Augmented Human Research最新文献

One of the important parts of computer vision is segmenting an image into various uses. The key objective of any segmentation technique is to stop the segmentation at a point beyond which it is unnecessary. The images in which objects are surrounded by asymmetric background show all the edges of the background too, when traditional techniques of edge detection were used. Hence, it was difficult to recognize the actual components in the image. This paper is about the use of preprocessing techniques so that we can refine the result and obtain only the edges which are necessary excluding the background noise. The designing and testing of all the methods have been done on MATLAB software.

The objective of this work is to contribute to the analysis and understanding of medical documents taken from health institutions in Saudi Arabia. The project aimed to use intelligent technologies and image processing tools to the automation of processing the medical documents. This consists particularly to assist medical staff to the treatment of the different medical forms in order to facilitate the storage of the important information and their centralization. As we worked on bilingual context, we proposed a system for identifying Arabic and Latin texts whether taped or manuscripted. In this way, we can identify the extracted blocks from different regions of interest and distribute them to different OCR systems to recognize them. We used SGLD as a texture measure of the image writing shapes. Then, we calculated Haralick descriptors that characterize them. The resulting recognition ratios were very efficient and promising.

Diseases like cancer have been termed as chronic fatal disease because of its deadly nature. The reason why cancer is termed as fatal is cancer progresses faster, and in most of the cases, these cells are detected at an advance stage. It is found that early detection of cancer is the key to lower death rate. In this study, overviews of applying AI technology for diagnosis of three types of cancer, breast, lung and liver, have been demonstrated. Various studies are reviewed for the different types of systems which are used for early detection of cancer. Automated or computer-aided systems with AI are considered as they provide a perfect fit to process a large dataset with accuracy and efficiency in detecting cancer. Diagnosis and treatment can be carried out with the help of these systems. Breast, lung and liver cancer studies have shown that some of these systems provide accurate precision in diagnosis and thus can solve the problem if these systems are implemented. However, these systems have to face a lot of hurdles to be implemented on a large scale. Image preprocessing, data management and other technology also need enhancement to be compatible with AI and machine learning algorithms to be implemented. Considering the experimental results, this study shows there is no doubt that the AI-implemented neural networks would be the future in cancer diagnosis and treatment.

Virtual reality is emerging freshly in the field of interdisciplinary research. In the past years, its area has grown over research and the industry has made important investments in the manufacturing of different VR products as well as in research. Virtual reality (VR) is developed by the union of technologies that are used to visualize and interact with virtual atmosphere. This atmosphere portrays a 3D space which may be imaginary, microscopic or macroscopic and based on practical laws of dynamics or imaginary dynamics. VR technology is getting supreme using computer hardware, software and virtual environment technology through which the real world can be simulated dynamically. The dynamical conditions can react according to the human language, form and so on rapidly that humans can communicate with virtual environment in true time. Therefore, VR technology can be put into application in education, military, sports training, and is portraying an important part in the evolution. The paper summarizes the developments in VR technology in the fields of education, military and sports, and then analyses the future trends of VR in these fields.

Neuromuscular disorders are characterized by abnormal functioning of muscles and nerves that communicate with the brain, resulting in muscle weakness and ultimately damage to nervous control, for instance amyotrophic lateral sclerosis (ALS) and myopathy (MYO). Diagnosis of these disorders is frequently done by examining ALS, MYO and normal electromyography (EMG) signals. In the present work, an efficient technique that involves wavelet transform using tunable-Q dynamics (TQWT) is proposed in order to identify disorders related to the neuromuscular domain of EMG signals. The EMG signal is decomposed by the TQWT technique into sub-bands, and these sub-bands are used to determine spectral features including spectral flatness, spectral stretch and spectral decrease, and statistical features including kurtosis, mean absolute deviation, and interquartile range. The extracted features are used as inputs into extreme learning machine classifiers in order to identify and analyze EMG signals associated with neuromuscular dysfunction. The results achieved with this technique illustrate a much better classification with regard to neuromuscular disturbance in electromyogram signals when compared with previous methods.

Technological advances in healthcare have saved innumerable patients and are continuously improving our quality of life. Fatigue among health indicators of individuals has become significant due to its association with cognitive performance and health outcomes and, is one of the major factors contributing to the degradation of performance in daily life. This review serves as a source of studies which helped in better understanding of fatigue and also gave significant detection methods and systematic approaches to figure out the impacts and causes of fatigue. Artificial intelligence was turned out to be one of the essential tactics to detect or monitor fatigue. Artificial neural network, wavelet transform, data analysis of mouse interaction and keyboard patterns, image analysis, kernel learning algorithms, relation of fatigue and anxiety, and heart rate data examination studies were used in this paper to precisely assess the source, factors and features which influenced the recognition of fatigue.

In this work, a spline adaptive sieve is designed for recognizing Wiener-style non-constricted arrangement. The proposed filter has ductile lookup table along impulse response sieve whose characteristic is infinite where up-sampling is carried out for a sub-part of low-order polynomial. This process can be applicable pro ECG to get better results for recognizing the QRS complex. The presented approach is suitable to realize the precise converse model directly from simulation data with reduced complexity. Further, variable-order fractional least mean square (VOFLMS) scheme can be developed pro better accuracy recognition. In order to achieve rapid convergence speed and lower error, the VOFLMS method actively adjusts the request for the fragmentary subordinate on the inaccuracy function. Simulation outcomes verify the efficiency of the proposed filter scheme along VOFLMS non-constricted arrangement recognition. It is demonstrated that the VOFLMS can adapt nonlinearity more satisfactorily as compared to other reported schemes in the literature.

Application of artificial intelligence (AI) in health-care detection is a domain of exceptional research and interest in today’s world. And hence among this domain, a considerable inclination is toward creating a smart system that is AI for aiding identification of brain-related disease—Alzheimer’s—using electroencephalogram (EEG). Certain AI-based techniques as well as systems have been created for EEG examination and interpretation, but they have a common drawback that is lack of shrewdness and acuteness. Therefore, to overcome these drawbacks, a different methodology or technique is suggested in this paper which is able to mold the AI technique for better EEG Cz strip K-complex identification. This suggested method and structure of AI detection system is relied on quantitative scrutinization of Cz strip and embedding-established EEG explication principles for detection of K-complex and Alzheimer’s. This technique unconditionally relied on facts and information of neuroscience that are applied by expert in health care such as neurologist to create a detailed review of sick person’s EEG. The suggested technique also allots a potential of learning on its own to the AI so that it can apply the events in future examinations.

The number of interconnected devices around us is constantly growing, and it may become challenging for users to control all these devices when control interfaces are distributed over mechanical elements, apps, and configuration webpages.If devices are even supposed to be connected and work together, this challenge is intensified. An alternative way for configuring and controlling devices in situ is enabled by wearable technologies. In this paper, we investigate interaction methods for smart appliances in augmented reality from an egocentric perspective. We examine how users can control appliances through augmented reality directly. The physical objects are augmented with interaction widgets, which are generated on demand and represent the connected devices along with their adjustable parameters.For example, a widget can be overlaid on a loudspeaker to control its volume. We explore three ways of manipulating the virtual widgets: (1) in-air finger pinching and sliding, (2) whole-arm gestures rotating and waving, (3) incorporating physical objects in the surrounding and mapping their movements to the interaction primitives. We compare these methods in a user study with 25 participants and find significant differences in the preference of the users, the speed of executing commands, and the granularity of the type of control. While these methods only apply to controlling a single device at a time, in a second part, we create a method to also take potential connections between devices into account. Users can view and configure connections between smart devices in augmented reality and furthermore can manipulate them or create new device connections using simple gestures. This facilitates the understanding of existing connections and their modification.

In this paper, extension of the 1-D adaptive filter schemes to 2D formation and the new 2D adaptive filters are designed. The results of proposed scheme are compared with 2D variable step-size normalized least mean squares, the 2D VSS affine projection algorithms, the 2D set-membership NLMS, and 2D SM APA. The performance of proposed scheme is compared with other reported methods for 2D adaptive filter design. Based on simulation results, it is demonstrated that the proposed method can achieve 85% and 90% reduction in normalized mean square error and normalized maximum error mean, respectively. Moreover, the proposed 2D-ANC filter applied for reconstruction of a biomedical image shows 6 dB signal-to-noise ratio improved as compared to recently reported algorithm.