains the ECG signal morphology e ffectively. We have used four different performance measures to select thresholding rules a nd efficient wavelet functions for removal of the noises from the signals such as Root Mean Square Error (RMSE), Signal to Noise Ratio (SNR), Percentage Root Mean Square D iff rence (PRD) & Noise Power (Pn). The best result has been obtained with the ‘R igrsure’ thresholding rule and ‘coif5’ wavelet function based on considered SNR for non-st ationary ECG signals.