HarDNet and Dual-Code Attention Mechanism based model for medical images segmentation

During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author

COVID-19 Vaccine and Booster Shots Compatibility Analyzer using CMOS-based Monochrome Encoding

The continuous increase in COVID-19 positive cases in the Philippines might further weaken the local healthcare system. As such, an efficient system must be implemented to further improve the immunization efforts of the country. In this paper, a contactless digital electronic device is proposed to assess the vaccine and booster brand compatibility. Using Logisim 2.7.1, the logic diagrams were designed and simulated with the help of truth tables and Boolean functions. Moreover, the finalized logic circuit design was converted into its equivalent complementary metal-oxide semiconductor (CMOS) and stick diagrams to help contextualize how the integrated circuits will be designed. Results have shown that the proposed device was able to accept three inputs of the top three COVID-19 vaccine brands (Sinovac, AstraZeneca, and Pfizer) and assess the compatibility of heterologous vaccinations. With the successful results of the circuit, it can be concluded that this low-power device can be used to manufacture a physical prototype for use in booster vaccination sites. © 2022 IEEE.

Detection of COVID-19 patient based on attention segmental recurrent neural network (ASRNN) Archimedes optimization algorithm using ultra-low-dose CT images

In this article, the detection of COVID-19 patient based on attention segmental recurrent neural network (ASRNN) with Archimedes optimization algorithm (AOA) using ultra-low-dose CT (ULDCT) images is proposed. Here, the ultra-low-dose CT images are gathered via real time dataset. The input images are preprocessed with the help of convolutional auto-encoder to recover the ULDCT images quality by removing noises. The preprocessed images are given to generalized additive models with structured interactions (GAMI) for extracting the radiomic features. The radiomic features, such as morphologic, gray scale statistic, Haralick texture are extracted using GAMI-Net. The ASRNN classifier, whose weight parameters optimized with Archimedes optimization algorithm enables COVID-19 ULDCT images classification as COVID-19 or normal. The proposed approach is activated in MATLAB platform. The proposed ASRNN-AOA-ULDCT attains accuracy 22.08%, 24.03%, 34.76%, 34.65%, 26.89%, 45.86%, and 32.14%;precision 23.34%, 26.45%, 34.98%, 27.06%, 35.87%, 34.44%, and 22.36% better than the existing methods, such as DenseNet-HHO-ULDCT, ELM-DNN-ULDCT, EDL-ULDCT, ResNet 50-ULDCT, SDL-ULDCT, CNN-ULDCT, and DRNN-ULDCT, respectively. © 2023 John Wiley & Sons, Ltd.

Electricity price estimation using deep learning approaches: An empirical study on Turkish markets in normal and Covid-19 periods

This study aims to estimate the prices in the next 24 h with deep learning methods in the Turkish electricity market. The model is based on hourly data for the period 2017–2021 using electricity prices. The model's Root Mean Square Error (RMSE) value is 3.14, and the explanatory power R2 is 0.94. Since this model also considers the subgroups in the database, it can make price predictions for the pandemic period. To test the robustness and consistency of the model, twelve RNN-based models were re-estimated with the same data set. Although all models successfully predict the prices, The TEDSE Model performs better than the others. This study will be especially beneficial to electricity market players and policymakers. In further studies, the TEDSE model can be used for price prediction in intraday energy markets. This study's most important contribution is methodology innovation, using the Transformer Encoder-Decoder with Self-Attention (TEDSE) model for the first time to estimate electricity prices. © 2023 Elsevier Ltd

MWG-Net: Multi-scale Wavelet Guidance Network for COVID-19 Lung Infection Segmentation from CT Images

Recently, accurate segmentation of COVID-19 infection from computed tomography (CT) scans is critical for the diagnosis and treatment of COVID-19. However, infection segmentation is a challenging task due to various textures, sizes and locations of infections, low contrast, and blurred boundaries. To address these problems, we propose a novel Multi-scale Wavelet Guidance Network (MWG-Net) for COVID-19 lung infection by integrating the multi-scale information of wavelet domain into the encoder and decoder of the convolutional neural network (CNN). In particular, we propose the Wavelet Guidance Module (WGM) and Wavelet &Edge Guidance Module (WEGM). Among them, the WGM guides the encoder to extract infection details through the multi-scale spatial and frequency features in the wavelet domain, while the WEGM guides the decoder to recover infection details through the multi-scale wavelet representations and multi-scale infection edge information. Besides, a Progressive Fusion Module (PFM) is further developed to aggregate and explore multi-scale features of the encoder and decoder. Notably, we establish a COVID-19 segmentation dataset (named COVID-Seg-100) containing 5800+ annotated slices for performance evaluation. Furthermore, we conduct extensive experiments to compare our method with other state-of-the-art approaches on our COVID-19-Seg-100 and two publicly available datasets, i.e., MosMedData and COVID-SemiSeg. The results show that our MWG-Net outperforms state-of-the-art methods on different datasets and can achieve more accurate and promising COVID-19 lung infection segmentation. IEEE

Segmentation Algorithm for COVID-19 Infections using Joint Mix and Context Encoder

Automatic image segmentation is critical for medical image segmentation. For example, automatic segmentation of infection area of COVID-19 before and after diagnosis and treatment can help us automatically analyze the diagnosis and treatment effect. The existing algorithms do not solve the problems of insufficient data and insufficient feature extraction at the same time. In this paper, we propose a new data augmentation algorithm to handle the insufficient data problem, named Joint Mix;we utilize an improved U-Net with context encoder to enhance the feature extraction ability. Experiments in the segmentation of COVID-19 infection region using CT images demonstrate its effectiveness. © 2022 IEEE.

Investigation on MLP, CNNs and Vision Transformer models performance for Extracting a Human Emotions via Facial Expressions

One of the difficult challenges in AI development is to make machine understand the human feeling through expression because human can express feeling in various ways, for example, through voices, facial actions or behaviors. Facial Emotion Recognition (FER) has been used in interrogating suspects and being a tool to help detect emotions in people with nerve damage or even in the COVID-19 pandemic when patients hide their timelines. It can be applied to detect lies through micro expression. In this work will mainly focus on FER. The results of Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Vision Transformer were compared. Human emotion expressions were classified by using facial expression datasets from AffectNet, Tsinghua, Extended Cohn Kanade (CK+), Karolinska Directed Emotional Faces (KDEF) and Real-world Affective Faces (RAF). Finally, all models were evaluated on the testing dataset to confirm their performance. The result shows that Vision Transformer model outperforms other models. © 2023 IEEE.

Portfolio Transformer for Attention-Based Asset Allocation

Traditional approaches to financial asset allocation start with returns forecasting followed by an optimization stage that decides the optimal asset weights. Any errors made during the forecasting step reduce the accuracy of the asset weightings, and hence the profitability of the overall portfolio. The Portfolio Transformer (PT) network, introduced here, circumvents the need to predict asset returns and instead directly optimizes the Sharpe ratio, a risk-adjusted performance metric widely used in practice. The PT is a novel end-to-end portfolio optimization framework, inspired by the numerous successes of attention mechanisms in natural language processing. With its full encoder-decoder architecture, specialized time encoding layers, and gating components, the PT has a high capacity to learn long-term dependencies among portfolio assets and hence can adapt more quickly to changing market conditions such as the COVID-19 pandemic. To demonstrate its robustness, the PT is compared against other algorithms, including the current LSTM-based state of the art, on three different datasets, with results showing that it offers the best risk-adjusted performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Feature Adaptation Predictive Coding for Quantized Block Compressive Sensing of COVID-19 X-Ray Images

With the development of remote X-ray detection for Corona Virus Disease 2019 (COVID-19), the quantized block compressive sensing technology plays an important role when remotely acquiring the chest X-ray images of COVID-19 infected people and significantly promoting the portable telemedicine imaging applications. In order to improve the encoding performance of quantized block compressive sensing, a feature adaptation predictive coding (FAPC) method is proposed for the remote transmission of COVID-19 X-ray images. The proposed FAPC method can adaptively calculate the block-wise prediction coefficients according to the main features of COVID-19 X-ray images, and thus provide the optimal prediction candidate from the feature-guided candidate set. The proposed method can implement the high-efficiency encoding of X-ray images, and then swiftly transmit the telemedicine-oriented chest images. The experimental results show that compared with the state-of-the-art predictive coding methods, both rate-distortion and complexity performance of our FAPC method have enough competitive advantages. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Multi-party Secure Comparison of Strings Based on Outsourced Computation

Data is an important production factor in the era of digital economy. Privacy computing can ensure that data providers do not disclose sensitive data, carry out multi-party joint analysis and computation, securely and privately complete the full excavation of data value in the process of circulation, sharing, fusion, and calculation, which has become a popular research topic. String comparison is one of the common operations in data processing. To address the string comparison problem in multi-party scenarios, we propose an algorithm for secure string comparison based on outsourced computation. The algorithm encodes the strings with one hot encoding scheme and encrypts the encoded strings using an XOR homomorphic encryption scheme. The proposed algorithm achieves efficient and secure string comparison and counts the number of different characters with the help of a cloud-assisted server. The proposed scheme is implemented and verified using the new coronavirus gene sequence as the comparison string, and the performance is compared with that of a state-of-the-art security framework. Experiments show that the proposed algorithm can effectively improve the string comparison speed and obtain correct comparison results without compromising data privacy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Analysis of Government Policy Sentiment Regarding Vacation during the COVID-19 Pandemic Using the Bidirectional Encoder Representation from Transformers (BERT)

To address the COVID-19 situation in Indonesia, the Indonesian government has adopted a number of policies. One of them is a vacation-related policy. Government measures with regard to this vacation policy have produced a wide range of viewpoints in society, which have been extensively shared on social media, including YouTube. However, there has not been any computerized system developed to date that can assess people's social media reactions. Therefore, this paper provides a sentiment analysis application to this government policy by employing a bidirectional encoder representation from transformers (BERT) approach. The study method began with data collecting, data labeling, data preprocessing, BERT model training, and model evaluation. This study created a new dataset for this topic. The data were collected from the comments section of YouTube, and were categorized into three categories: positive, neutral, and negative. This research yielded an F-score of 84.33%. Another contribution from this study regards the methodology for processing sentiment analysis in Indonesian. In addition, the model was created as an application using the Python programming language and the Flask framework. The government can learn the extent to which the public accepts the policies that have been implemented by utilizing this research. © 2023 by the authors.

Medical Image Segmentation Based on Transformer and HarDNet Structures

Medical image segmentation is a crucial way to assist doctors in the accurate diagnosis of diseases. However, the accuracy of medical image segmentation needs further improvement due to the problems of many noisy medical images and the high similarity between background and target regions. The current mainstream image segmentation networks, such as TransUnet, have achieved accurate image segmentation. Still, the encoders of such segmentation networks do not consider the local connection between adjacent chunks and lack the interaction of inter-channel information during the upsampling of the decoder. To address the above problems, this paper proposed a dual-encoder image segmentation network, including HarDNet68 and Transformer branch, which can extract the local features and global feature information of the input image, allowing the segmentation network to learn more image information, thus improving the effectiveness and accuracy of medical segmentation. In this paper, to realize the fusion of image feature information of different dimensions in two stages of encoding and decoding, we propose a feature adaptation fusion module to fuse the channel information of multi-level features and realize the information interaction between channels, and then improve the segmentation network accuracy. The experimental results on CVC-ClinicDB, ETIS-Larib, and COVID-19 CT datasets show that the proposed model performs better in four evaluation metrics, Dice, Iou, Prec, and Sens, and achieves better segmentation results in both internal filling and edge prediction of medical images. Accurate medical image segmentation can assist doctors in making a critical diagnosis of cancerous regions in advance, ensure cancer patients receive timely targeted treatment, and improve their survival quality. © 2013 IEEE.

Hybrid Deep Model for Sentiment Analysis of COVID-19 Twitter Data

Sentiment analysis is a natural language processing technique used to analyse textual data generated on social media platforms like Facebook and Twitter. Ever since the Covid19 pandemic started many posts were shared on the social media platform as videos and messages with real-time updates about the spread of the pandemic across all countries. Several misconceptions led the public to panic in addition to the health deterioration created by the disease due to the false information spread through social media. This has paved the way for this research on the sentiment analysis of reviews posted on Twitter related to the spread of Covid-19 disease. The dataset used for the proposed work is taken from the IEEE data port which is an open access dataset platform. The Hybrid Deep Sentiment Analysis (HDSA) model which is a fusion of the deep learning algorithms is employed in this work to analyse the sentiments in Covid-19 tweets. Stacked Denoising autoencoders are used for feature extraction from the dataset. Bi-Convolutional neural networks and Bi-Long Short-Term Memory Networks are used to reduce the feature dimensionality and obtain the long-term dependencies in the extracted data. The classification of the sentiments is implemented using the GANBERT technique. The proposed model exhibited 94°/0 accuracy compared to the other state-of-the-art models in the research of Sentiment Analysis of Covid-19-related tweets. © 2022 IEEE.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth ( ∼ 100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos ('talking-head videos') to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users ( n=242 ) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git. © 1983-2012 IEEE.

Mask Detection for Covid-19 under Extreme Conditions

Mask detection has become a hot topic since the COVID-19 pandemic began in recent years. However, most scholars only focus on the speed and accuracy of detection, and fail to pay attention to the fact that mask detection is not suitable for people living under extreme conditions due to the degraded image quality. In this work, a denoising convolutional auto-encoder, a multitask cascaded convolutional networks (MTCNN) and a MobileNet were used to solve the problem of mask detection for COVID-19 under extreme environments. First of all, a network based on AlexNet is designed for the auto-encoder. This study found that the two-layer max pooling layers in AlexNet could not accurately extract image features but damage the quality of restored image. Therefore, they were deleted, and other parameters such as channel number were also modified to fit the new net, and finally trained using cosine distance. In addition, for MTCNN, this study changed the output condition of ONet from thresholding to maximum return, and lowered the thresholds of PNet and RNet to solve the problem that faces might not be found in low-quality images with mask and other covers. Furthermore, MobileNet was trained using categorical cross entropy loss function with adam optimizer. In the end, the accuracy of system for the photos captured under extreme conditions enhance from 50 % to 85% in test images. © 2022 IEEE.

Evaluation of Bag-of-Words Classifiers for COVID-19 Detection from Cough Recordings

The paper assesses the efficiency of bag-of-words classifiers for reliable detection of Covid-19 from cough recordings. The effect of using two distinct encoding strategies and variable codebook dimensions is evaluated in terms of Area Under Curve (AUC), accuracy, sensitivity, and specificity. Three distinct feature extraction procedures are tested, followed by a Support Vector Machine (SVM) classifier. Experiments conducted on two cough recordings datasets indicate that sparse encoding yields best performances, showing robustness against feature type and codebook dimension. © 2022 IEEE.

District Level Covid Case Prediction using LSTM Models

Covid-19 has had an adverse effect on the world, with more than 440 million cases recorded so far. The outbreak has hampered the country's healthcare and economy. This calls for an accurate prediction model for the prediction of Covid Cases, so that it gives some time to the hospitals and administration, to make the necessary arrangement. For population-dense countries like India, the covid case dynamics of every district is different, hence this requires a district-wise case prediction of Covid Cases. In this paper, we perform prediction of covid cases across all districts of India using different architectures of Long short-term memory (LSTM) and performed a comparative analysis between them. To the best of our knowledge, this is the first such attempt at the district level. Bidirectional LSTM encoder-decoder outperformed other LSTM-based models and, gave a test set MAPE of 15.44, followed by LSTM Encoder Decoder, giving a MAPE of 19.72. © 2022 IEEE.

MPSKT: Multi-head ProbSparse Self-Attention for Knowledge Tracing

Over the past two years, COVID-19 has led to a widespread rise in online education, and knowledge tracing has been used on various educational platforms. However, most existing knowledge tracing models still suffer from long-term dependence. To address this problem, we propose a Multi-head ProbSparse Self-Attention for Knowledge Tracing(MPSKT). Firstly, the temporal convolutional network is used to encode the position information of the input sequence. Then, the Multi-head ProbSparse Self-Attention in the encoder and decoder blocks is used to capture the relationship between the input sequences, and the convolution and pooling layers in the encoder block are used to shorten the length of the input sequence, which greatly reduces the time complexity of the model and better solves the problem of long-term dependence of the model. Finally, experimental results on three public online education datasets demonstrate the effectiveness of our proposed model. © 2022 Association for Computing Machinery.

Human Trajectory Completion with Transformers

With outbreak of the COVID-19 pandemic, contact tracing has become an important problem. It has been proven that maintaining social distance and isolating affected people are highly beneficial for curbing the spread of COVID-19, which all depend on identifying people's trajectories. However, the current interview-based approach is costly, and the existing mobile app-based schemes rely on complete and accurate data. In this paper, we propose a transformer encoder-based approach with spatial position embedding extracted using a graph Combinatorial Laplacian matrix to interpolate incomplete human trajectories. To model human trajectory, we propose a graphical embedded module to extract spatial features based on predefined location clusters. The incomplete trajectory sequences are first preprocessed into matrices and then used to train a deep transformer encoder network for trajectory completion. Our experiments using a real world Bluetooth Low Energy (BLE) dataset validate the efficacy of our proposed approach, which outperforms several baseline methods. © 2022 IEEE.

Enabling video conferencing in low bandwidth

Frequent disruption in network connectivity is a major challenge in offering good quality of experience to the users of smart mobile applications. Various apps like Zoom, Google Meet, Skype, etc. for online video calling have become indispensable overnight due to this new paradigm shift in home-bound remote work culture driven by the Covid19 pandemic. However, the performance of these apps is tightly bound to the current network conditions. Under limited network coverage and low bandwidth, the data frames suffer from delay, jitter, and loss resulting in degraded quality of experience for the users. In this paper, we propose a server-less peer-to-peer architecture for the video conferencing apps with in-built adaptive compression techniques. The proposed architecture enables video streaming at a very low data rate just to offer a smooth streaming experience under poor connectivity. Video is compressed by ASCII encoding on the basis of the contrast factor of each pixel in the frame. It has been observed that only 29 KBPS bandwidth is sufficient to conduct video conferencing. © 2022 IEEE.