Driver and passenger safety is one of the prime concerns in modern day vehicle. Alarming statistics of accidents and increased number of vehicles on road demands for an intelligent safety mechanism that helps the driver in handling immediate precarious situations like sudden probability of a rear- end collision. The work proposes a mechanism that not only computes the deceleration of vehicle due to braking and displays the braking intensity through an array of LED but also involves monitoring the braking intensity levels and communicate it to the vehicles that are following it in lambertian range of IR transmitter module to avoid any collision pre-hand, due to any situation that may arise and cause immediate deceleration of the vehicle ahead. An ARM Cortex MO microcontroller will be interfaced with an accelerometer that senses the deceleration levels, a LED array to display the braking intensity and an IR transceiver module for inter-vehicle communication that would transmit pulses whose frequency is modulated proportional to the braking intensity level. To take decision and automatically control the motion of the following vehicle, a collision avoidance system consisting of CortexMO microcontroller is implemented that warns the drier using a buzzer and messages the active and passive safety mechanisms to be activated using CAN protocol and takes control decisions according to an algorithm designed to handle the situation.

This work investigates the stick–slip phenomenon during sliding motion between solid lubricant-impregnated epoxy polymer-coated steel bars and AISI 52,100 steel balls. An acoustic sensor detected the stick–slip phenomenon during the tribo-pair interaction. The wear characteristics of the workpiece coated with different epoxy coatings were observed and scrutinized. The RMS values of the acoustic sensor were correlated with the frictional coefficient to develop a standard based on the acoustic sensor, leading to the detection of the stick–slip phenomenon. As per the findings, the acoustic waveform remained relatively similar to the friction coefficient observed during the study and can be used effectively in detecting the stick–slip phenomenon between steel and polymer interaction. This work will be highly beneficial in industrial and automotive applications with a significant interaction of polymer and steel surfaces.

Any occupation which involves critical decision making in real-time requires attention and concentration. When repetitive and expanded working periods are encountered, it can result in microsleeps. Microsleeps are complete lapses in which a subject involuntarily stops responding to the task that they are currently performing due to temporary interruptions in visual-motor and cognitive coordination. Microsleeps can last up to 15 s while performing a particular task. In this study, the ability of a convolutional neural network (CNN) to detect microsleep states from 16-channel EEG data from 8 subjects, performing a 1D visuomotor was explored. The data were highly imbalanced. When averaged across 8 subjects there were 17 responsive states for every microsleep state. Two approaches were used to handle the CNN training with data imbalance – oversampling the minority class and cost-based learning. The EEG was analysed using a 4–s epoch with a step size of 0.25 s. Leave-one-subject-out cross-validation was used to evaluate the performance. The performance measures used for assessing the detection capability of the CNN were: sensitivity, precision, phi, geometric mean (GM), AUC ROC , and AUC PR . The performance measures obtained using the oversampling and cost-based learning methods were: AUC ROC = 0.90/0.90, AUC PR = 0.41/0.41 and a phi = 0.42/0.40, respectively. Although the performances were similar, the cost-based learning method had a considerably shorter training time than the oversampling method.