Multi-Scale Context Attention Network for Image Retrieval

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

The secondary structure of proteins is significant for studying the three-dimensional structure and functions of proteins. Several models from image understanding and natural language modeling have been successfully adapted in the protein sequence study area, such as Long Short-term Memory (LSTM) network and Convolutional Neural Network (CNN). Recently, Gated Convolutional Neural Network (GCNN) has been proposed for natural language processing and reduces latency while achieving high levels of sentence scoring. Conditionally Parameterized Convolution (CondConv), which use extra sample-dependant modules to conditionally adjust the convolutional network, have achieved great success in the image processing area. In this paper, we propose a novel Conditionally Parameterized Convolutional network (CondGCNN) which utilize the power of both CondConv and GCNN, and we leverage an ensemble encoder to combine the capabilities of both LSTM and CondGCNN to encode protein sequences to obtain better sequential features from proteins. In addition, due to the similarity between the image segmentation problem and the secondary structure prediction problem, we propose an ASP network (Atrous Spatial Pyramid Pooling (ASPP) based network) as the secondary structure generator in our proposed framework. We have conducted extensive ablation studies over each component in the proposed model to verify its effectiveness. Extensive experiments show that the proposed method can achieve higher performance on protein secondary structure prediction task than existing methods on CB513, Caspll and CASP12 datasets. Our method is expected to be useful for protein structure and further protein functions prediction.

In this paper, we develop a method based on a deep learning method in financial market prediction, which includes BRICS economies as the test cases. Financial markets are rife with volatility that is affected by a "bed of complexity," coddled by local and distal factors. To leverage these vast datasets both deep learning models such as Convolutional Neural Networks (CNNs), Long Short Term Memory (LSTM) networks as well as hybrid architectures are used in this study. The paper evaluates the predictive accuracy of the models, and by so doing, identifies their strengths in predicting temporal dependencies and intricate market patterns. In particular, deep learning techniques are applied to case studies of individual countries in the BRICS to highlight the application of deep learning to disparate country specific problems, such as liquidity crises and market shocks. These findings show that classical statistical methods are outperformed by deep learning systems in a precise and reliable financial forecasting. This research highlights the ability of AI driven systems to change financial decision making processes, improving investor confidence and improving economic stability in BRICS nations. This study also readers the value of deep learning in financial market analysis, especially in economies in the developing countries. Application of techniques and architectures e.g. Convolutional Neural Networks (CNNs) that excel at identifying spatial patterns, and Long Short-Term Memory (LSTM) networks renowned for their prowess on sequential and time series data, for real world market prediction are explained. In addition, the research discusses hybrid architectures which extend knowledge, fusing strengths of both architectures to improve prediction accuracy and how deep learning develops to solve particular financial challenges. Through reading these notes readers get exposed to data preprocessing techniques such as normalization and feature selection which are important for boosting deep learning performance. The paper also includes an introduction to the evaluation of models using MSE and R-squared values for validating them in terms of reliable outputs. This research combines deep learning theory and practical case study to offer a useful educational resource for students, researchers, and practitioners who want to apply AI in financial forecasting in complex and dynamic global markets.

Urban air quality index forecasting using multivariate convolutional neural network based customized stacked long short-term memory model

Long-term load forecasting is required for power system planning, long-term investments, and expansion policies. In this paper, an ensemble of Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) is proposed that minimizes the forecasting error for the long-term. The features are extracted from the decomposition of load series using Variational Mode Decomposition (VMD) into various timescale subseries' and are combined with the exogenous variables like temperature and rain. This data is then used to train a Fully Connected Neural Network (FCNN) that produces the final output. This ensemble is expected to provide an accurate forecast as local variations in the series are captured by CNN and long-term dependencies by LSTM, while the VMD decomposes the raw data into low and high-frequency subsequences. The efficacy of the methodology is assessed on the actual load data of Madhya Pradesh (MP) State, India. It is observed that the proposed method has higher forecasting accuracy.

Deep attention ConvLSTM-based adaptive fusion of clear-sky physical prior knowledge and multivariable historical information for probabilistic prediction of photovoltaic power

Urdu language uses cursive script which results in connected characters constituting ligatures. For identifying characters within ligatures of different scales (font sizes), Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) Network are used. Both network models are trained on formerly extracted ligature thickness graphs, from which models extract Meta features. These thickness graphs provide consistent information across different font sizes. LSTM and CNN are also trained on raw images to compare performance on both forms of inputs. For this research, two corpora, i.e. Urdu Printed Text Images (UPTI) and Centre for Language Engineering (CLE) Text Images are used. Overall performance of networks ranges between 90% and 99.8%. Average accuracy on Meta features is 98.08% while using raw images, 97.07% average accuracy is achieved.

Activity recognition computer vision algorithms can be used to detect the presence of autism-related behaviors, including what are termed “restricted and repetitive behaviors”, or stimming, by diagnostic instruments. Examples of stimming include hand flapping, spinning, and head banging. One of the most significant bottlenecks for implementing such classifiers is the lack of sufficiently large training sets of human behavior specific to pediatric developmental delays. The data that do exist are usually recorded with a handheld camera which is itself shaky or even moving, posing a challenge for traditional feature representation approaches for activity detection which capture the camera's motion as a feature. To address these issues, we first document the advantages and limitations of current feature representation techniques for activity recognition when applied to head banging detection. We then propose a feature representation consisting exclusively of head pose keypoints. We create a computer vision classifier for detecting head banging in home videos using a time-distributed convolutional neural network (CNN) in which a single CNN extracts features from each frame in the input sequence, and these extracted features are fed as input to a long short-term memory (LSTM) network. On the binary task of predicting head banging and no head banging within videos from the Self Stimulatory Behaviour Dataset (SSBD), we reach a mean F1-score of 90.77% using 3-fold cross validation (with individual fold F1-scores of 83.3%, 89.0%, and 100.0%) when ensuring that no child who appeared in the train set was in the test set for all folds. This work documents a successful process for training a computer vision classifier which can detect a particular human motion pattern with few training examples and even when the camera recording the source clip is unstable. The process of engineering useful feature representations by visually inspecting the representations, as described here, can be a useful practice by designers and developers of interactive systems detecting human motion patterns for use in mobile and ubiquitous interactive systems.

Human identification using camera-based surveillance systems is a challenging research topic, especially in cases where the human face is not visible to cameras and/or when humans captured on cameras have no clear visual identity owing to environments with low-illumination. With the development of deep learning algorithms, studies that are based on the human gait using convolutional neural networks (CNNs) and long short-term memory (LSTM) have achieved promising performance for human identification. However, CNN and LSTM-based methods have the limitation of having higher loss of temporal and spatial information, respectively. In our approach, we use shallow CNN stacked with LSTM and deep CNN followed by score fusion to capture more spatial and temporal features. In addition, there have been a few studies regarding gait-based human identification based on the front and back view images of humans captured in low-illumination environments. This makes it difficult to extract conventional features, such as skeleton joints, cycle, cadence, and the lengths of walking strides. To overcome these problems, we designed our method considering the front and back view images captured in both high- and low-illumination environments. The experimental results obtained using a self-collected database and the open database of the institute of automation Chinese academy of sciences gait dataset C show that the proposed method outperforms previous methods.

COVID-19 pandemic has indeed plunged the global community especially African countries into an alarming difficult situationculminating into a great deal amounts of catastrophes such as economic recession, political instability and loss of jobs. Thepandemic spreads exponentially and causes loss of lives. Following the outbreak of the omicron new variant of concern,forecasting and identification of the COVID-19 infection cases is very vital for government at various levels. Hence, havingknowledge of the spread at a particular point in time, swift actions can be taken by government at various levels with a view toaccordingly formulate new policies and modalities towards minimizing the trajectory of the consequences of COVID-19 pandemicto both public health and economic sectors. Here, a potent combination of Convolutional Neural Network (CNN) learning algorithm along with Long Short Term Memory(LSTM) learning algorithm has been proposed in this work in order to produce a hybrid of a deep learning algorithm ConvolutionalNeural Network - Long Short Term Memory (CNN-LSTM) for forecasting COVID-19 infection cases particularly in Nigeria, SouthAfrica and Botswana. Forecasting models for COVID-19 infection cases in Nigeria, South Africa and Botswana, were developedfor 10 days using deep learning-based approaches namely CNN, LSTM and CNN-LSTM deep learning algorithm respectively. The models were evaluated on the basis of four standard performance evaluation metrics which include accuracy, MSE, MAEand RMSE respectively. However, the CNN-LSTM deep learning-based forecasting model achieved the best accuracy of98.30%, 97.60%, and 97.74% for Nigeria, South Africa and Botswana respectively; and in the same manner, achieved lesserMSE, MAE and RMSE values compared to models developed with CNN and LSTM respectively. Taken together, the CNN-LSTM deep learning-based forecasting model for COVID-19 infection cases in Nigeria, South Africaand Botswana dramatically surpasses the two other DL based forecasting models (CNN and LSTM) for COVID-19 infectioncases in Nigeria, South Africa and Botswana in terms of not only the best accuracy of with 98.30%, 97.60%, and 97.74% but alsoin terms of lesser MSE, MAE and RMSE.

Speech spectrograms exhibit strong contextual dependencies along both time and frequency dimensions. In this paper, a novel composite model integrating a long short-term memory (LSTM) and convolutional neural network (CNN) to exploit temporal and spectral contextual speech information, respectively, is proposed for speech separation. LSTM and CNN operate in a parallel fashion to speed up the process and independently extract a complementary set of speech features. A fully-connected network then maps these features to the real and imaginary components of a ratio mask to enhance the magnitude and phase of the corrupted speech simultaneously. In the CNN path, a new delicately designed CNN with frequency dilated one-dimension (1D) convolutional layers is employed to expand the receptive field of CNN kernels without increasing the complexity. Furthermore, this CNN benefits from residual learning and skip connections to facilitate training and accelerate convergence. In spite of different neural networks included in the composite model, the proposed separation system not only has a low computational complexity, but also significantly outperforms some other deep learning-based methods.

Text classification is a classic task in the field of natural language processing. however, the existing methods of text classification tasks still need to be improved because of the complex abstraction of text semantic information and the strong relecvance of context. In this paper, we combine the advantages of two traditional neural network model, Long Short-Term Memory(LSTM) and Convolutional Neural Network(CNN). LSTM can effectively preserve the characteristics of historical information in long text sequences, and extract local features of text by using the structure of CNN. We proposes a hybrid model of LSTM and CNN, construct CNN model on the top of LSTM, the text feature vector output from LSTM is further extracted by CNN structure. The performance of the hybrid model is compared with that of other models in the experiment. The experimental results show that the hybrid model can effectively improve the accuracy of text classification.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

Research on short-term wind speed prediction based on deep learning model in multi-fan scenario of distributed generation

A data driven method for multi-step prediction of ship roll motion in high sea states