The coral reefs have been considered as an essential component of the marine ecosystem as they help ecologically as well as toward the development of medicine related to the severe diseases such as HIV infections, hea...
详细信息
ISBN:
(纸本)9798350350661;9798350350654
The coral reefs have been considered as an essential component of the marine ecosystem as they help ecologically as well as toward the development of medicine related to the severe diseases such as HIV infections, heart disease, etc. The Coral bleaching phenomenon has been found as the main cause that increases the worldwide dying out risk of coral reefs. The Artificial Intelligence (AI) based approach can become an essential way of early detection of coral reefs bleaching. This work has proposed a Deep Convolution autoencoder (DCAE) based model to detect the bleaching of the coral reefs. The Proposed DCAE model has been utilized to extract the deep feature image from the underwater image of coral reefs, which can be further utilize for the bleaching detection. The Kaggle repository of coral reef health dataset comprising the underwater images of healthy corals and bleached corals have been taken for the experimention. The proposed DCAE approach has achieved an accuracy of 76.60%, sensitivity of 80%, precision of 73.46%, and F1-Score of 76.59% in detecting the bleaching of coral reefs.
Optimizing molecular design and discovering novel chemical structures to meet specific objectives, such as quantitative estimates of the drug-likeness score (QEDs), is NP-hard due to the vast combinatorial design spac...
详细信息
ISBN:
(纸本)9783031426070;9783031426087
Optimizing molecular design and discovering novel chemical structures to meet specific objectives, such as quantitative estimates of the drug-likeness score (QEDs), is NP-hard due to the vast combinatorial design space of discrete molecular structures, which makes it near impossible to explore the entire search space comprehensively to exploit de novo structures with properties of interest. To address this challenge, reducing the intractable search space into a lower-dimensional latent volume helps examine molecular candidates more feasibly via inverse design. autoencoders are suitable deep learning techniques, equipped with an encoder that reduces the discrete molecular structure into a latent space and a decoder that inverts the search space back to the molecular design. The continuous property of the latent space, which characterizes the discrete chemical structures, provides a flexible representation for inverse design to discover novel molecules. However, exploring this latent space requires particular insights to generate new structures. Therefore, we propose using a convex hull (CH) surrounding the top molecules regarding high QEDs to ensnare a tight subspace in the latent representation as an efficient way to reveal novel molecules with high QEDs. We demonstrate the effectiveness of our suggested method by using the QM9 as a training dataset along with the Self-Referencing Embedded Strings (SELFIES) representation to calibrate the autoencoder in order to carry out the inverse molecular design that leads to unfolding novel chemical structure.
autoencoders are powerful models for non-linear dimensionality reduction. However, their neural network structure makes it difficult to interpret how the high dimensional features relate to the lowdimensional embeddin...
详细信息
ISBN:
(纸本)9783031295720;9783031295737
autoencoders are powerful models for non-linear dimensionality reduction. However, their neural network structure makes it difficult to interpret how the high dimensional features relate to the lowdimensional embedding, which is an issue in applications where explainability is important. There have been attempts to replace both the neural network components in autoencoders with interpretable genetic programming (GP) models. However, for the purposes of interpretable dimensionality reduction, we observe that replacing only the encoder with GP is sufficient. In this work, we propose the Genetic Programming Encoder for Autoencoding (GPE-AE). GPE-AE uses a multi-tree GP individual as an encoder, while retaining the neural network decoder. We demonstrate that GPE-AE is a competitive non-linear dimensionality reduction technique compared to conventional autoencoders and a GP based method that does not use an autoencoder structure. As visualisation is a common goal for dimensionality reduction, we also evaluate the quality of visualisations produced by our method, and highlight the value of functional mappings by demonstrating insights that can be gained from interpreting the GP encoders.
Vocal tract shape estimation is a necessary step for articulatory speech synthesis. However, the literature on the topic is scarce, and most current methods lack adequacy to many physical constraints related to speech...
详细信息
Vocal tract shape estimation is a necessary step for articulatory speech synthesis. However, the literature on the topic is scarce, and most current methods lack adequacy to many physical constraints related to speech production. This study proposes an alternative approach to the task to solve specific issues faced in the previous work, especially those related to critical articulators. We present an autoencoder-based method for tongue shape estimation during continuous speech. An autoencoder is trained to learn the data's encoding and serves as an auxiliary network for the principal one, which maps phonemes to the shapes. Instead of predicting the exact points in the target curve, the neural network learns how to predict the curve's main components, i.e., the autoencoder's representation. We show how this approach allows imposing critical articulators' constraints, controlling the tongue shape through the latent space, and generating a smooth output without relying on any postprocessing method.
The use of autoencoder models for image and video compression have been explored by a number of works published in recent years. While those works perform the original data compression in a single layer, in this work ...
详细信息
ISBN:
(数字)9781665466233
ISBN:
(纸本)9781665466233
The use of autoencoder models for image and video compression have been explored by a number of works published in recent years. While those works perform the original data compression in a single layer, in this work we propose the use of autoencoder models in two-layered video coding. The adoption of multi-layer encoder provides scalability and allows us for decoupling the traditional video coding implementation from the NN solutions. By restricting the use of the Neural Network (NN) solution in the enhancement layer, it becomes possible to decode the base layer bitstream without the necessity of running the decoding process with the NN. We implemented and evaluated two autoencoder models: one using a symmetric encoder/decoder architecture, and an asymmetric alternative that employs more layers on the decoder side. The models were trained to compress residues for a scenario using All Intra encoding with spatial scalability. The Asymmetric model outperformed the Symmetric one by providing better compression rates and quality results, which is confirmed by the respective BD-Rate and BD-PSNR average results of -17.06% and 0.7dB, respectively.
Like anything else on the internet, IoT devices are very susceptible to cyber-attacks that could take out the device or install spyware. In this paper, we propose an anomaly detection solution driven by an autoencoder...
详细信息
ISBN:
(纸本)9781665462839
Like anything else on the internet, IoT devices are very susceptible to cyber-attacks that could take out the device or install spyware. In this paper, we propose an anomaly detection solution driven by an autoencoder ensemble to detect botnets on IOT devices. In particular, the ensemble size is determined by hierarchical clustering of the features in the packet header. Moreover, one does not require an additional neural network to combine the decisions. The proposed approach is a more efficient solution for IOT problem setting and hence, overcomes the issue of lacking computational resources and memory on IOT devices, as well as run-time performance problems. Empirical results on two datasets, one from the 2016 Mirai botnet attacks on IoT devices and the other from Gafgyt malware attacks on various IOT devices, show the competitiveness and feasibility of our proposed solution.
An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation. The innovation at a time is statistic...
详细信息
An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation. The innovation at a time is statistically independent of the history of the time series. As such, it represents the new information contained at present but not in the past. Because of its simple probability structure, the innovations sequence is the most efficient signature of the original. Unlike the principle or independent component representations, an innovations sequence preserves not only the complete statistical properties but also the temporal order of the original time series. An long-standing open problem is to find a computationally tractable way to extract an innovations sequence of non-Gaussian processes. This paper presents a deep learning approach, referred to as Innovations autoencoder (IAE), that extracts innovations sequences using a causal convolutional neural network. An application of IAE to the one-class anomalous sequence detection problem with unknown anomaly and anomaly-free models is also presented.
Remaining Useful Life (RUL) is used to provide an early indication of failures that required performing maintenance and/or replacement of the system in advance. Accurate RUL prediction offers cost-effective operation ...
详细信息
Remaining Useful Life (RUL) is used to provide an early indication of failures that required performing maintenance and/or replacement of the system in advance. Accurate RUL prediction offers cost-effective operation for decision-makers in the industry. The availability of data using intelligence sensors leverages the power of data-driven methods for RUL estimation. Deep Learning is one example of a data-driven method that has a lot of applications in the industry. One of these applications is the RUL prediction where DL algorithms achieved good results. This paper presents an autoencoder-based Deep Belief Network (AE-DBN) model for Aircraft engines' RUL estimation. The AE-DBN DL model is utilized the feature extraction characteristic of AE and superiority in learning long-range dependencies of DBN. The efficiency of the proposed DL algorithm is evaluated by comparison between the proposed AE-DBRN and the state-of-the-art related method for RUL perdition for four datasets. Based on the Root Mean Square Error (RMSE) and Score indices, the outcomes reveal that the AE-DBN RUL prediction model is superior to other DL approaches.
Aiming at weak representation ability and severe loss of time series features in the traditional methods when facing large-scale and complex power load forecasting tasks, an LSTM-autoencoder model that integrates long...
详细信息
Aiming at weak representation ability and severe loss of time series features in the traditional methods when facing large-scale and complex power load forecasting tasks, an LSTM-autoencoder model that integrates long-term and short-term features of the samples is proposed for load forecasting. The encoder part simultaneously receives long time series and short time series as input to extract time series features of different levels and generate related latent vectors. The decoder tries to reconstruct the input sequence while outputting the prediction results to ensure that the latent vectors are meaningful. In addition, the model also uses a mixture of supervised and unsupervised training methods. Experiments based on a publicly available dataset from Alberta Electric System Operator showed that the method presented in this research is superior to many existing mainstream methods, with a mean absolute error of less than 52MW between the prediction results and the actual load values. (C) 2021 The Author(s). Published by Elsevier Ltd.
After the development of next-generation sequencing techniques, protein sequences are abundantly available. Determining the functional characteristics of these proteins is costly and time-consuming. The gap between th...
详细信息
After the development of next-generation sequencing techniques, protein sequences are abundantly available. Determining the functional characteristics of these proteins is costly and time-consuming. The gap between the number of protein sequences and their corresponding functions is continuously increasing. Advanced machine-learning methods have stepped up to fill this gap. In this work, an advanced deep-learning-based approach is proposed for protein function prediction using protein sequences. A set of autoencoders is trained in a semi-supervised manner with protein sequences. Each autoencoder corresponds to a single protein function only. In particular, 932 autoencoders corresponding to 932 biological processes and 585 autoencoders corresponding to 585 molecular functions are trained separately. Reconstruction losses of each protein sample for every autoencoder are used as a feature to classify these sequences into their corresponding functions. The proposed model is tested on test protein samples and achieves promising results. This method can be easily extended to predict any number of functions having an ample amount of supporting protein sequences. All relevant codes, data and trained models are available at https://***/richadhanuka/PFP-autoencoders.
暂无评论