December 2018
The Increasing Significance of Edge Analytics in Smart City Projects
With the increasing push towards smart city initiative, edge intelligence with machine learning capabilities is playing a significant role. Experts suggest that edge computing and machine learning together will change the game for home automation, traffic management, building security, infrastructure management, and city parking systems. Read More
DFT Challenges for Phase-Shifted Functional Clocks
The use of mixed-signal processing is becoming vital among a wide variety of applications like telecommunication, networking, sensor chips, etc. In many designs, phase-shifted clocks being used by RTL designers. Read this blog to know common challenges of phase-shifted clock designs and ways to fix them. Read More
Data Cleaning in Machine Learning: Best Practices and Methods
Machine learning is all about training and feeding data to algorithms to perform various compute intensive tasks. However, businesses typically face challenges in feeding the right data to machine learning algorithms or cleaning of irrelevant and error-prone data. In other words, when it comes to utilizing ML data, most of the time is spent on cleaning data sets or creating a dataset that is free of errors. Setting up a quality plan, filling missing values, removing rows, reducing data size are some of the best practices used for data cleaning in Machine Learning. Read More
Power Dissipation in VLSI: Moving to Low Power SoC Design While Improving Performance
In this day and age, we need sleeker devices with more capabilities and longer battery life. This can be accomplished by packing more components on smaller chips, thus moving to low geometry chip design. However, power dissipation or leakage current occurs in all the circuits that are currently used, which increases the overall power consumption, making it less suitable for mobile applications. This blog talks about the types of power dissipation and also mentions the ways to prevent this voltage loss. Read More
Whitepaper: Designing an Effective Traffic Management System Through Vehicle Classification and Counting Techniques
Traffic management plays an important role in city planning and regulating the density of vehicles on the road. For effective traffic management, vehicle classification and vehicle counting are the key modules that serve as a base for almost all the use cases built for traffic analysis. Classification and counting of vehicles, both moving and stationary, are done by applying image processing (video content analysis) algorithms on video streams taken from a stationary camera. Read More
Is Qualcomm® Snapdragon™ 624 on the Radar for Your Medical Device Design?
The healthcare industry is constantly evolving; from its operational policies to patient care activities, and everything in-between. These recent technological developments in the healthcare industry are giving rise to the concept of telemedicine and telehealth. Telehealth and telemedicine encompass a broad variety of embedded technologies and applications to perform diagnostics, healthcare monitoring and delivery of virtual medicine and healthcare services from a distance. For example, an embedded telehealth device monitors patient’s heartbeats by seeing color changes in the fingertips or monitoring skin abnormalities. Read More
Fault Detection Using a Bank of Kalman Filters and a Fast Fourier Transform
A gas turbine engine (GTE) is one of the most complex machines ever created, not only due to its constructive intricacies, but also for the dynamic behavior and sophisticated engineering required for its operation. Due to its high fuel efficiency, power ratings, and reliability, the GTE is used in various dynamic systems, including airplanes, helicopters, marine ships, and military tanks (the M1 Abrams, for instance). This article presents an aircraft jet engine sensor fault diagnostics and prediction implementation using a bank of Kalman filters and a Fast Fourier Transform. Read More