A depth camera-based novel method is proposed here for efficient facial expression recognition. For each pixel in a image, eight local directional strengths are obtained and ranked. Once the rank of all pixels obtained, histograms developed surrounding directions. The then concatenated to represent features image face. This approach named histogram pattern (LDRHP). To combine with LDRHP features, one more robust feature extraction technique strength (LDSP) proposed. Typical (LDP) considers...

Studies foresee a dramatic increase in the elderly population of Western Europe over next decades, putting pressure on healthcare systems. Healthcare robots are developed to facilitate independent living for people. This paper aims provide qualitative analysis recent projects robotics (2008-2024) and proposes new research directions older adults. We an overview current roadmap upcoming research. Our study began with literature search using four databases. Searches were performed articles...

Abstract Path planning in unknown environments is one of the most challenging research areas robotics. In this class path planning, robot acquires information from its sensory system. Sampling-based famous approaches with low memory and computational requirements that has been studied by many researchers during past few decades. We propose a sampling-based algorithm for using Tabu search. The search component our method guides sampling to find samples promising makes procedure more...

Gait recognition plays a very vital role in many practical applications of computer and robot vision smart environments such as health care for elderly using home technology. Hence, it has been attracting considerable attentions from machine researchers last decades. In this paper, we propose novel method depth video-based gait robust features deep learning. Local Directional Pattern (LDP) are first extracted silhouettes. Then, LDP augmented with optical flow motion to generate...

In this paper, we propose a new learning strategy for probabilistic roadmap (PRM) algorithm. The proposed is based on reducing the dispersion of generated set samples. We defined forbidden range around each selected sample and ignored region in further sampling. resultant planner, called low dispersion-PRM, an effective multi-query sampling-based planner that able to solve motion planning queries with smaller graphs. Simulation results indicated improved performance original PRM other...

Path planning with obstacles avoidance in dynamic environments is a crucial issue robotics. Numerous approaches have been suggested for the navigation of mobile robots moving obstacles. In this paper, about 50 articles reviewed and briefly described to offer an outline research progress motion robot last five years. The benefits drawbacks each article are also explained. These papers classified based on their issues into ten groups which are: stability, efficiency, smooth path, run time,...

In this work, we propose a novel human activity recognition method from depth videos using robust spatiotemporal features with convolutional neural network. From the images of activities, body parts are segmented based on random forest. in image an video, spatial extracted such as angles 3-D joint pairs, means and variances information each part body. The then augmented motion magnitude direction joints next video. Finally, applied to network for training recognition. deep learning-based...

Given the importance of an accurate wind speed forecasting for efficient utilization farms, and volatile nature data including its non-linear uncertain nature, has remained active field research. In this study, non-linearity is tackled using artificial neural network uncertainty by wavelet transform. To avoid trial-and-error process selection ANN structure, results auto correlation factor (ACF) partial (PACF) on historical are employed. Instead time series directly, a set better-behaved...

In the field of robotics, caregiving robots and personal assistants are assuming an increasingly prominent role, directly impacting human lives. Especially in healthcare domains, these systems starting to provide continuous 24/7 care by monitoring patients delivering real-time insights into their activities. The effective deployment future relies on equipping them with sophisticated Human Activity Recognition (HAR) algorithms. Many HAR algorithms based Artificial Intelligence (AI) Machine...

Ultrasonic Sensors have long been used for pipeline inspection. The combination of and eddy current sensors provide great resolution accuracy crack corrosion detection. In this study the authors integrated multiple with relative software filtering techniques to develop a low cost, maintenance system Furthermore, second objective is resolve Multi-Diameter capability PIG robots. According literature reviews, many oil gas pipelines are considered be unpiggable due their variation in diameter...

Introducing robots in healthcare facilities and homes may reduce the workload of personnel while providing users with better more available services. It also contribute to interactions that are engaging safe against transmitting contagious diseases for senior adults. A major challenge this regard is design adapt robot's behavior based on requirements preferences different users. In paper, we report a conducted use study how people perceive kinds robot encounters. We had two groups target...