Search

In recent years, the research pertaining to speech recognition technology in the Kazakh language has gained significant importance. This is due to the increasing demand for natural language processing applications in the region where Kazakh is predominantly spoken. Thus, there exists an urgent requirement for precise and dependable speech recognition systems. The research study examines the application of sophisticated deep learning methodologies, such as Natural Language Processing (NLP) and Hidden Markov Model (HMM), in facilitating speech recognition for the Kazakh language. Additionally, the investigation delves into how various techniques, including data preprocessing, acoustic modeling, and language modeling, can aid in devising effective speech recognition systems. The article deliberates on the feasible uses of speech recognition technology in the geographic area where Kazakh language is spoken and outlines its future research prospects. The investigation underscores the significance of persistent inquiry in this realm to confront distinctive obstacles encountered in creating speech recognition systems for languages with restricted resources. [ABSTRACT FROM AUTHOR]

Industrial collaborative robots play an essential role in smart manufacturing because they improve productivity while also ensuring workplace safety. However, the development of prognostic and health management systems to ensure the reliability of these robots has been a major challenge due to the lack of fault data. This paper proposed a digital twin scheme based on the fusion of the robot kinematic and dynamic models' information down to the powertrains (i.e., the joints motor, and gear) along with the control algorithms and uncertainty accommodation based upon deep learning. The presented digital twin concept has the potential to propel simulation-based fault prediction. We also highlight and discuss challenges and opportunities around the development of the hybrid digital twin for condition monitoring of industrial collaborative robots. [ABSTRACT FROM AUTHOR]

With the latest development in information technology, smart campuses have become a topic that attracts attention in the world of education, especially in higher education. The smart campus has the potential to change the way of managing, accessing facil- ities, and teaching and learning process. The smart campus can collaborate various latest technologies such as edge computing, blockchain, deep learning, virtual reality, and other trend recent technologies. Therefore, this research is a guideline for developing an effective and efficient smart campus system with the latest information and communication technology. This paper explains smart campus technology, features, architecture that have been implemented in real life. Thirty-two papers will be analyzed using the Systematic Literature Review (SLR) method. Hopefully, this guideline can be a valuable reference for smart campus designers, researchers, and practitioners interested in developing innovative and efficient smart campus systems. [ABSTRACT FROM AUTHOR]

[Display omitted] • Deep learning enabled predictive nucleic acid amplification tests analysis. • On-site fluorescence signal processing powered by cloud computing. • Accurate prediction can be obtained using the early 22.5% data. • Approach can be universally extended to other areas of biomedical research. Pandemics such as COVID-19 have exposed global inequalities in essential health care. Here, we proposed a novel analytics of nucleic acid amplification tests (NAATs) by combining paper microfluidics with deep learning and cloud computing. Real-time amplifications of synthesized SARS-CoV-2 RNA templates were performed in paper devices. Information pertained to on-chip reactions in time-series format were transmitted to cloud server on which deep learning (DL) models were preloaded for data analysis. DL models enable prediction of NAAT results using partly gathered real-time fluorescence data. Using information provided by the G-channel, accurate prediction can be made as early as 9 min, a 78% reduction from the conventional 40 min mark. Reaction dynamics hidden in amplification curves were effectively leveraged. Positive and negative samples can be unbiasedly and automatically distinguished. Practical utility of the approach was validated by cross-platform study using clinical datasets. Predicted clinical accuracy, sensitivity and specificity were 98.6%, 97.6% and 99.1%. Not only the approach reduced the need for the use of bulky apparatus, but also provided intelligent, distributable and robotic insights for NAAT analysis. It set a novel paradigm for analyzing NAATs, and can be combined with the most cutting-edge technologies in fields of biosensor, artificial intelligence and cloud computing to facilitate fundamental and clinical research. [ABSTRACT FROM AUTHOR]

Speaking of speech recognition within the English language, it is the process of recognizing oral speech and transcribing it into writing using exclusive algorithms. For the perishable skill of English language learning, use of innovative speech recognition technology using Advanced Speech Recognition Technologies MLP-LSTM is proposed in this paper to advance the existing online learning platforms. Previous research addresses the importance of NLP in English language learning but notes the challenges in effectively extracting and segmenting features from multimodal data. In order to overcome these problems, this paper incorporate the proposed MLP for feature extraction and LSTM for sequence learning. The utilization of MLP-LSTM provides not only a brilliant improvement of the capacity to transform spoken language and perceive it but also minimizes the Word Error Rate (WER) to 0.075. With this low WER, along with the total accuracy rate of 98.25 %, this paper focus on underlining how this system is more effective than traditional language learning tools. This paper has been implemented through Python Software. The given MLP-LSTM based speech recognition model lays the foundation for a highly complex yet accurate paced English language learning platform that will cater to the needs of the learners in the global scenario. [ABSTRACT FROM AUTHOR]

Sentiment analysis has been widely used in various fields of social media, education, and business. Specifically, in the education domain, the usage of sentiment analysis is difficult due to the huge amount of information, the nature of language, and processing the diverse perceptions of students. Deep learning emerges as an advanced concept in the realm of machine learning that learns features automatically from raw text data, making them well-suited for sentiment analysis tasks. In recent years, deep learning has been used in analyzing the sentiments. Deep learning architectures have surpassed other machine learning paradigms for performing sentiment analysis. The ability to analyze automatically the students’ sentiments enables HEI to process huge amounts of unstructured data quickly, efficiently, and cost-effectively. The paper aims to predict the sentiments of students’ reviews posted in VLE regarding online learning that enables the educators to optimize their teaching methods for the best results. This study paper explores the usage of CNN, LSTM, and hybrid CNN-LSTM for the prediction of sentiments. The proposed hybrid CNN-LSTM architecture achieves superior performance compared to other baseline algorithms with respect to accuracy, precision, recall, and F1 score. According to outcomes, the recommended technique achieves remarkable accuracy of 97%. The findings facilitate the progress of a more efficient deep learning sentiment prediction system that gives valuable insights from a huge volume of students’ textual data. [ABSTRACT FROM AUTHOR]

Academic research is crucial to the development of science and technology and is an important factor that affects national strength. When writing an academic research paper, a rhetorical structure is typically used to present the paper's ideas, but this task is quite difficult for junior researchers. To solve this problem, some studies have adopted text mining to assist with the writing, but the existing methods still require human intervention to generate sentences. Recently, due to the increasing maturity of deep learning technology and the ability to address the problem of automatic text generation, progress has been made in this area. The highly complex deep learning operations can correctly generate sequences and find correlations between sequences. When a user provides a few keywords and key sentences, the proposed algorithm can generate an introduction section for the user. The results show that the generated introduction is more coherent, clearer, and more fluent than existing summarization methods. In addition, the method proposed in this study improves the accuracy compared with traditional text extraction methods. The manuscript produced by this study has been evaluated to show that the study can produce a comprehensive introduction compared with previous studies. • The proposed framework can generate a comprehensive introduction based on users' brief inputs. • This paper demonstrates a three-testing-threshold approach to check the content quality. • The introduction generated through this method has less than 3% similarity to the original text by comparison. [ABSTRACT FROM AUTHOR]

This paper introduces a deep learning-based oracle style migration and generation technique, whose core capability lies in converting arbitrary modern Chinese characters into characters with oracle features. This paper proposes a StyleGAN-based oracle style migration and generation model, which utilizes a GAN framework of style encoder, image reconstructor, and multidiscriminator, thus realizing the generation of high-quality, high-resolution, diverse, and realistic oracle images. This paper also provides an in-depth evaluation of this paper's model in terms of multiple dimensions and key metrics, including style migration effect, style generation effect, generation efficiency and expert evaluation, and compares it with other comparative models to demonstrate the superiority and innovation of this paper's model. This paper provides an effective and innovative solution to solve the problem of recognizing and understanding ancient texts. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is now used in many sectors but its transformative impact on cybersecurity is unmatched. Cybersecurity is seen to rely heavily on artificial intelligence (AI), which has brought about automation of responses, detection of network threats and security consciousness. This paper examines various modern techniques involving deep learning, machine learning and behavior analysis among others that are used in dealing with the increasing number and complexity of cyber threats. The research also looks at how automated cybersecurity response and decision-making capacities have been transformed through AI. It also investigates into security intelligence modeling as a means of offering actionable insights towards strengthening organizational resilience. Additionally, the goal of this paper is to provide a nuanced understanding of how AI is reshaping cybersecurity and to outline future pathways for research and development in this dynamic field. [ABSTRACT FROM AUTHOR]

In tutorial format, this paper explores the intricate relationship between Artificial Intelligence (AI) and managerial decision-making, emphasizing the alignment problem--a critical challenge in ensuring AI systems align with human values and ethical standards. It defines AI and examines various methods, including machine learning algorithms, natural language processing, recommendation systems, sentiment analysis, data visualization, anomaly detection, expert systems, neural networks, and deep learning. The alignment problem is dissected into key aspects such as defining goals, value misalignment, robustness and safety, long-term consequences, and interpreting human preferences. The types of AI most affected by the alignment problem, including deep learning, reinforcement learning, generative adversarial networks, evolutionary algorithms, and open-ended learning systems, are highlighted. Practical examples illustrate how biases and misalignments manifest in business processes like recruitment, credit scoring, and automated trading. The paper also categorizes managerial decisions and discusses how AI methods support these decisions while addressing alignment issues. This document underscores the importance of aligning AI systems with human values to ensure ethical and effective outcomes in business environments. This paper is intended to be a road map of possible research topics on the effect of AI on Business Decision Making through the lens of the Alignment Problem. [ABSTRACT FROM AUTHOR]

This paper presents the basic quantum reinforcement learning theory and its applications to various engineering problems. With the advances in quantum computing and deep learning technologies, various research works have focused on quantum deep learning and quantum machine learning. In this paper, quantum neural network (QNN)‐based reinforcement learning (RL) models are discussed and introduced. Moreover, the pros of the QNN‐based RL algorithms and models, such as fast training, high scalability, and efficient learning parameter utilization, are presented along with various research results. In addition, one of the well‐known multi‐agent extensions of QNN‐based RL models, the quantum centralized‐critic and multiple‐actor network, is also discussed and its applications to multi‐agent cooperation and coordination are introduced. Finally, the applications and future research directions are introduced and discussed in terms of federated learning, split learning, autonomous control, and quantum deep learning software testing. [ABSTRACT FROM AUTHOR]

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid development of Internet technology, the amount of information and data is constantly increasing, leading to higher and higher demands for network big data analysis platforms. This paper primarily delves into the application of deep learning technology in digital text classification. In this paper, a deep learning-based algorithm is introduced in detail. It outlines the method of extracting specific numerical eigenvectors from large-scale non-negative eigenattribute samples and converting them into machine-readable code. ased on the aforementioned methodology, an analysis platform is designed, and its basic performance is simulated and tested. The test results indicate that the platform's ability to process abnormal data in Round A is 80, Round B is 90, Round C is 70, Round D is 85, and Round E is 75. The exception handling capacity of each category is represented visually through a bar chart, where the height of the bar signifies the size of the exception handling capacity for that specific category. [ABSTRACT FROM AUTHOR]

This paper summarizes the video sample collection and processing methods based on artificial intelligence platform, focusing on video noise cancellation, content segmentation and classification, and feature extraction and representation techniques. The paper believes that the deep learning technology, especially the convolutional neural network, shows great potential in image recognition and video analysis, and effectively improves the level of automation and accuracy of video processing. This paper discusses the importance of building a large-scale and high-quality video sample library, and how to improve the processing efficiency and accuracy of video data through intelligent technology. [ABSTRACT FROM AUTHOR]

Under the background of digitalization and networking, the fashion industry is undergoing unprecedented changes. In such a big environment, online clothing design based on artificial intelligence technology is a brand-new innovation and development direction. In this paper, the online fashion design is taken as the research object, and the latest artificial intelligence algorithm is combined to discuss the fashion design automation and personalized design method based on AI(Artificial Intelligence). The online clothing design system based on artificial intelligence uses deep learning, image recognition and machine learning methods to analyze user preferences, historical data and fashion trends, and automatically generate personalized and innovative clothing design schemes. In addition, this study also compares the differences between artificial intelligence-driven clothing design and traditional clothing design in creativity, cost-effectiveness and user satisfaction. In the AI design method, the design cycle is generally shorter, in which the automatic primary, intermediate and advanced design takes 8 days, 6 days and 4 days respectively, while the expert-aided design and fully customized design cycle takes 5 days and 7 days respectively. The research results of this paper will promote the automation and personalization of fashion design, and open up a brand-new working mode for the development of fashion industry. [ABSTRACT FROM AUTHOR]

Natural language processing, with parsing and generation, has a long tradition. Parsing has been easier to perform than a generation but with generative artificial intelligence (a.k.a Gen AI) and large language models (abbr. LLMs), this has changed. Generative artificial intelligence is a type of artificial intelligence that uses a large data set to create something in the genre of that data set. It can generate different outputs ranging from texts, audio, objects, pictures, and paintings to videos, but also synthetic data. LLMs use deep learning and deep neural networks to train on large text corpora for recognizing and generating texts. These models are based on massive data sets, collected from databases and the web. They use transformer models to detect how elements in sequences relate to each other. This provides context support. Two well-known large language models are the Generative Pre-trained Transformer, GPT, used in ChatGPT and Bidirectional Encoder Representations from Transformers, BERT. Although LLMs have advantages, they have problems. This paper presents generative artificial intelligence and LLMs with benefits and drawbacks. Results from applying these models have shown that they can work well for accuracy in specificity, user personalization and human-computer communication but they may not provide acceptable, reliable and truthful results. For example, ethics, hallucinations and incorrect information, or misjudgments, are some major problems. The paper ends with future directions, research questions on LLMs, and recommendations. [ABSTRACT FROM AUTHOR]

The paper addresses the topic of radar echo temporal extrapolation which is of major interest in both operational and research meteorology. Weather radar measurements are an important data source used by operational meteorologists for weather analysis, radar refectivity having a significant influence on short-term heavy rainfall prediction. Thus, extrapolating radar products' values is important for early storm evolution assessment. The paper proposes SepConv-ens approach for temporal extrapolation of radar observations using an ensemble of three separable convolution-based deep learning models. Experiments performed on real radar data from the Romanian National Meteorological Administration (NMA) highlight a good performance of SepConv-ens in predicting radar data up to more than 40 minutes ahead and a good correlation between the radar measurements and the predictions in terms of spatial and intensity evolution of the radar echoes. SepConv-ens is integrated in the operational visualization software utilized by the Romanian NMA and is the first attempt, at the national level, to offer an artificial intelligence-based automated assistance for operational meteorologists. [ABSTRACT FROM AUTHOR]

Considerable and high-quality scientific research papers play a crucial role in acquiring knowledge across various fields. Extracting information from the full text of these papers presents a challenging task. Named Entity Recognition (NER) stands out as a key step in information extraction. This recognition is indispensable for many tasks and applications requiring direct access to relevant information, such as knowledge discovery and document retrieval. However, effectively processing important contextual information remains a challenge in the literature. In our work, we introduce a supervised NER method named N-AMES (Named entity recognition using contextual Attention on Masked Entities and Sections). Leveraging the attention mechanism of the BERT transformer, our method effectively processes both global and local entity context information. By incorporating section titles into a sequence of text chunks and training the model on masked entities, our approach achieves remarkable performance. Specifically, our model achieves an F1-measure of 74.10% and 72.30% in partial matching evaluation, outperforming state-of-the-art models on two distinct full-text research paper datasets: SciREX for machine learning and CRAFT for biomedical entities. [ABSTRACT FROM AUTHOR]

The paper presents a deep-learning model that may be used to calculate saliency maps for video content. Classic saliency algorithms take into account only spatial information obtained from an image to generate a saliency map showing regions of higher importance—hence, regions where people are more likely to turn their gaze and attention. Algorithms for video stimuli add temporal information about the movements of objects on a frame-to-frame basis, resulting in more complex three-dimensional architectures. The paper analyses existing models and proposes a model based on one of them. The model's performance is compared with the literature using four widely accepted measures (AUC, NSS, SIM, and CC). It is comparable and, in many cases, even better than already published models. Additionally, because of some improvements in the architecture, it is significantly faster in terms of the number of frames processed per second. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of predicting irradiation and, consequently, predicting solar panel production in Poland. The work uses deep learning for this purpose. It is shown that the quality of prediction is highly dependent on the network structure used in a given geographical location. The paper proposes a fast algorithm for finding the optimal network structure depending on geographical location. It has been experimentally shown that the proposed approach determines network structures close to the optimal ones that are determined by using full search. For this purpose, real data for selected seven cities in Poland are used. These cities are very diverse in terms of geographical location and territory characteristics. [ABSTRACT FROM AUTHOR]

The International Code of Signals (INTERCO) consists of codes and signals used to communicate messages regarding the safety of navigation. These codes are used by vessels, and the signals can be sent in various ways, including flaghoist, signal lamp, flag semaphore, or as a radio message. This paper focuses only on flag signals, proposing their detection and classification using deep learning algorithms. The paper also addresses a specific scenario, where the detection and classification of flag signals are necessary for verifying the current status, operations, and behaviours of vessels, in line with the intention conveyed by the flag signal. The system discussed is regarded as a component of a larger system for ensuring navigation safety and monitoring ship behaviours near critical infrastructure such as ports, offshore wind farms, or other offshore constructions. To tackle this challenge, a convolutional neural network (CNN) has been employed. The paper delves into the process of preparing the image dataset, including annotation and augmentation, and discusses the CNN learning process based on the YOLO algorithm implementation, finally discussing the results of the computational experiment. [ABSTRACT FROM AUTHOR]

The development of the internet and social media means that people can easily convey various personal opinions or expressions. In line with this, many researchers are interested in examining the sentiments they make, considering that nowadays their opinions can be useful for various sectors such as product analysis, latest news analysis, or even political opinion analysis. Several approaches used to analyze public opinion on social media are Machine Learning and Deep Learning. This paper is devoted to finding the best AI-based models for sentiment analysis on social media especially those that are known for higher precision in complexity solving by using Systematic Literature Review (SLR). Of the many papers with the same topic interest, there are a total of 13 papers that meet our criteria which include title, methods, and results. Then, the papers are evaluated one by one in-depth and compared to find the best results. [ABSTRACT FROM AUTHOR]

Air is very beneficial and crucial for every living creature on earth, hence it is very important to protect the air quality in order to avoid diseases. However, due to the increase in population, some human activities have been causing detrimental damage to the air quality. Some people have realized the potential impact of this problem and have done studies on predicting future air pollution. Some implemented machine learning models such as random forest regression, support vector machine, etc, while others have utilized deep learning models in their research.. This study will implement five different models, specifically linear regression, ridge regression, random forest regression, and multilayer perceptron regression. There will be two datasets used in this paper which will be merged and processed. There will be three key evaluation metrics being used in this paper namely root mean squared error, mean absolute error, and r-squared. The results from all of the models have concluded that more optimization and factors are needed in order to boost the final result of this study. [ABSTRACT FROM AUTHOR]

Traffic accidents are a significant global problem, with human error being a major contributing factor. Autonomous vehicles have emerged as a promising solution to address this issue. Vehicle pedestrians understand the environment through sensor is crucial in this field because sensor data can be used by vehicle to drive safely such as navigate the route, avoid collision with other object such as pedestrian, car, building, animals, and many more. This paper proposed a comparison of 3D object detection models for autonomous vehicles using a study literature review technique. This technique consists of ten steps from including defining research question to produce the result. As a result, 9 papers were retrieved from 90 papers and then all object detection models are grouped into three parts to determine the best model based on dataset that being used such as KITTI, nuScenes, and Waymo Open Dataset. [ABSTRACT FROM AUTHOR]

Spam detection in SMS communication is a crucial task for maintaining the quality of messaging services and protecting users from unwanted and potentially harmful messages. Arabic SMS spam detection poses unique challenges due to the rich morphology and complex structure of the Arabic language, which can significantly impact the performance of traditional text classification methods. To address these challenges, this paper presents a novel approach for Arabic SMS spam detection using a hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. The proposed model leverages the strengths of CNNs in capturing local features and patterns in the text and the capability of Bi-LSTM networks to understand long-term dependencies and contextual information. This hybrid architecture is designed to effectively handle the complexities of the Arabic language and improve the accuracy of spam detection. The model was evaluated on a dataset of Arabic SMS messages, consisting of both ham (non-spam) and spam messages. The dataset underwent preprocessing steps, including text cleaning, tokenization, and padding, to prepare it for training the deep learning model. The hybrid model was trained using the Adam optimizer and evaluated using accuracy, precision, recall, and F1 score metrics. Early stopping was implemented to prevent overfitting during the training process. The results demonstrate that the hybrid model achieved high performance, with an accuracy of 0.9699, precision of 0.9739, recall of 0.9675, and an F1 score of 0.9707. These metrics indicate the model's effectiveness in accurately detecting spam in Arabic SMS messages. Additionally, the paper provides visualizations of the confusion matrix, ROC curve, and training-validation loss graph to illustrate the model's performance. The implications of this research are significant for the field of Arabic text classification and spam detection. The proposed hybrid model offers a robust solution for accurately classifying Arabic SMS messages, which can be integrated into messaging platforms to enhance spam detection capabilities and improve user experience. Future work could explore data augmentation techniques, transfer learning, and advanced hybrid architectures to further enhance the model's performance and applicability. [ABSTRACT FROM AUTHOR]

In recent years, multi-focus image fusion has emerged as a prominent area of research, with transformers gaining recognition in the field of image processing. Current approaches encounter challenges such as boundary artifacts, loss of detailed information, and inaccurate localization of focused regions, leading to suboptimal fusion outcomes necessitating subsequent post-processing interventions. To address these issues, this paper introduces a novel multi-focus image fusion technique leveraging the Swin Transformer architecture. This method integrates a frequency layer utilizing Wavelet Transform, enhancing performance in comparison to conventional Swin Transformer configurations. Additionally, to mitigate the deficiency of local detail information within the attention mechanism, Convolutional Neural Networks (CNN) are incorporated to enhance region recognition accuracy. Comparative evaluations of various fusion methods across three datasets were conducted in the paper. The experimental findings demonstrate that the proposed model outperformed existing techniques, yielding superior quality in the resultant fused images. [ABSTRACT FROM AUTHOR]

This paper intends to investigate the risk management of inclusive digital financial platforms. First, it explains the idea of smart cities, their function, and inclusive financial risk control technologies based on big data. The varieties of digital inclusive financial platforms and their risk profiles are next examined. The Back Propagation (BP) neural network is used to build a BP-KMV model based on the KMV model. Finally, utilizing M Company as a case study, this paper uses the BP-KMV model to examine the credit risk and risk management of unlisted enterprises on the digital inclusive financial platform. The results show that of the four unlisted companies, L Company has the greatest default rate (7.35%), while J Company has the lowest default rate (4.82%). The highest research and development (R&D) spending rate is 14.1% for J company, while the highest patent ownership rate is 43.09% for L company. The data demonstrates a negative correlation between the percentage of R&D expenditures and the default rate of unlisted enterprises. In other words, a larger default risk is associated with lower R&D expense rates. Additionally, there is a correlation between patent ownership and default rates that is positive, suggesting that higher patent ownership rates are linked to higher default rates. Additionally, the risk management technologies of M business can complement one another. The theoretical research of comprehensive digital inclusive finance risk control can be enriched by the risk analysis of digital inclusive financial platforms utilizing the BP-KMV model in the context of smart cities. [ABSTRACT FROM AUTHOR]

The man-machine interface encompasses a crucial area-emotion recognition through facial expressions. Despite its significance, emotion recognition faces challenges such as facial accessories, nonuniform illuminations, pose variations, audio speeches, text conversations, and hand and facial gestures. Understanding emotions like happiness, anger, anxiety, joy, and shock, along with their varying degrees and overlaps, is essential for accurate recognition. These nuances, inherent to humans, pose difficulties and costs in achieving standard results through facial recognition. Recognizing someone's mood through facial expression, conversation, voice modulation, and gestures is a skill humans excel at. However, replicating this ability through facial recognition has proven challenging and costly. This paper addresses these challenges by proposing diverse approaches to emotion detection. By exploring various modes, including facial expressions, conversation analysis, voice modulation, and gestures, the paper tackles current research problems and holds practical applications in public experiments and exhaustive sentiment analysis. The paper presents a good combo of various modes of emotion recognition on multiple datasets (tried and tested widely before amalgamating all to produce an excellent optimal result as an output of the model). [ABSTRACT FROM AUTHOR]

The safety and durability of concrete structure is an important issue in engineering quality management. In this paper, an image processing algorithm based on deep learning is proposed to realize real-time quality inspection and automatic defect identification of concrete structures. This algorithm uses the Convolutional Neural Network (CNN) to automatically extract the features of concrete surface quality images, and then identify the existence of defects, thus improving the detection efficiency and accuracy. In this paper, for this method, data samples with different specific structures are collected and manually labeled to the data set; then, a multi-layer CNN model with convolution layer, pool layer and full connection layer is designed to train the model, and then image enhancement technology is used to reduce information noise, and data enhancement technology is used to improve the problem-solving ability of the model. In addition, the strategy of Dropout is used to close some nodes to reduce parameters and prevent over-fitting, and the learning rate is adjusted to optimize the classification effect. In addition, this study constructs an all-weather real-time detection framework, including data acquisition, preprocessing, feature extraction, classification and identification and decision-making alarm system, to ensure the rapid positioning of the detection system. To sum up, the results of this study show that the deep learning image processing algorithm has good contrast performance in the field of real-time quality inspection of concrete structures. CNN model has better performance than GAN (Generative Adversarial Network) and LSTM (Long Short-Term Memory) models in detection time, defect identification resolution and detection accuracy. The maximum detection time is 366ms and the shortest is 213 ms. The successful development of this algorithm provides a new method for automatic detection of concrete structure quality, which has important application value in engineering practice. This research has a broad development prospect. [ABSTRACT FROM AUTHOR]

This paper explores the application of artificial intelligence technology in ensuring the security of digital currencies. With the increasing popularity of digital currencies, ensuring their security has become a crucial concern. AI techniques, such as machine learning and deep learning, can be employed to identify and prevent security threats in digital currency systems. Additionally, it investigates how AI enhances security measures and risk control on digital currency trading platforms, offering insights into real-time risk alert systems. Therefore, through empirical research in four distinct sections, this paper continuously refines and revises the theoretical model proposed in this project. The ultimate goal is to provide new theoretical tools for the management of financial stability in the process of Digital Currency replacing M0. this project gives the research content of the four parts, which include public perception, delivery path, underlying technology and virtual currency bubble, we hope that this research can offer valuable insights to relevant field managers. [ABSTRACT FROM AUTHOR]

In the contemporary era, the death rate is increasing due to lung cancer. However, technology is continuously enhancing the quality of well-being. To improve the survival rate, radiologists rely on Computed Tomography (CT) scans for early detection and diagnosis of lung nodules. This paper presented a detailed, systematic review of several identification and categorization techniques for lung nodules. The analysis of the report explored the challenges, advancements, and future opinions in computer-aided diagnosis CAD systems for detecting and classifying lung nodules employing the deep learning (DL) algorithm. The findings also highlighted the usefulness of DL networks, especially convolutional neural networks (CNNs) in elevating sensitivity, accuracy, and specificity as well as overcoming false positives in the initial stages of lung cancer detection. This paper further presented the integral nodule classification stage, which stressed the importance of differentiating between benign and malignant nodules for initial cancer diagnosis. Moreover, the findings presented a comprehensive analysis of multiple techniques and studies for nodule classification, highlighting the evolution of methodologies from conventional machine learning (ML) classifiers to transfer learning and integrated CNNs. Interestingly, while accepting the strides formed by CAD systems, the review addressed persistent challenges. [ABSTRACT FROM AUTHOR]

Handover (HO) management in Heterogeneous Networks (HetNets) poses challenges arising from network densification and dynamic environmental behaviors. Existing HO decision algorithms struggle to efficiently utilize network resources and ensure a high-quality user experience amidst the complexity of HetNets and the burgeoning growth of mobile users. This paper introduces a robust and data-driven HO decision model designed to enhance HO performance in HetNets. Initially, a conventional HO decision algorithm is developed based on users' Reference Signal Received Power (RSRP) values in MATLAB. Various simulation cases explore different HO parameters to observe their impact on handover performance. To address these challenges, a data-driven HO decision model leveraging Long Short-Term Memory (LSTM), a deep learning technique, is proposed for the regression task. The LSTM model is trained and tested using obtained RSRP values, and the future RSRP values predicted by the model are employed to trigger HO decisions in the proposed algorithm. Results from the traditional HO decision algorithm are compared with those of the proposed machine learning-based approach across various simulation runs, considering average Signal-to-Interference-plus-Noise Ratio (SINR), RSRP, user throughput values, the number of HOs and the Radio Link Failure (RLF) ratio. Different user speeds are also considered to establish a relationship between HO frequency and mobile user speed. The proposed model achieved reducing the rate of radio link failure to levels that are deemed acceptable in order to ensure a continuous connection. • HO management in HetNets is challenging due to network densification and dynamic environmental behaviors. • Existing HO decision algorithms are unable to efficiently ensure a high-quality user experience in HetNets. • The paper introduces a robust and data-driven HO decision model aimed at improving HO performance in HetNets. • To address the limitations of the traditional approach, a data-driven HO decision model is proposed based on LSTM. • The proposed algorithm's advantages and disadvantages are assessed based on the simulation results. [ABSTRACT FROM AUTHOR]

Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize losses. However, traditional movement track forecasting methods suffer the disadvantages of low efficiency and low accuracy. To address the these problems, a novel Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) model based on Multidimensional Features and Time Difference Series (MT-CNN-TCN) is presented in this paper. First, different types of meteorological data are processed and then the feature differences between adjoining moments are extracted. Second, a two-branch structure based on Two Dimensional Convolutional Neural Network (2DCNN), 3DCNN and TCN is taken to effectively integrate different types of meteorological features to strengthen its forecasting effect. Finally, experiments are conducted using Northwest Pacific TC data from years 2000–2019. Test results show that the proposed model MT-CNN-TCN can perform well at all three forecast periods (12 h, 24 h, and 48 h), with a significant improvement in accuracy by 7 %, 13 %, and 16 % respectively, compared with current forecasting methods such as Long Short Term Memory (LSTM). [ABSTRACT FROM AUTHOR]

The gaming industry produces vast amounts of user-generated feedback, making it challenging for developers to efficiently analyze and respond to real-time reviews. This study addresses the problem of classifying large-scale unstructured user feedback from Steam reviews. In this paper an approach that integrates traditional machine learning models and deep learning models is proposed. XGBoost is used to manage feature-rich datasets, reducing overfitting. Long-short-term memory (LSTM) and Bi-directional LSTM are used to enhance the accuracy and robustness of classification. Feature extraction techniques, such as sentiment analysis and topic modeling, are employed to enrich the dataset and improve model performance. The experimental results show that the XGBoost model achieved the highest performance with an accuracy of 0.9499 and a ROC-AUC score of 0.6113, demonstrating superior performance in distinguishing between positive and negative feedback. In comparison, deep learning models such as LSTM and Bi-directional LSTM showed lower ROC-AUC scores, indicating less effectiveness in handling the classification task. This approach offers game developers a reliable and scalable solution for classifying user sentiment, leading to better game improvements based on user reviews. [ABSTRACT FROM AUTHOR]

Globally, liver cancer ranks as the sixth most frequent malignancy cancer. The importance of early detection is undeniable, as liver cancer is the fifth most common disease in men and the ninth most common cancer in women. Recent advances in imaging, biomarker discovery, and genetic profiling have greatly enhanced the ability to diagnose liver cancer. Early identification is vital since liver cancer is often asymptomatic, making diagnosis difficult. Imaging techniques such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and ultrasonography can be used to identify liver cancer once a sample of liver tissue is taken. In recent research, reliable detection of liver cancer with minimal computing computational complexity and time has remained a serious difficulty. This paper employs the DenseNet model to enhance the detection of liver nodules with tumors by segmenting them using UNet and VGG using Fastai (UVF) in CT images. Its dense interconnections distinguish the DenseNet between layers. These dense connections facilitate the propagation of gradients and the flow of information throughout the network, thereby enhancing the efficacy and performance of training. DenseNet's architecture combines dense blocks, bottleneck layers, and transition layers, allowing it to achieve a compromise between expressiveness and computing efficiency. Finally, the 3D liver nodular models were created using a ray-casting volume rendering approach. Compared to other state-of-the-art deep neural networks, it is suitable for clinical applications to assist doctors in diagnosing liver cancer. The proposed approach was tested on a 3Dircadb dataset. According to experiments, UVF segmentation on the 3Dircadb dataset is 97.9% accurate. According to the study, the DenseNet and UVF segment liver cancer better than prior methods. The system proposes automated 3D liver cancer tumor visualization. [ABSTRACT FROM AUTHOR]

This review article provides a comprehensive analysis of the latest advancements and persistent challenges in Software-Defined Wide Area Networks (SD-WANs), with a particular emphasis on the multi-objective Controller Placement Problem (CPP). As SD-WAN technology continues to gain prominence for its capacity to offer flexible and efficient network management, the task of 36optimally placing controllers—responsible for orchestrating and managing network traffic—remains a critical yet complex challenge. This review delves into recent innovations in multi-objective controller placement strategies, including clustering techniques, heuristic-based approaches, and the integration of machine learning and deep learning models. Each methodology is critically evaluated in terms of its ability to minimize network latency, enhance fault tolerance, and improve overall network performance. Furthermore, this paper discusses the inherent limitations and challenges associated with these techniques, providing a critical evaluation of their current utility and outlining potential avenues for future research. By offering a thorough overview of state-of-the-art approaches to multi-objective controller placement in SD-WANs, this review aims to inform ongoing advancements and highlight emerging research opportunities in this evolving field. [ABSTRACT FROM AUTHOR]

Siamese networks utilize deep learning models to achieve a balance between tracking speed and accuracy in visual object tracking. However, in low light and other challenging lighting conditions, the contours and textures of the tracked object may not be accurately represented in the feature maps. This can result in blurriness and interference from similar distractions, as non-edge features may be overlooked. To tackle these challenges, this paper proposes a multi-feature object tracking approach that combines Siamese networks with Local Binary Patterns (LBP) and attention mechanisms. After preprocessing the video frames for LBP feature extraction, the resulting local binary pattern maps are input into a SiamRPN network, with ResNeSt as its backbone. The incorporation of local binary patterns enhances feature representation by capturing texture information from the target's appearance. Additionally, a coordinated attention mechanism is applied after each feature layer of the network to further improve tracking accuracy. This mechanism dynamically adjusts the weights of different features to optimize performance across various scenarios. The target's position is then determined by merging the deep and shallow features retrieved by the network, which are subsequently fed into the RPN network for regression classification. Experimental results demonstrate the effectiveness of the proposed algorithm in tracking objects. [ABSTRACT FROM AUTHOR]

Effective detection of DGA (Domain Generation Algorithm) domain names is crucial for identifying and countering Botnets, and safeguarding cyber security. In this paper, we propose a new detection method using a hybrid deep neural network with multi-dimensional features. Firstly, multi-dimensional features are employed to bolster extracting the implicit semantic content inherent in DGA domain names. Secondly, a hybrid deep neural network, which integrates both CNN (Convolutional Neural Network) and BiLSTM (Bi-directional Long Short-Term Memory network), is utilized to effectively extract and synthesize the distinctive features of DGA domain names. Finally, comparison experiments are designed to evaluate the model's overall performance and detection accuracy. Experimental results demonstrate the efficacy of the proposed model. In the two-classification, we attained a precision rate of 97.72% and an impressive F1 score of 98.20%, indicative of a fine balance between precision and recall. In the multi-classification, our model still performed well, with a precision rate of 96.90% and an F1 score of 96.92%, further underscoring its robustness and adaptability. Compared to other models, our model achieved a detection rate of 100% for more DGA families. The model demonstrated powerful abilities, especially in distinguishing among different semantic features, and it exhibited particularly exceptional detection performance for DGA domain names generated with fixed lengths or fixed letter patterns. [ABSTRACT FROM AUTHOR]

The medical image processing plays an important role in analyzing and detecting tumors and detecting cancer cells in their early stages. Microscopic images were used as a deep learning approach to recognize bone features. These images were acquired using microscopy, a time-consuming and labor-intensive process that required repeating. Cancer cells cannot be identified by conventional techniques because of the noise in the images. To address these challenges, this paper introduces the Gated Convolutional Neural Network (GCNN) techniques used to identify multiclass bone cancer, including non-tumor, non-viable, and viable tumors. As a first stage, the most basic part of image Preprocessing is to deposing without interrupting the diagnostics information during the removal of noise. The second stage is edge detection, used for image brightness discontinuity detection based on Scaled Region Edge Detector (SRED). It is used for image segmentation and data extraction within regions based on the Screen Cluster Area Segmentation (SCAS) to segment the Region of Interest (RoI) based on Relative Scalar Color Histogram (RSCH). The fourth step is Feature extraction is to find out the features and match the image feature from the Bone Cancer Detection object based on the maximum threshold weights using GCNN with Maximum Standard External Regions (MSER) used for features extracting applied to improve feature quality analysis and Feature support rate. This results in higher classification accuracy, Precision, recall under F-measure, and lower error rates. This enables a more achieved classification than other existing methods. [ABSTRACT FROM AUTHOR]

Utilizing Wireless Sensor Networks (WSNs), Internet of Things (IoTs) sensors, and Unmanned Aerial Vehicles (UAVs), in conjunction with optimization techniques and machine learning algorithms, can present a novel approach to Precision Agricultural (PA) crops. Agriculture has transitioned from traditional legacy systems to incorporate advanced smart technologies. Several complex farming problems are utilized to promote a variety of UAV sensing and Artificial Intelligence (AI) algorithms in PA applications of smart agriculture, especially in developing countries. This paper proposes the design of a conceptual UAV sensing system for crop management using a novel classification framework. UAV-based image datasets can be implemented and expanded to various types of crops. In addition, it can classify various types of rice species and detect weed farms as it consists of a multistage process for identifying and monitoring different crops. The proposed classification framework is evaluated using three different real UAV image datasets compared with Naive Bayes, Decision Tree (DT), Bagging, and Random Forest (RF) techniques. The classification performance metrics obtained are as follows: i) the WeedNet dataset with 100 % F1-score, 100 % recall, 100 % precision, and 100 % accuracy; ii) the Rice Seedling dataset with 99.5 % F1-score, 99.5 % recall, 99.5 % precision, and 99.5 % accuracy; and iii) the Rice Varieties dataset with 97.99 % F1-score, 97.99 % recall, 98.14 % precision, and 97.99 % accuracy. The success rates achieved by the proposed classification framework outperform those of other recent state-of-the-art techniques, demonstrating its efficacy in crop management applications. [ABSTRACT FROM AUTHOR]

Mechanical engineering drawings are commonly used in multiple industries, carrying essential information about the design and technical specifications of the parts they define. With large industry sectors shifting to advanced manufacturing processes and technologies such as additive manufacturing, arises the need for systems checking whether legacy parts described by engineering drawings can be optimally produced. To this end, the digitisation of engineering drawings has become the key issue for the following computer-aided engineering tasks towards advanced manufacturing. This paper presents a pipeline for information extraction in raster mechanical engineering drawings through a combination of traditional and deep-learning-based computer vision techniques. Object detection and text recognition techniques are implemented to achieve automatic interpretation of engineering drawings. A dataset of 217 industrial engineering drawings is created to evaluate the proposed method. Different types of information within engineering drawings, including information blocks, views, dimensions, and Geometric Dimensioning and Tolerancing (GD&T) information, are extracted automatically. A case study of engineering drawing digitisation for a complex part is presented to illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Compared with traditional machining processes, additive manufacturing (AM) has received widespread attention in recent years because of its high degree of modeling freedom. However, due to the multiple manufacturing errors and complex physical state changes involved in the process, the geometric deviation on the AM part surface is a challenge for controlling product geometrical quality. To address this problem, data-driven machine learning (ML) techniques have been widely studied in product quality controlling. However, traditional ML greatly depends on the training sample data, and suffers the risk of violating physical mechanisms due to the lack of domain knowledge. In order to take the best advantage of domain knowledge, prior information and deep learning algorithm, this paper proposes a knowledge-integrated deep learning algorithm and constructs the geometric deviation prediction model of the AM part surface. After that, the method was verified with design of experiments. The results show that compared with the data-driven neural network (DDNN), the knowledge-integrated neural network (KINN) has fewer iterations during the training process, less sample data requirement and more accurate prediction results. [ABSTRACT FROM AUTHOR]

The growing demand for efficient and reliable sensor networks in applications such as environmental monitoring, healthcare, and smart cities has highlighted the need for optimizing communication protocols, power consumption, and data management. Traditional methods often focus on optimizing individual layers of the network without considering the interactions across layers. This approach limits the overall performance, especially as networks scale in size and complexity. The lack of effective cross-layer optimization strategies hinders the performance of sensor networks, leading to suboptimal energy usage, low throughput, and high latency. Moreover, sensor nodes in such networks often face constraints such as limited energy, computation power, and memory, making traditional optimization methods inadequate for achieving high efficiency across all layers of the network. This paper proposes a cross-layer design and optimization framework leveraging Artificial Intelligence (AI) and Deep Learning (DL) algorithms, specifically Recurrent Neural Networks (RNN) and Deep Belief Networks (DBN), to address these challenges. The RNN is employed to model the temporal dependencies in the sensor data, while the DBN is used for optimizing decision-making processes across multiple network layers. The proposed framework dynamically adjusts routing, data aggregation, and power control parameters based on realtime conditions, improving overall network performance. Simulation results demonstrate that the proposed approach outperforms traditional cross-layer design methods. The RNN-DBN framework achieved a 35% improvement in energy efficiency, a 25% reduction in latency, and a 40% increase in data throughput compared to existing optimization techniques. These enhancements are particularly significant in large-scale, real-time sensor networks. [ABSTRACT FROM AUTHOR]

Multi-target tracking has made significant progress in recent years as a key player in the field of computer vision, but remains a challenging problem due to target similarity and complexity. In recent years, deep learning has pushed the field forward, and detection-based tracking methods use an end-to-end strategy that unifies target detection and trajectory modeling in a neural network framework, however, little use is made of appearance information. In this paper, we propose a Siamese structure-based approach that introduces an appearance search branch, aiming to enhance the system's ability to model the utilization of target appearance information. The method is validated on the basis of the FairMOT model, which generates a heat map reflecting the results of the target appearance search by means of feature vectors with multiple time dimensions and the Siamese module. The results of the detection branch and the appearance search branch are fused to form a final multi-target tracking system through post-processing and matching. Experiments demonstrate that the method achieves significant performance improvements over existing methods. This research provides a new perspective on the multi-target tracking problem, enhances the modeling and use of target appearance information through the appearance search branch, and provides an effective tool for system performance improvement in complex scenarios. [ABSTRACT FROM AUTHOR]

Vehicle Exterior Body Damage(VEBD) parts classification is important for claim processing, cost estimation, accident investigation, and vehicle damage assessment. Class imbalance in the VEBD part classification dataset is a primary factor affecting the classification performance of existing classification models. Although the availability of datasets and the system's capability significantly impact system performance, its damage part classification is still limited due to its dynamic body structure, size, shape, color, and types of damage. In this paper, we propose a novel heterogeneous ensemble learning (HEL) model based on VEBD data (VEBD-HEL) to deal with imbalanced data in VEBD. We validate the effectiveness of VEBD-HEL on two original and generated VEBD datasets. The experimental results demonstrate that compared with current state-of-the-art models, VEBD-HEL has the best comprehensive performance. The proposed model not only achieves good Accuracy (99. 93 %) rates for both the simple damage and the severe damage but also increases the Area Under Curve (AUC) to 99.83%. [ABSTRACT FROM AUTHOR]

With the advancement of Internet of Things (IoT) technology, underwater target detection and tracking have become increasingly important for ocean monitoring and resource management. Existing methods often fall short in handling high-noise and low-contrast images in complex underwater environments, lacking precision and robustness. This paper introduces a novel SVGS-DSGAT model that incorporates GraphSage for capturing and processing complex structural data, SVAM for guiding attention toward critical features, and DSGAT for refining feature relationships by emphasizing differences and similarities. These components work together to enhance the model's robustness and precision in underwater target recognition and tracking. The model integrates IoT technology to facilitate real-time data collection and processing, optimizing resource allocation and model responsiveness. Experimental results demonstrate that the SVGS-DSGAT model achieves an mAP of 40.8% on the URPC 2020 dataset and 41.5% on the SeaDronesSee dataset, significantly outperforming existing mainstream models. This IoT-enhanced approach not only excels in high-noise and complex backgrounds but also improves the overall efficiency and scalability of the system. This research provides an effective IoT solution for underwater target detection technology, offering significant practical application value and broad development prospects. [ABSTRACT FROM AUTHOR]

Video anomaly detection is a very important research topic, especially in the field of automatic driving, and timely acquisition of road conditions ahead is very important for safe driving. Past methods used convolution and other operations, resulting in severe delays or low detection accuracy. This paper introduces a cutting-edge video anomaly detection method that combines the advantages of image quality assessment and attention mechanisms while using image signal processing techniques to enhance the data. Our approach first uses image quality metrics to evaluate visual fidelity anomalies for each video frame, providing a computationally simple and effective method for initial anomaly recognition. Then, an attention mechanism is integrated into two deep learning models including convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This integration enables the system to dynamically focus on significant regions in the video. This capability is unmatched by traditional analysis methods. The dual-structure system shows higher sensitivity to various anomalies. In addition, the system is also equipped with image signals, which makes the data feature extraction more precise. Through thorough testing of the benchmark dataset, the proposed approach has been shown to significantly outperform current state-of-the-art models. It especially excels in challenging monitoring scenarios. For example, in the UCSD dataset, we achieved an area under curve (AUC) value of 99.9%, which exceeds most current methods. [ABSTRACT FROM AUTHOR]

Automatic Modulation Classification (AMC) has emerged as a critical research domain with wide-ranging applications in both civilian and military contexts. With the advent of artificial intelligence, deep learning techniques have gained prominence in AMC due to their unparalleled ability to automatically extract relevant features. However, most contemporary AMC models rely heavily on downsampling strategies to increase the receptive field while reducing computational complexity. Empirical evidence indicates that progressive downsampling substantially reduces the spatial resolution of feature maps, leading to poor generalization, particularly for closely related modulation schemes. To address these challenges, this paper proposes a novel Multiscale Dilated Pyramid Module (MDPM). In contrast to traditional downsampling techniques, MDPM mitigates resolution loss and retains a broader range of features, facilitating more comprehensive recognition. Furthermore, the multiscale features captured by MDPM enhance the robustness of the model to noise, thereby improving classification performance in noisy environments. The model's efficiency is further optimized through the integration of group convolutions and channel shuffle techniques. Extensive experimental results and evaluations confirm that the MDPM-based approach surpasses state-of-the-art methods, underscoring its significant potential for practical deployment. The signal database and model can be freely accessed at https://pan.baidu.com/s/1g_HQXcRXshrT8nwKUNDYrQ?pwd=9ug6. [ABSTRACT FROM AUTHOR]

This paper describes the detection of series arc faults, which constitute the major cause of electrical fires, in a power distribution system. Because the characteristics of series arc faults change considerably depending on the load type, their accurate detection and analysis are difficult. We propose a series‐arc‐fault detector that uses a transfer learning (TL)‐based feature fusion model. The model is trained stagewise for various features in the time and frequency domains using a one‐dimensional convolutional neural network combined with a long short‐term memory model that uses an attention mechanism to accurately detect arc‐fault features. To enhance the reliability of the proposed model, we implement an arc‐fault generator compliant with the UL1699 standard and acquire high‐quality data that suitably reflect the real environment. Experimental results show that the proposed model achieves an accuracy of 99.99% in classifying series arc faults for five different loads. Hence, a performance improvement of approximately 1.7% in classification accuracy is reached compared with a feature fusion model that does not incorporate TL‐based model transfer and the attention mechanism. [ABSTRACT FROM AUTHOR]