ECG signals filtering and analysis using the Compact Genetic Algorithm Based on Abstract Data Types in GPU/CUDA

This paper presents the process of adaptive filtering of cardiovascular disease signals from the processing and cleaning of ECG signals developed by the Compact Genetic Algorithm Based on Abstract Data Types (CGAADT), implemented in MATLAB using GPU/CUDA architecture from the examples of the base of MIT-BIH data. The results show that CGAADT can improve the filtering, cleaning, detection and diagnosis of arrhythmias using a single algorithm (CGAADT) in the adoption of a representation for the population with fixed size of chromosomes, pre-established by fragmentation of the GPU base when implemented in high performance systems, aiming to improve the health systems offered to patients with cardiovascular problems.

Face Image Set Recognition Based On Improved HOG-NMF and Convolutional Neural Networks

Objective Face recognition can be affected by unfavorable factors such as illumination, posture and expression, but the face image set is a collection of people’s various angles, different illuminations and even different expressions, which can effectively reduce these adverse effects and get higher face recognition rate. In order to make the face image set have higher recognition rate, a new method of combining face image set recognition is proposed, which combines an improved Histogram of Oriented Gradient (HOG) feature and Convolutional Neural Network (CNN). Method The method firstly segments the face images to be identified and performs HOG to extract features of the segmented images. Secondly, calculate the information entropy contained in each block as a weight coefficient of each block to form a new HOG features, and non-negative matrix factorization (NMF) is applied to reduce HOG features. Then the reduced-dimensional HOG features are modeled as image sets which keep your face details as much as possible. Finally, the modeled image sets are classified by using a convolutional neural network. Result The experimental results show that compared with the simple CNN method and the HOG-CNN method, the recognition rate of the method on the CMU PIE face set is increased by about 4%~10%. Conclusion The method proposed in this paper has more details of the face, overcomes the adverse effects, and improves the accuracy.

Using Grounded Theory to Explore the Words of Mouth in Live Broadcast Platform

The purpose of this study is to explore in depth the special context and unique experience of the live video streaming and to provide insights regarding an interpretation of the contextualization experiences model. This study uses grounded theory, depth interviews, and the physical travel of researchers to the field for participation and observations. Finally, the insight of the live broadcast platform contextualization was developed. The theoretical contribution of this study is to establish the words of mouth relationship of the live broadcast platform and ten related propositions. The study revealed the mystery of live video streaming.

Effect of Noise Pollution Among Milling Machine Operators in North-West Nigeria.

Commercial activities are mostly centralized to main markets in many towns and cities of the Northern part of Nigeria. Such central markets constitute the noisiest part of the towns. Yet, there is no evidence that the workers and traders in such markets are aware of the challenges excessive noise pollution pose to their health. This problem serves as the basis for this research, which investigated the major source of noise pollution in Kebbi central market and make recommendation to improve the wellbeing of the people in the market.The market was divided into thirteen sections based on activities. These sections were visited twice a day for two weeks to measure their sound levels. The sound level was measured with a CEM digital noise level meter with an accuracy of ±3.5dB@1KHz. Thereafter, an ergonomic observation assessment of the noisiest section was carried out. The assessment was carried out based on rapid entire body assessment (REBA) methodology. The average sound intensity in all the sections exceeded the recommended safe sound level of 40dB. However, only the sound intensity at the grain and spice milling section (89.13 dB) exceeded the noise harmfulness level of 85dB. Operators were encouraged to use ear muffs or earplugs to minimise the exposure to harmful noise level. Proper electrification of the section was also recommended to minimise the use of internal combustion engines. The findings emphasised the need for government and relevant authorities to carry out occupational safety awareness among workers in the non-formal sector of the society.

Deep Discriminative Restricted Boltzmann Machine (DDRBM) for Robust Face Spoofing Detection

Biometrics emerged as a robust solution for security systems. Despite, nowadays criminals are developing techniques to accurately simulate biometric traits of valid users, process known as spoofing attack, in order to circumvent the biometric applications. Face is among the main biometric characteristics, being extremely convenient for users given its non-intrusive capture by means of digital cameras. However, face recognition systems are the ones that most suffer with spoofing attacks since such cameras, in general, can be easily fooled with common printed photographs. In this sense, countermeasure techniques should be developed and integrated to the traditional face recognition systems in order to prevent such frauds. Among the main neural networks for face spoofing detection is the discriminative Restricted Boltzmann Machine (RBM) which, besides of efficiency, achieves great results in attack detection by learning the distributions of real and fake facial images. However, it is known that deeper neural networks present better accuracy results in many tasks. In this context, we propose a novel model called Deep Discriminative Restricted Boltzmann Machine (DDRBM) applied to face spoofing detection. Results on the NUAA dataset show a significative improvement in performance when compared to the accuracy rates of a traditional discriminative RBM on attack detection.

The Evolution of Human Computation: Past, Present and Future

Human computation is a technique that utilizes human abilities to perform computation tasks that are difficult for computers to process. Since the concept of human computation was introduced in 2003, many applications have been developed in an ad hoc manner and a large number of published works have focused on different aspects of human computation, such as computational techniques and performance analysis. To understand how to apply human computation to solve different problems today, it is important to understand how human computation evolves and why it happens. In light of the achievements of human computation so far, we consider what the future may hold for this relatively new field.

Efficient Human-Robot Interaction using Deep Learning with Mask R-CNN: Detection, Recognition, Tracking and Segmentation

我们通过提出深度神经网络与机械机器人系统的集成来解决社会人机交互问题，使其对人机交互活动具有鲁棒性。掩模R-CNN是一种用于物体检测的神经网络，可以有效地帮助定位可以被操纵以指示机器人头部运动的人脸。我们的方法不仅适用于检测和分割任务，而且能够与表示3D尺寸的并行微型机械手的机制，工作空间的位置和方向集成。它还可以解决目标分割问题，这似乎是当今计算机视觉中最具挑战性的问题之一。

Surfing the Web: the role of Social-Support in the adolescents’ Internet use

This research analyzes what predictors determine either a problematic internet use (PIU) or a functional Internet use (FIU) in 574 adolescents (303 females and 271 males). A cross-sectional study was proposed based on the compilation of an online questionnaire. It was hypothesized that Online Social-Support positively predicts PIU only when Offline Social-Support is low and Online Social-Support positively predicts FIU only when Offline Social-Support is high. Results show that Online Social-Support doesn't predict PIU, while, Offline Social-Support negatively affects It. FIU isn't affected by Offline Social-Support, while Online Social-Support predicts it. Gender differences occurs in PIU, Offline Social-Support and number of acquaintances in favor of males.

Structural Design, Optimization and Analysis of Robotic Arm Via Finite Elements.

The study set out to determine the optimum architecture of a robotic arm link based on weight and payload and perform vibrational and stress analyses on the resultant shape. Findings showed the effectiveness of topology optimization in preliminary stages of structural design. The subsequent linear static analyses confirmed the degree of safety of the robotic arm links. It was also shown that that preload in the actuator wire incorporated in the links can be manipulated to tune the natural frequency of the structure. These findings contribute to the ongoing design of the entire robotic first aid system by providing data, which will be used for selection of components and inspire confidence to proceed with manufacture.

Human Computer Interaction, Cognitive Cybernetic & Captological Education

This paper was inspired by the topics by Marshal McLuhan about cibernetisation media understanding, associated with new findings in intelligent systems that lead towards technological anthropomorphisation, and Larsen's model of cognitive controller mood. The results of research conducted from 1990 to the present day outlining the issues associated with captology are presented, and their transfer to specific areas in education outlined. The objective of the theory is to comprehend, interpret and describe the appearance of various disciplines in the natural and social sciences relating to cognitive cybernetics and Human Computer Interaction. In accordance with the unique principles, multidisciplinarity is replaced by pluriperspectivity, and an approach to integrating research methods with engineering design. The theory answers questions using cognitive cybernetics and its recognition and transformation of Descartes's saying: "cogito ergo sum", (I think, therefore I am). Work presents the relationship and correlation between man and technology as Human computer interaction with technological definitions Intelligent Systems and Captology. Special attention is focused on today's modern education with the use of virtual media and the cultural matrix within which the particular media is active. For intelligent educations systems to become more useful and acceptable, we need to consider the “system” as a synergistic composition of software behaviors, and the human interacting. Human interaction must be dominant and having considered the ruling. This cannot be achieved with today's captological educational media. Captological educational media stifles people, casts their most important, (social), role in education and makes them unhappy? Human Computer Interaction, as a strategy and philosophy, is the future of education!