A comparison of deep transfer learning backbone architecture techniques for printed text detection of different font styles from unstructured documents.

Object detection methods based on deep learning have been used in a variety of sectors including banking, healthcare, e-governance, and academia. In recent years, there has been a lot of attention paid to research endeavors made towards text detection and recognition from different scenesor images of unstructured document processing. The article's novelty lies in the detailed discussion and implementation of the various transfer learning-based different backbone architectures for printed text recognition. In this research article, the authors compared the ResNet50, ResNet50V2, ResNet152V2, Inception, Xception, and VGG19 backbone architectures with preprocessing techniques as data resizing, normalization, and noise removal on a standard OCR Kaggle dataset. Further, the top three backbone architectures selected based on the accuracy achieved and then hyper parameter tunning has been performed to achieve more accurate results. Xception performed well compared with the ResNet, Inception, VGG19, MobileNet architectures by achieving high evaluation scores with accuracy (98.90%) and min loss (0.19). As per existing research in this domain, until now, transfer learning-based backbone architectures that have been used on printed or handwritten data recognition are not well represented in literature. We split the total dataset into 80 percent for training and 20 percent for testing purpose and then into different backbone architecture models with the same number of epochs, and found that the Xception architecture achieved higher accuracy than the others. In addition, the ResNet50V2 model gave us higher accuracy (96.92%) than the ResNet152V2 model (96.34%).

Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort.

The quantification of carotid plaque has been routinely used to predict cardiovascular risk in cardiovascular disease (CVD) and coronary artery disease (CAD). To determine how well carotid plaque features predict the likelihood of CAD and cardiovascular (CV) events using deep learning (DL) and compare against the machine learning (ML) paradigm. The participants in this study consisted of 459 individuals who had undergone coronary angiography, contrast-enhanced ultrasonography, and focused carotid B-mode ultrasound. Each patient was tracked for thirty days. The measurements on these patients consisted of maximum plaque height (MPH), total plaque area (TPA), carotid intima-media thickness (cIMT), and intraplaque neovascularization (IPN). CAD risk and CV event stratification were performed by applying eight types of DL-based models. Univariate and multivariate analysis was also conducted to predict the most significant risk predictors. The DL's model effectiveness was evaluated by the area-under-the-curve measurement while the CV event prediction was evaluated using the Cox proportional hazard model (CPHM) and compared against the DL-based concordance index (c-index). IPN showed a substantial ability to predict CV events (p < 0.0001). The best DL system improved by 21% (0.929 vs. 0.762) over the best ML system. DL-based CV event prediction showed a ~ 17% increase in DL-based c-index compared to the CPHM (0.86 vs. 0.73). CAD and CV incidents were linked to IPN and carotid imaging characteristics. For survival analysis and CAD prediction, the DL-based system performs superior to ML-based models.

Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time-Frequency-Based Features and Deep Learning Models.

The milling machine serves an important role in manufacturing because of its versatility in machining. The cutting tool is a critical component of machining because it is responsible for machining accuracy and surface finishing, impacting industrial productivity. Monitoring the cutting tool's life is essential to avoid machining downtime caused due to tool wear. To prevent the unplanned downtime of the machine and to utilize the maximum life of the cutting tool, the accurate prediction of the remaining useful life (RUL) cutting tool is essential. Different artificial intelligence (AI) techniques estimate the RUL of cutting tools in milling operations with improved prediction accuracy. The IEEE NUAA Ideahouse dataset has been used in this paper for the RUL estimation of the milling cutter. The accuracy of the prediction is based on the quality of feature engineering performed on the unprocessed data. Feature extraction is a crucial phase in RUL prediction. In this work, the authors considers the time-frequency domain (TFD) features such as short-time Fourier-transform (STFT) and different wavelet transforms (WT) along with deep learning (DL) models such as long short-term memory (LSTM), different variants of LSTN, convolutional neural network (CNN), and hybrid models that are a combination of CCN with LSTM variants for RUL estimation. The TFD feature extraction with LSTM variants and hybrid models performs well for the milling cutting tool RUL estimation.

Adaptive variable sampling model for performance analysis in high cache-performance computing environments.

High-performance computing provides computing power for a variety of scientific disciplines, supporting advancements by offering insights beyond metacognition. Maximizing computing performance without wasting resources is a major research issue. Predicting the performance of a computer's next state is effective for scheduling. However, hardware performance monitors representing the computer's state require high expert knowledge, and there is no standardized model. In this paper, we propose an adaptive variable sampling model for performance analysis in high-performance computing environments. Our method automatically classifies the optimal variables from numerous variables related to performance prediction and predicts performance using the sampled variables. The optimal variables for performance analysis do not require expert knowledge during the sampling process. We conducted experiments in various architectures and applications to validate this method. This model performed at least 24.25% and up to 58.75% faster without any loss in accuracy.

Synergy of climate change with country success and city quality of life.

Most people around the world have felt the effects of climate change on their quality of life. This study sought to achieve the maximum efficiency for climate change actions with the minimum negative impact on the well-being of countries and cities. The Climate Change and Country Success (C3S) and Climate Change and Cities' Quality of Life (C3QL) models and maps of the world created as part of this research showed that as economic, social, political, cultural, and environmental metrics of countries and cities improve, so do their climate change indicators. For the 14 climate change indicators, the C3S and C3QL models indicated 68.8% average dispersion dimensions in the case of countries and 52.8% in the case of cities. Our research showed that increases in the success of 169 countries saw improvements in 9 climate change indicators out of the 12 considered. Improvements in country success indicators were accompanied by a 71% improvement in climate change metrics.

Enhancing the Breast Histopathology Image Analysis for Cancer Detection Using Variational Autoencoder.

A breast tissue biopsy is performed to identify the nature of a tumour, as it can be either cancerous or benign. The first implementations involved the use of machine learning algorithms. Random Forest and Support Vector Machine (SVM) were used to classify the input histopathological images into whether they were cancerous or non-cancerous. The implementations continued to provide promising results, and then Artificial Neural Networks (ANNs) were applied for this purpose. We propose an approach for reconstructing the images using a Variational Autoencoder (VAE) and the Denoising Variational Autoencoder (DVAE) and then use a Convolutional Neural Network (CNN) model. Afterwards, we predicted whether the input image was cancerous or non-cancerous. Our implementation provides predictions with 73% accuracy, which is greater than the results produced by our custom-built CNN on our dataset. The proposed architecture will prove to be a new field of research and a new area to be explored in the field of computer vision using CNN and Generative Modelling since it incorporates reconstructions of the original input images and provides predictions on them thereafter.

Intra-graph and Inter-graph joint information propagation network with third-order text graph tensor for fake news detection.

Although the Internet and social media provide people with a range of opportunities and benefits in a variety of ways, the proliferation of fake news has negatively affected society and individuals. Many efforts have been invested to detect the fake news. However, to learn the representation of fake news by context information, it has brought many challenges for fake news detection due to the feature sparsity and ineffectively capturing the non-consecutive and long-range context. In this paper, we have proposed Intra-graph and Inter-graph Joint Information Propagation Network (abbreviated as IIJIPN) with Third-order Text Graph Tensor for fake news detection. Specifically, data augmentation is firstly utilized to solve the data imbalance and strengthen the small corpus. In the stage of feature extraction, Third-order Text Graph Tensor with sequential, syntactic, and semantic features is proposed to describe contextual information at different language properties. After constructing the text graphs for each text feature, Intra-graph and Inter-graph Joint Information Propagation is used for encoding the text: intra-graph information propagation is performed in each graph to realize homogeneous information interaction, and high-order homogeneous information interaction in each graph can be achieved by stacking propagation layer; inter-graph information propagation is performed among text graphs to realize heterogeneous information interaction by connecting the nodes across the graphs. Finally, news representations are generated by attention mechanism consisting of graph-level attention and node-level attention mechanism, and then news representations are fed into a fake news classifier. The experimental results on four public datasets indicate that our model has outperformed state-of-the-art methods. Our source code is available at https://github.com/cuibenkuan/IIJIPN.

Segmentation on remote sensing imagery for atmospheric air pollution using divergent differential evolution algorithm.

Air pollution is a global issue causing major health hazards. By proper monitoring of air quality, actions can be taken to control air pollution. Satellite remote sensing is an effective way to monitor global atmosphere. Various sensors and instruments fitted to satellites and airplanes are used to obtain the radar images. These images are quite complex with various wavelength differentiated by very close color differences. Clustering of such images based on its wavelengths can provide the much-needed relief in better understanding of these complex images. Such task related to image segmentation is a universal optimization issue that can be resolved with evolutionary techniques. Differential Evolution (DE) is a fairly fast and operative parallel search algorithm. Though classical DE algorithm is popular, there is a need for varying the mutation strategy for enhancing the performance for varied applications. Several alternatives of classical DE are considered by altering the trial vector and control parameter. In this work, a new alteration of DE technique labeled as DiDE (Divergent Differential Evolution Algorithm) is anticipated. The outcomes of this algorithm were tested and verified with the traditional DE techniques using fifteen benchmark functions. The new variant DiDE exhibited much superior outcomes compared to traditional approaches. The novel approach was then applied on remote sensing imagery collected form TEMIS, a web based service for atmospheric satellite images and the image was segmented. Fuzzy Tsallis entropy method of multi-level thresholding technique is applied over DiDE to develop image segmentation. The outcomes obtained were related with the segmented results using traditional DE and the outcome attained was found to be improved profoundly. Experimental results illustrate that by acquainting DiDE in multilevel thresholding, the computational delay was greatly condensed and the image quality was significantly improved.

A novel nonlinear time-varying sigmoid transfer function in binary whale optimization algorithm for descriptors selection in drug classification.

In computational chemistry, the high-dimensional molecular descriptors contribute to the curse of dimensionality issue. Binary whale optimization algorithm (BWOA) is a recently proposed metaheuristic optimization algorithm that has been efficiently applied in feature selection. The main contribution of this paper is a new version of the nonlinear time-varying Sigmoid transfer function to improve the exploitation and exploration activities in the standard whale optimization algorithm (WOA). A new BWOA algorithm, namely BWOA-3, is introduced to solve the descriptors selection problem, which becomes the second contribution. To validate BWOA-3 performance, a high-dimensional drug dataset is employed. The proficiency of the proposed BWOA-3 and the comparative optimization algorithms are measured based on convergence speed, the length of the selected feature subset, and classification performance (accuracy, specificity, sensitivity, and f-measure). In addition, statistical significance tests are also conducted using the Friedman test and Wilcoxon signed-rank test. The comparative optimization algorithms include two BWOA variants, binary bat algorithm (BBA), binary gray wolf algorithm (BGWOA), and binary manta-ray foraging algorithm (BMRFO). As the final contribution, from all experiments, this study has successfully revealed the superiority of BWOA-3 in solving the descriptors selection problem and improving the Amphetamine-type Stimulants (ATS) drug classification performance.

A Review on State-of-the-Art Techniques for Image Segmentation and Classification for Brain MR Images.

The diagnosis of tumors in the initial stage plays a crucial role in improving the clinical outcomes of a patient. Evaluation of brain tumors from many MRI images generated regularly in a clinical environment is a complex and time-consuming process. Therefore,there comes a need for an efficient and accurate model for the early detection of tumors. This paper revolves around the current strategies used for brain tumor segmentation and classification from MRI images of the brain. This approach also tries to pave the way for the significance of their performance measure and quantitative evaluation of forefront strategies. This state of the art clearly describes the importance of several brain image segmentation and classification methodsduring the past 13 years of publication by various researchers. In this instance, new calculations are being made for potential clients to analyze the concerned area of research. This review acknowledges the key accomplishments expressed in the diagnostic measures and their success indicators of qualitative and quantitative measurement. This research study also explores the key outcomes and reasons for finding the lessons learned.

DC-CNN: Dual-channel Convolutional Neural Networks with attention-pooling for fake news detection.

Fake news detection mainly relies on the extraction of article content features with neural networks. However, it has brought some challenges to reduce the noisy data and redundant features, and learn the long-distance dependencies. To solve the above problems, Dual-channel Convolutional Neural Networks with Attention-pooling for Fake News Detection (abbreviated as DC-CNN) is proposed. This model benefits from Skip-Gram and Fasttext. It can effectively reduce noisy data and improve the learning ability of the model for non-derived words. A parallel dual-channel pooling layer was proposed to replace the traditional CNN pooling layer in DC-CNN. The Max-pooling layer, as one of the channels, maintains the advantages in learning local information between adjacent words. The Attention-pooling layer with multi-head attention mechanism serves as another pooling channel to enhance the learning of context semantics and global dependencies. This model benefits from the learning advantages of the two channels and solves the problem that pooling layer is easy to lose local-global feature correlation. This model is tested on two different COVID-19 fake news datasets, and the experimental results show that our model has the optimal performance in dealing with noisy data and balancing the correlation between local features and global features.

The Functional Outcome of Limb Salvage of Proximal Femur Tumors With Modular Endoprosthesis: A Prospective Study.

Introduction The proximal femur is a common site for primary bone sarcomas, including Ewing's sarcoma, chondrosarcoma, osteosarcoma, and giant cell tumors (GCT). Extensive resections are challenging to reconstruct because the size of the tumor may necessitate an extensive resection of the femur to achieve adequate oncologic clearance. The resection of the proximal femur can result in hip joint instability due to the loss of the strong native hip capsule or hip abductor strength. With a wide range of reconstruction options, such as resection arthrodesis, allograft-prosthetic composite (APC), and endoprosthesis, we can achieve limb salvage with good functional outcomes. Objective The objective of this case series is to evaluate the clinical outcomes and complications associated with endoprosthesis replacement in patients with proximal femur tumors. Methods A prospective analysis was conducted with 32 patients who underwent modular endoprosthesis replacement for proximal femoral tumors at our institution. Patient data, tumor characteristics, surgical details, and postoperative outcomes were collected and analyzed. Results The study involved 32 patients who met the inclusion criteria. They were assessed using the Musculoskeletal Tumor Society Score (MSTS), which showed good functional outcomes in 72.84% of the patients. The study highlights the functional outcomes and potential complications associated with the use of modular prostheses. Conclusion Endoprosthesis replacement in proximal femur tumors is a viable treatment option, providing good functional outcomes and an acceptable method for limb salvage, which enhances the quality of life.

Fault Detection in Induction Motor Using Time Domain and Spectral Imaging-Based Transfer Learning Approach on Vibration Data.

The induction motor plays a vital role in industrial drive systems due to its robustness and easy maintenance but at the same time, it suffers electrical faults, mainly rotor faults such as broken rotor bars. Early shortcoming identification is needed to lessen support expenses and hinder high costs by using failure detection frameworks that give features extraction and pattern grouping of the issue to distinguish the failure in an induction motor using classification models. In this paper, the open-source dataset of the rotor with the broken bars in a three-phase induction motor available on the IEEE data port is used for fault classification. The study aims at fault identification under various loading conditions on the rotor of an induction motor by performing time, frequency, and time-frequency domain feature extraction. The extracted features are provided to the models to classify between the healthy and faulty rotors. The extracted features from the time and frequency domain give an accuracy of up to 87.52% and 88.58%, respectively, using the Random-Forest (RF) model. Whereas, in time-frequency, the Short Time Fourier Transform (STFT) based spectrograms provide reasonably high accuracy, around 97.67%, using a Convolutional Neural Network (CNN) based fine-tuned transfer learning framework for diagnosing induction motor rotor bar severity under various loading conditions.

A Review of AI Cloud and Edge Sensors, Methods, and Applications for the Recognition of Emotional, Affective and Physiological States.

Affective, emotional, and physiological states (AFFECT) detection and recognition by capturing human signals is a fast-growing area, which has been applied across numerous domains. The research aim is to review publications on how techniques that use brain and biometric sensors can be used for AFFECT recognition, consolidate the findings, provide a rationale for the current methods, compare the effectiveness of existing methods, and quantify how likely they are to address the issues/challenges in the field. In efforts to achieve the key goals of Society 5.0, Industry 5.0, and human-centered design better, the recognition of emotional, affective, and physiological states is progressively becoming an important matter and offers tremendous growth of knowledge and progress in these and other related fields. In this research, a review of AFFECT recognition brain and biometric sensors, methods, and applications was performed, based on Plutchik's wheel of emotions. Due to the immense variety of existing sensors and sensing systems, this study aimed to provide an analysis of the available sensors that can be used to define human AFFECT, and to classify them based on the type of sensing area and their efficiency in real implementations. Based on statistical and multiple criteria analysis across 169 nations, our outcomes introduce a connection between a nation's success, its number of Web of Science articles published, and its frequency of citation on AFFECT recognition. The principal conclusions present how this research contributes to the big picture in the field under analysis and explore forthcoming study trends.

Kids' Emotion Recognition Using Various Deep-Learning Models with Explainable AI.

Human ideas and sentiments are mirrored in facial expressions. They give the spectator a plethora of social cues, such as the viewer's focus of attention, intention, motivation, and mood, which can help develop better interactive solutions in online platforms. This could be helpful for children while teaching them, which could help in cultivating a better interactive connect between teachers and students, since there is an increasing trend toward the online education platform due to the COVID-19 pandemic. To solve this, the authors proposed kids' emotion recognition based on visual cues in this research with a justified reasoning model of explainable AI. The authors used two datasets to work on this problem; the first is the LIRIS Children Spontaneous Facial Expression Video Database, and the second is an author-created novel dataset of emotions displayed by children aged 7 to 10. The authors identified that the LIRIS dataset has achieved only 75% accuracy, and no study has worked further on this dataset in which the authors have achieved the highest accuracy of 89.31% and, in the authors' dataset, an accuracy of 90.98%. The authors also realized that the face construction of children and adults is different, and the way children show emotions is very different and does not always follow the same way of facial expression for a specific emotion as compared with adults. Hence, the authors used 3D 468 landmark points and created two separate versions of the dataset from the original selected datasets, which are LIRIS-Mesh and Authors-Mesh. In total, all four types of datasets were used, namely LIRIS, the authors' dataset, LIRIS-Mesh, and Authors-Mesh, and a comparative analysis was performed by using seven different CNN models. The authors not only compared all dataset types used on different CNN models but also explained for every type of CNN used on every specific dataset type how test images are perceived by the deep-learning models by using explainable artificial intelligence (XAI), which helps in localizing features contributing to particular emotions. The authors used three methods of XAI, namely Grad-CAM, Grad-CAM++, and SoftGrad, which help users further establish the appropriate reason for emotion detection by knowing the contribution of its features in it.

A novel minimum generalized cross entropy-based multilevel segmentation technique for the brain MRI/dermoscopic images.

BACKGROUND: One of the challenging and the primary stages of medical image examination is the identification of the source of any disease, which may be the aberrant damage or change in tissue or organ caused by infections, injury, and a variety of other factors. Any such condition related to skin or brain sometimes advances in cancer and becomes a life-threatening disease. So, an efficient automatic image segmentation approach is required at the initial stage of medical image analysis. PURPOSE: To make a segmentation process efficient and reliable, it is essential to use an appropriate objective function and an efficient optimization algorithm to produce optimal results. METHOD: The above problem is resolved in this paper by introducing a new minimum generalized cross entropy (MGCE) as an objective function, with the inclusion of the degree of divergence. Another key contribution is the development of a new optimizer called opposition African vulture optimization algorithm (OAVOA). The proposed optimizer boosted the exploration, skill by inheriting the opposition-based learning. THE RESULTS: The experimental work in this study starts with a performance evaluation of the optimizer over a set of standards (23 numbers) and IEEE CEC14 (8 numbers) Benchmark functions. The comparative analysis of test results shows that the OAVOA outperforms different state-of-the-art optimizers. The suggested OAVOA-MGCE based multilevel thresholding approach is carried out on two different types of medical images - Brain MRI Images (AANLIB dataset), and dermoscopic images (ISIC 2016 dataset) and found superior than other entropy-based thresholding methods.

A possibilistic-robust-fuzzy programming model for designing a game theory based blood supply chain network.

This paper presents a bi-level blood supply chain network under uncertainty during the COVID-19 pandemic outbreak using a Stackelberg game theory technique. A new two-phase bi-level mixed-integer linear programming model is developed in which the total costs are minimized and the utility of donors is maximized. To cope with the uncertain nature of some of the input parameters, a novel mixed possibilistic-robust-fuzzy programming approach is developed. The data from a real case study is utilized to show the applicability and efficiency of the proposed model. Finally, some sensitivity analyses are performed on the important parameters and some managerial insights are suggested.

Test Case Prioritization, Selection, and Reduction Using Improved Quantum-Behaved Particle Swarm Optimization.

The emerging areas of IoT and sensor networks bring lots of software applications on a daily basis. To keep up with the ever-changing expectations of clients and the competitive market, the software must be updated. The changes may cause unintended consequences, necessitating retesting, i.e., regression testing, before being released. The efficiency and efficacy of regression testing techniques can be improved with the use of optimization approaches. This paper proposes an improved quantum-behaved particle swarm optimization approach for regression testing. The algorithm is improved by employing a fix-up mechanism to perform perturbation for the combinatorial TCP problem. Second, the dynamic contraction-expansion coefficient is used to accelerate the convergence. It is followed by an adaptive test case selection strategy to choose the modification-revealing test cases. Finally, the superfluous test cases are removed. Furthermore, the algorithm's robustness is analyzed for fault as well as statement coverage. The empirical results reveal that the proposed algorithm performs better than the Genetic Algorithm, Bat Algorithm, Grey Wolf Optimization, Particle Swarm Optimization and its variants for prioritizing test cases. The findings show that inclusivity, test selection percentage and cost reduction percentages are higher in the case of fault coverage compared to statement coverage but at the cost of high fault detection loss (approx. 7%) at the test case reduction stage.

A new humanitarian relief logistic network for multi-objective optimization under stochastic programming.

Millions of affected people and thousands of victims are consequences of earthquakes, every year. Therefore, it is necessary to prepare a proper preparedness and response planning. The objectives of this paper are i) minimizing the expected value of the total costs of relief supply chain, ii) minimizing the maximum number of unsatisfied demands for relief staff and iii) minimizing the total probability of unsuccessful evacuation in routes. In this paper, a scenario based stochastic multi-objective location-allocation-routing model is proposed for a real humanitarian relief logistics problem which focused on both pre- and post-disaster situations in presence of uncertainty. To cope with demand uncertainty, a simulation approach is used. The proposed model integrates these two phases simultaneously. Then, both strategic and operational decisions (pre-disaster and post-disaster), fairness in the evacuation, and relief item distribution including commodities and relief workers, victim evacuation including injured people, corpses and homeless people are also considered simultaneously in this paper. The presented model is solved utilizing the Epsilon-constraint method for small- and medium-scale problems and using three metaheuristic algorithms for the large-scale problem (case study). Empirical results illustrate that the model can be used to locate the shelters and relief distribution centers, determine appropriate routes and allocate resources in uncertain and real-life disaster situations.