Abstract: Based on traffic images characteristics, a general pre-processing system and method reduces input size of neural network object recognition models to focus on necessary regions. The system includes a light neural network (binary or low precision; based on configuration) to detect target regions for further processing and applies a deeper model to those specific regions. The present disclosure provides experimentation results on various types of methods, such as conventional convolutional neural networks, transformers, and adaptive models, to show the scalability of the system.

Abstract: Temporal knowledge distillation for active perception is provided. Despite significant performance improvements in object detection and classification using deep structures, they still require prohibitive runtime to process images and maintain the highest possible performance for real-time applications. Observing that a human visual system (HVS) relies heavily on temporal dependencies among frames from visual input to conduct recognition efficiently, embodiments described herein propose a novel framework dubbed as temporal knowledge distillation (TKD). The TKD framework distills temporal knowledge gained from a heavy neural network-based model over selected video frames (e.g., the perception of the moments) for a light-weight model. To enable the distillation, two novel procedures are described: 1) a long-short term memory (LSTM)-based key frame selection method; and 2) a novel teacher-bounded loss design.

Abstract: Adaptive and hierarchical convolutional neural networks (AH-CNNs) using partial reconfiguration on a field-programmable gate array (FPGA) are provided. An AH-CNN is implemented to adaptively switch between shallow and deep networks to reach a higher throughput on resource-constrained devices, such as a multiprocessor system on a chip (MPSoC) with a central processing unit (CPU) and FPGA. To this end, the AH-CNN includes a novel CNN architecture having three parts: 1) a shallow part which is a light-weight CNN model, 2) a decision layer which evaluates the shallow part's performance and makes a decision whether deeper processing would be beneficial, and 3) one or more deep parts which are deep CNNs with a high inference accuracy.

Abstract: A perimodiolar electrode for cochlear implantation includes an electrode carrier having a front end and a back end. The electrode carrier includes one or more contacts and a hydrophilic segment that swells after insertion in a cochlea and detaches at least in part from the carrier. In accordance with related embodiments, the hydrophilic segment may detach from the electrode carrier between the front end and the back end. The detached hydrophilic segment may surround the modiolus of a scala tympani of the cochlea or the inner wall of a scala tympani of the cochlea.

Abstract: The present invention refers to a method for preparing a herbal extract from Mellilotus sp. (Mellilotus officinalis), preferably comprising a treatment by pulsed electromagnetic field of high frequency. The herbal extract, optionally comprising selenium and/or urea and/or fructose and/or phosphoglycerol (or its sodium salt), is useful in the treatment of chronic wounds, in particular associated with states in which the normal wound repair ability is weakened, and preferably diabetic foot ulcers and/or bed sores.

Abstract: The present invention refers to a method for preparing a herbal extract from Rosa sp., Urtica dioica and/or Tanacetum vulgare, preferably comprising a treatment by pulsed electromagnetic field of high frequency. The herbal extract, optionally comprising selenium and/or urea, is useful in the treatment of conditions associated with impaired immune system, e.g. in HIV infection and AIDS.

Abstract: A perimodiolar electrode for cochlear implantation includes an electrode carrier having a front end and a back end. The electrode carrier includes one or more contacts and a hydrophilic segment that swells after insertion in a cochlea and detaches at least in part from the carrier. In accordance with related embodiments, the hydrophilic segment may detach from the electrode carrier between the front end and the back end. The detached hydrophilic segment may surround the modiolus of a scala tympani of the cochlea or the inner wall of a scala tympani of the cochlea.

Abstract: A perimodiolar electrode for cochlear implantation includes an electrode carrier having a front end and a back end. The electrode carrier includes one or more contacts and a hydrophilic segment that swells after insertion in a cochlea and detaches at least in part from the carrier. In accordance with related embodiments, the hydrophilic segment may detach from the electrode carrier between the front end and the back end. The detached hydrophilic segment may surround the modiolus of a scala tympani of the cochlea or the inner wall of a scala tympani of the cochlea.