Inductively coupled magic angle spinning microresonators benchmarked for high-resolution single embryo metabolomic profiling.

The magic angle coil spinning (MACS) technique has been introduced as a very promising extension for solid state NMR detection, demonstrating sensitivity enhancements by a factor of 14 from the very first time it has been reported. The main beneficiary of this technique is the scientific community dealing with mass- and volume-limited, rare, or expensive samples. However, more than a decade after the first report on MACS, there is a very limited number of groups who have continued to develop the technique, let alone it being widely adopted by practitioners. This might be due to several drawbacks associated with the MACS technology until now, including spectral linewidth, heating due to eddy currents, and imprecise manufacturing. Here, we report a device overcoming all these remaining issues, therefore achieving: (1) spectral resolution of approx 0.01 ppm and normalized limit of detection of approx. 13 nmol s0.5 calculated using the anomeric proton of sucrose at 3 kHz MAS frequency; (2) limited temperature increase inside the MACS insert of only 5 °C at 5 kHz MAS frequency in an 11.74 T magnetic field, rendering MACS suitable to study live biological samples. The wafer-scale fabrication process yields MACS inserts with reproducible properties, readily available to be used on a large scale in bio-chemistry labs. To illustrate the potential of these devices for metabolomic studies, we further report on: (3) ultra-fine 1H-1H and 13C-13C J-couplings resolved within 10 min for a 340 mM uniformly 13C-labeled glucose sample; and (4) single zebrafish embryo measurements through 1H-1H COSY within 4.5 h, opening the gate for the single embryo NMR studies.

Precise Modeling of the Protective Effects of Quercetin against Mycotoxin via System Identification with Neural Networks.

Cell cytotoxicity assays, such as cell viability and lactate dehydrogenase (LDH) activity assays, play an important role in toxicological studies of pharmaceutical compounds. However, precise modeling for cytotoxicity studies is essential for successful drug discovery. The aim of our study was to develop a computational modeling that is capable of performing precise prediction, processing, and data representation of cell cytotoxicity. For this, we investigated protective effect of quercetin against various mycotoxins (MTXs), including citrinin (CTN), patulin (PAT), and zearalenol (ZEAR) in four different human cancer cell lines (HeLa, PC-3, Hep G2, and SK-N-MC) in vitro. In addition, the protective effect of quercetin (QCT) against various MTXs was verified via modeling of their nonlinear protective functions using artificial neural networks. The protective model of QCT is built precisely via learning of sparsely measured experimental data by the artificial neural networks (ANNs). The neuromodel revealed that QCT pretreatment at doses of 7.5 to 20 µg/mL significantly attenuated MTX-induced alteration of the cell viability and the LDH activity on HeLa, PC-3, Hep G2, and SK-N-MC cell lines. It has shown that the neuromodel can be used to predict the protective effect of QCT against MTX-induced cytotoxicity for the measurement of percentage (%) of inhibition, cell viability, and LDH activity of MTXs.

Accurate Natural Trail Detection Using a Combination of a Deep Neural Network and Dynamic Programming.

This paper presents a vision sensor-based solution to the challenging problem of detecting and following trails in highly unstructured natural environments like forests, rural areas and mountains, using a combination of a deep neural network and dynamic programming. The deep neural network (DNN) concept has recently emerged as a very effective tool for processing vision sensor signals. A patch-based DNN is trained with supervised data to classify fixed-size image patches into "trail" and "non-trail" categories, and reshaped to a fully convolutional architecture to produce trail segmentation map for arbitrary-sized input images. As trail and non-trail patches do not exhibit clearly defined shapes or forms, the patch-based classifier is prone to misclassification, and produces sub-optimal trail segmentation maps. Dynamic programming is introduced to find an optimal trail on the sub-optimal DNN output map. Experimental results showing accurate trail detection for real-world trail datasets captured with a head mounted vision system are presented.

A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms.

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems.

Boosting-based on-road obstacle sensing using discriminative weak classifiers.

This paper proposes an extension of the weak classifiers derived from the Haar-like features for their use in the Viola-Jones object detection system. These weak classifiers differ from the traditional single threshold ones, in that no specific threshold is needed and these classifiers give a more general solution to the non-trivial task of finding thresholds for the Haar-like features. The proposed quadratic discriminant analysis based extension prominently improves the ability of the weak classifiers to discriminate objects and non-objects. The proposed weak classifiers were evaluated by boosting a single stage classifier to detect rear of car. The experiments demonstrate that the object detector based on the proposed weak classifiers yields higher classification performance with less number of weak classifiers than the detector built with traditional single threshold weak classifiers.

Guided Soft Attention Network for Classification of Breast Cancer Histopathology Images.

An attention guided convolutional neural network (CNN) for the classification of breast cancer histopathology images is proposed. Neural networks are generally applied as black box models and often the network's decisions are difficult to interpret. Making the decision process transparent, and hence reliable is important for a computer-assisted diagnosis (CAD) system. Moreover, it is crucial that the network's decision be based on histopathological features that are in agreement with a human expert. To this end, we propose to use additional region-level supervision for the classification of breast cancer histopathology images using CNN, where the regions of interest (RoI) are localized and used to guide the attention of the classification network simultaneously. The proposed supervised attention mechanism specifically activates neurons in diagnostically relevant regions while suppressing activations in irrelevant and noisy areas. The class activation maps generated by the proposed method correlate well with the expectations of an expert pathologist. Moreover, the proposed method surpasses the state-of-the-art on the BACH microscopy test dataset (part A) with a significant margin.

Learning Semantic Graphics Using Convolutional Encoder-Decoder Network for Autonomous Weeding in Paddy.

Weeds in agricultural farms are aggressive growers which compete for nutrition and other resources with the crop and reduce production. The increasing use of chemicals to control them has inadvertent consequences to the human health and the environment. In this work, a novel neural network training method combining semantic graphics for data annotation and an advanced encoder-decoder network for (a) automatic crop line detection and (b) weed (wild millet) detection in paddy fields is proposed. The detected crop lines act as a guiding line for an autonomous weeding robot for inter-row weeding, whereas the detection of weeds enables autonomous intra-row weeding. The proposed data annotation method, semantic graphics, is intuitive, and the desired targets can be annotated easily with minimal labor. Also, the proposed "extended skip network" is an improved deep convolutional encoder-decoder neural network for efficient learning of semantic graphics. Quantitative evaluations of the proposed method demonstrated an increment of 6.29% and 6.14% in mean intersection over union (mIoU), over the baseline network on the task of paddy line detection and wild millet detection, respectively. The proposed method also leads to a 3.56% increment in mIoU and a significantly higher recall compared to a popular bounding box-based object detection approach on the task of wild-millet detection.

Memristive Imitation of Synaptic Transmission and Plasticity.

In this paper, a memristive artificial neural circuit imitating the excitatory chemical synaptic transmission of biological synapse is designed. The proposed memristor-based neural circuit exhibits synaptic plasticity, one of the important neurochemical foundations for learning and memory, which is demonstrated via the efficient imitation of short-term facilitation and long-term potentiation. Moreover, the memristive artificial circuit also mimics the distinct biological attributes of strong stimulation and deficient synthesis of neurotransmitters. The proposed artificial neural model is designed in SPICE, and the biological functionalities are demonstrated via various simulations. The simulation results obtained with the proposed artificial synapse are similar to the biological features of chemical synaptic transmission and synaptic plasticity.

Osteoporosis detection in panoramic radiographs using a deep convolutional neural network-based computer-assisted diagnosis system: a preliminary study.

OBJECTIVES: To evaluate the diagnostic performance of a deep convolutional neural network (DCNN)-based computer-assisted diagnosis (CAD) system in the detection of osteoporosis on panoramic radiographs, through a comparison with diagnoses made by oral and maxillofacial radiologists. METHODS: Oral and maxillofacial radiologists with >10 years of experience reviewed the panoramic radiographs of 1268 females {mean [± standard deviation (SD)] age: 52.5 ± 22.3 years} and made a diagnosis of osteoporosis when cortical erosion of the mandibular inferior cortex was observed. Among the females, 635 had no osteoporosis [mean (± SD) age: 32.8 ± SD 12.1 years] and 633 had osteoporosis (72.2 ± 8.5 years). All panoramic radiographs were analysed using three CAD systems, single-column DCNN (SC-DCNN), single-column with data augmentation DCNN (SC-DCNN Augment) and multicolumn DCNN (MC-DCNN). Among the radiographs, 200 panoramic radiographs [mean (± SD) patient age: 63.9 ± 10.7 years] were used for testing the performance of the DCNN in detecting osteoporosis in this study. The diagnostic performance of the DCNN-based CAD system was assessed by receiver operating characteristic (ROC) analysis. RESULTS: The area under the curve (AUC) values obtained using SC-DCNN, SC-DCNN (Augment) and MC-DCNN were 0.9763, 0.9991 and 0.9987, respectively. CONCLUSIONS: The DCNN-based CAD system showed high agreement with experienced oral and maxillofacial radiologists in detecting osteoporosis. A DCNN-based CAD system could provide information to dentists for the early detection of osteoporosis, and asymptomatic patients with osteoporosis can then be referred to the appropriate medical professionals.

A Non-Resonant Kinetic Energy Harvester for Bioimplantable Applications.

A linear non-resonant kinetic energy harvester for implantable devices is presented. The design contains a metal platform with permanent magnets, two stators with three-dimensional helical coils for increased power generation, ball bearings, and a polydimethylsiloxane (PDMS) package for biocompatibility. Mechanical excitation of this device within the body due to daily activities leads to a relative motion between the platform and stators, resulting in electromagnetic induction. Initial prototypes without packaging have been fabricated and characterized on a linear shaker. Dynamic tests showed that the friction force acting on the platform is on the order of 0.6 mN. The resistance and the inductance of the coils were measured to be 2.2 Ω and 0.4 µH, respectively. A peak open circuit voltage of 1.05 mV was generated per stator at a platform speed of 5.8 cm/s. Further development of this device offers potential for recharging the batteries of implantable biomedical devices within the body.

Memristor bridge synapse-based neural network and its learning.

Analog hardware architecture of a memristor bridge synapse-based multilayer neural network and its learning scheme is proposed. The use of memristor bridge synapse in the proposed architecture solves one of the major problems, regarding nonvolatile weight storage in analog neural network implementations. To compensate for the spatial nonuniformity and nonideal response of the memristor bridge synapse, a modified chip-in-the-loop learning scheme suitable for the proposed neural network architecture is also proposed. In the proposed method, the initial learning is conducted in software, and the behavior of the software-trained network is learned by the hardware network by learning each of the single-layered neurons of the network independently. The forward calculation of the single-layered neuron learning is implemented on circuit hardware, and followed by a weight updating phase assisted by a host computer. Unlike conventional chip-in-the-loop learning, the need for the readout of synaptic weights for calculating weight updates in each epoch is eliminated by virtue of the memristor bridge synapse and the proposed learning scheme. The hardware architecture along with the successful implementation of proposed learning on a three-bit parity network, and on a car detection network is also presented.