Natural disasters such as severe flooding can cause catastrophic losses to properties and human lives. Constant real-time water level monitoring prior a event minimise damages casualties. Many of the currently deployed systems typically use combination float-type or ultrasonic sensing, image processing computer vision techniques. However, these incur high computing hardware requirements, which hinder deployment in resource-constrained low-cost environments. The recent development...

Creating a navigation system for autonomous companion robots has always been difficult process, which must contend with dynamically changing environment, is populated by myriad of obstructions and an unspecific number people, other than the intended person, to follow. This study documents implementation indoor robot model, based on multi-sensor fusion, using Microsoft Robotics Developer Studio 4 (MRDS). The model relies depth camera, limited array proximity sensors active IR marker tracking...

The study proposed a dynamic path planning (DPP) method that combines instance image segmentation and elementary matrix calculations to enable robot identify the angular position of entities in its surroundings. DPP fuses visual depth information for scene understanding estimation with reduced computation resources. This designed, developed, evaluated deep-learning based companion prototype indoor navigation obstacle avoidance using an RGB-D camera as sole input sensor. A simulated...

The omnidirectional self-balancing robot or otherwise known as ballbot belongs to a special class of balancing robots. With only one contact point with the ground, is able achieve higher degree agility lower footprint than most mobile While practical applications platforms such Segway PT have gained much traction over last decade, directional limitations in movements are still prevalent wheeled To motion, ball used replacement wheels. Similar concept inverted pendulum, achieved using...

The world is moving towards online learning as part of an effort to safeguard the health communities due inevitable COVID-19 pandemic. Transitioning from traditional presents challenges that have be addressed by academics in order maintain experience and ensure objectives are equally achieved. In engineering education, practical one core activities greatly affected implementation learning. Students unable access physical laboratory closure university requirements social distancing. This...

Human tracking research has been reinforced with the introduction of vision-based motion sensors such as Microsoft Kinect and Intel RealSense since 2009. No longer limited to just wearable sensors, embedded environments 2D camera feed, stereoscopic digital cameras Infrared imaging enabled perceivable depth distance contribute geo-location, activity tracking, automated detection abnormal events. However, current systems have a zone subjected environmental lighting, lens occlusion hardware...

In the ever-evolving landscape of insurance services, strategic cross-selling health to existing customers stands as a pivotal endeavor. This study delves into this domain, aiming harness potential machine learning and deep methodologies identify prospects for adoption within customer base, irrespective their current holdings. To achieve goal, conducts various experiments employing different algorithms, such TabPFN, Graph Convolutional Network (GCN), LightGBM, Hist Gradient Boosting XGBoost....

One of the main challenges faced in developing autonomous navigation for indoor robots is designing strategy to account a combination obstacle avoidance while fulfilling additional maneuvering requirements. An existing child-following companion robot prototype called CARMI used as case study this paper. CARMI's function autonomously follow child, maintaining her within optimal detection zone its vision-based activity tracking system, all navigating through furniture and obstructions. This...

The paper presents a simplified mathematical model of the bipedal walking robot with four degrees freedom. It novel sensing and balancing method for minimum possible walk proposed involves design semi-rigid ankle to facilitate fast accurate measurements sideway (sagittal) instability robot. use new hip-mass carrying strategy in forward direction system two counter masses body allows decouple algorithms from stability restoring solutions. different helps improve response time efficiency...

This paper presents joint space trajectory planning strategy for the legs of 4-DOF parallelogram bipedal robot. The use two sets pulley-based mechanisms in each leg allows to reduce number actuators by one and keep legs' feet parallel horizontal walking surface. By reducing some design overall weight, energy consumption complexity robot controller can be reduced. walk patterns presented body mass carried hip (main structure) always vertically aligned with center foot area during single-leg...

This paper presents the development of an Unmanned Aerial Vehicle (UAV) based system that is designed to perform vehicle recognition for parking enforcement purpose. The proposed intended be used monitor and enforce fee payment in a multi-entrance multi-exit open lot. useful when condition not suitable implement single-entry single-exit barrier gate at developed on UAV equipped with camera deployed from ground station patrols lot through fixed flight path pre-defined waypoints mission...

A majority of insurers are in the opinion that Artificial Intelligence (AI) has potential to create a better customer experience, improve direction-making and achieve cost savings. One area interest for AI insurance is recommendation on-demand policies. This automated can expedite process as it does not involve any agents. research involves utilization dataset, comprising 9422 records 86 features related social-demographics purchases. The data transformed into graph-based representation...

This paper presents the conceptual design of a new four degree-of-freedom minimalist bipedal walking robot and specifically discusses on physical development robot's sagittal balancing mechanism its control in single support phase. The proposed combines novel method for stability sensing during strides. utilizes an additional flexible ankle joint which is able to provide responsive accurate measurement instability robot. use double mass developed algorithm are responsible maintain sideway...