Raunsolomon4307

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machine learning and pattern recognition. selleck kinase inhibitor One of the most important challenge of deep learning is to figure out relations between a feature and the depth of deep neural networks (deep nets for short) to reflect the necessity of depth. Our purpose is to quantify this feature-depth correspondence in feature extraction and generalization. We present the adaptivity of features to depths and vice-verse via showing a depth-parameter trade-off in extracting both single feature and composite features. Based on these results, we prove that implementing the classical empirical risk minimization on deep nets can achieve the optimal generalization performance for numerous learning tasks. Our theoretical results are verified by a series of numerical experiments including toy simulations and a real application of earthquake seismic intensity prediction.Recently, drug abuse has become a worldwide concern. Among varieties of drugs, KET is found to be favorite in drug addicts, especially teenagers, for recreational purposes. KET is a kind of analgesic and anesthetic drug which can induce hallucinogenic and dissociative effects after high-dose abuse. Hence, it is critical to develop a rapid and sensitive detection method for strict drug control. In this study, we proposed a cloud-enabled smartphone based fluorescence sensor for quantitative detection of KET from human hair sample. The lateral flow immunoassay (LFIA) was used as the detecting strategy where UCNPs were introduced as fluorescent labels. The sensor was capable of identifying the up-converted fluorescence and calculating the signal intensities on TL and CL to obtain a T/C value, which was corresponding to the KET concentration. The sensor transmitted the test data to the cloud-enabled smartphone through Type-C interface, and the data were further uploaded to the edge of the network for cloud-edge computing and storage. The entire detection took only 5 minutes with high stability and reliability. The detection limit of KET was 1 ng/mL and a quantitative detection range from 1 to 150 ng/mL. Furthermore, based on the huge development of Internet of Things (IoT), an App was developed on the smartphone for anti-drug situational awareness. Based on this system, it was convenient for Police Department to perform on-site KET detection. Moreover, it was critical for prediction of the development trend of future events, benefiting much to constructing a harmonious society.We developed a forward-looking (FL) multimodal endoscopic system that offers color, spectral classified, high-frequency ultrasound (HFUS) B-mode, and integrated backscattering coefficient (IBC) images for tumor detection in situ. Examination of tumor distributions from the surface of the colon to deeper inside is essential for determining a treatment plan of cancer. For example, the submucosal invasion depth of tumors in addition to the tumor distributions on the colon surface is used as an indicator of whether the endoscopic dissection would be operated. Thus, we devised the FL multimodal endoscopic system to offer information on the tumor distribution from the surface to deep tissue with high accuracy. This system was evaluated with bilayer gelatin phantoms which have different properties at each layer of the phantom in a lateral direction. After evaluating the system with phantoms, it was employed to characterize forty human colon tissues excised from cancer patients. The proposed system could allow us to obtain highly resolved chemical, anatomical, and macro-molecular information on excised colon tissues including tumors, thus enhancing the detection of tumor distributions from the surface to deep tissue. These results suggest that the FL multimodal endoscopic system could be an innovative screening instrument for quantitative tumor characterization.

High-density surface electromyography (HD-sEMG) has been utilized extensively in neuromuscular research. Despite its potential advantages, limitations in electrode design have largely prevented widespread acceptance of the technology. Commercial electrodes have limited spatial fidelity, because of a lack of sharpness of the signal, and variable signal stability. We demonstrate here a novel tattoo electrode that addresses these issues. Our dry HD electrode grid exhibits remarkable deformability which ensures superior conformity with the skin surface, while faithfully recording signals during different levels of muscle contraction.

We fabricated a 4 cm×3 cm tattoo HD electrode grid on a stretchable electronics membrane for sEMG applications. The grid was placed on the skin overlying the biceps brachii of healthy subjects, and was used to record signals for several hours while tracking different isometric contractions.

The sEMG signals were recorded successfully from all 64 electrodes across the grid. These electrodes were able to faithfully record sEMG signals during repeated contractions while maintaining a stable baseline at rest. During voluntary contractions, broad EMG frequency content was preserved, with accurate reproduction of the EMG spectrum across the full signal bandwidth.

The tattoo grid electrode can potentially be used for recording high-density sEMG from skin overlying major limb muscles. Layout programmability, good signal quality, excellent baseline stability, and easy wearability make this electrode a potentially valuable component of future HD electrode grid applications.

The tattoo electrode can facilitate high fidelity recording in clinical applications such as tracking the evolution and time-course of challenging neuromuscular degenerative disorders.

The tattoo electrode can facilitate high fidelity recording in clinical applications such as tracking the evolution and time-course of challenging neuromuscular degenerative disorders.Seated postural abilities are critical to functional independence and participation in children with cerebral palsy, Gross Motor Functional Classification System (GMFCS) levels III-IV. In this proof-of-concept study, we investigated the feasibility of a motor learning-based seated postural training with a robotic Trunk-Support-Trainer (TruST) in a longitudinal single-subject-design (13y, GMFCS IV), and its potential effectiveness in a group of 3 children (6-14y, GMFCS III-IV). TruST is a motorized-cable driven belt placed on the child's trunk to exert active-assistive forces when the trunk moves beyond stability limits. TruST-intervention addresses postural-task progression by tailoring the assistive-force fields to the child's sitting balance to train trunk control during independent short-sitting posture. TruST-intervention consisted of 2 training blocks of six 2hour-sessions per block (3 sessions per week). Pelvic strapping was required in the 1st block to prevent falls. As primary outcomes, we used the modified functional reach test, gross motor function measure-item set (GMFM-IS), Box & Blocks, and postural kinematics. After TruST-intervention children did not require pelvic strapping to prevent a fall, improved trunk stability during reaching (baseline = 5.49cm, 1week post-training = 16.38cm, 3mos follow-up = 14.63cm, ) and increased their sitting workspace (baseline = 127.55cm2, 1week post-training, = 409.92cm2, 3mos follow-up = 270.03cm2, ). Three children also improved in the GMFM-IS. In summary, our novel robotic TruST-intervention is feasible and can effectively maximize functional independent sitting in children with CP GMFCS III-IV.Pseudomonas genus is among the top nosocomial pathogens known to date. Being highly opportunistic, members of pseudomonas genus are most commonly connected with nosocomial infections of urinary tract and ventilator-associated pneumonia. Nevertheless, vaccine development for this pathogenic genus is slow because of no information regarding immunity correlated functional mechanism. In this present work, an immunoinformatics pipeline is used for vaccine development based on epitope-based peptide design, which can result in crucial immune response against outer membrane proteins of pseudomonas genus. A total of 127 outer membrane proteins were analysed, studied and out of them three sequences were obtained to be the producer of non-allergic, highly antigenic T-cell and B-cell epitopes which show good binding affinity towards class II HLA molecules. After performing rigorous screening utilizing docking, simulation, modelling techniques, we had one nonameric peptide (WLLATGIFL) as a good vaccine candidate. The predicted epitopes needs to be further validated for its apt use as vaccine. This work paves a new way with extensive therapeutic application against Pseudomonas genus and their associated diseases.Acoustic droplet vaporization (ADV) provides the on-demand production of bubbles for use in ultrasound (US)-based diagnostic and therapeutic applications. The droplet-to-bubble transition process has been shown to involve localized internal gas nucleation, followed by a volume expansion of threefold to fivefold and inertial bubble oscillation, all of which take place within a few microseconds. Monitoring these ADV processes is important in gauging the mechanical effects of phase-change droplets in a biological environment, but this is difficult to achieve using regular optical observations. In this study, we utilized acoustic characterization [i.e., simultaneous passive cavitation detection (PCD) and active cavitation detection (ACD)] to investigate the acoustic signatures emitted from phase-change droplets ADV and determined their correlations with the physical behaviors observed using high-speed optical imaging. The experimental results showed that activation with three-cycle 5-MHz US pulse resulted in the acoustic signals.In the last few decades, the medical and healthcare scientific communities have focused their attention on the use or development of real-time monitoring devices and remote control systems. New generations of wearable, portable, and implantable devices offer better and more accurate measurements/prognosis for those that suffer from diseases and/or disabilities. Thus, there are still challenging issues of current ultrasound imaging (USI) systems, such as low-quality ultrasound images, slow time response to emergencies, and location-based operation. Thus, in response to these challenges, we present a new low-cost, portable/wearable 3-D array ultrasound prognosis system with advanced imaging capabilities that offer high-resolution (HR) accurate results in a near real-time response. The USI unique features are based on 2-D array transducers with 3-D overlapping capabilities and a new image enhancement methodology compatible with the system's structural characteristics to compensate for any loss of image quality. This system will offer an alternative way of ultrasound examination, independent of the radiologist's skills, that is, a system to be capable of automatic scanning of the volume of interest (VOI) without the guidance of the radiologist.