Pancreatic cancer is a kind of malignant carcinoma with high mortality, which is devoid of early diagnostic biomarker and effective therapeutic methods. Recently, long non-coding RNAs (lncRNAs) have ...been reported as a crucial role in regulating the development of various kinds of tumors. Here, we found lncRNA small nuclear RNA host gene 12 (SNHG12) is highly expressed in pancreatic cancer tissues and cell lines through qRT-PCR, which suggested that SNHG12 possibly accelerates the progression of pancreatic cancer. Further study revealed that SNHG12 promoted cancer cells growth and invasion via absorbing miR-320b. Flow cytometry and transwell chamber assay were utilized to verify the promoting effects on proliferation and invasion that SNHG12 acts in pancreatic cancer cells. Evidence that SNHG12 increased cell invasive ability through up-regulated EMT process was lately obtained by Western blotting assay. Consequently, we extrapolated that SNHG12/miR-320b could be invoked as a promising early diagnostic hallmark and therapeutic strategy for pancreatic cancer.
The identification of maize leaf diseases will meet great challenges because of the difficulties in extracting lesion features from the constant-changing environment, uneven illumination reflection ...of the incident light source and many other factors. In this paper, a novel maize leaf disease recognition method is proposed. In this method, we first designed a maize leaf feature enhancement framework with the capability of enhancing the features of maize under the complex environment. Then a novel neural network is designed based on backbone Alexnet architecture, named DMS-Robust Alexnet. In the DMS-Robust Alexnet, dilated convolution and multi-scale convolution are combined to improve the capability of feature extraction. Batch normalization is performed to prevent network over-fitting while enhancing the robustness of the model. PRelu activation function and Adabound optimizer are employed to improve both convergence and accuracy. In experiments, it is validated from different perspectives that the maize leaf disease feature enhancement algorithm is conducive to improving the capability of the DMS-Robust Alexnet identification. Our method demonstrates strong robustness for maize disease images collected in the natural environment, providing a reference for the intelligent diagnosis of other plant leaf diseases.
This paper presents a peach surface defect recognition method based on GWOABC-KM (Gray Wolf algorithm and K-means optimized by improved bee swarm algorithm). Firstly, aiming at the problem of poor ...sharpness and noise in peach images taken in natural environment, the peach images collected by IDCNN (DCNN model combined with Inception structure) are denoised. Then, aiming at the problem that the complex background interferes greatly and affects the accurate segmentation of defective areas, the denoising is carried out by using threshold and edge detection fusion algorithm. The background information of the processed image is removed to get the complete peach image. Finally, the GWOABC algorithm is used to determine the type of peach defect. The method was validated on the peach dataset collected, and the detection rate was 93.7% and 97.4% respectively. Compared with the traditional fruit surface defect detection, this algorithm can better complete the surface defect recognition.
In order to realize the intelligent diagnosis of maize diseases with complicated backgrounds and similar disease spot characteristics in the real field environment, MFaster R-CNN is proposed by ...improving the Faster R-CNN algorithm. Firstly, a batch normalization processing layer is added to the convolution layer to speed up the convergence speed of the network and improve the generalization ability of the model; secondly, a central cost function is proposed to construct a mixed loss function to improve the detection accuracy of similar lesions; then, four kinds of pre-trained convolution structures are selected as the basic feature extraction network of Faster R-CNN for training, and the random gradient descent algorithm is used to optimize the training model to test the optimal feature extraction network; finally, the trained model is used to select test sets under different weather conditions for comparison, and MFaster R-CNN is compared with Faster R-CNN and SSD. The experimental results show that in MFaster R-CNN disease detection framework, VGG16 convolution layer structure as feature extraction network has better performance, the average recall rate is 0.9719, F1 is 0.9718, the overall average accuracy rate can reach 97.23%; compared with Faster R-CNN, MFaster R-CNN has an average accuracy of 0.0886 higher and a single image detection time of 0.139 s less; compared with the SSD, the average accuracy is 0.0425 higher, and the single image detection time is reduced by 0.018 s. Our method also provides a basis for timely and accurate prevention and control of maize diseases in the field.
To solve the problems of the traditional convolutional neural network’s needs of long training time and poor accuracy in the process of fruit image classification, the present study proposes a fruit ...image classification method based on the multi-optimization convolutional neural network with the background of fruit classification. Firstly, in order to avoid the interference of external noise and influence the accuracy of classification, the wavelet threshold is used to denoise the fruit image, which can reduce image noise while preserving the details of the image. Secondly, to correct the over-bright fruit image or the over-dark fruit image, the gamma transform is adopted to correct the image. Finally, in the process of constructing the convolutional neural network, the SOM network is introduced for pre-learning the samples. Besides, the weights of the trained optimal SOM network are applied to the full connection layer, and an integrated optimization model of convolution and full connection is established for feature extraction and regression classification. The optimized convolutional neural network was adopted to classify fruits. According to the application results, the accuracy of the optimized convolutional neural network for fruit classification reaches 99%. Therefore, the improved convolutional neural network depth learning algorithm makes better performance to achieve fruit classification.
In allusion to the problems of citrus surface defect identification such as blurred edges, unclear images, more interference and difficulty in defect identification, surface defect identification of ...citrus based on KF-2D-Renyi and ABC-SVM was proposed in this paper. First, the method based on the dark channel prior (DCP) was used to defog the citrus images collected. Then, the firefly algorithm based on Kent chaos was used to optimize two-dimensional Renyi entropy threshold segmentation algorithm (2D-Renyi). The citrus surface defects were segmented, and the image features were extracted. Finally, the image feature vectors were input into the ABC-SVM classifier to determine the citrus defect types. We selected 8 kinds of citrus surface defects to carry on the experiment. In testing the segmentation algorithms, compared with the traditional threshold segmentation algorithms, the KF-2D-Renyi segmentation algorithm has a great improvement. The recognition rates for the defects whose features are obvious such as Sooty mould and Anthracnose could reach 100%. The recognition rates for the defects which are difficult to identify such as Thrips scar, Oleocellosis and Scale injury reached 95.18%, 96.37% and 98.43% respectively. In testing the classification algorithms, compared with the standard SVM classifier, the PSO-SVM classifier and the neural network classifiers, the average recognition rate of the ABC-SVM classifier reached 98.45%. The experimental results show that the method in this paper can effectively detect and classify citrus surface defects.
Aiming at the essential feature of the time-continuity of birdsong in nature, this paper proposed a birdsong classification model composed of two feature channels, which combines the features of time ...domain and time frequency domain. In order to make better use of the features, we used the improved average threshold method to denoise the original time-domain waveform features to reduce the influence of noise features. The most suitable feature extractor and the best fusion method of these two features are discussed. In this paper, the 3D convolutional neural network (3DCNN) and 2D convolutional neural network (2DCNN) were respectively applied as feature extractors of log_mel spectrum and waveform images. Then the advanced feature, which was extracted from these two feature channels, was fused in the middle stage, and the output enhanced feature was used as the input of double gated recurrent unit (d-GRU) network. In the work, birdsongs of four species from Xeno-Canto were selected for testing. The results showed that these three methods had improved the classification effect: feature fusion method in time domain and time-frequency domain, weighted average threshold noise reduction method and the method of extracting birdsong features via different types of feature extractors. The method of this paper had achieved mean average precision (
MAP
) of 95.9% in the classification comparison experiments, which was an inspiring outcome.
The target detection of smoke through remote sensing images obtained by means of unmanned aerial vehicles (UAVs) can be effective for monitoring early forest fires. However, smoke targets in UAV ...images are often small and difficult to detect accurately. In this paper, we use YOLOX-L as a baseline and propose a forest smoke detection network based on the parallel spatial domain attention mechanism and a small-scale transformer feature pyramid network (PDAM–STPNNet). First, to enhance the proportion of small forest fire smoke targets in the dataset, we use component stitching data enhancement to generate small forest fire smoke target images in a scaled collage. Then, to fully extract the texture features of smoke, we propose a parallel spatial domain attention mechanism (PDAM) to consider the local and global textures of smoke with symmetry. Finally, we propose a small-scale transformer feature pyramid network (STPN), which uses the transformer encoder to replace all CSP_2 blocks in turn on top of YOLOX-L’s FPN, effectively improving the model’s ability to extract small-target smoke. We validated the effectiveness of our model with recourse to a home-made dataset, the Wildfire Observers and Smoke Recognition Homepage, and the Bowfire dataset. The experiments show that our method has a better detection capability than previous methods.
•15 kinds of birdsong data sets were built by ourselves.•The Mel-Sinc spectral diagram of feature fusion is proposed.•ScSEnet enhanced spectrum wavy information is embedded in the backbone ...network.•The proposed MFF-ScSEnet can realize better performance in bird song recognition.
Bird diversity plays an important role in ecological balance, and bird song identification is of great practical significance. The spectrum generated by feature extraction shows good performance on classification. However, the information extracted by the filter in the process of spectrogram generation can cause information loss, which limits the learning ability of birdsong recognition. This study proposes a feature fusion network (MFF-ScSEnet) to solve this problem. The audios of the birdsong extracted the Mel-spectrogram with low-frequency feature advantage by the Mel-filter, and the Sinc-spectrogram with timbral feature advantage by the Sincnet-filter, respectively, and perform the early fusion strategy. The ScSEnet attention module is introduced into the backbone network ResNet18 to enhance the sound ripple information of the spectrogram, reduce the influence of spectrogram noise information on the recognition and improve the recognition performance of the network. Based on the feature fusion network MFF-ScSEnet in this paper, the accuracy of the experimental results on the self-built birdsong dataset (Huabei_dataset), the public datasets of Urbansound8K and Birdsdata reached 96.28%, 98.34%, and 96.66%, respectively. The results indicated that the method proposed in this paper is superior to the recent and latest birdsong recognition method.
The classification of birdsong has very important signification to monitor the bird population in the habitats. Aiming at the birdsong dataset with complex and diverse audio background, this paper ...attempts to introduce an acoustic feature for voice and music analysis: Chroma. It is spliced and fused with the commonly used birdsong features, Log-Mel Spectrogram (LM) and Mel Frequency Cepstrum Coefficient (MFCC), to enrich the representational capacity of single feature; At the same time, in view of the characteristic that birdsong has continuous and dynamic changes in time, a 3DCNN-LSTM combined model is proposed as a classifier to make the network more sensitive to the birdsong information that changes with time. In this paper, we selected four bird audio data from the Xeno-Canto website to evaluate how LM, MFCC and Chroma were fused to maximize the birdsong audio information. The experimental results show that the LM-MFCC-C feature combination achieves the best result of 97.9% mean average precision (mAP) in the experiment.
PDF
