Using Cultural Algorithms to Improve Wearable Device Gesture Recognition Performance

Waris, Faisal; Reynolds, Robert G.

doi:10.1109/ssci.2015.97

Cited by 8 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has greatly reduced the number of doctors and nurses. The workload of the staff and nurses cannot regularly inspect the patient's physical parameters, only on the terminal equipment regularly [10].…”

Section: Development Background Of Wireless Communicationmentioning

confidence: 99%

Wearable-Based Virtual Display Information Processing and Data Fusion Research

Lv¹,

Liu

2022

Mobile Information Systems

View full text Add to dashboard Cite

This paper is combined with the existing acquisition module design to achieve the upper computer online information monitoring system. Real-time mapping technology is adopted to change the trend of data collection potential for real-time tracking and monitoring. The monitoring data can be predicted and analyzed by changing trend, at the same time combined with SQL2008 database technology, user login system, registration system, monitoring system, data query, and data storage system. The integration and other functions are improved, so that the system not only has the advantages of information management platform but also realizes the remote client base matching layer wireless information real-time monitoring function. Data fusion technology refers to the information processing technology that uses computer to automatically analyze and synthesize some observation information obtained in time and sequence under certain criteria, so as to complete the required decision-making and evaluation tasks. The intelligent wearable online information monitoring system designed in this paper realizes wireless sensor network, to some extent feedback and monitoring of underlying real information. Through the corresponding information processing and data fusion, the user can easily and clearly get product information. Based on the existing 80 sets of data, the experiment trains and extracts 320 feature vectors, which verify the effectiveness of the method.

show abstract

Section: Development Background Of Wireless Communicationmentioning

confidence: 99%

Wearable-Based Virtual Display Information Processing and Data Fusion Research

Lv¹,

Liu

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Automotive industry is changing the way in which the user interacts with the car: from push and rotational buttons to smart devices. In [145], authors develop a gesture recognition application based on data coming from smartwatch sensors (gyroscope and accelerometer). The recognized gestures include twisting, swiping, tapping and others.…”

Section: E Miscellaneousmentioning

confidence: 99%

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Borrego-Carazo

Castells-Rufas

Biempica³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The advent of machine learning (ML) methods for the industry has opened new possibilities in the automotive domain, especially for Advanced Driver Assistance Systems (ADAS). These methods mainly focus on specific problems ranging from traffic sign and light recognition to pedestrian detection. In most cases, the computational resources and power budget found in ADAS systems are constrained while most machine learning methods are computationally intensive. The usual solution consists in adapting the ML models to comply with the memory and real-time (RT) requirements for inference. Some models are easily adapted to resource-constrained hardware, such as Support Vector Machines, while others, like Neural Networks, need more complex processes to fit into the desired hardware. The ADAS hardware (HW platforms) are diverse, from complex MPSoC CPUs down to classical MCUs, DPSs and application-specific FPGAs and ASICs or specific GPU platforms (such as the NVIDIA families Tegra or Jetson). Therefore, there is a tradeoff between the complexity of the ML model implemented and the selected platform that impacts the performance metrics: function results, energy consumption and speed (latency and throughput). In this paper, a survey in the form of systematic review is conducted to analyze the scope of the published research works that embed ML models into resource-constrained implementations for ADAS applications and what are the achievements regarding the ML performance, energy and speed trade-off. INDEX TERMS Machine learning, embedded software, automotive engineering, GPU, FPGA, ADAS. I. INTRODUCTION Safety is increasingly important for drivers and other users of the driving environment such as pedestrians, cyclists, bikers, scooters, etc. Only in 2016, road accidents in the European Union summed up to 25.600 fatalities and 1.4 million people injured [1]. Many measures are being taken by public institutions (improving road quality, enhancing driver consciousness and driving regulations, etc.) to improve these numbers. However, the cause of most of these accidents resides in human errors or distractions. For this reason, automotive firms are pushing up research on improving safety. The cornerstone of these advances are Advanced Driver Assistance Systems (ADAS). ADAS systems consist in several sensors, processing and actuators components that help drivers to avoid accidents and The associate editor coordinating the review of this manuscript and approving it for publication was Ye Duan.

show abstract

Optimizing AI Pipelines

Waris

Reynolds

2020

Cultural Algorithms

View full text Add to dashboard Cite

Using Cultural Algorithms to Improve Wearable Device Gesture Recognition Performance

Cited by 8 publications

References 0 publications

Wearable-Based Virtual Display Information Processing and Data Fusion Research

Wearable-Based Virtual Display Information Processing and Data Fusion Research

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Optimizing AI Pipelines

Contact Info

Product

Resources

About