Search

Thousands of papers are published at conferences every year. Conference organizers manually assign accepted papers to the sessions according to the title and keywords given by the author. Then organizer names each session, based on his/her experience. These are complex and time-consuming processes and often fail to collect papers on a similar topic in content. This often causes the participant to exit the session after listening to the presentation of one or two papers, because the session name does not fully represent the papers in the session and the papers in the session are not close in content. As a solution to these problems, this paper proposes a method for automatically organizing conference sessions. The method first introduces a network created with a deep learning-based document similarity. Then, sessions are determined with a community discovery method specific to this network, and finally, session titles are extracted with a topic modeling approach. To the best of our knowledge, this paper is the first effort in this direction. Experiments conducted on sessions of three real conferences show that the proposed method is able to create up to 21% better similar sessions, and session names better represent the papers in that session. [ABSTRACT FROM AUTHOR]

Chinese paper-cutting, as an ancient folk art, is facing difficulties in preserving and passing down its traditions due to a lack of skilled paper-cut artists. In contrast to other image generation tasks, paper-cut images not only necessitate symmetry and exaggeration but also demand a certain level of resemblance to human facial features. To address these issues, this paper proposes a dual-branch generative adversarial network model for automatically generating paper-cut images, referred to as CutGAN. Specifically, we first construct a paper-cut dataset consisting of 891 pairs of facial images and handcrafted paper-cut images to train and evaluate CutGAN. Next, during the pre-training phase, we utilize gender and eyeglasses recognition tasks to train the fixed encoder. In the fine-tuning phase, we design a flexible encoder based on the modified U-net structure without skip connections. Furthermore, we introduce an average face loss to augment the diversity and improve the quality of the generated paper-cut images. We conducted extensive qualitative and quantitative experiments, as well as ablation experiments, comparing CutGAN with state-of-the-art baseline models on the test set. The experimental results indicate that CutGAN outperforms other image translation models by generating paper-cut images that more accurately capture the essence of Chinese paper-cut art and closely resemble actual facial images. [ABSTRACT FROM AUTHOR]

Because huge amount of scientific papers have been published at an accelerating rate, it is beneficial to do intelligent paper classification, especially fine-grained classification. However, existing natural language processing techniques are mostly coarse-grained. Some characteristics of fine-grained scientific paper classification needs special attention. One is that the number of data may well be quite limited. Number of papers in the lower level sub-fields inevitably becomes less. Meanwhile, emerging sub-fields with new discoveries will have few papers, nevertheless these sub-fields can be important. Furthermore, fine-grained labeling of scientific papers requires high expertise and is time consuming. Another aspect of scientific papers is that they contain multi-modal information. To address the above two issues, we propose a multi-modal hierarchical fusion network (MHFNet) for fine-grained paper classification. We treat paper abstract features, image features, and paper title features as three modalities. The MobileNetV2 model and the ALBERT model are combined in the proposed model to encode multi-modal information. Comparison results with baseline methods on both sufficiently large datasets and number-limited datasets show improvements, even more on number-limited datasets. [ABSTRACT FROM AUTHOR]

Medical images are important records to improve people's health care, and their security has become an important issue when they are transmitted through various media especially print and scan equipments. This paper proposes a digital watermarking method for medical images based on live QR code, DWT-SVD, Hough transform and bilinear interpolation. A live QR code including private information was embedded into the SVD blocks of LL3sub-band wavelet of medical image. Adjusting the embedding strength, a trade-off between invisibility and robustness was achieved. We printed and scanned the watermarked medical image with common printers and scanners and get the watermarked images after print-scanning. In extraction method, the Hough transform was used to detect the edge of the watermarked medical image and calculate the rotation angle and scaling ratio, and bilinear interpolation was used to correct geometric distortion of watermarked image. Then we extracted live QR code from corrected image successfully. Experimental results indicated that the proposed method provides sufficient security for medical images against print and scan attacks. [ABSTRACT FROM AUTHOR]

In recent years, human activity recognition (HAR) has been widely used in medical rehabilitation, smart home and other fields. Currently, the recognition performance highly depends on feature extraction and effective algorithm. On the one hand, traditional manual feature extraction and classification algorithms hinder the improvement of HAR. On the other hand, the latest deep learning technology can automatically process data and extract features, but it faces the problems of poor feature quality and information loss. In order to solve this problem, this paper proposes a new recognition method using only wearable sensor data. In the feature extraction stage, the axis information of each sensor is extracted separately into one-dimensional data, and information of all axes is integrated into a two-dimensional graph. Then, two deep convolutional neural network models are designed to train the features based on one-dimensional data and two-dimensional graph respectively. Finally, weighted voting method is used to get the classification results. Experiments have shown that the average recognition accuracy of the method in this paper is about 3% higher than that of other HAR deep neural network methods, which shown the advantage of the method in this paper in obtaining better recognition result with limited data. [ABSTRACT FROM AUTHOR]

Computer vision is one of the artificial intelligence's most challenging fields, enabling computers to interpret, analyse and derive meaningful information from the visual world. There are various utilizations of computer vision algorithms, and most of them, from simpler to more complicated, have an object and shape recognition in common. Traditional pen and paper tests are designed in a pre-established format and consist of numerous basic shapes, which designate the important parts of the test itself. With that in mind, many computer vision applications regarding pen and paper tests arise as an opportunity. Massive courses and large schooling organizations mostly conduct their exams in paper format and assess them manually, which imposes a significant burden on the teaching staff. Any kind of automatization that will facilitate the grading process is highly desirable. Hence, an automated answer recognition system in assessment was developed to mitigate the problems above. The system uses images of scanned test pages obtained from the test scanning process and performs the necessary image manipulation steps to increase target recognition accuracy. Further, it manages to identify regions of interest containing multiple-choice questions and contours. Finally, the system verifies obtained results using the knowledge of the whereabouts of the test template regions of interest. [ABSTRACT FROM AUTHOR]

In the field of medical image recognition, industrial defect detection and other fields, because it is impossible to extract the edge of the color image directly, the recognition effect is poor. In order to extract the edge of the color image directly and retain the color information of the edge. This paper proposes a color image edge extraction method called function series. In this paper, the template threshold denoising method is used to denoise the input image. Then the key features of the input image are enhanced by using the image key feature enhancement function proposed in this paper. Then use the function series to extract the color features of the H, S, I space of the input image. The extracted color features are decomposed by eigenvalue decomposition, and the color information with larger eigenvalue is retained to enhance the color information of the edge. Finally, the edge of the target image with color information is obtained by the inverse transformation of the function series. The experimental results show that the correct edge recognition rate of this method is 92.09%. Moreover, this method can accurately extract the contour of the color image, and the color information is preserved completely. Compared with other methods, the correct recognition rate of this method is higher than that of the comparison method and can retain more abundant color information. The method proposed in this paper provides a new extraction method for color image edge extraction, which has certain practical value. [ABSTRACT FROM AUTHOR]

Federated learning(FL) is a popular distributed machine learning framework which can protect users' private data from being exposed to adversaries. However, related work shows that sensitive private information can still be compromised by analyzing parameters uploaded by clients. Applying differential privacy to federated learning has been a popular privacy-preserving way to achieve strict privacy guarantees in recent years. To reduce the impact of noise, this paper proposes to apply local differential privacy(LDP) to federated learning. We propose a gradient compression federated learning framework based on adaptive local differential privacy budget allocation(GFL-ALDPA). We propose a novel adaptive privacy budget allocation scheme based on communication rounds to reduce the loss of privacy budget and the amount of model noise. It can maximize the limited privacy budget and improve the model accuracy by assigning different privacy budgets to different communication rounds during training. Furthermore, we also propose a gradient compression mechanism based on dimension reduction, which can reduce the communication cost, overall noise size, and loss of the total privacy budget of the model simultaneously to ensure accuracy under a specific privacy-preserving guarantee. Finally, this paper presents the experimental evaluation on the MINIST dataset. Theoretical analysis and experiments demonstrate that our framework can achieve a better trade-off between privacy preservation, communication efficiency, and model accuracy. [ABSTRACT FROM AUTHOR]

This paper focuses on source camera model identification technology in the field of digital image forensics. The research goal is to identify the source camera model, and researchers generally use the algorithm design of convolutional neural networks combined with noise residuals. However, traditional features such as noise residuals are easily polluted by noise and compression, which substantially affects the classification accuracy of source camera model identification algorithms for traditional features. Based on existing source camera model identification methods, this paper proposes the use of color correction features as the basic features of source camera model identification for the first time and proposes a new algorithm for source camera model identification based on image color correction features. A convolutional neural network is utilized to extract image color correction features and identify and classify source camera models. This paper has carried out experimental verification on a large-scale dataset, and the source camera model recognition accuracy of the proposed method in this paper can reach 97.23%; the recognition accuracy under compression conditions has reached 91.28%. The experimental results show that the image color correction feature is better than the source camera model in terms of recognition and has great research and application potential in the field of recognition. Additionally, the proposed algorithm is highly robust even after image compression and pollution, outperforming other methods under both original image conditions and compressed image conditions. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) has gained much attention since sensor technology has become more advanced and cost-effective. HAR is a process of identifying the daily living activities of an individual with the help of an efficient learning algorithm and prospective user-generated datasets. This paper addresses the technical advancement and classification of HAR systems in detail. Design issues, future opportunities, recent state-of-the-art related works, and a generic framework for activity recognition are discussed in a comprehensive manner with analytical discussion. Different publicly available datasets with their features and incorporated sensors are also descr-processing techniques with various performance metrics like - Accuracy, F1-score, Precision, Recall, Computational times and evaluation schemes are discussed for the comprehensive understanding of the Activity Recognition Chain (ARC). Different learning algorithms are exploited and compared for learning-based performance comparison. For each specific module of this paper, a compendious number of references is also cited for easy referencing. The main aim of this study is to give the readers an easy hands-on implementation in the field of HAR with verifiable evidence of different design issues. [ABSTRACT FROM AUTHOR]

Although paper shredding is widely used to prevent confidential papers from being misused, still it cannot be considered a convenient process. The size of paper shreds became smaller and smaller, as new methods of shredded paper reassembly and reconstruction are evolving. This paper focuses on clustering, which is a possible phase in the assembly process. This work considers real strip-cut shreds, in addition to images shredded by a simulator in one direction to make strip-cut shreds of different sizes, from wide to narrow shreds, and images shredded in two directions, possibly reflecting cross-cut and micro-cut shreds. K-means is used to cluster shreds, the features tested are gray-level ranges, and the well-known gray-level co-occurrence matrix, invariant moments, segmentation-based fractal texture analysis algorithm, and color moments. The number of shreds grouped in the same cluster with originally adjacent neighbors is used to indicate clustering effectiveness, in addition to the overall accuracy of strip-cut shreds clustering. When the number of clusters is 5, and the k-means experiments run 100 times for 38 images, the overall accuracy of gray-level ranges in simulated strip-cut shreds is 84.87, 89.27, and 93.5 percent in the three different sizes tested, also in cross-cut and micro-cut shreds, gray-level ranges achieve a relatively high number of shreds with 3 and 4 originally adjacent neighbors found in the same cluster. [ABSTRACT FROM AUTHOR]

Crowd counting from a single image is a challenging task due to perspective distortion and large-scale variation in crowd scenes. Many Researches only focus on local features to create density maps which is not effective in handing the challenges. This paper proposes a novel network named global-to-local adaptive spatial encoder network, which focuses on global features to generate a total structure density map of the population distribution, and then utilizes local features to reconstruct the total structure density map in detail to generate high-quality density map. To capture global features, local information and correlate them, we design a contextual module using different kernels with convolution and transposed convolution. To create a density map from global structure to local detail, two branches are designed, the global distribution branch and the local detail branch. The former aims to capture the population distribution region of interest in terms of global structure, and the latter aims to focus on the local details of each unit. Furthermore, to overcome the problem of pixel-wise loss of MSE, this paper proposes an efficient loss function that focuses on perceiving the possible crowd distribution over the whole image. We also apply a new upsampling mechanism that learns to create high-quality density maps on its own is advisable. The proposed network can capture the characteristics of pedestrian distribution and predict accurate results. It is evaluated on four crowd counting datasets (ShanghaiTech, NWPU, UCF_QNRF, UCF_CC_50), it obtains MAE of 67.1 and MSE, and achieves 108.8 in ShanghaiTech and gets MAE of 139.2 and the best MSE of 217.7 in UCF_CC_50 dataset and so on, and our method shows state-of-the-art on all the datasets. [ABSTRACT FROM AUTHOR]

Authors, editors, and reviewers need to have a good perception regarding the quality of a manuscript in order to improve their skills, save effort, and prevent errors that can affect the submission procedure. In this paper, we compared the author's perception of a manuscript's quality with the manuscript's actual impact. In addition, we analyzed the uncertainty of the author's perception of the manuscript's quality. From there, we defined 'partition' as the author's ability to perceive the actual quality. We did this by launching a website for the use of the scientific community. This webpage provided a tool to help improve an investigator's skill in understanding and recognizing the quality of a manuscript so as to help researchers improve and maximize their works' potential impact. We carried out the experiment with 106 experienced users who tested our webpage. We found that the Abstract, the Title, and the Keywords were enough to perform a substantially decent evaluation of a manuscript. Most of the researchers were able to determine the quality of a paper in less than a minute from this small amount of information. [ABSTRACT FROM AUTHOR]

Paper folding-and-punching tests are used to measure spatial abilities in humans. This paper presents a qualitative model for paper folding (QPF) and a computer game (Paper Folding Game) developed to apply and show the reasoning capabilities of the QPF model. This interactive game presents paper-folding activities intended to help users train and understand how to fold a paper to get a specific shape. Then, it presents paper-folding-and-punching tests to the players. The Paper Folding Game can automatically generate paper-folding-and-punching questions with varying degrees of difficulty depending on the number of folds and holes made, thus producing additional levels for training. The reasoning mechanisms in the QPF model are used by the Paper Folding Game to infer the right answer to each paper-folding-and-punching question. This reasoning capability allows the game to provide feedback to the players when they are wrong and also to create other plausible answers automatically, so that random question-answers are shown to the players in the master-mode. The Paper Folding Game has been implemented using Unity engine and it is available to download from GooglePlay and AppleStore for everyone to train their spatial reasoning skills. [ABSTRACT FROM AUTHOR]

With the rapid development of globalization, the demand for translation between different languages is also increasing. Although pre-training has achieved excellent results in neural machine translation, the existing neural machine translation has almost no high-quality suitable for specific fields. Alignment information, so this paper proposes a pre-training neural machine translation with alignment information via optimal transport. First, this paper narrows the representation gap between different languages by using OTAP to generate domain-specific data for information alignment, and learns richer semantic information. Secondly, this paper proposes a lightweight model DR-Reformer, which uses Reformer as the backbone network, adds Dropout layers and Reduction layers, reduces model parameters without losing accuracy, and improves computational efficiency. Experiments on the Chinese and English datasets of AI Challenger 2018 and WMT-17 show that the proposed algorithm has better performance than existing algorithms. [ABSTRACT FROM AUTHOR]

Social media sites are now quite popular among internet users for sharing news and opinions. This has become possible due to the inexpensive Internet, easy availability of digital devices, and the no-cost policy to create a user account on social media platforms. People are fascinated by social media sites because they can easily connect with others to share their interests, news, and opinions. According to studies, someone who lacks credibility is more likely to spread false information in order to achieve goals of any kind, be it influencing political opinions, earning attention, or making money. The automatic detection of social media related fake news has thus emerged as a highly anticipated research area in recent years. This paper offers a comprehensive review of the automatic detection of fake news on social media platforms. It contains details of the key models or techniques related to machine/deep learning proposed (or developed) during the period of the year 2011 to the year 2022 along with the performance metrics of each model or technique. The paper discusses (a). the key challenges faced during the development of an effective and efficient fake news detection system, (b). some popular datasets for carrying out fake news detection related research, and (c). the major research gaps, and future research directions in the area of automatic fake news detection on social media. [ABSTRACT FROM AUTHOR]

Image Captioning is the process of generating textual descriptions of given images. It encompasses two major fields of deep learning, computer vision, and natural language processing. This paper presents an Image Captioning model which uses the Convolution Neural Network (CNN) model for feature extraction and a transformer architecture for the generation of sequences from these feature vectors. For feature extraction, this paper uses different CNN architectures like Xception, InceptionV3, ResNet50V2, VGG19, DenseNet201, ResNet152V2, EfficientNetV2B3, EfficientNetV2B0. The proposed method takes advantage of the transformer model for faster processing, and Beam search is implemented to get the top N most probable sequences for each image. The architecture is trained on Flickr8k dataset and the model outperforms the existing methods. The proposed model achieves a BLEU_4 score of 0.2184 on the Flickr8k dataset. [ABSTRACT FROM AUTHOR]

Numerous authors have presented the blockchain in their literature as a disruptive combustion engine with the potential to transform organizations and technology in the current digital economy, with features like validation of transactions, safeguarding of entries, preservation of records, immutability, decentralization, consensus, and faster settlement. However, literature on scientific production and collaboration through bibliometric and network analysis is still lacking. Based on the data extracted from the Web of Science from 2014-2020 with 6790 records, the emerging trends and collaboration patterns of blockchain technology are studied with the use of bibliometrics and network analysis. The study asserts (i) the impact of open-access publication on the growth and visibility of literature, (ii) the collaboration patterns and it's impact on team size, (iii) the ranking of countries based on their national and international collaboration, and (iv) thematic analysis of literature. The results show growth in the literature since 2017, and open-access publications have received more citations. Very few authors are actively working in the field, as only 73.7% of authors have published a single paper on the blockchain. China published the highest number of papers, followed by the United States of America and the United Kingdom. Singapore published a large number of papers with international collaboration and Russia with national collaboration, whereas the USA showed a balance between national and international publications. Finally, thematic analysis figured out the five key themes as supply chain management, smart contract, security, distributed ledger technology, and internet of things in contrast to the blockchain. Hence, this study investigates scientific productions by means of open-access publications, collaboration patterns, ranking, and key areas in blockchain literature. [ABSTRACT FROM AUTHOR]

In recent years, the field of security requirements specification by formal methods has changed radically. The security requirement specification is now one of the widely recognized as well as actively pursued research challenges in both requirement engineering and security engineering communities. In this paper, we focus on the research metadata to find the state of the art in the field of security requirements specification using the formal approach. In order, a review was taken up to perform metadata, obtained from frequently used databases. In total, 200 publications were retrieved; out of which 110 were found to be relevant to our research questions. The results of metadata provided an insight into the main contributions of the field, research gaps, and challenges, which motivated the discussion for important research direction in the future. [ABSTRACT FROM AUTHOR]

Even though temporal information matters for the quality of video saliency detection, many problems still arise/emerge in present network frameworks, such as bad performance in time-space coherence and edge continuity. In order to solve these problems, this paper proposes a full convolutional neural network, which integrates temporal differential and pixel gradient to fine tune the edges of salient targets. Considering the features of neighboring frames are highly relevant because of their proximity in location, a co-attention mechanism is used to put pixel-wise weight on the saliency probability map after features extraction with multi-scale pooling so that attention can be paid on both the edge and central of images. And the changes of pixel gradients of original images are used to recursively improve the continuity of target edges and details of central areas. In addition, residual networks are utilized to integrate information between modules, ensuring stable connections between the backbone network and modules and propagation of pixel gradient changes. In addition, a self-adjustment strategy for loss functions is presented to solve the problem of overfitting in experiments. The method presented in the paper has been tested with three available public datasets and its effectiveness has been proved after comparing with 6 other typically stat-of-the-art methods. [ABSTRACT FROM AUTHOR]

For the problem of blurred images in the process of UAV video inspection of oil and gas pipelines, a PSO-2D-VMD-BD denoising algorithm is proposed in this paper. The procedure of the developed algorithm is that: (1) the particle swarm optimization (PSO) is used to optimize K and α of the two-dimensional variational modal decomposition (2D-VMD); (2) use the 2D-VMD to decompose the oil and gas pipelines image into K intrinsic mode functions (IMFs); (3) use the Bhattacharyy Distance (BD) and the probability density function (PDF) to distinguish the signal-dominant IMFs (S-D IMFs) and the noise-dominant IMFs (N-D IMFs), and then use the wavelet threshold denoising method to eliminate the noise in the N-D IMFs; and (4) finally, the oil and gas pipelines image is reconstructed using the denoised N-D IMFs and S-D IMFs to obtain the denoised image. Compared to median filtering, wavelet threshold filtering, the Rudin Osher Fatemi (ROF), the 2D-VMD-BD, and the PSO-2D-VMD-KLD, theoretical analysis and simulation results indicate that the solution presented in this paper achieved a decent denoising effect, which can provide a solid foundation for the subsequent recognition of oil and gas pipelines by UAV inspection. [ABSTRACT FROM AUTHOR]

Blockchain, the mechanism that powers the Bitcoin cryptocurrency, is seen to be both enticing and essential for providing improved security and privacy for a variety of applications in many different fields, including the Internet of Things (IoT) ecosystem. Blockchain has therefore been viewed as a potential technology for IoT since it offers important answers for the digital currency that can handle issues with high maintenance costs, trust and security, and other issues. However, as far as we are aware, no thorough bibliometric analysis has been done in this area. Therefore, this paper has performed a bibliometric analysis of digital currency based on blockchain-enabled IoT between 2015 and 2022 by 1332 articles selected. The Web of Science (WoS), one of the most esteemed databases, served as the study's primary data source. Besides, a network of country collaboration and a network of co-occurrences for co-word analysis was created using the VOSviewer tool. The results showed that the number of cryptocurrencies and cryptocurrency publications on the blockchain had been enhanced quickly since 2018. Computer science, engineering, telecommunications, commerce, economics, medicine, agriculture, and law were among the areas studied in the blockchain domain. Furthermore, China has surpassed the United States as the leading country in terms of total publications and financing for related-topic research. Regarding the total number of citations, 2016 is the most influential, and IEEE Access is the most significant and prolific journal in the number of citations and publications. [ABSTRACT FROM AUTHOR]

This paper focuses on the adverse impact of outlier points and the ambiguity of candidate localizations in 3D object detection in terms of point cloud dataset. First, outlier points can disperse real feature extracting and mislead object detection, we propose an outlier weakening strategy. The neighborhood points of each point in the point set can be established via multi-directional search algorithm, and the correlations among points in the neighborhood are figured out via self-attention mechanism, then each point representation can be enhanced with the key information from its neighborhood, thus the negative impact of outlier points will be weakened due to obtaining real knowledge of object from neighborhood context. Second, multiple proposed boxes for object localization usually containing the same sampling points, this causes vagueness in differing them from each other and leads to incorrect object positioning. This paper proposes a voxel coding strategy with adaptive pooling, the candidate boxes are divided into voxels, and each voxel is further divided into multiple columns, then they are weighted and aggregated according to the importance of each column, thus can pop out the most confident spatial voxel encodings as reliable object localization nominees. This algorithm achieves an average accuracy of 82.98% and 93.2% on the KITTI dataset Car category and ModelNet40 dataset, respectively. [ABSTRACT FROM AUTHOR]

Accurate segmentation of rectal tumor lesion regions can provide an essential basis for clinical treatment and prognosis monitoring of tumors. However, there are many problems in the rectal tumor segmentation task at present: the lack of high-quality datasets; the mainstream segmentation network cannot complete the high-precision segmentation task of rectal tumors. In this paper, we investigate image enhancement and segmentation algorithms for convolutional neural networks and construct a rectal tumor MRI dataset by improving the CycleGAN network and loss function to achieve domain migration and reconstruction of rectal tumor CT and MRI images, given the small amount of rectal tumor image data and the existence of different modalities and regimes in CT and MRI. For the rectal tumor segmentation problem, a novel segmentation network DCMSG-UNet was designed based on the U-Net network. this network uses dilated convolution and multi-headed self-attention mechanisms to improve the base feature extraction module of the segmentation network, adds a decoder path, and uses the GAM hybrid attention mechanism to amplify the dimensional interaction features of the additional decoder path. Comparison experiments with six network models, DeepLabV3+, U-Net, UNet++, UNet3+, TransUNet, and Swin-Unet, show that the segmented region obtained from the DCMSG-UNet model proposed in this paper is closer to the real tumor region, with a DICE metric of 0.8416 and a Hausdorff distance of 11.3229, which can effectively segment the tumor. The experimental results show that our proposed method performs significantly better than the above methods, with a DICE metrics improvement of about 6%. To visualize the segmentation results, this paper designed a rectal tumor MRI image segmentation system based on PyQt5 to realize human-computer interaction and assist doctors in clinical diagnosis. [ABSTRACT FROM AUTHOR]

The swift growth of diverse editing software has resulted in image splicing manipulation becoming more complex, the discovery of a meticulously crafted splice forgery in digital images poses a significant challenge for both humans and machines. Existing image splicing manipulation detection algorithms have low localization accuracy and poor detection of small manipulation areas. In this paper, we proposed an end-to-end effective image manipulation location method based on a multi-scale and dual-channel model, MD_Unet. First, a dual-channel encoding network model is constructed. Adding a high-pass filtering branch containing SRM filters and Gabor filters at the input of the model and helps it to learn the manipulation traces of the image. Secondly, the dual-channel features are fused using an improved multi-scale pyramid pooling module. Then, Squeeze-Excitation is introduced to recalibrate the fused features so that the network pays more attention to splicing manipulation-related features. Finally, the fused feature map is input to the decoder, and the predicted image is decoded layer by layer to segment the manipulation region. We have performed extensive experimental validation and powerfully demonstrate the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

Processing is a popular graphical library and IDE developed for electronic art and visual design communities, with a strong focus on teaching art, design, and creative technologies students computer programming fundamentals in a visual context. Processing provides a collection of special commands to draw, animate, and handle user input using Java. Users can enable Python Mode (also called Processing.py) for Processing in the IDE interface. This leverages Jython, a Java implementation of Python, to interface with Processing's Java core, providing a way to write Processing code using Python syntax. This paper proposes that combining Processing and Python provides an ideal development environment for teaching creative programming fundamentals. Several new Processing-Python tools have emerged, but no attempts to integrate one of the most promising, the py5 library created by Jim Schmitz, into a Processing-like-IDE experience. py5 offers features not available with Jython, such as compatibility with Python 3 and support for CPython libraries. This paper presents a new coding environment, thonny-py5mode, developed as a software plugin for the Thonny IDE, which brings a convenient, beginner-friendly setup like that of Processing's Python Mode to users working with py5. [ABSTRACT FROM AUTHOR]

The degree of students' attentiveness in the classroom is known as learning attention and is the main indicator used to portray students' learning status in the classroom. Studying smart classroom time-series image data and analyzing students' attention to learning are important tools for improving student learning effects. To this end, this paper proposes a learning attention analysis algorithm based on the head pose sight estimation.The algorithm first employs multi-scale hourglass attention to enable the head pose estimation model to capture more spatial pose features.It is also proposed that the multi-classification multi-regression losses guide the model to learn different granularity of pose features, making the model more sensitive to subtle inter-class distinction of the data;Second, a sight estimation algorithm on 3D space is innovatively adopted to compute the coordinates of the student's sight landing point through the head pose; Finally, a model of sight analysis over the duration of a knowledge point is constructed to characterize students' attention to learning. Experiments show that the algorithm in this paper can effectively reduce the head pose estimation error, accurately characterize students' learning attention, and provide strong technical support for the analysis of students' learning effect. The algorithm demonstrates its potential application value and can be deployed in smart classrooms in schools. [ABSTRACT FROM AUTHOR]

According to World Health Organization (WHO), it is estimated that approximately 50 million people have Epilepsy worldwide. 10 million people are effected in India by Epilepsy hardly very few come out with the disorder and undertake proper treatment rest risk their life without recognition of disease. Epilepsy is a chronic disease of the brain which is non-communicable. An epileptic seizure is the second most commonly occurring neurological disorder of the brain. It can be detected using Electroencephalography (EEG) signals, an effective diagnostic tool used to study brain anatomy. Technological advancements and modernization of analytical tools have improved the scope of validation and decision-making. It is important to predict and evaluate epilepsy in its initial stages to avoid the risk and complication. This review paper focuses on the methodology, techniques, and dataset used from different sources to classify and categorize epileptic seizures. The paper includes a detailed review of dataset sources, challenges, and ways forward in understanding epileptic seizures for futuristic learning and decision making. It also concentrates on the comparison of machine learning and deep learning methodology used with different datasets. [ABSTRACT FROM AUTHOR]

Manifold learning is a widely adopted nonlinear dimensionality reduction technique employed to discover low-dimensional representations from high-dimensional data and to explore the intrinsic data structure. It encompasses a range of nonlinear techniques, including Isomap, Local Linear Embedding (LLE), Local Tangent Space Alignment (LTSA), and Multidimensional Scaling (MDS), among others. Isomap, as a popular method in manifold learning, has exhibited promising results. However, it encounters several challenges, such as the Topological Stability Problem, Shortest Path Distance, and noise sensitivity, which compromise its accuracy and elevate its computational demands. This survey paper presents three novel existing approaches to address these challenges and enhance the performance of Isomap. Firstly, the FastIsomap method, an existing approach that combines state-of-the-art algorithms like the KD tree and NN-descent to increase graph accuracy while reducing computational cost. Secondly, the FastIsomapVis method, also an existing technique, employs a hierarchical divide-and-conquer strategy employing the KD tree and Dijkstra Buckets Double, which enhances accuracy and reduces computational time in Isomap. Lastly, the NR-Isomap method, another existing approach, used the Local Tangent Space Alignment algorithm to remove noise sensitivity and short-circuit edge problems. The existing methods improve the accuracy of Isomap but also streamline its computational requirements. Furthermore, this survey paper discusses the open issues and future research directions for Isomap and manifold learning methods. It can be a valuable resource for researchers seeking insights across diverse domains. [ABSTRACT FROM AUTHOR]

A commonly used method in image enhancement is Contrast-Limited Adaptive Histogram Equalization, which is simple and fast. However, this algorithm is to segment the image into multiple rectangular areas, and then perform the image processing, this method works poorly when working on images with poor radial contrast, prone to local image information loss, and the characteristics of the whole image information are of poor quality after being processed. In this paper, we proposed a histogram equalization method of radial ring segmentation image, aiming at the image enhancement processing of less obvious radial contrast. Compared with the classical HE and CLAHE algorithms, the algorithm proposed in this paper can effectively enhance the information entropy of the processed images by an average of 12%. As a result, the images carry more information and exhibit richer texture features. Moreover, the contrast enhancement effect is improved, and the brightness of the images is more moderate. [ABSTRACT FROM AUTHOR]

In this paper, we present the first version of Study's system, a system that modernizes learning to spell based on dictation for elementary school children. Study's system configuration is composed of an ISKN Repaper tablet connected to a computer with a screen. The ISKN Repaper tablet allows children to write on an ordinary paper attached to the tablet slate using an ordinary pen. Study's system uses handwriting recognition HTR models on three stages to recognize children handwriting and localize different spelling errors. Study's system is based on dictation academic method; it enables better learning for children, where they receive feedback at moments of adequate concentration. Furthermore, Study's system allows teachers to gain a better understanding of children, track their learning progression more effectively, and adapt to their profiles more efficiently. [ABSTRACT FROM AUTHOR]

Recently, the Honey Badger Algorithm (HBA) was proposed as a metaheuristic algorithm. Honey badger hunting behaviour inspired the development of this algorithm. In the exploitation phase, HBA performs poorly and stagnates at the local best solution. On the other hand, the sand cat swarm optimization (SCSO) is a very competitive algorithm compared to other common metaheuristic algorithms since it has outstanding performance in the exploitation phase. Hence, the purpose of this paper is to hybridize HBA with SCSO so that the SCSO can overcome deficiencies of the HBA to improve the quality of the solution. The SCSO can effectively exploit optimal solutions. For the research conducted in this paper, a hybrid metaheuristic algorithm called HBASCSO was developed. The proposed approach was evaluated against challenging CEC benchmark instances taken from CEC2015, CEC2017, and CEC2019 benchmark suites The HBASCSO is also evaluated concerning the original HBA, SCSO, as well as several other recently proposed algorithms. To demonstrate that the proposed method performs significantly better than other competitive algorithms, 30 independent runs of each algorithm were evaluated to determine the best, worst, mean, and standard deviation of fitness functions. In addition, the Wilcoxon rank-sum test is used as a non-parametric comparison, and it has been found that the proposed algorithm outperforms other algorithms. Hence, the HBASCSO achieves an optimum solution that is better than the original algorithms. [ABSTRACT FROM AUTHOR]

Sound Event Detection (SED) plays a significant role in the present research, implemented in several areas such as Computer Science, Healthcare, Environmental Science, Security and Surveillance, etc. With the advancement of technology, SED can be deployed to mimic the human auditory system. In this paper, we have undertaken a Systematic Literature Review focused on sound event detection, presenting a comprehensive and well-structured analysis and in-depth discussions. This review is based on the authors' extensive knowledge and expertise in the field, and it compares various algorithms employed for sound event detection. The primary objective of this study is to offer valuable insights into datasets, feature extraction techniques, and execution models commonly used in SED, along with an examination of their corresponding accuracy, challenges, and limitations. Furthermore, the paper delves into identifying potential trends within the field, offering forward-looking information that can be invaluable for future research and development efforts in sound event detection. This systematic review aims to contribute to the continued advancement of SED technologies and applications by synthesizing existing knowledge and identifying emerging directions. It provides a foundation for researchers, practitioners, and stakeholders to make informed decisions and explore new possibilities within this evolving domain. [ABSTRACT FROM AUTHOR]

With the development of computing technology, the storage space and computing power of IoT devices have developed rapidly. Due to the social nature of people, users who have social relationships with each other IoT devices are relatively close in some time periods, but are far away from traditional edge nodes. It is far away, so service providers can temporarily rent suitable IoT devices to act as edge storage nodes based on the storage computing power and social status of user equipment. In the process of selecting edge nodes by service providers, this paper firstly describes the social relationships of users to which the edge nodes belong and some requirements for storage. Then, based on the above considerations, a method based on social and The edge node selection algorithm of equipment storage, and the subsequent modeling of the problem of service providers' selection of edge nodes as the problem of maximizing social benefits, through the use of matching algorithms, proves that the algorithm proposed in this paper can effectively select edge nodes, and subsequent simulation experiments The experimental results also show that the proposed algorithm can maximize the social benefits of service providers and users. [ABSTRACT FROM AUTHOR]

Contrast enhancement is a crucial aspect of image processing, as it improves visual quality by adjusting the brightness and contrast of an image. This paper comprehensively explores contrast enhancement techniques, classified into three categories: Image Processing (IP) based methods Deep Learning (DL) based approaches, and Generative Adversarial Network (GAN) methods. The paper also details various quality evaluation methods for enhanced images and compares different algorithms. The performance of the presented algorithms is evaluated using metrics such as Structural Similarity Index Measurement (SSIM), Absolute Mean Brightness Error (AMBE), Average Information Content (AIC), Contrast Improvement Index (CII), Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Universal Quality Index (UQI), and Color Enhancement Factor (CEF). The comparative analysis aims to provide insights into improving image quality, information content and error production within each category, facilitating informed decision-making in selecting contrast enhancement techniques for diverse applications. [ABSTRACT FROM AUTHOR]

In recent years, Internet traffic patterns have been changing. Most of the traffic demand by end users is multimedia, in particular, video streaming accounts for over 53%. This demand has led to improved network infrastructures and computing architectures to meet the challenges of delivering these multimedia services while maintaining an adequate quality of experience. Focusing on the preparation and adequacy of multimedia content for broadcasting, Cloud and Edge Computing infrastructures have been and will be crucial to offer high and ultra-high definition multimedia content in live, real-time, or video-on-demand scenarios. For these reasons, this review paper presents a detailed study of research papers related to encoding and transcoding techniques in cloud computing environments. It begins by discussing the evolution of streaming and the importance of the encoding process, with a focus on the latest streaming methods and codecs. Then, it examines the role of cloud systems in multimedia environments and provides details on the cloud infrastructure for media scenarios. After doing a systematic literature review, we have been able to find 49 valid papers that meet the requirements specified in the research questions. Each paper has been analyzed and classified according to several criteria, besides to inspect their relevance. To conclude this review, we have identified and elaborated on several challenges and open research issues associated with the development of video codecs optimized for diverse factors within both cloud and edge architectures. Additionally, we have discussed emerging challenges in designing new cloud/edge architectures aimed at more efficient delivery of media traffic. This involves investigating ways to improve the overall performance, reliability, and resource utilization of architectures that support the transmission of multimedia content over both cloud and edge computing environments ensuring a good quality of experience for the final user. [ABSTRACT FROM AUTHOR]

Fingerprint liveness detection systems have been affected by spoofing, which is a severe threat for fingerprint-based biometric systems. Therefore, it is crucial to develop some techniques to distinguish the fake fingerprints from the real ones. The software based techniques can detect the fingerprint forgery automatically. Also, the scheme shall be resistant against various distortions such as noise contamination, pixel missing and block missing, so that the forgers cannot deceive the detector by adding some distortions to the faked fingerprint. In this paper, we propose a fingerprint forgery detection algorithm based on a suggested adaptive thresholding pattern. The anisotropic diffusion of the input image is passed through three levels of the wavelet transform. The coefficients of different layers are adaptively thresholded and concatenated to produce the feature vector which is classified using the SVM classifier. Another contribution of the paper is to investigate the effect of various distortions such as pixel missing, block missing, and noise contamination. Our suggested approach includes a novel method that exhibits improved resistance against a range of distortions caused by environmental phenomena or manipulations by malicious users. In quantitative comparisons, our proposed method outperforms its counterparts by approximately 8% and 5% in accuracy for missing pixel scenarios of 90% and block missing scenarios of size 70 × 70 , respectively. This highlights the novelty approach in addressing such challenges. [ABSTRACT FROM AUTHOR]

Multi-period portfolio optimization (MPO) is one of the most important problems to be solved to help investors select optimal portfolios for investment plans. The portfolios are influenced by the risk factors in the market and it is important to select optimal portfolios that can maximize the returns with minimum risk values. Other than the risk factor, there are several other influential factors that reduce the optimality of the portfolios. Therefore, by considering all possible constraints, this study proposes a multi-constraint MPO model that selects the optimal portfolio based on the asset returns. To solve the multi-constrained problem, a novel quantum-inspired whale optimization algorithm (QWOA) is introduced in this paper. The proposed algorithm enhances the traditional optimization model to work in a multi-constrained scenario. Here, quantum entanglement is adapted to reduce the slow convergence issue of whale optimization. Apart from considering only the risk factors, this paper also considers certain higher-order moments (HOM), such as skewness, kurtosis, transaction cost, diversification, boundary and budget constraints. These factors affect the portfolios as the market is dynamic, and timely changes are always seen. Thus, optimizing the mentioned factors aids in attaining an optimal portfolio. Empirical evaluations are performed, and the results suggested that the proposed model provided beneficial outcomes as compared with other algorithms like whale optimization algorithm (WOA), gray wolf optimization (GWO), fruitfly optimization algorithm (FOA), particle swarm optimization (PSO) and fruitfly algorithm (FA). The overall net return rate of the proposed model is always above 0.85% for different values of upper bounds, and the obtained Sharpe ratio, Sortino ratio, STARR ratio, information ratio, Shannon entropy, and downside deviation values of the proposed algorithm are 5.016254, 0.89327, − 0.01987, 0.103826, 3.04452 and 0.2854. Hence, the proposed approach is highly effective for optimizing the constrained MPO. [ABSTRACT FROM AUTHOR]

Leaf diseases are hazardous to the yield and quality of food crops. There are many deep learning algorithms developed for their detection that may require large computational resources to train a single model with voluminous amounts of data. In the agriculture domain, various plant diseases are found across the country. Accumulating such a huge dataset from various regions is a tedious task, and training them with a single model can also be challenging. This paper proposes Federated Deep Learning (FDL) for Plant Leaf Disease Detection. This concept allows multiple local models to get trained with their region-based datasets and share their knowledge with siblings through the parent, instead of sharing complete datasets. Knowledge transfer significantly reduces the computational costs. This paper formulates the federated dataset using PlantVillage, to simulate the configuration of the FDL. A lightweight and efficient Hierarchical Convolutional Neural Network (H-CNN) is proposed for parent model and child models with 0.09 million parameters and 0.35MB model size. The simulation results show that the proposed FDL attains 93% testing accuracy, outperforming state-of-the-art methods namely, FedAdam and FedAvg with 86.8% and 87.7% respectively. In addition to this, the proposed FDL achieves 95.7%, 95.4% and 95.3% of weighted precision, weighted recall and weighted F1-score respectively for first local model and 92.1%, 90.8% and 91.2% respectively of weighted precision, weighted recall and weighted F1-score respectively for second local model. [ABSTRACT FROM AUTHOR]

The electrical activity of the brain can be monitored using the electroencephalogram (EEG), which can be used in the detection of seizures. This paper proposes an epileptic seizure detection algorithm that uses inter-intra Head-body-tail (HBT) features. Initially, the EEG signals are subdivided into non-overlapping frames. From each frame, three regions namely head (H), body (B), and tail (T) are constructed. Intra features named intra-correlative features are extracted within a frame while the inter-HBT features namely magnitude change and zero crossing feature are extracted between adjacent HBT frames. This paper also proposes a complementary convolutional neural network (CP-CNN) which uses two parallel sections of a traditional 1 D -CNN network. The complementary CNN is proposed to preserve the components that are eliminated by the traditional 1 D -CNN network in the feature extraction process. The evaluation of the proposed seizure detection algorithm was done with the evaluation metrics namely accuracy, sensitivity, F1-score, and specificity with the datasets namely CHB-MIT EEG dataset where the recordings were done from 22 subjects, and the Siena EEG dataset where the recordings were performed from 14 subjects. The proposed seizure detection provides an accuracy, sensitivity, F1-score, and Specificity of 98.17 % , 94.21 % , 95.79 % , and 98.25 % respectively for the CHB-MIT dataset. For the Siena-EEG dataset the accuracy, sensitivity, F1-score, and specificity were estimated as 98.76 % , 94.15 , 95.14%, and 98.77 % respectively. [ABSTRACT FROM AUTHOR]

With the rapid development of big data technology, electronic documents are more and more widely used. Aiming at the characteristics of large amount of data, complex format and non-standard information data of electronic documents, this paper uses data mining technology to realize the correlation construction between documents. Firstly, on the basis of dynamic incremental association rules, according to the characteristics of electronic document business, the association rules are improved. Secondly, the advantages of Boolean matrix operation, original data association rules and frequent 2-item set are used to improve the acquisition ability of the system for frequent items of document features. The experimental results show: that algorithm in this paper has higher computational efficiency in the process of file increment change and deletion change, and is suitable for electronic file processing in the case of big data. [ABSTRACT FROM AUTHOR]

The world population is growing very fast and the lifestyle of human beings is changing with time and place. So, there is a need for disease management which includes disease diagnosis, its detection and classification, cure and lastly for future disease prevention. The outermost protective layer of a human body is the skin. Skin not only impacts a person's health but also psychologically impacts one's life. Computer-aided systems are very helpful in skin disease detection and classification and their application is growing rapidly in healthcare. This literature review paper aims to help the researchers to get a synthesized and appropriate information for the same. We have included papers from 2021 to 2023 for the review from the Scopus database. 45 studies are selected for the review of which 32 studies use deep learning techniques, 11 use machine learning techniques and 2 studies use a hybrid approach. The studies are compared on various parameters like models, datasets, and performance metrics. The work also identified some of the challenges like dealing with noise and also explained disease symptoms. [ABSTRACT FROM AUTHOR]

This paper extends and improves the performance of a digital reversible watermarking algorithm based on histogram shifting presented in previous works. The considered algorithm exploits the property of image histograms of some kinds of medical images which present many contiguous 0-runs, i.e., a comb structure in the gray level frequencies. In particular, radiographic images exhibit this structure after contrast enhancement during the acquisition process. The previous work suggested performing gray-level histogram shifting according to a local optimization technique. In this paper, we apply combinatorial optimization techniques to entire blocks of contiguous 0-runs using a non-linear objective function transformed to fit a linear optimization algorithm. The obtained results show a meaningful improvement in the payload capacity of the original data-hiding method. A mild Peak Signal-to-Noise Ratio (PSNR) reduction is still acceptable for a qualitative preview of the images, which can be completely restored to their original cover form thanks to the reversibility of the method. [ABSTRACT FROM AUTHOR]

The surveillance and management of cargo fleets is a crucial objective of intelligent transportation systems. Load, especially overload, has a destructive effect on roads and bridges, and monitoring it can increase the life of road surface and its structure. For low-end hardware with lack of CPU power and no GPU support, this paper presents a rapid method to detect whether heavy vehicles have loads or not; then it proposes a fast method for classifying load types to distinguish soil and construction waste from other miscellaneous loads for heavy weight vehicles. This paper applies a method for classifying cargo types using image processing and texture image classification. This method extracts features for statistical analysis of texture images based on gray-level co-occurrence matrices and local binary patterns. The classification is carried out by support vector machine, k-nearest neighborhood, K-mean, artificial neural networks and random forest classifiers. A large number of positive and negative patterns have been used to train these classifiers. We compare the performance of proposed extracted features and classifiers. The simulation results demonstrate that soil and construction waste can be identified from other miscellaneous loads effective in real-time implementation. [ABSTRACT FROM AUTHOR]

This paper addresses the self-supervised learning of several critical factors in Visual Simultaneous Localization and Mapping (VSLAM) in low-level vision: interest point learning, descriptor learning, ego-motion estimation, and depth estimation. The key insight we have is that appearance and geometry constraints can be used to couple these fundamental vision issues. We propose a self-supervised framework for joint training of neural networks for multiple objectives to address complicated issues, simplify systems, and provide important information for deep monocular VSLAM systems. First, we input two adjacent images into pose and depth networks to obtain their corresponding depth maps and camera poses. Then, we employ a differentiable geometry module and utilize the depth maps and camera poses to generate pseudo-input images needed for the interest point network and construct the geometry loss. Further, we input the pseudo-input image and source image into the interest point network to obtain the corresponding interest points, descriptors, and scores. Subsequently, we construct the appearance loss. Finally, we combine the geometry and appearance losses to constrain the whole network in an unsupervised manner. The novelty of this paper is that it integrates the key information necessary in monocular VSLAM into a unified framework that takes into account interest point learning, descriptor learning, ego-motion estimation, and depth estimation at the same time. Without providing any ground truth, our model can combine sub-problems for self-supervised learning and achieve state-of-the-art performance in their respective domains. [ABSTRACT FROM AUTHOR]

Acute leukemia is a proliferation of white blood cells that originates in the bone marrow and impinges on the working of the lymphatic system. Due to the abrupt and aggressive nature of spreading, it requires prompt medical attention. The procedure adopted by hematologists for evaluating morphological features and counting the cells is quite time-consuming, cumbersome, and error-prone. Thus, automatic methods are recommended to overcome the limitations of manual segmentation. The motive of this systematic review is to investigate the various automatic segmentation techniques of acute leukemia using blood and bone marrow smear images. The guidelines of PRISMA have been adopted for systematic review. For the identification of the papers, three online databases are used, namely PubMed, Science Direct, and Google Scholar. A query has been used to find the relevant research article. Inclusion and exclusion criteria are used to scrutinize the papers, and four research questions have been framed to explore the literature to investigate further. In the preview of four different questions, the various methods have been compared based on accuracy, and the various challenges have been highlighted with respect to the methods and distinct datasets of blood and bone marrow smear images. This systematic review summarizes the various automated segmentation techniques under the pretext of framed research questions based on the PRISMA Model. The different types of datasets, performance evaluation parameters, and various obstacles with future scope have also been discussed. [ABSTRACT FROM AUTHOR]

Glaucoma is an eye disease that damages the optic nerve (or retina) and impairs vision. This disease can be prevented with regular checkups, but this increases the workload for professionals and the time it takes to get results. So an automated method using deep learning would be helpful for detection of disease. In order to shorten the diagnosis time for glaucoma, this paper proposed a deep learning based method for automatic glaucoma detection. The experiments are conducted on glaucoma datasets available on Kaggle. This paper used transfer learning based pretrained models namely DenseNet169, MobileNet, InceptionV3, Xception, ReseNet152V2,and VGG19. Among all models DenseNet169 gives best result with accuracy 0.993590 and precision and recall of 0.993671 and 0.9935895 respectively. A comparison of the best model results with existing work shows that the proposed model provides better results. [ABSTRACT FROM AUTHOR]

In the realm of speaker identification, pitch frequency serves as a fundamental feature. However, this feature can be compromised when a speaker records his speech in a closed room, resulting in distorted signal features. This distortion not only reduces the effectiveness of speaker identification systems, but also opens the door for potential deception by hackers who exploit the reverberation effects in closed rooms. To address this concern, the correction of estimated pitch frequencies emerges as an essential step for the success of speaker identification systems. This paper presents a Hybrid Approach for Estimating Pitch Frequency (HAEPF) that integrates both the Zero Crossing Rate (ZCR) and Auto-Correlation Function (ACF) methods. Furthermore, the paper delves into the modeling of reverberant speech using comb filtering, shedding light on how multiple reflections impact the accuracy of pitch frequency estimation. Several simulation experiments were conducted to assess pitch frequency estimation for speech signals, both in the presence and absence of reverberation. The estimation errors were calculated for all three scenarios of reverberation (mild, moderate, and severe). The results clearly indicate that as the degree of reverberation, characterized by the comb filter order, increases, the pitch frequency estimation error also increases. The estimation accuracy of the proposed approach is calculated in terms of Pitch Frequency Estimation Error (PFEE), Gross Pitch Error (GPE) and Octave Error (OER) and is compared with those of several established pitch frequency estimation methods. The proposed approach exhibits a notable enhancement even in noisy environments, reducing PFEE by 43%, and achieving GPE and OER of less than 0.3 and 0.12, respectively, at a Signal-to-Noise Ratio (SNR) of 0 dB. [ABSTRACT FROM AUTHOR]

Twitter has evolved into a primary platform for sharing opinions and insights on current events, such as the ongoing coronavirus pandemic. It's now regarded as one of the foremost sources for conducting analyses, making predictions, and extracting valuable knowledge for machine learning endeavors. it's crucial for the public and authorities to have access to timely and relevant situational information. This enables them to respond effectively and make informed decisions. This paper categorizes situational information into seven distinct groups and examining the behavioral and emotional shifts that individuals are experiencing amid the Covid-19 pandemic. In this paper, we have done analysis of real-time sentiment in tweets related to the Covid-19 pandemic. We have collected the historical Covid-19 tweets from 01/10/2020 to 30/03/2021. We have proposed an adaptive ensemble learning and Stacked-CNN model and applied the proposed models on the collected datasets for Covid-19 situational information analysis. The experimental results demonstrate the effectiveness of the Adaptive ensemble model and the Stacked CNN model in providing better predictions for real-time sentiment analysis of tweets related to the Covid-19 pandemic. The proposed methods can provide valuable insights into public opinion and emotions and has practical applications in areas like public health communication, crisis management, and understanding community concerns. [ABSTRACT FROM AUTHOR]

The underwater sensor network (UWSN) has become the most demandable area because of its numerous advancements in the real world. Water covers over 70% of the earth's surface, and there is more important information below the water's surface. Sensor networks detect information in the water and transmit it to the base station via the sink. UWSN is made up of autonomous and independent sensor nodes. These are placed spatially in the water to gather and transmit pertinent data. However, the communication may suffer due to several challenges like 3D topology, less bandwidth, routing and power constraints. This paper reviews underwater sensor networks based on routing, localization, and fault tolerance. It also reviews and compares the recently proposed algorithms to fulfil drawbacks in existing methods. Each factor's challenges are briefly discussed and compared in this paper. Future directions for underwater sensor networks are analyzed and discussed, along with their emerging applications and challenges. [ABSTRACT FROM AUTHOR]