Search

Even though Electric Powered Wheelchairs (EPWs) are a useful tool for meeting the needs of people with disabilities, some disabled people find it difficult to use regular EPWs that are joystick-controlled. Smart wheelchairs that use Brain–Computer Interface (BCI) technology present an efficient solution to this problem. This article presents a cutting-edge intelligent control wheelchair that is intended to improve user involvement and security. The suggested method combines facial expression analysis via a camera with EEG signal processing using the EMOTIV Insight EEG dataset. The system generates control commands by identifying specific EEG patterns linked to facial expressions such as eye blinking, winking left and right, and smiling. Simultaneously, the system uses computer vision algorithms and inertial measurements to analyze gaze direction in order to establish the user's intended steering. The outcomes of the experiments prove that the proposed system is reliable and efficient in meeting the various requirements of people, presenting a positive development in the field of smart wheelchair technology. [ABSTRACT FROM AUTHOR]

This research conducts a comparative analysis of Faster R-CNN and YOLOv8 for real-time detection of fishing vessels and fish in maritime surveillance. The study underscores the significance of this investigation in advancing fisheries monitoring and object detection using deep learning. With a clear focus on comparing the performance of Faster R-CNN and YOLOv8, the research aims to elucidate their effectiveness in real-time detection, emphasizing the relevance of such capabilities in fisheries management. By conducting a thorough literature review, the study establishes the current state-of-the-art in object detection, particularly within the context of fisheries monitoring, while discussing existing methods, challenges, and limitations. The findings of this study not only shed light on the superiority of YOLOv8 in precise detection but also highlight its potential impact on maritime surveillance and the protection of marine resources. [ABSTRACT FROM AUTHOR]

Today's surveillance video systems are getting paired with monitoring technology. This technology is capable of analyzing video streams in real-time for the detection and tracking of objects or events. Video surveillance goes beyond security barriers by allowing the operator to detect a whole bunch of things and events that they have pre-configured beforehand. In this paper, we explore 4 distinct variants of the YOLO object detection approach and evaluate their respective performance for images, videos, and live videos with video surveillance scenarios. The findings have revealed that YOLOv8 and YOLOv7 stand out with the highest precision scores, indicating their ability to make accurate positive identifications. YOLOv6 leads in terms of recall, demonstrating its effectiveness in identifying positive samples. In the realm of speed, YOLOv8 excels with an impressive 217 FPS for image processing, followed by YOLOv5 at 91 FPS, underlining the advantages of utilizing GPU acceleration for rapid computations. YOLOv7, while being the slowest, offers the lowest inference time, although it does come with higher model complexity, suggesting a trade-off between speed and computational resources. Moreover, YOLOv8 exhibits the highest mAP, affirming its precision in object detection. On the other hand, YOLOv7 achieves the highest F1-score, indicating a well-balanced trade-off between precision and recall. In practical video surveillance applications, YOLOv8 emerges as the most accurate and efficient model for processing images, videos, and live feeds, delivering reliable results with a lower level of complexity. [ABSTRACT FROM AUTHOR]

The growing demand for portable electronic devices has led to an increased emphasis on power consumption within the semiconductor industry. As a result, designers are now encouraged to consider the impact of their decisions not only on speed and area, but also on power throughout the design space exploration. This article presents a high-level design space exploration methodology. It allows characterising a software application computing on TI-DSPs. The proposed approach exploits parametric models representing the consumption's behaviour of both DSP's architecture and algorithm. This consists in releasing the laws of consumption on a high level. This approach makes it possible to deduce the power and the energy consumption of a code in an advanced language for a given target. Feasibility and the interest of the approach were proved using MPEG2. This new approach was based on a functional level power analysis. The advantage of this approach was that the consumption and performance estimation can be made at a high level. Moreover, the proposed approach gives a detailed function-level characterization of the energy behaviour of application, enabling estimation of software energy consumption. Key words: Low power, DSP, MPEG2, modelling, methodology, INTRODUCTION The design of embedded systems on chip is a complex process, involving different steps at different abstraction levels. Design steps can be grouped into two major tasks: architecture design [...]