Current Issue : April - June Volume : 2020 Issue Number : 2 Articles : 5 Articles
Images acquired under deprived weather environment are frequently corrupted\ndue to the presence of haze, mist, fog or other aerosols in a form of\nnoise. Haze elimination is essential in computer vision and computational\nphotography applications. Generally, there is the existence of numerous approaches\ntowards haze removal which are mostly meant for hazy images under\ndaytime environments. Although the potency of these proposed approaches\nhas been comprehensively established on daylight hazy images. However\nthese procedures inherit significant limitations on images influenced by\nnight-time hazy environments. Since night time haze removal dehazing remains\nan ill-posed problem, we proposed a novel method for night-time single\nimage dehazing which is efficient under night-time environments. The\nproposed scheme is a dark channel-based local image dehazing procedure\nthat locally estimates the atmospheric intensity for each selected mask on a\ncorrupted image independently and not the entire image. This is done in order\nto overcome the challenge of night-scenes that are exposed to multiple/\nartificial lights source and spatially non-uniform environmental illumination.\nWe performed an adaptive filtering on the combined dehazed masks\nto improve the degraded image. We validated the supremacy of the proposed\napproach in terms of speed and robustness through computer-based experiments.\nConclusively, we displayed comparison results with state-of-the-art\nand extensively emphasized the comparative advantage of our scheme....
Reliability and safety are major issues in tower crane applications. A new\nadaptive neurofuzzy system is developed in this work for real-time health\ncondition monitoring of tower cranes, especially for hoist gearboxes. Vibration\nsignals are measured using a wireless smart sensor system. Fault detection\nis performed gear-by-gear in the gearbox. A new diagnostic classifier is\nproposed to integrate strengths of several signal processing techniques for\nfault detection. A hybrid machine learning method is proposed to facilitate\nimplementation and improve training convergence. The effectiveness of the\ndeveloped monitoring system is verified by experimental tests....
A study of the ultrasonic vocalizations of several adult male BALB/c mice in the presence\nof a female, is undertaken in this study. A total of 179 distinct ultrasonic syllables referred to\nas â??phonemesâ? are isolated, and in the resulting dataset, k-means and agglomerative clustering\nalgorithms are implemented to group the ultrasonic vocalizations into clusters based on features\nextracted from their pitch contours. In order to find the optimal number of clusters, the elbow\nmethod was used, and nine distinct categories were obtained. Results when the k-means method was\napplied are presented through a matching matrix, while clustering results when the agglomerative\ntechnique was applied are presented as a dendrogram. The results of both methods are in line with\nthe manual annotations made by the authors, as well as with the ones presented in the literature.\nThe two methods of unsupervised analysis applied on 14 element feature vectors provide evidence\nthat vocalizations can be grouped into nine clusters, which translates into the claim that there is a\ndistinct repertoire of â??syllablesâ? or â??phonemesâ?....
This paper proposes a method of automatically detecting and classifying low frequency\nnoise generated by power transformers using sensors and dedicated machine learning algorithms.\nThe method applies the frequency spectra of sound pressure levels generated during operation by\ntransformers in a real environment. The spectra frequency interval and its resolution are automatically\noptimized for the selected machine learning algorithm. Various machine learning algorithms,\noptimization techniques, and transformer types were researched: two indoor type transformers from\nSchneider Electric and two overhead type transformers manufactured by ABB. As a result, a method\nwas proposed that provides a way in which inspections of working transformers (from background)\nand their type can be performed with an accuracy of over 97%, based on the generated low-frequency\nnoise. The application of the proposed preprocessing stage increased the accuracy of this method by\n10%. Additionally, machine learning algorithms were selected which offer robust solutions (with the\nhighest accuracy) for noise classification....
Modern achievements accomplished in both cognitive neuroscience and humanâ??machine\ninteraction technologies have enhanced the ability to control devices with the human brain by\nusing Brainâ??Computer Interface systems. Particularly, the development of brain-controlled mobile\nrobots is very important because systems of this kind can assist people, suffering from devastating\nneuromuscular disorders, move and thus improve their quality of life. The research work\npresented in this paper, concerns the development of a system which performs motion control in a\nmobile robot in accordance to the eyesâ?? blinking of a human operator via a synchronous and\nendogenous Electroencephalography-based Brainâ??Computer Interface, which uses alpha brain\nwaveforms. The received signals are filtered in order to extract suitable features. These features are\nfed as inputs to a neural network, which is properly trained in order to properly guide the robotic\nvehicle. Experimental tests executed on 12 healthy subjects of various gender and age, proved that\nthe system developed is able to perform movements of the robotic vehicle, under control, in\nforward, left, backward, and right direction according to the alpha brainwaves of its operator, with\nan overall accuracy equal to 92.1%....
Loading....