Agriculture is considered as the important field which makes its huge contribution over the country's economic growth. The yield of food crops and the precise categorization of crops based on several characteristi...
详细信息
Agriculture is considered as the important field which makes its huge contribution over the country's economic growth. The yield of food crops and the precise categorization of crops based on several characteristics are of primary importance in this agricultural industry. However, due to a lack of an effective classification method, this industry has significant issues correctly classifying the crops. In addition, classifying food crops using data mining is highly efficient as these techniques can deal with huge amounts of crop data. To this extent, this paper proposes an efficient classification model based on the cropland data extracted from the cropland images. Initially, the dataset is pre-processed based on data-mining techniques like data cleaning and data discretization. Then, the data are clustered based on their relevance using an Improved Density-based Spatial Clustering of Applications with Noise (IDBSCAN) clustering technique. Finally, classification is performed accurately using the Adaptive Capsule Transient auto-encoder (ACTAE). The experimental validation of a proposed approach proved its efficiency over the other existing models with an overall accuracy rate of 97% which is incomparable to the other crop classification models implemented over the cropland dataset.
Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common *** ofmedical images is very important to secure patient *** these images consumes a lot of time onedge computing;theref...
详细信息
Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common *** ofmedical images is very important to secure patient *** these images consumes a lot of time onedge computing;therefore,theuse of anauto-encoder for compressionbefore encodingwill solve such a *** this paper,we use an auto-encoder to compress amedical image before encryption,and an encryption output(vector)is sent out over the *** the other hand,a decoder was used to reproduce the original image back after the vector was received and *** convolutional neural networks were conducted to evaluate our proposed approach:The first one is the auto-encoder,which is utilized to compress and encrypt the images,and the other assesses the classification accuracy of the image after decryption and *** hyperparameters of the encoder were tested,followed by the classification of the image to verify that no critical information was lost,to test the encryption and encoding *** this approach,sixteen hyperparameter permutations are utilized,but this research discusses three main cases in *** first case shows that the combination of Mean Square Logarithmic Error(MSLE),ADAgrad,two layers for the auto-encoder,and ReLU had the best auto-encoder results with a Mean Absolute Error(MAE)=0.221 after 50 epochs and 75%classification with the best result for the classification *** second case shows the reflection of auto-encoder results on the classification results which is a combination ofMean Square Error(MSE),RMSprop,three layers for the auto-encoder,and ReLU,which had the best classification accuracy of 65%,the auto-encoder gives MAE=0.31 after 50 *** third case is the worst,which is the combination of the hinge,RMSprop,three layers for the auto-encoder,and ReLU,providing accuracy of 20%and MAE=0.485.
Unsupervised feature learning is a fundamental and highly prioritized problem in medical image analysis. Although it has shown considerable improvements, it remains challenging because of its weak feature expression a...
详细信息
Unsupervised feature learning is a fundamental and highly prioritized problem in medical image analysis. Although it has shown considerable improvements, it remains challenging because of its weak feature expression ability, low model-learning efficiency, and weak robustness. To address these limitations, a novel unsupervised feature learning method in the medical image classification task, named de-melting reduction auto-encoder (DMRAE), is proposed in this study. A joint fusion network structure is constructed;it not only improves the expression of target features but also reduces the loss of feature decoding and parameters. To obtain a robust solution, a newly designed decomposed-reconstructed loss function is used to strengthen the semantic context between adjacent feature extractor layers, success-fully avoiding the insufficient model-learning ability from the single optimization objective and improv-ing the quality of the extracted features. Finally, extensive experiments on datasets consisting of 400 breast ultrasonographic images and 6000 lung computed tomography images are conducted to demon-strate the effectiveness of the proposed method. Experimental results reveal that the DMRAE significantly reduces the annotation effort and outperforms existing methods by a significant margin.(c) 2022 Elsevier B.V. All rights reserved.
The increased fraud risk due to the most recent methods of paying with a credit card, such as real-time payments and cards with near-field communication (NFC) capabilities, makes detecting credit card fraud an essenti...
详细信息
This paper presents a new nonlinear non-intrusive reduced-order model (NL-NIROM) that outperforms traditional proper orthogonal decomposition (POD)-based reduced order model (ROM). This improvement is achieved through...
详细信息
This paper presents a new nonlinear non-intrusive reduced-order model (NL-NIROM) that outperforms traditional proper orthogonal decomposition (POD)-based reduced order model (ROM). This improvement is achieved through the use of auto-encoder (AE) and self-attention based deep learning methods. The novelty of this work is that it uses stacked auto-encoder (SAE) network to project the original high-dimensional dynamical systems onto a low dimensional nonlinear subspace and predict fluid dynamics using an self-attention based deep learning method. This paper introduces a new model reduction neural network architecture for fluid flow problem, as well as, a linear non-intrusive reduced order model (L-NIROM) based on POD and self-attention mechanism. In the NL-NIROM, the SAE network compresses high-dimensional physical information into several much smaller sized representations in a reduced latent space. These representations are expressed by a number of codes in the middle layer of SAE neural network. Then, those codes at different time levels are trained to construct a set of hyper-surfaces using self-attention based deep learning methods. The inputs of the self-attention based network are previous time levels' codes and the outputs of the network are current time levels' codes. The codes at current time level are then projected back to the original full space by the decoder layers in the SAE network. The capability of the new model, NL-NIROM, is demonstrated through two test cases: flow past a cylinder, and a lock exchange. The results show that the NL-NIROM is more accurate than the popular model reduction method namely POD based L-NIROM.
BackgroundMost bile duct (BDI) injuries during laparoscopic cholecystectomy (LC) occur due to visual misperception leading to the misinterpretation of anatomy. Deep learning (DL) models for surgical video analysis cou...
详细信息
BackgroundMost bile duct (BDI) injuries during laparoscopic cholecystectomy (LC) occur due to visual misperception leading to the misinterpretation of anatomy. Deep learning (DL) models for surgical video analysis could, therefore, support visual tasks such as identifying critical view of safety (CVS). This study aims to develop a prediction model of CVS during LC. This aim is accomplished using a deep neural network integrated with a segmentation model that is capable of highlighting hepatocytic *** images from LC videos were annotated with four hepatocystic landmarks of anatomy segmentation. A deep autoencoder neural network with U-Net to investigate accurate medical image segmentation was trained and tested using fivefold cross-validation. Accuracy, Loss, Intersection over Union (IoU), Precision, Recall, and Hausdorff Distance were computed to evaluate the model performance versus the annotated ground *** total of 1550 images from 200 LC videos were annotated. Mean IoU for segmentation was 74.65%. The proposed approach performed well for automatic hepatocytic landmarks identification with 92% accuracy and 93.9% precision and can segment challenging ***, can potentially provide an intraoperative model for surgical video analysis and can be trained to guide surgeons toward reliable hepatocytic anatomy segmentation and produce selective video documentation of this safety step of LC.
Personalized tag recommender systems automatically recommend users a set of tags used to annotate items according to users' past tagging information. Learning the representations of involved entities (i.e. users, ...
详细信息
Personalized tag recommender systems automatically recommend users a set of tags used to annotate items according to users' past tagging information. Learning the representations of involved entities (i.e. users, items and tags) and capturing the complex relationships among them are crucial for personalized tag recommender systems. However, few studies have been conducted to simultaneously achieve these two sub-goals. In this research, we propose a novel personalized tag recommendation model based on the denoising auto-encoder, namely DAE-PTR, which learns the representations of entities and encodes the complex relationships by exploiting the denoising auto-encoder framework. Specifically, for each user, we firstly generate the corrupted version of the respective tagging information by adding the multiplicative mask-out/drop-out noise into the original input. Then, we learn the latent representations from the corrupted input via the auto-encoder framework by using the cross-entropy loss. More importantly, we integrate the latent user and item embeddings into the processing of encoding, which makes the learnt hidden representations of the auto-encoder network encode multiple types of relationships among entities, i.e. the relationships between users and tags, between items and tags, and among tags. Finally, we employ the decoder component to reconstruct the original input based on the learnt latent representations. Experimental results on the real-world datasets show that our proposed DAE-PTR model is superior to the traditional personalized tag recommendation models.
The colorization of grayscale images is a challenging task in image processing. Recently, deep learning has shown remarkable performance in image colorization. However, the detail loss and color distortion are still s...
详细信息
The colorization of grayscale images is a challenging task in image processing. Recently, deep learning has shown remarkable performance in image colorization. However, the detail loss and color distortion are still serious problem for most existing methods, and some useful features may be lost in the processes of various convolutional layers because of the vanishing gradient problem. Therefore, there is still a considerable space to reach the roof of image colorization. In this work, we propose a deep convolutional auto-encoder with special multi-skip connections for image colorization in YUV color space, and the specific contributions or designs of this work are shown as the following five points. First, a given gray image is used as the Y channel to input a deep learning model to predict U and V channel. Second, the adopted encoder-decoder consists of a main path and two branch paths, and the branch path has two skip connection ways that include one shortcut in each three layers and one shortcut in each six layers. Third, the convolutional kernel size is set as 2*2 that is a special consideration in the path of one shortcut in each six layers. Fourth, a composite loss function is proposed based on the mean square error and gradient that is defined to calculate the errors between the ground truth and the predicted result. Finally, we also discuss the reasonable network parameters, such as the way of shortcut connection, the convolutional kernel size of shortcut connection, and loss function parameters. Experiments on different image datasets show that the proposed image colorization model is effective, and the scores of the PNSR, RMSE, SSIM, and Pearson correlation coefficient are, respectively, to 27.0595, 0.1311, 0.561, and 0.9771.
The Internet of Bio-Nano Things (IoBNT) is envisioned to be a heterogeneous network of artificial and natural units that are connected to the Internet. Hence, it extends the connectivity and control to unconventional ...
详细信息
ISBN:
(纸本)9798350343205;9798350343199
The Internet of Bio-Nano Things (IoBNT) is envisioned to be a heterogeneous network of artificial and natural units that are connected to the Internet. Hence, it extends the connectivity and control to unconventional domains, such as the human body. A potential use case for IoBNT is the communication from the outside to the inside of the human body. In this scenario, typically the Receiver (RX) inside the human body has limited computational complexity, while the Transmitter (TX) outside has large computational resources. In this paper, we address this scenario and propose a novel Asymmetric auto-encoder (AAEC) architecture for end-to-end learning of a Molecular Communication (MC) system. It applies a Neural Network (NN) at the TX and a low-complexity slope detector at the RX. We discuss the different layers of the NN-based TX and the corresponding training approach. Moreover, we investigate the explainability of the NN-based TX and show through the use of meta modeling that it can be approximated by a linear model. In addition, we demonstrate that the proposed AAEC resembles an MC system with Zero Forcing (ZF) precoding for low and moderate Inter Symbol Interference (ISI). Finally, through numerical results, we confirmed the aforementioned findings and showed that the proposed AAEC outperforms MC systems with and without ZF precoding, especially in high ISI scenarios.
Secondary crashes occur within the spatial and temporal impact area of primary crashes, resulting in traffic delays and safety problems. While most existing studies focus on the likelihood of secondary crashes, predic...
详细信息
Secondary crashes occur within the spatial and temporal impact area of primary crashes, resulting in traffic delays and safety problems. While most existing studies focus on the likelihood of secondary crashes, predicting the spatio-temporal location of secondary crashes could offer valuable insights for implementing prevention strategies. This includes guiding the deployment of emergency response measures and determining appropriate speed limits. The main objective of this study is to develop a prediction method for the spatial and temporal locations of secondary crashes. A hybrid deep learning model SSAE-LSTM is proposed by combining stacked sparse auto-encoder (SSAE) and long short-term memory network (LSTM). Traffic and crash data on the California I-880 highway covering the period of 2017-2021 are collected. The identification of secondary crashes is performed by the speed contour map method. The time and distance gaps between primary and secondary crashes are modeled using multiple 5-minute interval traffic variables as inputs. Multiple models are developed for benchmarking purposes, including PCA-LSTM, which incorporates principal component analysis (PCA) and LSTM, SSAE-SVM, which incorporates SSAE and support vector machine (SVM), and back propagation neural network (BPNN). The performance comparison indicates that the hybrid SSAE-LSTM model outperforms the other models in terms of both spatial and temporal prediction. In particular, SSAE4-LSTM1 (with 4 SSAE layers and 1 LSTM layer) demonstrates superior spatial prediction performance, while SSAE4-LSTM2 (with 4 SSAE layers and 2 LSTM layers) excels in temporal prediction. A joint spatio-temporal evaluation is also conducted to measure the overall accuracy of the optimal models over different permitted spatio-temporal ranges. Finally, practical suggestions are provided for secondary crash prevention.
暂无评论