Corynebacteriumspp. are rarely considered pathogens, but data onCorynebacteriumspp. as a cause of orthopedic infections are sparse. Therefore, we asked how oftenCorynebacteriumspp. caused an infection in a defined cohort of orthopedic patients with a positive culture. In addition, we aimed to determine the species variety and the susceptibility of isolated strains to define potential treatment strategies. We retrospectively assessed all bone and joint samples that were collected between 2006 and 2015 from an orthopedic ward and that were positive forCorynebacteriumspp. by culture. The isolates were considered relevant to an infection if the sameCorynebacteriumsp. was present in at least two samples. We found 97 orthopedic cases with isolation ofCorynebacteriumspp. (128 positive samples). These were mainlyCorynebacterium tuberculostearicum(n= 26),Corynebacterium amycolatum(n= 17),Corynebacterium striatum(n= 13), andCorynebacterium afermentans(n= 11). Compared to the species found in a cohort of patients with positive blood cultures hospitalized in nonorthopedic wards, we found significantly moreC. striatum- andC. tuberculostearicum-positive cases but noC. jeikeium-positive cases in our orthopedic cohort. Only 16 out of 66 cases (24.2%) with an available diagnostic set of at least two samples had an infection. Antibiotic susceptibility testing (AST) showed various susceptibility results for all antibiotics except vancomycin and linezolid, to which 100% of the isolates were susceptible. The rates of susceptibility of corynebacteria isolated from orthopedic samples and of isolates from blood cultures were comparable. In conclusion, our study results confirmed that aCorynebacteriumsp. is most often isolated as a contaminant in a cohort of orthopedic patients. AST is necessary to define the optimal treatment in orthopedic infections.

The trend in Internet of Things research points toward performing increasingly compute-intensive data analysis tasks on embedded sensor nodes, rather than server centers. Exploiting the technological advances in both energy efficiency, and Tiny Machine Learning algorithms and methods, an increasing number of recognition and classification tasks can be performed by small, low-power, wireless sensor nodes. This paper presents WideVision, a wireless, wide-area sensing platform capable of performing on-board person detection with power requirements in the mW range. The WideVision platform integrates seamlessly into the Internet of Things, by coupling a dedicated multiradio platform, including a LoRa interface, enabling mediumand long-range communication, with a novel parallel RISC-V microcontroller. We evaluate the proposed platform with the GAP8 microcontroller, which includes an 8-core RISC-V cluster, and greyscale camera to perform person detection by training and deploying an advanced, quantized neural network, achieving a statistical accuracy 84.5% for a 5-person detection task with a latency of only 182 ms. Experimental results demonstrate that the WideVision sensor node platform while performing inference at a rate of one image per minute on-board, is capable of lasting 300 days on a 2400 mAh Li-ion battery, and 65 days when evaluating one image per 10 seconds while providing effective surveillance of its perimeter.