Search results

The purpose of this paper is to describe a new approach to sentence representation learning leading to text classification using Bidirectional Encoder Representations from Transformers (BERT) embeddings. This work proposes a novel BERT-convolutional neural network (CNN)-based model for sentence representation learning and text classification. The proposed model can be used by industries that work in the area of classification of similarity scores between the texts and sentiments and opinion analysis.

The approach developed is based on the use of the BERT model to provide distinct features from its transformer encoder layers to the CNNs to achieve multi-layer feature fusion. To achieve multi-layer feature fusion, the distinct feature vectors of the last three layers of the BERT are passed to three separate CNN layers to generate a rich feature representation that can be used for extracting the keywords in the sentences. For sentence representation learning and text classification, the proposed model is trained and tested on the Stanford Sentiment Treebank-2 (SST-2) data set for sentiment analysis and the Quora Question Pair (QQP) data set for sentence classification. To obtain benchmark results, a selective training approach has been applied with the proposed model.

On the SST-2 data set, the proposed model achieved an accuracy of 92.90%, whereas, on the QQP data set, it achieved an accuracy of 91.51%. For other evaluation metrics such as precision, recall and F1 Score, the results obtained are overwhelming. The results with the proposed model are 1.17%–1.2% better as compared to the original BERT model on the SST-2 and QQP data sets.

The novelty of the proposed model lies in the multi-layer feature fusion between the last three layers of the BERT model with CNN layers and the selective training approach based on gated pruning to achieve benchmark results.

This work aims to present a deep learning model for face mask detection in surveillance environments such as automatic teller machines (ATMs), banks, etc. to identify persons wearing face masks. In surveillance environments, complete visibility of the face area is a guideline, and criminals and law offenders commit crimes by hiding their faces behind a face mask. The face mask detector model proposed in this work can be used as a tool and integrated with surveillance cameras in autonomous surveillance environments to identify and catch law offenders and criminals.

The proposed face mask detector is developed by integrating the residual network (ResNet)34 feature extractor on top of three You Only Look Once (YOLO) detection layers along with the usage of the spatial pyramid pooling (SPP) layer to extract a rich and dense feature map. Furthermore, at the training time, data augmentation operations such as Mosaic and MixUp have been applied to the feature extraction network so that it can get trained with images of varying complexities. The proposed detector is trained and tested over a custom face mask detection dataset consisting of 52,635 images. For validation, comparisons have been provided with the performance of YOLO v1, v2, tiny YOLO v1, v2, v3 and v4 and other benchmark work present in the literature by evaluating performance metrics such as precision, recall, F1 score, mean average precision (mAP) for the overall dataset and average precision (AP) for each class of the dataset.

The proposed face mask detector achieved 4.75–9.75 per cent higher detection accuracy in terms of mAP, 5–31 per cent higher AP for detection of faces with masks and, specifically, 2–30 per cent higher AP for detection of face masks on the face region as compared to the tested baseline variants of YOLO. Furthermore, the usage of the ResNet34 feature extractor and SPP layer in the proposed detection model reduced the training time and the detection time. The proposed face mask detection model can perform detection over an image in 0.45 s, which is 0.2–0.15 s lesser than that for other tested YOLO variants, thus making the proposed detection model perform detections at a higher speed.

The proposed face mask detector model can be utilized as a tool to detect persons with face masks who are a potential threat to the automatic surveillance environments such as ATMs, banks, airport security checks, etc. The other research implication of the proposed work is that it can be trained and tested for other object detection problems such as cancer detection in images, fish species detection, vehicle detection, etc.

The proposed face mask detector can be integrated with automatic surveillance systems and used as a tool to detect persons with face masks who are potential threats to ATMs, banks, etc. and in the present times of COVID-19 to detect if the people are following a COVID-appropriate behavior of wearing a face mask or not in the public areas.

The novelty of this work lies in the usage of the ResNet34 feature extractor with YOLO detection layers, which makes the proposed model a compact and powerful convolutional neural-network-based face mask detector model. Furthermore, the SPP layer has been applied to the ResNet34 feature extractor to make it able to extract a rich and dense feature map. The other novelty of the present work is the implementation of Mosaic and MixUp data augmentation in the training network that provided the feature extractor with 3× images of varying complexities and orientations and further aided in achieving higher detection accuracy. The proposed model is novel in terms of extracting rich features, performing augmentation at the training time and achieving high detection accuracy while maintaining the detection speed.

This paper aims to Solar photovoltaic (PV) power can significantly impact the power system because of its intermittent nature. Hence, an accurate solar PV power forecasting model is required for appropriate power system planning.

In this paper, a long short-term memory (LSTM)-based double deep Q-learning (DDQL) neural network (NN) is proposed for forecasting solar PV power indirectly over the long-term horizon. The past solar irradiance, temperature and wind speed are used for forecasting the solar PV power for a place using the proposed forecasting model.

The LSTM-based DDQL NN reduces over- and underestimation and avoids gradient vanishing. Thus, the proposed model improves the forecasting accuracy of solar PV power using deep learning techniques (DLTs). In addition, the proposed model requires less training time and forecasts solar PV power with improved stability.

The proposed model is trained and validated for several places with different climatic patterns and seasons. The proposed model is also tested for a place with a temperate climatic pattern by constructing an experimental solar PV system. The training, validation and testing results have confirmed the practicality of the proposed solar PV power forecasting model using LSTM-based DDQL NN.

The purpose of this study is to propose a performance measurement (PM) model for agricultural extension agents. Based on an interdisciplinary approach, management accounting-agricultural extension, the study has three main research objectives: highlight the main concepts to be embedded in a PM model for agricultural extension agents in an agricultural extension organization (RO1); identify main PM components of the proposed PM model for agricultural extension agents (RO2); and investigate empirically the causal relationships in the proposed PM model (RO3).

An interdisciplinary literature review and a proposed PM model for agricultural extension agents are presented (RO1 and RO2). An empirical survey is incorporated, carried out in early 2011 (RO3), to examine three groups, totaling around 274 respondents. Data were collected through personal interviews using structured questionnaire forms. Path analysis technique was applied.

The authors propose a PM model consisting of five components. The five components are: agricultural extension agents’ characteristics, agents’ work attitudes, services provided, use of agricultural extension services and farmers’ satisfaction with agricultural extension services. The overall findings of the empirical surveys were found to validate the suggested causal relations among the components of the model. Findings indicate that 85 per cent of changes in farmers’ satisfaction with services are explained by changes in the preceding variables in the model.

It is, however, important to view this study with a few limitations in mind; for instance, using a survey method (e.g. sampling and the use of questionnaires in data collection); and the constraints associated with the model. That is to say that the components of the model could be further increased to incorporate other aspects of stakeholders, e.g. the economic impact of governmental financial policies on tax and the customs duties on agricultural products.

A Food and Agriculture Organization of the United Nations agricultural extension reference manual recommends certain purposes for a PM in agricultural extension organizations; interestingly, all these are already embedded in the proposed PM model, which makes it unequivocally a useful PM model for agriculture extension agents in agricultural extension organizations worldwide. Furthermore, the proposed model contributes significantly to agricultural extension practitioners and academics alike. It focuses the attention of agricultural extension organizations on the causal relationships among the model’s components. These components are linked to the agricultural extension organization strategies.

In addition to the practical implications above, the proposed PM model demonstrates the need for placing equal importance on all five components included and setting performance indicator (PI) targets.

The importance of this study emerges from the fact that it is helpful to examine the development and implementation of PM models across various disciplines to enhance understanding. The PM model overcomes the shortcomings in previous PM models of agricultural extension agents’ criteria/models in the agricultural extension literature. It is not merely a theoretically proposed model because the proposed causal relations amongst its variables are empirically investigated. Following management accounting and strategy theories, the authors propose that the relative importance of the attributes of PI in the proposed model differs according to each agricultural extension organization’s strategy, size and organizational structure.

The purpose of this paper is to propose a comprehensive version of a hybrid autoregressive integrated moving average (ARIMA), and artificial neural networks (ANNs) in order to yield a more general and more accurate hybrid model for exchange rates forecasting. For this purpose, the Kalman filter technique is used in the proposed model to preprocess and detect the trend of raw data. It is basically done to reduce the existing noise in the underlying data and better modeling, respectively.

In this paper, ARIMA models are applied to construct a new hybrid model to overcome the above-mentioned limitations of ANNs and to yield a more general and more accurate model than traditional hybrid ARIMA and ANNs models. In our proposed model, a time series is considered as a function of a linear and nonlinear component, so, in the first phase, an ARIMA model is first used to identify and magnify the existing linear structures in data. In the second phase, a multilayer perceptron is used as a nonlinear neural network to model the preprocessed data, in which the existing linear structures are identified and magnified by ARIMA and to predict the future value of time series.

In this paper, a new Kalman filter based hybrid artificial neural network and ARIMA model are proposed as an alternate forecasting technique to the traditional hybrid ARIMA/ANNs models. In the proposed model, similar to the traditional hybrid ARIMA/ANNs models, the unique strengths of ARIMA and ANN in linear and nonlinear modeling are jointly used, aiming to capture different forms of relationship in the data; especially, in complex problems that have both linear and nonlinear correlation structures. However, there are no aforementioned assumptions in the modeling process of the proposed model. Therefore, in the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be generally guaranteed that the performance of the proposed model will not be worse than either of their components used separately. In addition, empirical results in both weekly and daily exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models.

In the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be guaranteed that the performance of the proposed model will not be worse than either of the components used separately. In addition, empirical results in exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models. Therefore, it can be used as an appropriate alternate model for forecasting in exchange ratemarkets, especially when higher forecasting accuracy is needed.

Object detection models have gained considerable popularity as they aid in lot of applications, like monitoring, video surveillance, etc. Object detection through the video tracking faces lot of challenges, as most of the videos obtained as the real time stream are affected due to the environmental factors.

This research develops a system for crowd tracking and crowd behaviour recognition using hybrid tracking model. The input for the proposed crowd tracking system is high density crowd videos containing hundreds of people. The first step is to detect human through visual recognition algorithms. Here, a priori knowledge of location point is given as input to visual recognition algorithm. The visual recognition algorithm identifies the human through the constraints defined within Minimum Bounding Rectangle (MBR). Then, the spatial tracking model based tracks the path of the human object movement in the video frame, and the tracking is carried out by extraction of color histogram and texture features. Also, the temporal tracking model is applied based on NARX neural network model, which is effectively utilized to detect the location of moving objects. Once the path of the person is tracked, the behaviour of every human object is identified using the Optimal Support Vector Machine which is newly developed by combing SVM and optimization algorithm, namely MBSO. The proposed MBSO algorithm is developed through the integration of the existing techniques, like BSA and MBO.

The dataset for the object tracking is utilized from Tracking in high crowd density dataset. The proposed OSVM classifier has attained improved performance with the values of 0.95 for accuracy.

This paper presents a hybrid high density video tracking model, and the behaviour recognition model. The proposed hybrid tracking model tracks the path of the object in the video through the temporal tracking and spatial tracking. The features train the proposed OSVM classifier based on the weights selected by the proposed MBSO algorithm. The proposed MBSO algorithm can be regarded as the modified version of the BSO algorithm.

In general, Indian Classical Music (ICM) is classified into two: Carnatic and Hindustani. Even though, both the music formats have a similar foundation, the way of presentation is varied in many manners. The fundamental components of ICM are raga and taala. Taala basically represents the rhythmic patterns or beats (Dandawate et al., 2015; Kirthika and Chattamvelli, 2012). Raga is determined from the flow of swaras (notes), which is denoted as the wider terminology. The raga is defined based on some vital factors such as swaras, aarohana-avarohna and typical phrases. Technically, the fundamental frequency is swara, which is definite through duration. Moreover, there are many other problems for automatic raga recognition model. Thus, in this work, raga is recognized without utilizing explicit note series information and necessary to adopt an efficient classification model.

This paper proposes an efficient raga identification system through which music of Carnatic genre can be effectively recognized. This paper also proposes an adaptive classifier based on NN in which the feature set is used for learning. The adaptive classifier exploits advanced metaheuristic-based learning algorithm to get the knowledge of the extracted feature set. Since the learning algorithm plays a crucial role in defining the precision of the raga recognition, this model prefers to use the GWO.

Through the performance analysis, it is witnessed that the accuracy of proposed model is 16.6% better than NN with LM, NN with GD and NN with FF respectively, 14.7% better than NN with PSO. Specificity measure of the proposed model is 19.6, 24.0, 13.5 and 17.5% superior to NN with LM, NN with GD, NN with FF and NN with PSO, respectively. NPV of the proposed model is 19.6, 24, 13.5 and 17.5% better than NN with LM, NN with GD, NN with FF and NN with PSO, respectively. Thus it has proven that the proposed model has provided the best result than other conventional classification methods.

This paper intends to propose an efficient raga identification system through which music of Carnatic genre can be effectively recognized. This paper also proposes an adaptive classifier based on NN.

Biometric identification system has become emerging research field because of its wide applications in the fields of security. This study (multimodal system) aims to find more applications than the unimodal system because of their high user acceptance value, better recognition accuracy and low-cost sensors. The biometric identification using the finger knuckle and the palmprint finds more application than other features because of its unique features.

The proposed model performs the user authentication through the extracted features from both the palmprint and the finger knuckle images. The two major processes in the proposed system are feature extraction and classification. The proposed model extracts the features from the palmprint and the finger knuckle with the proposed HE-Co-HOG model after the pre-processing. The proposed HE-Co-HOG model finds the Palmprint HE-Co-HOG vector and the finger knuckle HE-Co-HOG vector. These features from both the palmprint and the finger knuckle are combined with the optimal weight score from the fractional firefly (FFF) algorithm. The layered k-SVM classifier classifies each person's identity from the fused vector.

Two standard data sets with the palmprint and the finger knuckle images were used for the simulation. The simulation results were analyzed in two ways. In the first method, the bin sizes of the HE-Co-HOG vector were varied for the various training of the data set. In the second method, the performance of the proposed model was compared with the existing models for the different training size of the data set. From the simulation results, the proposed model has achieved a maximum accuracy of 0.95 and the lowest false acceptance rate and false rejection rate with a value of 0.1.

In this paper, the multimodal biometric recognition system based on the proposed HE-Co-HOG with the k-SVM and the FFF is developed. The proposed model uses the palmprint and the finger knuckle images as the biometrics. The development of the proposed HE-Co-HOG vector is done by modifying the Co-HOG with the holoentropy weights.

Chronic diseases are considered as one of the serious concerns and threats to public health across the globe. Diseases such as chronic diabetes mellitus (CDM), cardio vasculardisease (CVD) and chronic kidney disease (CKD) are major chronic diseases responsible for millions of death. Each of these diseases is considered as a risk factor for the other two diseases. Therefore, noteworthy attention is being paid to reduce the risk of these diseases. A gigantic amount of medical data is generated in digital form from smart healthcare appliances in the current era. Although numerous machine learning (ML) algorithms are proposed for the early prediction of chronic diseases, these algorithmic models are neither generalized nor adaptive when the model is imposed on new disease datasets. Hence, these algorithms have to process a huge amount of disease data iteratively until the model converges. This limitation may make it difficult for ML models to fit and produce imprecise results. A single algorithm may not yield accurate results. Nonetheless, an ensemble of classifiers built from multiple models, that works based on a voting principle has been successfully applied to solve many classification tasks. The purpose of this paper is to make early prediction of chronic diseases using hybrid generative regression based deep intelligence network (HGRDIN) model.

In the proposed paper generative regression (GR) model is used in combination with deep neural network (DNN) for the early prediction of chronic disease. The GR model will obtain prior knowledge about the labelled data by analyzing the correlation between features and class labels. Hence, the weight assignment process of DNN is influenced by the relationship between attributes rather than random assignment. The knowledge obtained through these processes is passed as input to the DNN network for further prediction. Since the inference about the input data instances is drawn at the DNN through the GR model, the model is named as hybrid generative regression-based deep intelligence network (HGRDIN).

The credibility of the implemented approach is rigorously validated using various parameters such as accuracy, precision, recall, F score and area under the curve (AUC) score. During the training phase, the proposed algorithm is constantly regularized using the elastic net regularization technique and also hyper-tuned using the various parameters such as momentum and learning rate to minimize the misprediction rate. The experimental results illustrate that the proposed approach predicted the chronic disease with a minimal error by avoiding the possible overfitting and local minima problems. The result obtained with the proposed approach is also compared with the various traditional approaches.

Usually, the diagnostic data are multi-dimension in nature where the performance of the ML algorithm will degrade due to the data overfitting, curse of dimensionality issues. The result obtained through the experiment has achieved an average accuracy of 95%. Hence, analysis can be made further to improve predictive accuracy by overcoming the curse of dimensionality issues.

The proposed ML model can mimic the behavior of the doctor's brain. These algorithms have the capability to replace clinical tasks. The accurate result obtained through the innovative algorithms can free the physician from the mundane care and practices so that the physician can focus more on the complex issues.

Utilizing the proposed predictive model at the decision-making level for the early prediction of the disease is considered as a promising change towards the healthcare sector. The global burden of chronic disease can be reduced at an exceptional level through these approaches.

In the proposed HGRDIN model, the concept of transfer learning approach is used where the knowledge acquired through the GR process is applied on DNN that identified the possible relationship between the dependent and independent feature variables by mapping the chronic data instances to its corresponding target class before it is being passed as input to the DNN network. Hence, the result of the experiments illustrated that the proposed approach obtained superior performance in terms of various validation parameters than the existing conventional techniques.

COVID-19 has occurred in more than 150 countries and causes a huge impact on the health of many people. The main purpose of this work is, COVID-19 has occurred in more than 150 countries and causes a huge impact on the health of many people. The COVID-19 diagnosis is required to detect at the beginning stage and special attention should be given to them. The fastest way to detect the COVID-19 infected patients is detecting through radiology and radiography images. The few early studies describe the particular abnormalities of the infected patients in the chest radiograms. Even though some of the challenges occur in concluding the viral infection traces in X-ray images, the convolutional neural network (CNN) can determine the patterns of data between the normal and infected X-rays that increase the detection rate. Therefore, the researchers are focusing on developing a deep learning-based detection model.

The main intention of this proposal is to develop the enhanced lung segmentation and classification of diagnosing the COVID-19. The main processes of the proposed model are image pre-processing, lung segmentation and deep classification. Initially, the image enhancement is performed by contrast enhancement and filtering approaches. Once the image is pre-processed, the optimal lung segmentation is done by the adaptive fuzzy-based region growing (AFRG) technique, in which the constant function for fusion is optimized by the modified deer hunting optimization algorithm (M-DHOA). Further, a well-performing deep learning algorithm termed adaptive CNN (A-CNN) is adopted for performing the classification, in which the hidden neurons are tuned by the proposed DHOA to enhance the detection accuracy. The simulation results illustrate that the proposed model has more possibilities to increase the COVID-19 testing methods on the publicly available data sets.

From the experimental analysis, the accuracy of the proposed M-DHOA–CNN was 5.84%, 5.23%, 6.25% and 8.33% superior to recurrent neural network, neural networks, support vector machine and K-nearest neighbor, respectively. Thus, the segmentation and classification performance of the developed COVID-19 diagnosis by AFRG and A-CNN has outperformed the existing techniques.

This paper adopts the latest optimization algorithm called M-DHOA to improve the performance of lung segmentation and classification in COVID-19 diagnosis using adaptive K-means with region growing fusion and A-CNN. To the best of the authors’ knowledge, this is the first work that uses M-DHOA for improved segmentation and classification steps for increasing the convergence rate of diagnosis.