Smart sensors are an emerging technology that allows combining the data acquisition with the elaboration directly on the Edge device, very close to the sensors. To push this concept to the extreme, technology companies are proposing a new generation of sensors allowing to move the intelligence from the edge host device, typically a microcontroller, directly to the ultra-low-power sensor itself, in order to further reduce the miniaturization, cost and energy efficiency. This paper evaluates the capabilities of a novel and promising solution from STMicroelectronics. The presence of a floating point unit and an accelerator for binary neural networks provide capabilities for in-sensor feature extraction and machine learning. We propose a comparison of full-precision and binary neural networks for activity recognition with accelerometer data generated by the sensor itself. Experimental results have demonstrated that the sensor can achieve an inference performance of 10.7 cycles/MAC, comparable to a Cortex-M4-based microcontroller, with fullprecision networks, and up to 1.5 cycles/MAC with large binary models for low latency inference, with an average energy consumption of only 90 µJ/inference with the core running at 5 MHz.
Category: Ankle Introduction/Purpose: Insertional Achilles tendinopathy can be a distressing problem for an active patient. Treatment begins conservatively, and when this fails a patient’s next best option may involve operating on the affected tendon. Depending on the disease state of the tendon, the surgeon may decide to repair or augment the Achilles with a flexor hallucis longus (FHL) transfer. The current literature supports the gastrocnemius recession for non-insertional cases, but is inconsistent in its efficacy for insertional cases. Our study looks at how patients with insertional Achilles tendinopathy with a small tear involving 20% of the tendon or less responded to an isolated gastrocnemius recession. Our hypothesis was that patients could do well without the need for a large repair or FHL transfer procedure. Methods: We retrospectively reviewed patients who underwent an isolated gastrocnemius recession for recalcitrant insertional Achilles tendinopathy between January 2015 and July 2018. Patients were included based on the diagnosis of insertional Achilles tendinopathy, having an MRI confirming tendinopathy, a tear involving less than 20% of the tendon or no tear, and no other concurrent pathologies. These criteria yielded 14 patients. One of these 14 patients was removed from the data analysis due to non-surgical complaints after surgery stemming from new onset posterior ankle pain. The patient charts were reviewed for their subjective VAS pain scores during office visits pre and postoperatively. Immediate preoperative visit, initial postoperative visit and final visit VAS scores were recorded. Results: The average time of chart follow up for the 13 patients included in the study was 15.5±10.5 weeks postoperatively (range 4-38). 2 patients were found to have a tear <20% (15%), and the remaining 11 patients were found to have no tear on their MRI (85%). The average final preoperative VAS pain score for the patients was 5.4±1.8 (range 3-9). The average final postoperative VAS pain score for the patients was 0.9±1.3 (range 0-5). These values were found to be statistically different (p<0.001). Of note all patients saw a reduction in their pain score of at least 2 points. Conclusion: Previous literature is inconclusive on the efficacy of the gastrocnemius recession for insertional Achilles tendinopathy. No other study has identified the amount or type of tendon involvement by advanced imaging. Our study supports the notion that patients with MRI confirmed tendinopathy and a tear involving less than 20% of the tendon or no tear, often do quite well in reaching a reduction in their pain. Our study is limited in power due to our small sample size, but the results suggest that this procedure deserves more attention for the treatment of insertional Achilles tendinopathy when appropriate.
Introduction/Purpose: Plantar fasciitis is a debilitating problem that can cause long-term pain. Multiple different studies with various modalities have been suggested to treat the inflammation of the plantar fascia. None of them have provided a cause for the inflammation. A few recent studies have shown gastrocnemius equinus to be a driving factor in foot pain, which includes plantar fasciitis. Our belief is that the inflammation is due to a stretch placed on the plantar fascia due to a gastrocnemius equinus contracture and the beginning of an arch collapse per the Grand Rapids arch collapse model. As such, we wanted to review our results with an isolated gastrocnemius recession for the treatment of plantar fasciitis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.