Search

Deep learning, a subset of machine learning that utilizes neural networks, has seen significant advancements in recent years. These advancements have led to breakthroughs in a wide range of fields, from natural language processing to computer vision, and have the potential to revolutionize many industries or organizations. They have also demonstrated exceptional performance in the identification and mapping of seagrass images. However, these deep learning models, particularly the popular Convolutional Neural Networks (CNNs) require architectural engineering and hyperparameter tuning. This paper proposes a Deep Neuroevolutionary (DNE) model that can automate the architectural engineering and hyperparameter tuning of CNNs models by developing and using a novel metaheuristic algorithm, named 'Boosted Atomic Orbital Search (BAOS)'. The proposed BAOS is an improved version of the recently proposed Atomic Orbital Search (AOS) algorithm which is based on the principle of atomic model and quantum mechanics. The proposed algorithm leverages the power of the Lévy flight technique to boost the performance of the AOS algorithm. The proposed DNE algorithm (BAOS-CNN) is trained, evaluated and compared with six popular optimisation algorithms on a patch-based multi-species seagrass dataset. This proposed BAOS-CNN model achieves the highest overall accuracy (97.48%) among the seven evolutionary-based CNN models. The proposed model also achieves the state-of-the-art overall accuracy of 92.30% and 93.5% on the publicly available four classes and five classes version of the 'DeepSeagrass' dataset, respectively. This multi-species seagrass dataset is available at: https://ro.ecu.edu.au/datasets/141/., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Noman et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T waves have shown promising results, their ability to handle arrhythmias has not been studied in any detail. In this paper we investigate the effect of arrhythmias on delineation quality and develop strategies to improve performance in such cases. We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset. Furthermore, we assess various models across a wide array of arrhythmias and observe that models with a strong performance on standard benchmarks may still perform poorly on arrhythmias that are underrepresented in these benchmarks, such as tachycardias. We propose solutions to address this discrepancy., Competing Interests: I have read the journal’s policy and the authors of this manuscript have the following competing interests: CJ, TP, WK and OvK received financial support through NRF grants 2022R1A5A6000840 as well as RS-2022-00165404, NRF2023005562, funded by the Korean Government. SHK, SYO, JHJ, JSH, WJK and MJC received financial support through grants 1711174270, RS-2021-KD000008 funded by the Korean government. In addition, SHK, SYO, JHJ, JSH, WJK and MJC are Stockholders of Medifarmsoft Co., Ltd., (Copyright: © 2024 Joung et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

The identification research of hydrogenation catalyst information has always been one of the most important businesses in the chemical industry. In order to aid researchers in efficiently screening high-performance catalyst carriers and tackle the pressing challenge at hand, it is imperative to find a solution for the intelligent recognition of hydrogenation catalyst images. To address the issue of low recognition accuracy caused by adhesion and stacking of hydrogenation catalysts, An image recognition algorithm of hydrogenation catalyst based on FPNC Net was proposed in this paper. In the present study, Resnet50 backbone network was used to extract the features, and spatially-separable convolution kernel was used to extract the multi-scale features of catalyst fringe. In addition, to effectively segment the adhesive regions of stripes, FPN (Feature Pyramid Network) is added to the backbone network for deep and shallow feature fusion. Introducing an attention module to adaptively adjust weights can effectively highlight the target features of the catalyst. The experimental results showed that the FPNC Net model achieved an accuracy of 94.2% and an AP value improvement of 19.37% compared to the original CenterNet model. The improved model demonstrates a significant enhancement in detection accuracy, indicating a high capability for detecting hydrogenation catalyst targets., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Hou et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Deep learning methods are being increasingly widely used in static malware detection field because they can summarize the feature of malware and its variants that have never appeared before. But similar to the picture recognition model, the static malware detection model based on deep learning is also vulnerable to the interference of adversarial samples. When the input feature vectors of the malware detection model is based on static features of Windows PE (Portable Executable, PE) file, the model is vulnerable to gradient-based attacks. Regarding the issue above, a method of adversarial sample generation is proposed, which can summarize the blind spots of the original detection model. However, the existing malware adversarial sample generation method is not universal and low in generation efficiency due to the need for human control and difficulty in maintaining a normal file format. In response to these problems, this paper proposes a novel method of automatic adversarial samples generation based on deep reinforcement learning. Firstly, a static PE malware detection model based on deep learning called DeepDetectNet is constructed, the original AUC of which can reach 0.989. Then, an adversarial sample generation model based on reinforcement learning called RLAttackNet is implemented, which generates malware samples that can bypass DeepDetectNet. Finally, when we re-input the adversarial samples into the previously trained DeepDetectNet, the original defects of DeepDetectNet can be reinforced. Experimental results show that the RLAttackNet proposed in this paper can generate about 19.13% of malware samples bypass DeepDetectNet. When DeepDetectNet is retrained with these adversarial samples, the AUC value improves from 0.989 to 0.996 and attack success rate has a significant drop, from 19.13% to 3.1%, compared with the original model., Competing Interests: The authors have declared that no competing interests exist.

An improved algorithm based on Yolov8s is proposed to address the slower speed, higher number of parameters, and larger computational cost of deep learning in coal gangue target detection. A lightweight network, Fasternet, is used as the backbone to increase the speed of object detection and reduce the model complexity. By replacing Slimneck with the C2F part in the HEAD module, the aim is to reduce model complexity and improve detection accuracy. The detection accuracy is effectively improved by replacing the Detect layer with Detect-DyHead. The introduction of DIoU loss function instead of CIoU loss function and the combination of BAM block attention mechanism makes the model pay more attention to critical features, which further improves the detection performance. The results show that the improved model compresses the storage size of the model by 28%, reduces the number of parameters by 28.8%, reduces the computational effort by 34.8%, and improves the detection accuracy by 2.5% compared to the original model. The Yolov8s-change model provides a fast, real-time and efficient detection solution for gangue sorting. This provides a strong support for the intelligent sorting of coal gangue. [ABSTRACT FROM AUTHOR]

Time series data complexity presents new challenges in clustering analysis across fields such as electricity, energy, industry, and finance. Despite advances in representation learning and clustering with Variational Autoencoders (VAE) based deep learning techniques, issues like the absence of discriminative power in feature representation, the disconnect between instance reconstruction and clustering objectives, and scalability challenges with large datasets persist. This paper introduces a novel deep time series clustering approach integrating VAE with metric learning. It leverages a VAE based on Gated Recurrent Units for temporal feature extraction, incorporates metric learning for joint optimization of latent space representation, and employs the sum of log likelihoods as the clustering merging criterion, markedly improving clustering accuracy and interpretability. Experimental findings demonstrate a 27.16% improvement in average clustering accuracy and a 47.15% increase in speed on industrial load data. This study offers novel insights and tools for the thorough analysis and application of time series data, with further exploration of VAE's potential in time series clustering anticipated in future research. [ABSTRACT FROM AUTHOR]

Recommendation algorithms save a lot of valuable time for people to get the information they are interested in. However, the feature calculation and extraction process of each machine learning or deep learning recommendation algorithm are different, so how to obtain various features with different dimensions, i.e., how to integrate the advantages of each model and improve the model inference efficiency, becomes the focus of this paper. In this paper, a better deep learning model is obtained by integrating several cutting-edge deep learning models. Meanwhile, to make the integrated learning model converge better and faster, the parameters of the integrated module are initialized, constraints are imposed, and a new activation function is designed for better integration of the sub-models. Finally, the integrated large model is distilled for knowledge distillation, which greatly reduces the number of model parameters and improves the model inference efficiency. [ABSTRACT FROM AUTHOR]

The paper presents an algorithm to approach the problem of Maximum Clique Enumeration, a well known NP-hard problem that have several real world applications. The proposed solution, called LGP-MCE, exploits Geometric Deep Learning, a Machine Learning technique on graphs, to filter out nodes that do not belong to maximum cliques and then applies an exact algorithm to the pruned network. To assess the LGP-MCE, we conducted multiple experiments using a substantial dataset of real-world networks, varying in size, density, and other characteristics. We show that LGP-MCE is able to drastically reduce the running time, while retaining all the maximum cliques. [ABSTRACT FROM AUTHOR]

In the paper, we proposed a deep learning-based industrial equipment detection algorithm ROMS R-CNN (Rotation Occlusion Multi-Scale Region-CNN). It can solve the problem of inaccurate detection of industrial equipment under complex working conditions such as multi-scale ratio, rotation tilt, occlusion and overlap. The method proposed in this paper first is to construct the MobileNetV2 as the feature pyramid network, and then to combine high semantic information with high resolution information solved industrial equipment detection of different scales. Secondly, a specific rotation anchor scheme is proposed, and the data set is clustered through the k-means algorithm to obtain a specific aspect ratio. Combined with the rotation angle, a rotation anchor of any direction and size is generated to solve the problem of easy tilting of industrial equipment. Finally, a Non-Maximum Suppression algorithm with penalty factors is introduced to solve the overlapping in industrial equipment detection. The experimental results in common industrial equipment detection show that this method is better than other algorithms, significantly improves the missed detection and false detection, and the mAP reaches 0.939. [ABSTRACT FROM AUTHOR]

In order to improve the detection performance of image fusion in focus areas and realize end-to-end decision diagram optimization, we design a multi-focus image fusion network based on deep learning. The network is trained using unsupervised learning and a multi-scale hybrid attention residual network model is introduced to enable solving for features at different levels of the image. In the training stage, multi-scale features are extracted from two source images with different focal points using hybrid multi-scale residual blocks (MSRB), and the up-down projection module (UDP) is introduced to obtain multi-scale edge information, then the extracted features are operated to obtain deeper image features. These blocks can effectively utilize multi-scale feature information without increasing the number of parameters. The deep features of the image are extracted in its test phase, input to the spatial frequency domain to calculate and measure the activity level and obtain the initial decision map, and use post-processing techniques to eliminate the edge errors. Finally, the decision map is generated and optimized, and the final fused image is obtained by combining the optimized decision map with the source image. The comparative experiments show that our proposed model achieves better fusion performance in subjective evaluation, and the quality of the obtained fused images is more robust with richer details. The objective evaluation metrics work better and the image fusion quality is higher. [ABSTRACT FROM AUTHOR]

A recurrent criticism concerning the use of online social media data in political science research is the lack of demographic information about social media users. By employing a face-recognition algorithm to the profile pictures of Facebook users, the paper derives two fundamental demographic characteristics (age and gender) of a sample of Facebook users who interacted with the most relevant British parties in the two weeks before the Brexit referendum of 23 June 2016. The article achieves the goals of (i) testing the precision of the algorithm, (ii) testing its validity, (iii) inferring new evidence on digital mobilisation, and (iv) tracing the path for future developments and application of the algorithm. The findings show that the algorithm is reliable and that it can be fruitfully used in political and social sciences both to confirm the validity of survey data and to obtain information from populations that are generally unavailable within traditional surveys. [ABSTRACT FROM AUTHOR]

In palynology, the visual classification of pollen grains from different species is a hard task which is usually tackled by human operators using microscopes. Its complete automatization would save a high quantity of resources and provide valuable improvements especially for allergy-related information systems, but also for other application fields as paleoclimate reconstruction, quality control of honey based products, collection of evidences in criminal investigations or fabric dating and tracking. This paper presents three state-of-the-art deep learning classification methods applied to the recently published POLEN23E image dataset. The three methods make use of convolutional neural networks: the first one is strictly based on the idea of transfer learning, the second one is based on feature extraction and the third one represents a hybrid approach, combining transfer learning and feature extraction. The results from the three methods are indeed very good, reaching over 97% correct classification rates in images not previously seen by the models, where other authors reported around 70. [ABSTRACT FROM AUTHOR]

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance. [ABSTRACT FROM AUTHOR]

Big web data from sources including online news and Twitter are good resources for investigating deep learning. However, collected news articles and tweets almost certainly contain data unnecessary for learning, and this disturbs accurate learning. This paper explores the performance of word2vec Convolutional Neural Networks (CNNs) to classify news articles and tweets into related and unrelated ones. Using two word embedding algorithms of word2vec, Continuous Bag-of-Word (CBOW) and Skip-gram, we constructed CNN with the CBOW model and CNN with the Skip-gram model. We measured the classification accuracy of CNN with CBOW, CNN with Skip-gram, and CNN without word2vec models for real news articles and tweets. The experimental results indicated that word2vec significantly improved the accuracy of the classification model. The accuracy of the CBOW model was higher and more stable when compared to that of the Skip-gram model. The CBOW model exhibited better performance on news articles, and the Skip-gram model exhibited better performance on tweets. Specifically, CNN with word2vec models was more effective on news articles when compared to that on tweets because news articles are typically more uniform when compared to tweets. [ABSTRACT FROM AUTHOR]

We investigate the use of Twitter data to deliver signals for syndromic surveillance in order to assess its ability to augment existing syndromic surveillance efforts and give a better understanding of symptomatic people who do not seek healthcare advice directly. We focus on a specific syndrome—asthma/difficulty breathing. We outline data collection using the Twitter streaming API as well as analysis and pre-processing of the collected data. Even with keyword-based data collection, many of the tweets collected are not be relevant because they represent chatter, or talk of awareness instead of an individual suffering a particular condition. In light of this, we set out to identify relevant tweets to collect a strong and reliable signal. For this, we investigate text classification techniques, and in particular we focus on semi-supervised classification techniques since they enable us to use more of the Twitter data collected while only doing very minimal labelling. In this paper, we propose a semi-supervised approach to symptomatic tweet classification and relevance filtering. We also propose alternative techniques to popular deep learning approaches. Additionally, we highlight the use of emojis and other special features capturing the tweet’s tone to improve the classification performance. Our results show that negative emojis and those that denote laughter provide the best classification performance in conjunction with a simple word-level n-gram approach. We obtain good performance in classifying symptomatic tweets with both supervised and semi-supervised algorithms and found that the proposed semi-supervised algorithms preserve more of the relevant tweets and may be advantageous in the context of a weak signal. Finally, we found some correlation (r = 0.414, p = 0.0004) between the Twitter signal generated with the semi-supervised system and data from consultations for related health conditions. [ABSTRACT FROM AUTHOR]

DIBR-3D technology has evolved over the past few years with the demands of consumers increasing in recent times for future free-view 3D videos on their home televisions. The main issue in 3D technology is the lack of 3D content available to watch using the traditional TV systems. Although, some sophisticated devices like stereoscopic cameras have been used to fill the gap between the 3D content demand and 3D content supply. But the content generated through these sophisticated devices can not be displayed on the traditional TV systems, so there needs to be some mechanism which is inline with the traditional TV. Furthermore, the huge collection of existing 2D content should be converted to 3D using depth image-based rendering techniques. This conversion technique can highly contribute in overcoming the shortage problem of the 3D content. This paper presents a novel approach for converting 2D degraded image for DIBR 3D-TV view. This degraded or noisy/blur image is enhanced through image dehazing and Directional Filter Bank (DFB). This enhancement is necessary because of the occlusion effect or hole filling problem that occurs due to imperfect depth map. The enhanced image is then segmented into the foreground image and the background image. After the segmentation, the depth map is generated using image profiles. Moreover, Stereoscopic images are finally produced using the DIBR procedure which is based on the 2D input image and the corresponding depth map. We have verified the results of the proposed approach by comparing the results with the existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at . [ABSTRACT FROM AUTHOR]

Antenna selection in Multiple-Input Multiple-Output (MIMO) systems has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity. Recently, deep learning based methods have achieved promising performance in many application fields. This paper proposed a deep learning (DL) based antenna selection technique. First, we generated the label of training antenna systems by maximizing the channel capacity. Then, we adopted the deep convolutional neural network (CNN) on the channel matrices to explicitly exploit the massive latent cues of attenuation coefficients. Finally, we used the adopted CNN to assign the class label and then select the optimal antenna subset. Experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based antenna selection. [ABSTRACT FROM AUTHOR]

Ex-ante online risk assessment for building emergency evacuation is essential to protect human life and property. Current risk assessment methods are limited by the tradeoff between accuracy and efficiency. In this paper, we propose an online method that overcomes this tradeoff based on multimedia data (e.g. videos data from surveillance cameras) and deep learning. The method consists of two parts. The first estimates the evacuee position as input for training the assessment model to then perform risk assessment in real scenarios. The second considers a social force model based on the evacuation simulation for the output of training model. We verify the proposed method in simulation and real scenarios. Model sensitivity analyses and large-scale tests demonstrate the usability and superiority of the proposed method. By the method, the computation time of risk assessment could be decreased from 10 minutes (by traditional simulation method) to 2.18 s. [ABSTRACT FROM AUTHOR]

Deep learning techniques, e.g., Convolutional Neural Networks (CNNs), have been explosively applied to the research in the fields of information retrieval and natural language processing. However, few research efforts have addressed semantic indexing with deep learning. The use of semantic indexing in the biomedical literature has been limited for several reasons. For instance, MEDLINE citations contain a large number of semantic labels from automatically annotated MeSH terms, and for a great deal of the literature, only the information of the title and the abstract is readily available. In this paper, we propose a Boltzmann Convolutional neural network framework (B-CNN) for biomedicine semantic indexing. In our hybrid learning framework, the CNN can adaptively deal with features of documents that have sequence relationships, and can capture context information accordingly; the Deep Boltzmann Machine (DBM) merges global (the entity in each document) and local information through its training with undirected connections. Additionally, we have designed a hierarchical coarse to fine style indexing structure for learning and classifying documents, and a novel feature extension approach with word sequence embedding and Wikipedia categorization. Comparative experiments were conducted for semantic indexing of biomedical abstract documents; these experiments verified the encouraged performance of our B-CNN model. [ABSTRACT FROM AUTHOR]

This paper presents a new method to reduce the computational cost when using Neural Networks as Language Models, during recognition, in some particular scenarios. It is based on a Neural Network that considers input contexts of different length in order to ease the use of a fallback mechanism together with the precomputation of softmax normalization constants for these inputs. The proposed approach is empirically validated, showing their capability to emulate lower order N-grams with a single Neural Network. A machine translation task shows that the proposed model constitutes a good solution to the normalization cost of the output softmax layer of Neural Networks, for some practical cases, without a significant impact in performance while improving the system speed. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of quantifying biomarkers in multi-stained tissues based on the color and spatial information of microscopy images of the tissue. A deep learning-based method that can automatically localize and quantify the regions expressing biomarker(s) in any selected area on a whole slide image is proposed. The deep learning network, which we refer to as Whole Image (WI)-Net, is a fully convolutional network whose input is the true RGB color image of a tissue and output is a map showing the locations of each biomarker. The WI-Net relies on a different network, Nuclei (N)-Net, which is a convolutional neural network that classifies each nucleus separately according to the biomarker(s) it expresses. In this study, images of immunohistochemistry (IHC)-stained slides were collected and used. Images of nuclei (4679 RGB images) were manually labeled based on the expressing biomarkers in each nucleus (as p16 positive, Ki-67 positive, p16 and Ki-67 positive, p16 and Ki-67 negative). The labeled nuclei images were used to train the N-Net (obtaining an accuracy of 92% in a test set). The trained N-Net was then extended to WI-Net that generated a map of all biomarkers in any selected sub-image of the whole slide image acquired by the scanner (instead of classifying every nucleus image). The results of our method compare well with the manual labeling by humans (average F-score of 0.96). In addition, we carried a layer-based immunohistochemical analysis of cervical epithelium, and showed that our method can be used by pathologists to differentiate between different grades of cervical intraepithelial neoplasia by quantitatively assessing the percentage of proliferating cells in the different layers of HPV positive lesions. [ABSTRACT FROM AUTHOR]

Accurate and robust tomographic reconstruction from dynamic positron emission tomography (PET) acquired data is a difficult problem. Conventional methods, such as the maximum likelihood expectation maximization (MLEM) algorithm for reconstructing the activity distribution-based on individual frames, may lead to inaccurate results due to the checkerboard effect and limitation of photon counts. In this paper, we propose a stacked sparse auto-encoder based reconstruction framework for dynamic PET imaging. The dynamic reconstruction problem is formulated in a deep learning representation, where the encoding layers extract the prototype features, such as edges, so that, in the decoding layers, the reconstructed results are obtained through a combination of those features. The qualitative and quantitative results of the procedure, including the data based on a Monte Carlo simulation and real patient data demonstrates the effectiveness of our method. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Prediction of stock price has been a hot topic in artificial intelligence field. Computational intelligent methods such as machine learning or deep learning are explored in the prediction system in recent years. However, making accurate predictions of stock price direction is still a big challenge because stock prices are affected by nonlinear, nonstationary, and high dimensional features. In previous works, feature engineering was overlooked. How to select the optimal feature sets that affect stock price is a prominent solution. Hence, our motivation for this article is to propose an improved many-objective optimization algorithm integrating random forest (I-NSGA-II-RF) algorithm with a three-stage feature engineering process in order to decrease the computational complexity and improve the accuracy of prediction system. Maximizing accuracy and minimizing the optimal solution set are the optimization directions of the model in this study. The integrated information initialization population of two filtered feature selection methods is used to optimize the I-NSGA-II algorithm, using multiple chromosome hybrid coding to synchronously select features and optimize model parameters. Finally, the selected feature subset and parameters are input to the RF for training, prediction, and iterative optimization. Experimental results show that the I-NSGA-II-RF algorithm has the highest average accuracy, the smallest optimal solution set, and the shortest running time compared to the unmodified multi-objective feature selection algorithm and the single target feature selection algorithm. Compared to the deep learning model, this model has interpretability, higher accuracy, and less running time. [ABSTRACT FROM AUTHOR]

With the development of computer technology, speech synthesis techniques are becoming increasingly sophisticated. Speech cloning can be performed as a subtask of speech synthesis technology by using deep learning techniques to extract acoustic information from human voices and combine it with text to output a natural human voice. However, traditional speech cloning technology still has certain limitations; excessively large text inputs cannot be adequately processed, and the synthesized audio may include noise artifacts like breaks and unclear phrases. In this study, we add a text determination module to a synthesizer module to process words the model has not included. The original model uses fuzzy pronunciation for such words, which is not only meaningless but also affects the entire sentence. Thus, we improve the model by splitting the letters and pronouncing them separately. Finally, we also improved the preprocessing and waveform conversion modules of the synthesizer. We replace the pre-net module of the synthesizer and use an upgraded noise reduction algorithm combined with the SV2TTS framework to achieve a system with superior speech synthesis performance. Here, we focus on improving the performance of the synthesizer module to achieve higher-quality speech synthesis audio output. [ABSTRACT FROM AUTHOR]

Network attacks using Command and Control (C&C) servers have increased significantly. To hide their C&C servers, attackers often use Domain Generation Algorithms (DGA), which automatically generate domain names for C&C servers. Researchers have constructed many unique feature sets and detected DGA domains through machine learning or deep learning models. However, due to the limited features contained in the domain name, the DGA detection results are limited. In order to overcome this problem, the domain name features, the Whois features and the N-gram features are extracted for DGA detection. To obtain the N-gram features, the domain name whitelist and blacklist substring feature sets are constructed. In addition, a deep learning model based on BiLSTM, Attention and CNN is constructed. Additionally, the Domain Center is constructed for fast classification of domain names. Multiple comparative experiment results prove that the proposed model not only gets the best Accuracy, Precision, Recall and F1, but also greatly reduces the detection time. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a branch of natural language analytics that aims to correlate what is expressed which comes normally within unstructured format with what is believed and learnt. Several attempts have tried to address this gap (i.e., Naive Bayes, RNN, LSTM, word embedding, etc.), even though the deep learning models achieved high performance, their generative process remains a "black-box" and not fully disclosed due to the high dimensional feature and the non-deterministic weights assignment. Meanwhile, graphs are becoming more popular when modeling complex systems while being traceable and understood. Here, we reveal that a good trade-off transparency and efficiency could be achieved with a Deep Neural Network by exploring the Credit Assignment Paths theory. To this end, we propose a novel algorithm which alleviates the features' extraction mechanism and attributes an importance level of selected neurons by applying a deterministic edge/node embeddings with attention scores on the input unit and backward path respectively. We experiment on the Twitter Health News dataset were the model has been extended to approach different approximations (tweet/aspect and tweets' source levels, frequency, polarity/subjectivity), it was also transparent and traceable. Moreover, results of comparing with four recent models on same data corpus for tweets analysis showed a rapid convergence with an overall accuracy of ≈83% and 94% of correctly identified true positive sentiments. Therefore, weights can be ideally assigned to specific active features by following the proposed method. As opposite to other compared works, the inferred features are conditioned through the users' preferences (i.e., frequency degree) and via the activation's derivatives (i.e., reject feature if not scored). Future direction will address the inductive aspect of graph embeddings to include dynamic graph structures and expand the model resiliency by considering other datasets like SemEval task7, covid-19 tweets, etc. [ABSTRACT FROM AUTHOR]

Deep learning based on a convolutional neural network (CNN) has been successfully applied to stereo matching. Compared with the traditional method, the speed and accuracy of this method have been greatly improved. However, the existing stereo matching framework based on a CNN often encounters two problems. First, the existing stereo matching network has many parameters, which leads to the matching running time being too long. Second, the disparity estimation is inadequate in some regions where reflections, repeated textures, and fine structures may lead to ill-posed problems. Through the lightweight improvement of the PSMNet (Pyramid Stereo Matching Network) model, the common matching effect of ill-conditioned areas such as repeated texture areas and weak texture areas is solved. In the feature extraction part, ResNeXt is introduced to learn unitary feature extraction, and the ASPP (Atrous Spatial Pyramid Pooling) module is trained to extract multiscale spatial feature information. The feature fusion module is designed to effectively fuse the feature information of different scales to construct the matching cost volume. The improved 3D CNN uses the stacked encoding and decoding structure to further regularize the matching cost volume and obtain the corresponding relationship between feature points under different parallax conditions. Finally, the disparity map is obtained by a regression. We evaluate our method on the Scene Flow, KITTI 2012, and KITTI 2015 stereo datasets. The experiments show that the proposed stereo matching network achieves a comparable prediction accuracy and much faster running speed compared with PSMNet. [ABSTRACT FROM AUTHOR]

The quantitative study of cell morphology is of great importance as the structure and condition of cells and their structures can be related to conditions of health or disease. The first step towards that, is the accurate segmentation of cell structures. In this work, we compare five approaches, one traditional and four deep-learning, for the semantic segmentation of the nuclear envelope of cervical cancer cells commonly known as HeLa cells. Images of a HeLa cancer cell were semantically segmented with one traditional image-processing algorithm and four three deep learning architectures: VGG16, ResNet18, Inception-ResNet-v2, and U-Net. Three hundred slices, each 2000 × 2000 pixels, of a HeLa Cell were acquired with Serial Block Face Scanning Electron Microscopy. The first three deep learning architectures were pre-trained with ImageNet and then fine-tuned with transfer learning. The U-Net architecture was trained from scratch with 36, 000 training images and labels of size 128 × 128. The image-processing algorithm followed a pipeline of several traditional steps like edge detection, dilation and morphological operators. The algorithms were compared by measuring pixel-based segmentation accuracy and Jaccard index against a labelled ground truth. The results indicated a superior performance of the traditional algorithm (Accuracy = 99%, Jaccard = 93%) over the deep learning architectures: VGG16 (93%, 90%), ResNet18 (94%, 88%), Inception-ResNet-v2 (94%, 89%), and U-Net (92%, 56%). [ABSTRACT FROM AUTHOR]

This study investigates the use of deep learning methods to improve the accuracy of a predictive model for dementia, and compares the performance to a traditional machine learning model. With sufficient accuracy the model can be deployed as a first round screening tool for clinical follow-up including neurological examination, neuropsychological testing, imaging and recruitment to clinical trials. Seven cohorts with two years of data, three to eight years prior to index date, and an incident cohort were created. Four trained models for each cohort, boosted trees, feed forward network, recurrent neural network and recurrent neural network with pre-trained weights, were constructed and their performance compared using validation and test data. The incident model had an AUC of 94.4% and F1 score of 54.1%. Eight years removed from index date the AUC and F1 scores were 80.7% and 25.6%, respectively. The results for the remaining cohorts were between these ranges. Deep learning models can result in significant improvement in performance but come at a cost in terms of run times and hardware requirements. The results of the model at index date indicate that this modeling can be effective at stratifying patients at risk of dementia. At this time, the inability to sustain this quality at longer lead times is more an issue of data availability and quality rather than one of algorithm choices. [ABSTRACT FROM AUTHOR]

Objective: The Centers for Disease Control and Prevention (CDC) coordinates a labor-intensive process to measure the prevalence of autism spectrum disorder (ASD) among children in the United States. Random forests methods have shown promise in speeding up this process, but they lag behind human classification accuracy by about 5%. We explore whether more recently available document classification algorithms can close this gap. Materials and methods: Using data gathered from a single surveillance site, we applied 8 supervised learning algorithms to predict whether children meet the case definition for ASD based solely on the words in their evaluations. We compared the algorithms’ performance across 10 random train-test splits of the data, using classification accuracy, F1 score, and number of positive calls to evaluate their potential use for surveillance. Results: Across the 10 train-test cycles, the random forest and support vector machine with Naive Bayes features (NB-SVM) each achieved slightly more than 87% mean accuracy. The NB-SVM produced significantly more false negatives than false positives (P = 0.027), but the random forest did not, making its prevalence estimates very close to the true prevalence in the data. The best-performing neural network performed similarly to the random forest on both measures. Discussion: The random forest performed as well as more recently available models like the NB-SVM and the neural network, and it also produced good prevalence estimates. NB-SVM may not be a good candidate for use in a fully-automated surveillance workflow due to increased false negatives. More sophisticated algorithms, like hierarchical convolutional neural networks, may not be feasible to train due to characteristics of the data. Current algorithms might perform better if the data are abstracted and processed differently and if they take into account information about the children in addition to their evaluations. Conclusion: Deep learning models performed similarly to traditional machine learning methods at predicting the clinician-assigned case status for CDC’s autism surveillance system. While deep learning methods had limited benefit in this task, they may have applications in other surveillance systems. [ABSTRACT FROM AUTHOR]

Caveolae are plasma membrane invaginations whose formation requires caveolin-1 (Cav1), the adaptor protein polymerase I, and the transcript release factor (PTRF or CAVIN1). Caveolae have an important role in cell functioning, signaling, and disease. In the absence of CAVIN1/PTRF, Cav1 forms non-caveolar membrane domains called scaffolds. In this work, we train machine learning models to automatically distinguish between caveolae and scaffolds from single molecule localization microscopy (SMLM) data. We apply machine learning algorithms to discriminate biological structures from SMLM data. Our work is the first that is leveraging machine learning approaches (including deep learning models) to automatically identifying biological structures from SMLM data. In particular, we develop and compare three binary classification methods to identify whether or not a given 3D cluster of Cav1 proteins is a caveolae. The first uses a random forest classifier applied to 28 hand-crafted/designed features, the second uses a convolutional neural net (CNN) applied to a projection of the point clouds onto three planes, and the third uses a PointNet model, a recent development that can directly take point clouds as its input. We validate our methods on a dataset of super-resolution microscopy images of PC3 prostate cancer cells labeled for Cav1. Specifically, we have images from two cell populations: 10 PC3 and 10 CAVIN1/PTRF-transfected PC3 cells (PC3-PTRF cells) that form caveolae. We obtained a balanced set of 1714 different cellular structures. Our results show that both the random forest on hand-designed features and the deep learning approach achieve high accuracy in distinguishing the intrinsic features of the caveolae and non-caveolae biological structures. More specifically, both random forest and deep CNN classifiers achieve classification accuracy reaching 94% on our test set, while the PointNet model only reached 83% accuracy. We also discuss the pros and cons of the different approaches. [ABSTRACT FROM AUTHOR]

Purpose: To benchmark the human and machine performance of spectral-domain (SD) and swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for the compartments vitreous, retina, choroid, sclera. Methods: A convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment the posterior eye compartments. Independent benchmark data sets (30 SDOCT and 30 SSOCT) were manually segmented by three classes of graders with varying levels of ophthalmic proficiencies. Nine graders contributed to benchmark an additional 60 images in three consecutive runs. Inter-human and intra-human class agreement was measured and compared to the CNN results. Results: The CNN training data consisted of a total of 6210 manually segmented images derived from 2070 B-scans (1046 SDOCT and 1024 SSOCT; 630 C-Scans). The CNN segmentation revealed a high agreement with all grader groups. For all compartments and groups, the mean Intersection over Union (IOU) score of CNN compartmentalization versus group graders’ compartmentalization was higher than the mean score for intra-grader group comparison. Conclusion: The proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders. [ABSTRACT FROM AUTHOR]

Over the last few decades, the Internet has experienced tremendous growth in data traffic. This continuous growth due to the increase in the number of connected devices and platforms has dramatically boosted content consumption. However, retrieving content from the servers of Content Providers (CPs) can increase network traffic and incur high network delay and congestion. To address these challenges, we propose a joint deep learning and auction-based approach for congestion-aware caching in Named Data Networking (NDN), which aims to prevent congestion and minimize the content downloading delays. First, using recorded network traffic data on the Internet Service Provider (ISP) network, we propose a deep learning model to predict future traffic over transit links. Second, to prevent congestion and avoid high latency on transit links, which may experience congestion in the future; we propose a caching model that helps the ISP to cache content that has a high predicted future demand. Paid-content requires payment to be downloaded and cached. Therefore, we propose an auction mechanism to obtain paid-content at an optimal price. The simulation results show that our proposal prevents congestion and increases the profits of both ISPs and CPs. [ABSTRACT FROM AUTHOR]

Gene co-expression networks (GCNs) are constructed from Gene Expression Matrices (GEMs) in a bottom up approach where all gene pairs are tested for correlation within the context of the input sample set. This approach is computationally intensive for many current GEMs and may not be scalable to millions of samples. Further, traditional GCNs do not detect non-linear relationships missed by correlation tests and do not place genetic relationships in a gene expression intensity context. In this report, we propose EdgeScaping, which constructs and analyzes the pairwise gene intensity network in a holistic, top down approach where no edges are filtered. EdgeScaping uses a novel technique to convert traditional pairwise gene expression data to an image based format. This conversion not only performs feature compression, making our algorithm highly scalable, but it also allows for exploring non-linear relationships between genes by leveraging deep learning image analysis algorithms. Using the learned embedded feature space we implement a fast, efficient algorithm to cluster the entire space of gene expression relationships while retaining gene expression intensity. Since EdgeScaping does not eliminate conventionally noisy edges, it extends the identification of co-expression relationships beyond classically correlated edges to facilitate the discovery of novel or unusual expression patterns within the network. We applied EdgeScaping to a human tumor GEM to identify sets of genes that exhibit conventional and non-conventional interdependent non-linear behavior associated with brain specific tumor sub-types that would be eliminated in conventional bottom-up construction of GCNs. Edgescaping source code is available at under the MIT license. [ABSTRACT FROM AUTHOR]

We have attempted to reproduce the results in Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, published in JAMA 2016; 316(22), using publicly available data sets. We re-implemented the main method in the original study since the source code is not available. The original study used non-public fundus images from EyePACS and three hospitals in India for training. We used a different EyePACS data set from Kaggle. The original study used the benchmark data set Messidor-2 to evaluate the algorithm's performance. We used another distribution of the Messidor-2 data set, since the original data set is no longer available. In the original study, ophthalmologists re-graded all images for diabetic retinopathy, macular edema, and image gradability. We have one diabetic retinopathy grade per image for our data sets, and we assessed image gradability ourselves. We were not able to reproduce the original study's results with publicly available data. Our algorithm's area under the receiver operating characteristic curve (AUC) of 0.951 (95% CI, 0.947-0.956) on the Kaggle EyePACS test set and 0.853 (95% CI, 0.835-0.871) on Messidor-2 did not come close to the reported AUC of 0.99 on both test sets in the original study. This may be caused by the use of a single grade per image, or different data. This study shows the challenges of reproducing deep learning method results, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis. Our source code and instructions are available at: . [ABSTRACT FROM AUTHOR]

Early defibrillation by an automated external defibrillator (AED) is key for the survival of out-of-hospital cardiac arrest (OHCA) patients. ECG feature extraction and machine learning have been successfully used to detect ventricular fibrillation (VF) in AED shock decision algorithms. Recently, deep learning architectures based on 1D Convolutional Neural Networks (CNN) have been proposed for this task. This study introduces a deep learning architecture based on 1D-CNN layers and a Long Short-Term Memory (LSTM) network for the detection of VF. Two datasets were used, one from public repositories of Holter recordings captured at the onset of the arrhythmia, and a second from OHCA patients obtained minutes after the onset of the arrest. Data was partitioned patient-wise into training (80%) to design the classifiers, and test (20%) to report the results. The proposed architecture was compared to 1D-CNN only deep learners, and to a classical approach based on VF-detection features and a support vector machine (SVM) classifier. The algorithms were evaluated in terms of balanced accuracy (BAC), the unweighted mean of the sensitivity (Se) and specificity (Sp). The BAC, Se, and Sp of the architecture for 4-s ECG segments was 99.3%, 99.7%, and 98.9% for the public data, and 98.0%, 99.2%, and 96.7% for OHCA data. The proposed architecture outperformed all other classifiers by at least 0.3-points in BAC in the public data, and by 2.2-points in the OHCA data. The architecture met the 95% Sp and 90% Se requirements of the American Heart Association in both datasets for segment lengths as short as 3-s. This is, to the best of our knowledge, the most accurate VF detection algorithm to date, especially on OHCA data, and it would enable an accurate shock no shock diagnosis in a very short time. [ABSTRACT FROM AUTHOR]

Background: Glaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment are therefore needed to prevent sight loss. Methods: We developed a novel glaucoma detection algorithm that segments and analyses colour photographs to quantify optic nerve rim consistency around the whole disc at 15-degree intervals. This provides a profile of the cup/disc ratio, in contrast to the vertical cup/disc ratio in common use. We introduce a spatial probabilistic model, to account for the optic nerve shape, we then use this model to derive a disc deformation index and a decision rule for glaucoma. We tested our algorithm on two separate image datasets (ORIGA and RIM-ONE). Results: The spatial algorithm accurately distinguished glaucomatous and healthy discs on internal and external validation (AUROC 99.6% and 91.0% respectively). It achieves this using a dataset 100-times smaller than that required for deep learning algorithms, is flexible to the type of cup and disc segmentation (automated or semi-automated), utilises images with missing data, and is correlated with the disc size (p = 0.02) and the rim-to-disc at the narrowest rim (p<0.001, in external validation). Discussion: The spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings. [ABSTRACT FROM AUTHOR]

We introduce the CDRP (Concatenated Diagnostic-Relapse Prognostic) architecture for multi-task deep learning that incorporates a clinical algorithm, e.g., a risk stratification schema to improve prognostic profiling. We present the first application to survival prediction in High-Risk (HR) Neuroblastoma from transcriptomics data, a task that studies from the MAQC consortium have shown to remain the hardest among multiple diagnostic and prognostic endpoints predictable from the same dataset. To obtain a more accurate risk stratification needed for appropriate treatment strategies, CDRP combines a first component (CDRP-A) synthesizing a diagnostic task and a second component (CDRP-N) dedicated to one or more prognostic tasks. The approach leverages the advent of semi-supervised deep learning structures that can flexibly integrate multimodal data or internally create multiple processing paths. CDRP-A is an autoencoder trained on gene expression on the HR/non-HR risk stratification by the Children’s Oncology Group, obtaining a 64-node representation in the bottleneck layer. CDRP-N is a multi-task classifier for two prognostic endpoints, i.e., Event-Free Survival (EFS) and Overall Survival (OS). CDRP-A provides the HR embedding input to the CDRP-N shared layer, from which two branches depart to model EFS and OS, respectively. To control for selection bias, CDRP is trained and evaluated using a Data Analysis Protocol (DAP) developed within the MAQC initiative. CDRP was applied on Illumina RNA-Seq of 498 Neuroblastoma patients (HR: 176) from the SEQC study (12,464 Entrez genes) and on Affymetrix Human Exon Array expression profiles (17,450 genes) of 247 primary diagnostic Neuroblastoma of the TARGET NBL cohort. On the SEQC HR patients, CDRP achieves Matthews Correlation Coefficient (MCC) 0.38 for EFS and MCC = 0.19 for OS in external validation, improving over published SEQC models. We show that a CDRP-N embedding is indeed parametrically associated to increasing severity and the embedding can be used to better stratify patients’ survival. [ABSTRACT FROM AUTHOR]

The development of whole slide scanners has revolutionized the field of digital pathology. Unfortunately, whole slide scanners often produce images with out-of-focus/blurry areas that limit the amount of tissue available for a pathologist to make accurate diagnosis/prognosis. Moreover, these artifacts hamper the performance of computerized image analysis systems. These areas are typically identified by visual inspection, which leads to a subjective evaluation causing high intra- and inter-observer variability. Moreover, this process is both tedious, and time-consuming. The aim of this study is to develop a deep learning based software called, DeepFocus, which can automatically detect and segment blurry areas in digital whole slide images to address these problems. DeepFocus is built on TensorFlow, an open source library that exploits data flow graphs for efficient numerical computation. DeepFocus was trained by using 16 different H&E and IHC-stained slides that were systematically scanned on nine different focal planes, generating 216,000 samples with varying amounts of blurriness. When trained and tested on two independent datasets, DeepFocus resulted in an average accuracy of 93.2% (± 9.6%), which is a 23.8% improvement over an existing method. DeepFocus has the potential to be integrated with whole slide scanners to automatically re-scan problematic areas, hence improving the overall image quality for pathologists and image analysis algorithms. [ABSTRACT FROM AUTHOR]

With the introduction of various advanced deep learning algorithms, initiatives for image classification systems have transitioned over from traditional machine learning algorithms (e.g., SVM) to Convolutional Neural Networks (CNNs) using deep learning software tools. A prerequisite in applying CNN to real world applications is a system that collects meaningful and useful data. For such purposes, Wireless Image Sensor Networks (WISNs), that are capable of monitoring natural environment phenomena using tiny and low-power cameras on resource-limited embedded devices, can be considered as an effective means of data collection. However, with limited battery resources, sending high-resolution raw images to the backend server is a burdensome task that has direct impact on network lifetime. To address this problem, we propose an energy-efficient pre- and post- processing mechanism using image resizing and color quantization that can significantly reduce the amount of data transferred while maintaining the classification accuracy in the CNN at the backend server. We show that, if well designed, an image in its highly compressed form can be well-classified with a CNN model trained in advance using adequately compressed data. Our evaluation using a real image dataset shows that an embedded device can reduce the amount of transmitted data by ∼71% while maintaining a classification accuracy of ∼98%. Under the same conditions, this process naturally reduces energy consumption by ∼71% compared to a WISN that sends the original uncompressed images. [ABSTRACT FROM AUTHOR]