A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the ...time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
Environment-related parameters, including viscosity, polarity, temperature, hypoxia, and pH, play pivotal roles in controlling the physical or chemical behaviors of local molecules. In particular, in ...a biological environment, such factors predominantly determine the biological properties of the local environment or reflect corresponding status alterations. Abnormal changes in these factors would cause cellular malfunction or become a hallmark of the occurrence of severe diseases. Therefore, in recent years, they have increasingly attracted research interest from the fields of chemistry and biological chemistry. With the emergence of fluorescence sensing and imaging technology, several fluorescent chemosensors have been designed to respond to such parameters and to further map their distributions and variations in vitro/in vivo. In this work, we have reviewed a number of various environment-responsive chemosensors related to fluorescent recognition of viscosity, polarity, temperature, hypoxia, and pH that have been reported thus far.
Organic solid materials with color-tunable emissions have been extensively applied in various fields. However, a rational design and facile synthesis of an ideal fluorophore are still challenging due ...to the undesirable aggregation-caused quenching effect in concentrated solution and solid form. Herein, we have developed a series of 2-(2′-hydroxyphenyl)benzothiazole (HBT)-derived color-tunable solid emitters by switching functional groups at the ortho-position of a hydroxyl group via formylation and an aldol condensation reaction. By tuning the electron-withdrawing ability and the π-conjugated framework introduced by the functional groups, fluorophores emit light covering the full-color range from blue to near-infrared regions with high quantum yields in their solid form and show a significant solvatochromic effect in polar solvents. The aggregation-induced emission (AIE) or aggregation-induced emission enhancement (AIEE) and excited-state intramolecular proton transfer (ESIPT) involving fluorescence mechanism, along with their inter/intramolecular interactions in crystals, are elucidated to depict the key factors for tunable emissions and high emitting efficiency. Furthermore, high-quality white-light-emitting materials are obtained in various solvents and polydimethylsiloxane (PDMS) films with combined fluorophores. Overall, these studies report a promising strategy for the construction of organic solid materials with color-tunable emission and shed light on methods for obtaining desirable emission efficiency.
Image style transfer aims to assign a specified artist's style to a real image. However, most existing methods cannot generate textures of various thicknesses due to the rich semantic information of ...the input image. The image loses some semantic information through style transfer with a uniform stroke size. To address the above problems, we propose an improved multi-stroke defocus adaptive style transfer framework based on a stroke pyramid, which mainly fuses various stroke sizes in the image spatial dimension to enhance the image content interpretability. We expand the receptive field of each branch and then fuse the features generated by the multiple branches based on defocus degree. Finally, we add an additional loss term to enhance the structural features of the generated image. The proposed model is trained using the Common Objects in Context (COCO) and Synthetic Depth of Field (SYNDOF) datasets, and the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) are used to evaluate the overall quality of the output image and its structural similarity with the content image, respectively. To validate the feasibility of the proposed algorithm, we compare the average PSNR and SSIM values of the output of the modified model and those of the original model. The experimental results show that the modified model improves the PSNR and SSIM values of the outputs by 1.43 and 0.12 on average, respectively. Compared with the single-stroke style transfer method, the framework proposed in this study improves the readability of the output images with more abundant visual expression.
In this study, a convolutional neural network with threshold optimization (CNN-THOP) is proposed to solve the issue of overlabeling or downlabeling arising during the multilabel image annotation ...process in the use of a ranking function for label annotation along with prediction probability. This model fuses the threshold optimization algorithm to the CNN structure. First, an optimal model trained by the CNN is used to predict the test set images, and batch normalization (BN) is added to the CNN structure to effectively accelerate the convergence speed and obtain a group of prediction probabilities. Second, threshold optimization is performed on the obtained prediction probability to derive an optimal threshold for each class of labels to form a group of optimal thresholds. When the prediction probability for this class of labels is greater than or equal to the corresponding optimal threshold, this class of labels is used as the annotation result for the image. During the annotation process, the multilabel annotation for the image to be annotated is realized by loading the optimal model and the optimal threshold. Verification experiments are performed on the MIML, COREL5K, and MSRC datasets. Compared with the MBRM, the CNN-THOP increases the average precision on MIML, COREL5K, and MSRC by 27%, 28% and 33%, respectively. Compared with the E2E-DCNN, the CNN-THOP increases the average recall rate by 3% on both COREL5K and MSRC. The most precise annotation effect for CNN-THOP is observed on the MIML dataset, with a complete matching degree reaching 64.8%.
A self-calibrating bipartite viscosity sensor 1 for cellular mitochondria, composed of coumarin and boron-dipyrromethene (BODIPY) with a rigid phenyl spacer and a mitochondria-targeting unit, was ...synthesized. The sensor showed a direct linear relationship between the fluorescence intensity ratio of BODIPY to coumarin or the fluorescence lifetime ratio and the media viscosity, which allowed us to determine the average mitochondrial viscosity in living HeLa cells as ca. 62 cP (cp). Upon treatment with an ionophore, monensin, or nystatin, the mitochondrial viscosity was observed to increase to ca. 110 cP.
Based on modulation of the conjugated polymethine π-electron system of a cyanine dye derivative, a ratiometric near-infared fluorescent probe (Cy7A) for hydrazine (N2H4) has been designed and ...synthesized. Cy7A can be selectively hydrazinolysized with great changes in its fluorescent excitation/emission profiles, which makes it possible to detect N2H4 in water samples and living cells and, for the first time, visualize N2H4 in living mice.
The security of car driving is of interest due to the growing number of motor vehicles and frequent occurrence of road traffic accidents, and the combination of advanced driving assistance system ...(ADAS) and vehicle-road cooperation can prevent more than 90% of traffic accidents. Lane detection, as a vital part of ADAS, has poor real-time performance and accuracy in multiple scenarios, such as road damage, light changes, and traffic jams. Moreover, the sparse pixels of lane lines on the road pose a tremendous challenge to the task of lane line detection. In this study, we propose a model that fuses non bottleneck skip residual connections and an improved attention pyramid (IAP) to effectively obtain contextual information about real-time scenes and improve the robustness and real-time performance of current lane detection models. The proposed model modifies the efficient residual factorized pyramid scene parsing network (ERF-PSPNet) and utilizes skip residual connections in non bottleneck-1D modules. A decoder with an IAP provides high-level feature maps with pixel-level attention. We add an auxiliary segmenter and a lane predictor side-by-side after the encoder, the former for lane prediction and the latter to assist with semantic segmentation for classification purposes, as well as to solve the gradient disappearance problem. On the CULane dataset, the F1 metric reaches 92.20% in the normal scenario, and the F1 metric of the model is higher than the F1 metrics of other existing models, such as ERFNet-HESA, ENet_LGAD, and DSB+LDCDI, in normal, crowded, night, dazzling light and no line scenarios; in addition, the mean F1 of the nine scenarios reached 74.10%, the runtime (time taken to test 100 images) of the model was 5.88 ms, and the number of parameters was 2.31M, which means that the model achieves a good trade-off between real-time performance and accuracy compared to the current best results (i.e., a running time of 13.4 ms and 0.98M parameters).
Cellular viscosity is a critical factor in governing diffusion‐mediated cellular processes and is linked to a number of diseases and pathologies. Fluorescent molecular rotors (FMRs) have recently ...been developed to determine viscosity in solutions or biological fluid. Herein, we report a “distorted‐BODIPY”‐based probe BV‐1 for cellular viscosity, which is different from the conventional “pure rotors”. In BV‐1, the internal steric hindrance between the meso‐CHO group and the 1,7‐dimethyl group forced the boron–dipyrrin framework to be distorted, which mainly caused nonradiative deactivation in low‐viscosity environment. BV‐1 gave high sensitivity (x=0.62) together with stringent selectivity to viscosity, thus enabling viscosity mapping in live cells. Significantly, the increase of cytoplasmic viscosity during apoptosis was observed by BV‐1 in real time.
Different from the conventional “pure rotors”, a “distorted difluoroboron dipyrromethene (BODIPY)”‐based fluorescent probe (BV‐1) for cellular viscosity has been developed. BV‐1 gave high sensitivity with stringent selectivity to viscosity, thus enabling viscosity mapping in live cells (see figure). Significantly, the increase of cytoplasmic viscosity during apoptosis was observed by BV‐1 in real time.
An image classification algorithm based on adaptive feature weight updating is proposed to address the low classification accuracy of the current single-feature classification algorithms and simple ...multifeature fusion algorithms. The MapReduce parallel programming model on the Hadoop platform is used to perform an adaptive fusion of hue, local binary pattern (LBP) and scale-invariant feature transform (SIFT) features extracted from images to derive optimal combinations of weights. The support vector machine (SVM) classifier is then used to perform parallel training to obtain the optimal SVM classification model, which is then tested. The Pascal VOC 2012, Caltech 256 and SUN databases are adopted to build a massive image library. The speedup, classification accuracy and training time are tested in the experiment, and the results show that a linear growth tendency is present in the speedup of the system in a cluster environment. In consideration of the hardware costs, time, performance and accuracy, the algorithm is superior to mainstream classification algorithms, such as the power mean SVM and convolutional neural network (CNN). As the number and types of images both increase, the classification accuracy rate exceeds 95%. When the number of images reaches 80,000, the training time of the proposed algorithm is only 1/5 that of traditional single-node architecture algorithms. This result reflects the effectiveness of the algorithm, which provides a basis for the effective analysis and processing of image big data.