Search

Background and objectives Computer-aided diagnosis relies on machine learning algorithms that require filtered and preprocessed data as the input. Aligning the image in the desired direction is an additional manual step in post-processing, commonly overlooked due to workload issues. Several state-of-the-art approaches for fracture detection and disease-struck region segmentation benefit from correctly oriented images, thus requiring such preprocessing of X-ray images. Furthermore, it is desirable to have archived studies in a standardized format. Radiograph hanging protocols also differ from case to case, which means that images are not always aligned and oriented correctly. As a solution, the paper proposes XAOM, an X-ray Alignment and Orientation Method for images from 21 different body regions. Methods Typically, other methods are crafted for this purpose to suit a specific body region and form of usage. In contrast, the method proposed in this paper is comprehensive and easily tuned to align and orient X-ray images of any body region. XAOM consists of two stages. For the first stage of the method, aligning X-ray images, we experimented with the following approaches: Hough transform, Fast line detection algorithm, and Principal Component Analysis method. For the second stage, we have experimented with the adaptations of several well known convolutional neural network topologies for correctly predicting image orientation: LeNet5, AlexNet, VGG16, VGG19, and ResNet50. Results In the first stage, the PCA-based approach performed best. The average difference between the angle detected by the algorithm and the angle marked by the experts on the test set containing 200 pediatric X-ray images was 1.65 ∘ , while the median value was 0.11 ∘ . In the second stage, the VGG16-based network topology achieved the best accuracy of 0.993 on a test set containing 4,221 images. Conclusion XAOM is highly accurate at aligning and orienting pediatric X-ray images of 21 common body regions according to a set standard. The proposed method is also robust and can be easily adjusted to the different alignment and rotation criteria. Availability The Python source code of the best performing implementation of XAOM is publicly available at https://github.com/fhrzic/XAOM .

In developing nations, many expanding cities are facing challenges that result from the overwhelming numbers of people and vehicles. Collecting real-time, reliable and precise traffic flow information is crucial for urban traffic management. The main purpose of this paper is to develop an adaptive model that can assess the real-time vehicle counts on urban roads using computer vision technologies. This paper proposes an automatic real-time background update algorithm for vehicle detection and an adaptive pattern for vehicle counting based on the virtual loop and detection line methods. In addition, a new robust detection method is introduced to monitor the real-time traffic congestion state of road section. A prototype system has been developed and installed on an urban road for testing. The results show that the system is robust, with a real-time counting accuracy exceeding 99% in most field scenarios.

The Basso, Beattie and Bresnahan (BBB) Locomotor Rating Scale is a standardized assessment scale for use in experimental spinal cord injury (SCI) research. This paper describes a computer program, ScoreCentre, which aims to simplify the recording and handling of BBB locomotor scale data. The program assists with the recording of observational data from open-field testing and then automatically calculates BBB scores. Possible errors associated with data entry and manual calculation of scores are thus essentially eliminated. In addition, significant time is saved by the automated derivation of scores and subscores and elimination of the need to manually transfer data from paper records to a computer. ScoreCentre can also be used as a training aid, to help familiarize users with the BBB scale and to explore how changes in the observations impact on overall BBB score. ScoreCentre includes simple experiment management functions such as control of trial blinding, administration of drugs in a blinded fashion and longitudinal data analysis. ScoreCentre provides all the advantages of electronic records, such as ease of use, analysis and archiving, and allows the elimination of paper records if appropriate. When paper records are required, for example for archiving and auditing, they can be automatically produced by ScoreCentre. ScoreCentre will assist with both the learning and use of the BBB locomotor scale, thus facilitating the use of this standardized outcome measure in SCI research. ScoreCentre is available to download from www.rmeonline.net/scorecentre.

Artificial Intelligence in healthcare employs machine learning algorithms to emulate human cognition in the analysis of complicated or large sets of data. Specifically, artificial intelligence taps on the ability of computer algorithms and software with allowable thresholds to make deterministic approximate conclusions. In comparison to traditional technologies in healthcare, artificial intelligence enhances the process of data analysis without the need for human input, producing nearly equally reliable, well defined output. Schizophrenia is a chronic mental health condition that affects millions worldwide, with impairment in thinking and behaviour that may be significantly disabling to daily living. Multiple artificial intelligence and machine learning algorithms have been utilized to analyze the different components of schizophrenia, such as in prediction of disease, and assessment of current prevention methods. These are carried out in hope of assisting with diagnosis and provision of viable options for individuals affected. In this paper, we review the progress of the use of artificial intelligence in schizophrenia.

IntroductionThe use of machine learning (ML) methods would improve the diagnosis of respiratory changes in systemic sclerosis (SSc). This paper evaluates the performance of several ML algorithms associated with the respiratory oscillometry analysis to aid in the diagnostic of respiratory changes in SSc. We also find out the best configuration for this task.MethodsOscillometric and spirometric exams were performed in 82 individuals, including controls (n = 30) and patients with systemic sclerosis with normal (n = 22) and abnormal (n = 30) spirometry. Multiple instance classifiers and different supervised machine learning techniques were investigated, including k-Nearest Neighbors (KNN), Random Forests (RF), AdaBoost with decision trees (ADAB), and Extreme Gradient Boosting (XGB).Results and discussionThe first experiment of this study showed that the best oscillometric parameter (BOP) was dynamic compliance, which provided moderate accuracy (AUC = 0.77) in the scenario control group versus patients with sclerosis and normal spirometry (CGvsPSNS). In the scenario control group versus patients with sclerosis and altered spirometry (CGvsPSAS), the BOP obtained high accuracy (AUC = 0.94). In the second experiment, the ML techniques were used. In CGvsPSNS, KNN achieved the best result (AUC = 0.90), significantly improving the accuracy in comparison with the BOP (p p ConclusionsOscillometric principles combined with machine learning algorithms provide a new method for diagnosing respiratory changes in patients with systemic sclerosis. The present study's findings provide evidence that this combination may help in the early diagnosis of respiratory changes in these patients.

Many current convolutional neural networks are hard to meet the practical application requirement because of the enormous network parameters. For accelerating the inference speed of networks, more and more attention has been paid to network compression. Network pruning is one of the most efficient and simplest ways to compress and speed up the networks. In this paper, a pruning algorithm for the lightweight task is proposed, and a pruning strategy based on feature representation is investigated. Different from other pruning approaches, the proposed strategy is guided by the practical task and eliminates the irrelevant filters in the network. After pruning, the network is compacted to a smaller size and is easy to recover accuracy with fine-tuning. The performance of the proposed pruning algorithm is validated on the acknowledged image datasets, and the experimental results prove that the proposed algorithm is more suitable to prune the irrelevant filters for the fine-tuning dataset.

Eliminating unnecessary exposure is a principle of server security. The huge IPv6 address space enhances security by making scanning infeasible, however, with recent advances of IPv6 scanning technologies, network scanning is again threatening server security. In this paper, we propose a new model named addressless server, which separates the server into an entrance module and a main service module, and assigns an IPv6 prefix instead of an IPv6 address to the main service module. The entrance module generates a legitimate IPv6 address under this prefix by encrypting the client address, so that the client can access the main server on a destination address that is different in each connection. In this way, the model provides isolation to the main server, prevents network scanning, and minimizes exposure. Moreover it provides a novel framework that supports flexible load balancing, high-availability, and other desirable features. The model is simple and does not require any modification to the client or the network. We implement a prototype and experiments show that our model can prevent the main server from being scanned at a slight performance cost.

In a progressively interconnected world where the Internet of Things (IoT), ubiquitous computing, and artificial intelligence are leading to groundbreaking technology, cybersecurity remains an underdeveloped aspect. This is particularly alarming for brain-to-computer interfaces (BCIs), where hackers can threaten the user’s physical and psychological safety. In fact, standard algorithms currently employed in BCI systems are inadequate to deal with cyberattacks. In this paper, we propose a solution to improve the cybersecurity of BCI systems. As a case study, we focus on P300-based BCI systems using support vector machine (SVM) algorithms and EEG data. First, we verified that SVM algorithms are incapable of identifying hacking by simulating a set of cyberattacks using fake P300 signals and noise-based attacks. This was achieved by comparing the performance of several models when validated using real and hacked P300 datasets. Then, we implemented our solution to improve the cybersecurity of the system. The proposed solution is based on an EEG channel mixing approach to identify anomalies in the transmission channel due to hacking. Our study demonstrates that the proposed architecture can successfully identify 99.996% of simulated cyberattacks, implementing a dedicated counteraction that preserves most of BCI functions.

This paper proposes a UAV platform that autonomously detects, hunts, and takes down other small UAVs in GPS-denied environments. The platform detects, tracks, and follows another drone within its sensor range using a pre-trained machine learning model. We collect and generate a 58,647-image dataset and use it to train a Tiny YOLO detection algorithm. This algorithm combined with a simple visual-servoing approach was validated on a physical platform. Our platform was able to successfully track and follow a target drone at an estimated speed of 1.5 m/s. Performance was limited by the detection algorithm's 77% accuracy in cluttered environments and the frame rate of eight frames per second along with the field of view of the camera.

To prevent large interconnected power system from a cascading failure, brownout or even blackout, grid operators require access to faster than real-time information to make appropriate just-in-time control decisions. However, the communication and computational system limitations of currently used supervisory control and data acquisition (SCADA) system can only deliver delayed information. However, the deployment of synchrophasor measurement devices makes it possible to capture and visualize, in near-real-time, grid operational data with extra granularity. In this paper, a cellular computational network (CCN) approach for frequency situational intelligence (FSI) in a power system is presented. The distributed and scalable computing unit of the CCN framework makes it particularly flexible for customization for a particular set of prediction requirements. Two soft-computing algorithms have been implemented in the CCN framework: a cellular generalized neuron network (CCGNN) and a cellular multi-layer perceptron network (CCMLPN), for purposes of providing multi-timescale frequency predictions, ranging from 16.67 ms to 2 s. These two developed CCGNN and CCMLPN systems were then implemented on two different scales of power systems, one of which installed a large photovoltaic plant. A real-time power system simulator at weather station within the Real-Time Power and Intelligent Systems (RTPIS) laboratory at Clemson, SC, was then used to derive typical FSI results.

The promotion of cloud computing makes the virtual machine (VM) increasingly a target of malware attacks in cybersecurity such as those by kernel rootkits. Memory forensic, which observes the malicious tracks from the memory aspect, is a useful way for malware detection. In this paper, we propose a novel TKRD method to automatically detect kernel rootkits in VMs from private cloud, by combining VM memory forensic analysis with bio-inspired machine learning technology. Malicious features are extracted from the memory dumps of the VM through memory forensic analysis method. Based on these features, various machine learning classifiers are trained including Decision tree, Rule based classifiers, Bayesian and Support vector machines (SVM). The experiment results show that the Random Forest classifier has the best performance which can effectively detect unknown kernel rootkits with an Accuracy of 0.986 and an AUC value (the area under the receiver operating characteristic curve) of 0.998.

Spurred by advances in processing power, memory, storage, and an unprecedented wealth of data, computers are being asked to tackle increasingly complex learning tasks, often with astonishing success. Computers have now mastered a popular variant of poker, learned the laws of physics from experimental data, and become experts in video games − tasks that would have been deemed impossible not too long ago. In parallel, the number of companies centered on applying complex data analysis to varying industries has exploded, and it is thus unsurprising that some analytic companies are turning attention to problems in health care. The purpose of this review is to explore what problems in medicine might benefit from such learning approaches and use examples from the literature to introduce basic concepts in machine learning. It is important to note that seemingly large enough medical data sets and adequate learning algorithms have been available for many decades, and yet, although there are thousands of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Thus, part of my effort will be to identify what obstacles there may be to changing the practice of medicine through statistical learning approaches, and discuss how these might be overcome.

With the development of multi-/many-core processors, applications need to be written as parallel programs to improve execution efficiency. For data-intensive applications that use multiple threads to read/write files simultaneously, an I/O sub-system can easily become a bottleneck when too many of these types of threads exist; on the contrary, too few threads will cause insufficient resource utilization and hurt performance. Therefore, programmers must pay much attention to parallelism control to find the appropriate number of I/O threads for an application. This paper proposes a parallelism control mechanism named IOPA that can adjust the parallelism of applications to adapt to the I/O capability of a system and balance computing resources and I/O bandwidth. The programming interface of IOPA is also provided to programmers to simplify parallel programming. IOPA is evaluated using multiple applications with both solid state and hard disk drives. The results show that the parallel applications using IOPA can achieve higher efficiency than those with a fixed number of threads.

Feature selection is a key problem in tumor classification and related tasks. This paper presents a tumor classification approach with neighborhood rough set-based feature selection. First, some uncertainty measures such as neighborhood entropy, conditional neighborhood entropy, neighborhood mutual information and neighborhood conditional mutual information, are in- troduced to evaluate the relevance between genes and related decision in neighborhood rough set. Then some important proper- ties and propositions of these measures are investigated, and the relationships among these measures are established as well. By using improved minimal-Redundancy-Maximal-Relevancy, combined with sequential forward greedy search strategy, a novel feature selection algorithm with low time complexity is proposed. Finally, several cancer classification tasks are demonstrated using the proposed approach. Experimental results show that the proposed algorithm is efficient and effective.

The paper describes the design and training of a fuzzy neural network used for early diagnosis of a patient through an FPGA based implementation of a smart instrument. The system employs a fuzzy interface cascaded with a feed-forward neural network. In order to obtain an optimum decision regarding the future pathophysiological state of a patient, the optimal weights of the synapses between the neurons have been determined by using inverse delayed function model of neurons. The neurons that are considered in the proposed network are devoid of self connections instead of commonly used self connected neurons. The current work also find out the optimal number of neurons in the hidden layer for accurate diagnosis as against the available number of CLB in the FPGA. The system has been trained and tested with renal data of patients taken at 10 days interval of time. Applying the methodology, the chance of attainment of critical renal condition of a patient has been predicted with an accuracy of 95.2%, 30 days ahead of actually attaining the critical condition. The system has also been tested for pathophysiological state prediction of patients at multiple time steps ahead and the prediction at the next instant of time stands out to be the most accurate.

The automatic detection and recognition of sound events by computers is a requirement for a number of emerging sensing and human computer interaction technologies. Recent advances in this field have been achieved by machine learning classifiers working in conjunction with time-frequency feature representations. This combination has achieved excellent accuracy for classification of discrete sounds. The ability to recognise sounds under real-world noisy conditions, called robust sound event classification, is an especially challenging task that has attracted recent research attention. Another aspect of real-word conditions is the classification of continuous, occluded or overlapping sounds, rather than classification of short isolated sound recordings. This paper addresses the classification of noise-corrupted, occluded, overlapped, continuous sound recordings. It first proposes a standard evaluation task for such sounds based upon a common existing method for evaluating isolated sound classification. It then benchmarks several high performing isolated sound classifiers to operate with continuous sound data by incorporating an energy-based event detection front end. Results are reported for each tested system using the new task, to provide the first analysis of their performance for continuous sound event detection. In addition it proposes and evaluates a novel Bayesian-inspired front end for the segmentation and detection of continuous sound recordings prior to classification.

Advancements in biometrics-based authentication have led to its increasing prominence and are being incorporated into everyday tasks. Existing vehicle security systems rely only on alarms or smart card as forms of protection. A biometric driver recognition system utilizing driving behaviors is a highly novel and personalized approach and could be incorporated into existing vehicle security system to form a multimodal identification system and offer a greater degree of multilevel protection. In this paper, detailed studies have been conducted to model individual driving behavior in order to identify features that may be efficiently and effectively used to profile each driver. Feature extraction techniques based on Gaussian mixture models (GMMs) are proposed and implemented. Features extracted from the accelerator and brake pedal pressure were then used as inputs to a fuzzy neural network (FNN) system to ascertain the identity of the driver. Two fuzzy neural networks, namely, the evolving fuzzy neural network (EFuNN) and the adaptive network-based fuzzy inference system (ANFIS), are used to demonstrate the viability of the two proposed feature extraction techniques. The performances were compared against an artificial neural network (NN) implementation using the multilayer perceptron (MLP) network and a statistical method based on the GMM. Extensive testing was conducted and the results show great potential in the use of the FNN for real-time driver identification and verification. In addition, the profiling of driver behaviors has numerous other potential applications for use by law enforcement and companies dealing with buses and truck drivers.

This paper describes a texture segmentation method using genetic programming (GP), which is one of the most powerful evolutionary computation algorithms. By choosing an appropriate representation texture, classifiers can be evolved without computing texture features. Due to the absence of time-consuming feature extraction, the evolved classifiers enable the development of the proposed texture segmentation algorithm. This GP based method can achieve a segmentation speed that is significantly higher than that of conventional methods. This method does not require a human expert to manually construct models for texture feature extraction. In an analysis of the evolved classifiers, it can be seen that these GP classifiers are not arbitrary. Certain textural regularities are captured by these classifiers to discriminate different textures. GP has been shown in this study as a feasible and a powerful approach for texture classification and segmentation, which are generally considered as complex vision tasks.

In this paper we present a framework for structured variable selection (SVS). The main concept of the proposed schema is to take a step towards the integration of two different aspects of data mining: database and machine learning perspective. The framework is flexible enough to use not only microarray data, but other high-throughput data of choice (e.g. from mass spectrometry, microarray, next generation sequencing). Moreover, the feature selection phase incorporates prior biological knowledge in a modular way from various repositories and is ready to host different statistical learning techniques. We present a proof of concept of SVS, illustrating some implementation details and describing current results on high-throughput microarray data.

The practical applicability of brain-computer interface (BCI) technology is limited due to its insufficient reliability and robustness. One of the major problems in this regard is the extensive variability and inconsistency of brain signal patterns, observed especially in electroencephalogram (EEG). This paper presents a fuzzy logic (FL) approach to the problem of handling of the resultant uncertainty effects. In particular, it outlines the design of a novel type-2 FL system (T2FLS) classifier within the framework of an EEG-based BCI, and examines its on-line applicability in the presence of short-and long-term nonstationarities of spectral EEG correlates of motor imagery (imagination of left vs. right hand movement). The developed system is shown to effectively cope with real-time constraints. In addition, a comparative post hoc analysis has revealed that the proposed T2FLS classifier outperforms conventional BCI methods, like LDA and SVM, in terms of the maximum classification accuracy (CA) rates by a relatively small, yet statistically significant, margin.

This work describes how evolutionary computation can be used to synthesize low-level image operators that detect interesting points on digital images. Interest point detection is an essential part of many modern computer vision systems that solve tasks such as object recognition, stereo correspondence, and image indexing, to name but a few. The design of the specialized operators is posed as an optimization/search problem that is solved with genetic programming (GP), a strategy still mostly unexplored by the computer vision community. The proposed approach automatically synthesizes operators that are competitive with state-of-the-art designs, taking into account an operator's geometric stability and the global separability of detected points during fitness evaluation. The GP search space is defined using simple primitive operations that are commonly found in point detectors proposed by the vision community. The experiments described in this paper extend previous results (Trujillo and Olague, 2006a,b) by presenting 15 new operators that were synthesized through the GP-based search. Some of the synthesized operators can be regarded as improved manmade designs because they employ well-known image processing techniques and achieve highly competitive performance. On the other hand, since the GP search also generates what can be considered as unconventional operators for point detection, these results provide a new perspective to feature extraction research.

Knowledge-based systems (KBS) and intelligent computing systems have been used in the medical planning, diagnosis and treatment. The KBS consists of rule-based reasoning (RBR), case-based reasoning (CBR) and model-based reasoning (MBR) whereas intelligent computing method (ICM) encompasses genetic algorithm (GA), artificial neural network (ANN), fuzzy logic (FL) and others. The combination of methods in KBS such as CBR-RBR, CBR-MBR and RBR-CBR-MBR and the combination of methods in ICM is ANN-GA, fuzzy-ANN, fuzzy-GA and fuzzy-ANN-GA. The combination of methods from KBS to ICM is RBR-ANN, CBR-ANN, RBR-CBR-ANN, fuzzy-RBR, fuzzy-CBR and fuzzy-CBR-ANN. In this paper, we have made a study of different singular and combined methods (185 in number) applicable to medical domain from mid 1970s to 2008. The study is presented in tabular form, showing the methods and its salient features, processes and application areas in medical domain (diagnosis, treatment and planning). It is observed that most of the methods are used in medical diagnosis very few are used for planning and moderate number in treatment. The study and its presentation in this context would be helpful for novice researchers in the area of medical expert system.

An optimal design of support vector machine (SVM)-based classifiers for prediction aims to optimize the combination of feature selection, parameter setting of SVM, and cross-validation methods. However, SVMs do not offer the mechanism of automatic internal relevant feature detection. The appropriate setting of their control parameters is often treated as another independent problem. This paper proposes an evolutionary approach to designing an SVM-based classifier (named ESVM) by simultaneous optimization of automatic feature selection and parameter tuning using an intelligent genetic algorithm, combined with k-fold cross-validation regarded as an estimator of generalization ability. To illustrate and evaluate the efficiency of ESVM, a typical application to microarray classification using 11 multi-class datasets is adopted. By considering model uncertainty, a frequency-based technique by voting on multiple sets of potentially informative features is used to identify the most effective subset of genes. It is shown that ESVM can obtain a high accuracy of 96.88% with a small number 10.0 of selected genes using 10-fold cross-validation for the 11 datasets averagely. The merits of ESVM are three-fold: (1) automatic feature selection and parameter setting embedded into ESVM can advance prediction abilities, compared to traditional SVMs; (2) ESVM can serve not only as an accurate classifier but also as an adaptive feature extractor; (3) ESVM is developed as an efficient tool so that various SVMs can be used conveniently as the core of ESVM for bioinformatics problems.