scholarly journals Eye blink detection using CNN to detect drowsiness level in drivers for road safety

Author(s):  
Pothuraju Vishesh ◽  
Raghavendra S ◽  
SantoshKumar Jankatti ◽  
Rekha V

<span><span>Blinking is a regular bodily function and it is the semiautomatic fast closing of the eyelid. A specific blink is examined by dynamic folding of the eyelid. It is a vital function of the eye which helps in spread of tears across and eliminates irritants from the shallow of cornea. In this research work we made use of convolution neural network, the deep learning concepts and image processing to detect drowsiness level in drivers. To train the blink detection model the mobilenet V2 is used as base. The loss function used for training was RMSprop and the optimizer is binary cross entropy. The dlib facial landmark was exploited to perceive and pre-process the detected faces. The dataset used for the training model is selected from the “Xiaoyang Tan” of nanjing university of aeronautics and astronautics. Based on the experimental outcome the projected method achieves an accuracy of 97%. The prototype developed serves as a base for further development of this process to achieve better road safety</span>.</span>

Author(s):  
Arijit Bag

Background: IC50 is one of the most important parameters of a drug. But, it is very difficult to predict this value of a new compound without experiment. There are only a few QSAR based methods available for IC50 prediction which is also highly dependable on huge number of known data. Thus, there is an immense demand for a sophisticated computational method of IC50 prediction, in the field of in-silico drug designing. Objective: Recently developed quantum computation based method of IC50 prediction by Bag and Ghorai requires an affordable known data. In present research work further development of this method is carried out such that the requisite number of known data being minimal. Methods: To retrench the cardinal data span and shrink the effects of variant biological parameters on the computed value of IC50, a relative approach of IC50 computation is pursued in the present method. To predict an approximate value of IC50 of a small molecule, only the IC50 of a similar kind of molecule is required for this method. Results: The present method of IC50 computation is tested for both organic and organometallic compounds as HIV-1 capsid A inhibitor and cancer drugs. Computed results match very well with the experiment. Conclusion: This method is easily applicable to both organic and organometallic com- pounds with acceptable accuracy. Since this method requires only the dipole moments of an unknown compound and the reference compound, IC50 based drug search is possible with this method. An algorithm is proposed here for IC50 based drug search.


Author(s):  
Fei Rong ◽  
Li Shasha ◽  
Xu Qingzheng ◽  
Liu Kun

The Station logo is a way for a TV station to claim copyright, which can realize the analysis and understanding of the video by the identification of the station logo, so as to ensure that the broadcasted TV signal will not be illegally interfered. In this paper, we design a station logo detection method based on Convolutional Neural Network by the characteristics of the station, such as small scale-to-height ratio change and relatively fixed position. Firstly, in order to realize the preprocessing and feature extraction of the station data, the video samples are collected, filtered, framed, labeled and processed. Then, the training sample data and the test sample data are divided proportionally to train the station detection model. Finally, the sample is tested to evaluate the effect of the training model in practice. The simulation experiments prove its validity.


The driver of an automobile is the key part of the “driver–car–road–environment” system, the stable functioning of which determines the efficiency and safety of road traffic. The driver as the operator of the “driver –car–road–environment” system receives most of the information from the road, data from moving and standing objects, road signs, traffic lights, surface conditions and traffic conditions. An analysis of most traffic accidents shows that the weakest part of the “driver–car–road–environment" system, restricting its effectiveness and dependability, is the person. To ensure the necessary dependability and safety, the driver of any vehicle must be careful. This is supported by an appropriate psychophysiological state, which, in turn, depends on many factors. The article presents an analysis of research work taking into account the influence of various factors on the dependability of a vehicle driver. Means and methods of research are described. Recommendations are given on creating a stand for studying the influence of the psychophysiological state of the driver on road safety. Keywords Driver dependability; road traffic; automobile; traffic environment; road accidents; road safety


Author(s):  
Mangey Ram ◽  
Ashok Singh Bhandari ◽  
Akshay Kumar

Roads have always been the main source of transportation all over the world. Easy accessibility and more safety are the most important features of road transportation. Improvements in these areas are constantly required and invited. Solar road studs are one of the remarkable improvements in road safety. Solar road studs use solar energy, which is the most sustainable and pollution-free source of energy that provides reliable power supplies and fuel diversification. Solar road studs are flashing solar cell-powered LED lighting devices used in road construction to delineate road edges and centerlines. This research work is dedicated to evaluating the reliability measures which include availability, mean time to failure (MTTF), cost analysis, and sensitivity analysis with their graphical representation by using the Markov process. Along with reliability assessment, Particle Swarm Optimization (PSO) technique is applied to optimize the cost of the system.


2020 ◽  
Vol 170 ◽  
pp. 06008
Author(s):  
Prashant Awsarmal ◽  
S. L. Hake ◽  
Shubham Vaidya ◽  
P. K. Bhandari ◽  
M. P. Wagh

Efficient road network is a part-n-parcel of rapid industralization, urbanization and development of nation. While designing roads and highways, main emphasis is given on speed which will help to reduce time of journey and save fuel. But safety of drivers and passengers travelling along road is also important. In past, it was observed that while travelling, due to excess speed passengers safety was compromised. It will lead to accidents. It may cause severe injuries and loss of human life. Therefore it is important to check every aspect of vehicles as well as road during its design, construction and throughout the life of the road. Road safety audit is conducted to check performance of new road projects on grounds of offering maximum safety. Also checks are applied to study performance of existing roads to suggest repairs, rehabiliatation and maintenance work in order to improve condition of roads. During audit process, accident prone locations are identified. Past accident record from traffic department, Police department, hospitals etc are referred to understand damage that had occured. Even road geometry is investigated on technical basis. In present investigation, particular stretch of Beed Bypass Road passing through Aurangabad city in Maharashtra state, India was selected. On this road, accident sites where major accidents occurred in past were identified and investigated for different parameters. Based upon study, different causes of accidents and thereafter preventive methods were recommended during research work.


2017 ◽  
Vol 10 (13) ◽  
pp. 385
Author(s):  
Jincy J Fernandez ◽  
Nithyanandam Pandian ◽  
Raghuvamsh Chavali ◽  
Ashwanth Kumar Appalaghe

In today’s internet world, all the data are represented and stored in digital form. Almost any entity in this world can be represented digitally, ranging from simple text to complex multimedia work. Now, the challenge is to claim the ownership and prevent theft of one’s own digital data. Multimedia theft has driven the attention of many stakeholders who spend huge money and precious time in creating or making such valuable digital data. Among all the multimedia entities, image files are more vulnerable for theft since it is the basic component of any visuals. The notion of this research work is to propose an image theft detection model which will determine whether partial theft or complete theft of an image has occurred or not. A biometric feature, i.e., fingerprint of the owner is embedded on the digital image at a micro level, such that even a very small portion of image theft can be determined, and the ownership of the image can be claimed by the owner. This research is limited to the spatial domain, i.e. raw image. Assessment metrics of the results shows that embedding the biometric feature on an image does not distort the image quality and its artifacts.


2013 ◽  
Vol 415 ◽  
pp. 45-51
Author(s):  
Nawakorn Ditsariyakul ◽  
Viboon Sangveraphunsiri

This research work is to develop a concept of movable virtual wall for miniature tasks operation of a master-slave manipulator arm with force reflection. The purposes are to improve accuracy of the operation and preventing over travelling beyond a desired boundary. The predicted distance of the end-effector can be calculated based on various end-effector and hand models. From the experiments, movable virtual wall shows adjusting some wall parameters, the over travelling through the forbidden boundary can be prevented and the possibility of further development to improve miniature tasks operation.


Comunicar ◽  
2015 ◽  
Vol 23 (45) ◽  
pp. 151-159 ◽  
Author(s):  
Rosabel Roig-Vila ◽  
Santiago Mengual-Andrés ◽  
Patricia Quinto-Medrano

The emergence of Information and Communication Technologies (ICTs) poses new educational challenges for teachers, to which it can respond from a consistent training model. This study has as its aim to analyze the technological, pedagogical and content knowledge needed for Primary Education teachers to integrate ICTs into teaching. A research work based on a quantitative non-experimental methodology which involved 224 Preschool and Primary Education teachers working in the province of Alicante (Spain) was performed with that aim. The important results showed that teachers are more knowledgeable in the pedagogical and content fields than in technology, which means that their level of technological knowledge does not suffice to integrate ICTs into their teaching tasks. Significant differences were additionally identified between gender and years of experience, together with the relationship between the fun use of technology and the knowledge of its essential aspects. Our findings confirm the need for a digital literacy campaign addressed to teachers, involving not only a technological type of training but also an overall pedagogical and content approach. This is in keeping with the TPACK model (Technological, Pedagogical and Content Knowledge), which appears as a reference framework to be taken into account when it comes to teachers’ professional development and its connection with the teaching-learning processes in the classroom wherever Information and Communication Technologies are present. La emergencia de las tecnologías de información y comunicación (TIC) plantea nuevos desafíos educativos al profesorado, a los cuales puede responder desde un modelo de formación coherente. El propósito de este estudio es analizar los conocimientos tecnológicos, pedagógicos y disciplinares del profesorado de Educación Primaria, necesarios para la integración de las TIC en la labor docente. Para ello, se llevó a cabo una investigación con una metodología cuantitativa de carácter no experimental en la que participaron 224 profesores de Educación Infantil y Primaria de la provincia de Alicante. Los resultados mostraron que los docentes poseen mayores conocimientos pedagógicos y disciplinares que tecnológicos, lo que conlleva a escasos conocimientos para la integración de las TIC en la labor docente. Se constataron, además, diferencias significativas entre el género y los años de experiencia docente, y la relación entre el uso lúdico de la tecnología y los conocimientos sobre sus aspectos fundamentales. Según los resultados obtenidos, se corrobora la necesidad de una alfabetización digital del profesorado abordada no solo desde una formación tecnológica, sino también pedagógica y disciplinar de forma global. Ello responde al modelo TPACK (Technological, Pedagogical and Content Knowledge), el cual se contempla como un marco de referencia a tener en cuenta por lo que respecta al desarrollo profesional del profesorado y su vinculación a los procesos de enseñanza-aprendizaje en el aula donde las TIC estén presentes.


Author(s):  
G Manoharan ◽  
K Sivakumar

Outlier detection in data mining is an important arena where detection models are developed to discover the objects that do not confirm the expected behavior. The generation of huge data in real time applications makes the outlier detection process into more crucial and challenging. Traditional detection techniques based on mean and covariance are not suitable to handle large amount of data and the results are affected by outliers. So it is essential to develop an efficient outlier detection model to detect outliers in the large dataset. The objective of this research work is to develop an efficient outlier detection model for multivariate data employing the enhanced Hidden Semi-Markov Model (HSMM). It is an extension of conventional Hidden Markov Model (HMM) where the proposed model allows arbitrary time distribution in its states to detect outliers. Experimental results demonstrate the better performance of proposed model in terms of detection accuracy, detection rate. Compared to conventional Hidden Markov Model based outlier detection the detection accuracy of proposed model is obtained as 98.62% which is significantly better for large multivariate datasets.


2021 ◽  
Vol 264 ◽  
pp. 05027
Author(s):  
Botir Abdullaev ◽  
Davron Yuldoshev ◽  
Tolqin Muminov ◽  
Dilmurod Axmedov

The issues of public transport service, its quality, road safety along the route are becoming a priority worldwide. After all, ensuring the safety of public transport serves to increase its attractiveness. Research-based on different approaches to road safety is being conducted in the areas. However, the issue of road safety in public transport remains relevant. Traffic accidents on bus routes occur mainly at intersections, haul sections, and intermediate stops. Intersections of single-level highways are among the areas where traffic accidents are most likely to occur. It should be noted that the assessment of road safety in public transport is based not only on traffic accidents and violations but also on the intensity and variability of traffic and pedestrian traffic, the degree of organization of traffic, road condition and geometric elements, parameters of intermediate stations and many other factors. It is advisable to tie. Therefore, this research work aims to assess the traffic safety of directional buses and consists of several stages. This article is devoted to improving the method of assessing road safety at intersections of single-level highways.


Sign in / Sign up

Export Citation Format

Share Document