Deep Research Research Articles

Deep Learning-Based Image Style Transformation Research on Landscape Paintings of Wei, Jin and North-South Dynasties

Abstract In this paper, the convolutional neural network is applied to the processing of stylistic features in the images of landscape paintings of Wei Jin and North and South Dynasties. After convolution and pooling activation, rich and less parametric feature maps are generated to lay a solid foundation for generative adversarial networks. Meanwhile, in order to ensure the rigor of the image dataset of landscape painting images under scene transformation, an improvement is proposed on the basis of traditional GAN technology, and a function represents the improved CycleGAN model. The experimental dataset has been constructed, and the loss function, network training, and hyperparameters have been designed for the model. The visual and conversion outcomes of the model-generated images are evaluated through simulation experiments. The migration of all landscape painting style textures is within the range of (0.5,2.4) at a gray level of 8. The migration styles increase as the gray level increases, and the data between groups does not overlap. In the subjective evaluation of the landscape painting style transformation generated by the model used in this paper, the score of the generated image is 3.8135 points, while the number of high scores is more than 65% of the votes. The model constructed in this paper has a better effect on the transformation of the image style of the Wei, Jin, and North and South Dynasties, and it can satisfy people’s visual needs.

Domain affiliated distilled knowledge transfer for improved convergence of Ph-negative MPN identifier.

Ph-negative Myeloproliferative Neoplasm is a rare yet dangerous disease that can turn into more severe forms of disorders later on. Clinical diagnosis of the disease exists but often requires collecting multiple types of pathologies which can be tedious and time-consuming. Meanwhile, studies on deep learning-based research are rare and often need to rely on a small amount of pathological data due to the rarity of the disease. In addition, the existing research works do not address the data scarcity issue apart from using common techniques like data augmentation, which leaves room for performance improvement. To tackle the issue, the proposed research aims to utilize distilled knowledge learned from a larger dataset to boost the performance of a lightweight model trained on a small MPN dataset. Firstly, a 50-layer ResNet model is trained on a large lymph node image dataset of 3,27,680 images, followed by the trained knowledge being distilled to a small 4-layer CNN model. Afterward, the CNN model is initialized with the pre-trained weights to further train on a small MPN dataset of 300 images. Empirical analysis showcases that the CNN with distilled knowledge achieves 97% accuracy compared to 89.67% accuracy achieved by a clone CNN trained from scratch. The distilled knowledge transfer approach also proves to be more effective than more simple data scarcity handling approaches such as augmentation and manual feature extraction. Overall, the research affirms the effectiveness of transferring distilled knowledge to address the data scarcity issue and achieves better convergence when training on a Ph-Negative MPN image dataset with a lightweight model.

Review of Deep Learning-based Pedestrian Re-identification Research

Review of Deep Learning-based Pedestrian Re-identification Research

Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions.

Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020. Breast imaging plays a significant role in early diagnosis and intervention to improve the outcome of breast cancer patients. In the past decade, deep learning has shown remarkable progress in breast cancer imaging analysis, holding great promise in interpreting the rich information and complex context of breast imaging modalities. Considering the rapid improvement in deep learning technology and the increasing severity of breast cancer, it is critical to summarize past progress and identify future challenges to be addressed. This paper provides an extensive review of deep learning-based breast cancer imaging research, covering studies on mammograms, ultrasound, magnetic resonance imaging, and digital pathology images over the past decade. The major deep learning methods and applications on imaging-based screening, diagnosis, treatment response prediction, and prognosis are elaborated and discussed. Drawn from the findings of this survey, we present a comprehensive discussion of the challenges and potential avenues for future research in deep learning-based breast cancer imaging.

Digitized Perception of Piano Accompaniment in Songs with the Involvement of Deep Learning Techniques

Abstract In this paper, we use the Hanning window function to add windows to the piano accompaniment human brain perception signal, and the noise and redundant features in the piano accompaniment human brain perception signal are downgraded by principal component analysis and Relief algorithm for dimensionality reduction processing and feature selection. Based on the basic structure of RCNN, the ReConv-EEG Net EEG identity recognition method is established, and the feature vectors in the recurrent network are classified and computed through the feed-forward layer, the normalization layer and the output layer to obtain the feature values of the EEG signals. Under different speed accompaniments, the subjects perceived the high-speed piano accompaniment with the lowest α -wave power spectral value of 47.85 on average, while the original speed accompaniment had the most significant α -wave power spectral value of 49.12 on average.Meanwhile, there were differences in the perception of piano accompaniment among subjects, and the mean EEG δ -wave synchronization indexes of the non-musicians and the musicians differed by an average of 0.2297 when they were listening to the same accompaniment.The method in this paper contributes to developing a new method for deep learning-assisted music perception research in the field. Also, it lays the data foundation for applying the technique to the field.

Multi-Spatial Pyramid Feature and Optimizing Focal Loss Function for Object Detection

Previous deep convolutional neural network research has made significant progress toward improving the speed and accuracy of object detection. However, despite these advancements, the inaccurate detection of multi-object (small objects) remains challenging in the traffic environments. In this paper, we propose a new architecture called YOLOM, which is specifically designed to achieve enhanced multi-object (small objects) detection precision. YOLOM incorporates several innovative features: a multi-spatial pyramid (MSP), an optimized focal loss (OFLoss) function, and an objectness loss that incorporates effective intersection over union (EIoU) calculations. These features collectively yield enhanced accuracy and reduce the miss rate of small objects, particularly in the multi-object cases. According to the sizes of receptive field features with different spatial scales with pooling layers, we propose the MSP module. We optimize the focal loss as a classification function instead of the cross-entropy loss, which solves some class imbalance problems caused by anchor-free detection when encountering disparate datasets. Due to the superior performance of EIoU in confidence scoring, we use EIoU to participate in the objectness loss calculation of our work. Therefore, our method substitutes EIoU for YOLOX's objectness loss. The experimental results demonstrate that our strategies significantly outperform some end-to-end object detection methods.

Prediction of Energy Consumption in Horizontal Roughing Process of Hot Rolling Strip Based on TDADE Algorithm

The steel industry is the key industry of energy consumption. The optimization of rolling process parameters is an effective measure to reduce and optimize energy consumption. Accurate energy consumption prediction has an indispensable guiding function in the planning of process parameters. However, the traditional energy consumption prediction and machine learning methods have been unable to fit the needs of high precision and reliability. Taking the horizontal roughing process (HRP) of hot rolling process as the research object, this paper mainly introduces an energy consumption prediction mechanism model (ECPMM) based on a roller adaptive wear strategy by analyzing the strip forming mechanism and rolling process. Then, two directions adaptive differential evolution (TDADE) algorithm is proposed based on a novel adaptive strategy. This algorithm has better convergence speed and global optimization ability than other optimization algorithms in the parameter optimization of ECPMM. We carried out comparative experiments on five machine learning algorithms. The results show that the ECPMM optimized by TDADE is superior to the five machine learning algorithms in prediction accuracy and stability. Finally, we conducted ablation experiments on the energy consumption characteristics of the HRP process, which turns out that using a smaller reduction and roller radius can reduce energy consumption. Summarizing the above experimental results suggests that the ECPMM has high accuracy and robustness, and satisfies the requirements of practical application. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —It is necessary to carry out the deep analysis and research of energy consumption prediction involved in the process planning of strip hot rolling, the inspiration of this article is stem from this point. The commonly used energy consumption prediction methods include mechanism modeling and machine learning, but both have disadvantages, like low prediction accuracy and black box, which must have to be performed to solve by adapting the production demand of high reliability. In this paper, the combination of the mechanism model and data-driven method is used to realize the accurate prediction of energy consumption and improve the reliability of the model. To the best of our knowledge, this is the first paper about the research on energy consumption prediction of hot rolling process based on mechanism model and data-driven, especially in data size, time granularity, algorithm design, and prediction performance. Such research is helpful to guide engineers to design rolling energy consumption. We will dive a bit deeper into learning the energy consumption and process parameters during the rolling process in future studies.

Управління ресурсним потенціалом підприємства в умовах невизначеності

In the modern conditions of the operation of the enterprise, the formation and effective management of existing resources and opportunities, which can be used in the production and economic activity of the enterprise, is of great importance. The aim of the article is to study the processes of managing the enterprise's resource potential under conditions of uncertainty. Ensuring stable economic growth based on the effective use of the enterprise's resource potential is a necessary condition and a priority factor for strengthening improvement in the development of any economic entity. In today's world, under the conditions of limited resources, it is the internal resource potential of the enterprise that should be considered the main factor of its sustainable development. The formation of a management system for the effective use and further development of resource potential is a mandatory priority for both the management of the enterprise and all links of its structural subdivisions. Modern scientific approaches to the study of enterprise resource potential management require the consideration and analysis of theoretical approaches that should not only objectively reflect this object, but also be a tool for its further study and analysis. Resource potential is a specific economic category that studies the dependence between the volume, composition of resources, as well as the achievement of effective results of the enterprise. The result of effective use of resource potential is, first of all, the production of quality products, which makes it possible to achieve high efficiency. In connection with the insufficiently deep research of the resource potential in the domestic economy, this term did not receive an unambiguous interpretation of its economic essence. The article reveals the content and constituent elements of the enterprise's potential, in particular, regarding the formation and management of resource potential in conditions of uncertainty, the theoretical basis of enterprise resource potential management is considered, the constituent elements of the enterprise's resource potential are determined, among which it is especially appropriate to pay attention to the types, elements and sources of resource formation. For a more detailed study of the economic essence of the concepts of "enterprise potential", "resource potential", an analysis of their interpretations in modern scientific literature was carried out.

Research on the Construction of Campus Security Prevention and Control System Based on Internet of Things Technology

Abstract Campus safety is related to the healthy growth of students, and the research focus of this paper is to explore the impact of Internet of Things (IoT) technology on campus safety prevention and control. Based on the correlation between ISM and DEMATEL methods, this paper constitutes an integrated DEMATEL-ISM model by using neighbor matrix and reachable matrix to transform each other. It constructs a risk factor model for campus security prevention and control evaluation based on Internet of Things technology according to the modeling steps after soliciting experts’ suggestions through questionnaires. Combined with the SEM model to estimate students’ campus risk identification ability, the path index was used to construct the college security awareness score index to explore the relationship between latent variables (influencing factors) and observed variables (risk identification ability). The results show that every 1% increase in the safety climate of the social environment will lead to the rise of 0.58%, 0.20%, and 0.52% in the on-campus environment factor, the campus safety management team building factor, and the students’ literacy factor, respectively. A 0.17% increase in the on-campus environment will occur with every 1% increase in students’ literacy in higher education. This study contributes to a deeper understanding of the role of IoT technology in enhancing campus security prevention and control. It can provide deep research references for subsequent risk grading evaluation, risk warning prevention and control, and supervision in campus risk management.

Дослідження моделей та алгоритмів систем локалізацій джерел магнітних аномалій

Introduction. The application of modern geophysical methods are caused by the challenges of nowadays Ukraine standing with. The high efficiency of geophysical research is shown by the methods of magnetic exploration. Method of analyzing the array of data from the magnetometer is used to localize the magnetic anomaly’s sources. Such localization is implemented by using various mathematical models and algorithms of software systems. Purpose. The aim of the article is to show an overview of mathematical models and algorithms for the localization of magnetic anomalies’ sources (disturbances). They allow to speed up the processing of magnetometric research’s data and visualize the obtained results. Methods. The article examines the mathematical models of the magnetic anomaly&lt; such as magnetic dipole model, the Gaussian model, the Schwartz model. The multilayer model, and also provides the overview of the main methods for the localization of the described anomaly – the filtering method, the least square method, the gradient analysis method. A list of software and online resources is given, this software is used to analyze magnetometer data and locate magnetic anomalies’ sources. Results. Four mathematical models of magnetic anomalies that allow describing objects of various configurations are considered in the article, and the main methods of determining these objects in the magnetometer data array are given. The article presents the most popular software used for magnetometric data processing. Most of the software is used in geophysics for deep research and requires significant computing resources. A software application was proposed and developed. It allows importing data from the moving platform and magnetometer, analyzing data and visualizing the results. Conclusion. The results of the review emphasize the importance of improving existing mathematical models and developing specialized software for magnetic anomalies’ source localization.

Progress in MXene‐based catalysts for oxygen evolution reaction

AbstractElectrochemical water splitting for hydrogen generation is considered one of the most promising strategies for reducing the use of fossil fuels and storing renewable electricity in hydrogen fuel. However, the anodic oxygen evolution process remains a bottleneck due to the remarkably high overpotential of about 300 mV to achieve a current density of 10 mA cm−2. The key to solving this dilemma is the development of highly efficient catalysts with minimized overpotential, long‐term stability, and low cost. As a new 2D material, MXene has emerged as an intriguing material for future energy conversion technology due to its benefits, including superior conductivity, excellent hydrophilic properties, high surface area, versatile chemical composition, and ease of processing, which make it a potential constituent of the oxygen evolution catalyst layer. This review aims to summarize and discuss the recent development of oxygen evolution catalysts using MXene as a component, emphasizing the synthesis and synergistic effect of MXene‐based composite catalysts. Based on the discussions summarized in this review, we also provide future research directions regarding electronic interaction, stability, and structural evolution of MXene‐based oxygen evolution catalysts. We believe that a broader and deeper research in this area could accelerate the discovery of efficient catalysts for electrochemical oxygen evolution.

The Impact of Egocentric Parenting Patterns on Children in Egocentric Novel by Sahid Muhammad

This research was conducted to determine the impact of parents who have an egocentric nature and the parenting patterns used by children to see school counseling guidance on mothers and fathers in inappropriate and egocentric parenting patterns on children so that at least children can choose or take the results they want. always chosen by parents. The research method used is a narrative method using a qualitative approach. Then technique collection of relevant data with method library data collection, reading, recording and managing material study. Deep data analysis research This use data reduction is conclude the data so researcher know step in research. The results of this research are that there are still some parents who apply inappropriate parenting patterns, mothers and fathers with an egocentric nature will make children unable to make decisions because children are not allowed to choose. What children like. So it can be concluded that if the good and bad of a child's character is seen from the parenting style carried out by the mother and father at home, then it is necessary to provide direction in the form of parenting patterns with counseling guidance to the students' parents at school.

Research progress of monoclonal antibody in the treatment of lung cancer

The largest cause of cancer-related deaths is lung cancer. Conventional therapies like chemotherapy, surgery and radiation therapy have been widely used in treating cancer including lung cancer. However, the fact is that these conventional therapies may generate severe adverse effects. For example, they are lack of specificity, they could not treat the target tissue specifically. When processing these conventional treatments, adjacent normal cells and tissues may be harmed. With this kind of problem in treating lung cancer, more and more therapeutic drugs and therapies are being develop to reduce such problems. Monoclonal antibody treatment is an example. Since the concept of magic bullet had been introduced by Pual Ehrlich, scientists have been inspired to conduct further and deeper research into monoclonal antibody treatment. In this concept, antibodies are said to be magic bullets since they are useful tool to treat foreign cells. Since then, scientists had been devoting themselves to the development of monoclonal antibodies. These days several monoclonal antibodies are FDA approved. Since monoclonal antibodies work through various mechanisms, it plays an important role in cancer therapies. One monoclonal antibody is specific to only one type of antigen and it works by trigger the immune system. Monoclonal antibodies would become the focus of future research.

Transboundary Livestock Network in Africa: How Circulate Pathogens and Where to Act to Prevent the Epizootics Spread?

Objectives: Transboundary animal diseases (TADs) of domestic ruminants are closely linked to livestock movements, consequently, understanding these latter provides information on the pathogen's dissemination pathways. This descriptive study, using the mapping and network analysis (NA) method, aims to characterize the cross-border mobility network of domestic ruminants on the African continent, to understand how it works, to identify the main countries controlling livestock mobility, to deduct their relationships with other countries, and finally, to highlight the articulation points of the network at which actions should be taken to stop the epizootics spread. Methodology: This is a synthetic, descriptive study, whose results make it possible to place it within the framework of epidemiological surveillance with a continental scope, aiming to guide the efforts of the concerned authorities. Based on deep documentary research, a total of 483 transhumant and commercial cross-border movements were identified. These movements were mapped by the geographic information system (GIS) to reconstruct the network of international movements between countries. The most regular movements, numbering 190 and constituting a more stable exchange network over time, were subjected to processing by the NA method, to highlight different indicators that permit the characterization of the network. The results obtained were then compared with health data on the distribution of the five main notifiable animal diseases circulating in the African continent in addition to rinderpest. All analyses were conducted using “R” software. Results: The centrality indicators enabled the identification of the main central countries, including the most active and unavoidable ones that contribute to diseases spread in Africa. They also made it possible to quantify their importance in the influence of movement, while the global measurements and network cohesion parameters showed that the latter is vulnerable to the spread of epizootics. This study revealed a strong livestock exchange relationship between 25 African countries, extending from nations on the Atlantic Ocean coasts to those of the Indian Ocean ones, which were found to be the most vulnerable to the establishment of contagious diseases. Different communities of countries whose livestock movements appear to be very cohesive and which presage significant mutual contamination have been highlighted. Certain African countries have proven to be key points in the articulation of flows between different countries and different regions and contribute significantly to the dissemination of diseases between the different regions of the continent. Accordingly, key countries where actions should be taken to stop the epizootics spread were identified. Conclusion: The results allowed a better understanding of diseases diffusion pathways through livestock movements across Africa and highlighted the main movement focal points which represent a high-risk of diseases spread, as well as the capacity to influence their diffusion through the control of the animal’s movement or the deployment of prophylactic actions at their level.

BRAIN TUMOR DETECTION

Brain tumor detection is a significant problem in medical diagnostics since early and accurate detection improves patient outcomes. Traditional tumor identification techniques often depend on manual interpretation of medical examination, which can be time-consuming and prone to humanerror. Algorithms based on deep learning have emerged in recent years as a viable way to automateand enhance brain tumor identification using medical imaging data. This paper conveys an extensive look on the use of deep learning for brain tumor identification. A Convolutional NeuralNetwork(CNN) architecture is put forward to reach minimum accuracy of 97% and maximum of 100%, using its abilities to automatically learn hierarchical attributes from medical imagery that involve Magnetic Resonance Imaging(MRI) scans. To learn discriminative features suggestive oftumor presence, the suggested CNN framework is trained an extensive collection of labeled brainMRI images. The findings from experiments show that the proposed deep learning approach works. The trained CNN is quite good at differentiating between tumor and non-tumor regions in brain scans. Furthermore, cross-validation and unbiased evaluation are used to assess the model’scapacity to generalize to data that was previously unavailable. Deep learning in brain tumor identification has the potential to greatly enhance diagnostic accuracy, reduce human error, and speed up decision-making. As deep learning research advances, future studies may look at the amalgamation of multi-modal imaging data, transfer learning, and ensemble techniques in order to boost the robustness and generalizability of brain tumor diagnosis. The proposed deep learning-based brain tumor detection system offers the potential for improving medical professionals’ capacity to properly and instantly diagnose brain tumors, ultimately leading to improvements in patient care and outcomes. Keywords: Brain Tumor detection, Diagnosis, Deep Learning, Convolutional NeuralNetworks, Pooling, MRI Dataset

Potential risks of developing countries in the process of exploration and extraction of deep-sea mineral resources

&lt;p&gt;Deep sea mining involves the extraction of minerals from the ocean floor. As deep sea mining is a relatively new practice, there is still much to be learned about the technology and the potential risks associated with it by the developing countries. Developing states must ensure that proper safety measures are in place to prevent accidents and minimize the risk of environmental damage. While the potential benefits of deep sea mining are significant, it is essential to ensure that the process is carried out responsibly and sustainably to protect both the environment and local communities. Developing countries face numerous challenges when it comes to actively participating in deep-sea exploration. Some of these challenges include a lack of adequate resources, limited technological capabilities, and limited access to funding. Additionally, developing countries often lack the necessary legal frameworks and regulatory systems to effectively regulate deep-sea exploration, licensing and extraction activities, especially within the continental shelves and the Exclusive Economic Zones (EEZ). These challenges can make it difficult for developing countries to fully participate in this important area of scientific research for a sustainable blue economy. This paper suggests an effective partnership between oceanographic research institutes from developing countries with research institutes from countries like France, Germany, UK, Belgium, Netherlands, China and International seabed Authority (ISA) in deep sea marine scientific research. The paper identifies the need for a joint collaboration for the purpose of acquiring reliable data on the seabed topography, location, shape, coverage, and abundance of deep-sea mineral resources in the continental shelves, exclusive economic zones of developing countries, and area beyond the national jurisdiction. There is also a need to develop legal framework on deep sea policy for sustainable actualization of developing nations’ blue economy.&lt;strong&gt;&lt;/strong&gt;&lt;/p&gt;

Fairness in Deep Learning: A Survey on Vision and Language Research

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring unfair decision-making, the AI community has concentrated efforts on correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI . In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy that builds upon previous proposals but is tailored for deep learning research to better organize the literature on debiasing methods for fairness. We review all important neural-based methods and evaluation metrics while discussing the current challenges, trends, and important future work directions for the interested researcher and practitioner.

Создание «Поморской энциклопедии» на Архангельском Севере: история, опыт и проблемы

This article dwells on the process of creating the five-volume Pomor Encyclopaedia. This regional encyclopaedia combines and structures current knowledge about the most significant events in the history, economy and culture of the Arkhangelsk Region, as well as about its geography and nature. The fundamental publication involved deep research into the key problems of Pomorye and can be credited with well-designed biographical entries and carefully selected bibliography. In addition, the authors highlight the difficulties that arose in the course of such a large-scale project.

Exploring the Cargo Potential: A Comprehensive Analysis of Kertajati Airport

Kertajati Airport was constructed to cater the growing demand from West Java Province and its surrounding areas, aiming to address the limitations faced by the previous airport, Husein Sastranegara International Airport in Bandung. The intention was to relieve pressure from Soekarno-Hatta International Airport and accommodate passengers from the former airport. However, since its inauguration in 2018, the airport's activities have fallen short of initial expectations. In response to this challenge, the West Java Provincial Government has strategized to reposition Kertajati Airport as a dedicated cargo-centric facility, aiming to pivot its focus to a financial solution. This study encompasses an in-depth analysis of the cargo potential, considering the key commodities within West Java, strategies for cargo transfer from Soekarno-Hatta and Husein Sastranegara airports, estimated travel time and associated costs to Kertajati Airport, and the most efficient aircraft types for cargo transportation. The findings reveal that Kertajati Airport's catchment area encompasses 19 districts/cities (70%) within West Java and 3 districts/cities (9%) in Central Java. The demand forecasting analysis projects the volume for international and domestic cargo in 2028 originating from Soekarno-Hatta Airport, indicating a 13% transfer, are 62 tons and 56 tons, respectively. Concurrently, the anticipated demand volume for international and domestic cargo transfer from Husein Sastranegara Airport in 2023 are 4 tons and 30 tons, respectively. The concentration of cargo potential lies prominently in areas rich in key commodities, notably Bandung City, Bandung Barat District, Tasikmalaya District, Garut District, and Sumedang District. The results indicate that there is a potential to promote the Kertajati Airport into a cargo-centric facility. More deep research with more data will give more confidence to focus in developing this facility.

Multi-station Magnetotelluric Data Processing Based on Singular Value Decompositionl

Singular value decomposition is an efficient matrix analysis method. This paper intends to use SVD to process magnetotelluric data from multiple stations. The data of multiple magnetotellus observation stations can make the main reactance of magnetotellus obtained by data processing more robust, suppress the interference signal, improve the data quality, and effectively increase the signal strength. The obtained results are more in line with the actual situation, and the decomposition by singular value method can greatly improve the efficiency of electromagnetic signal processing. Better access to underground information, geological resource exploration and deep earth research.