Pub Date : 2024-11-16DOI: 10.1016/j.jksuci.2024.102233
Huan Wang, Wei Song
Studying the correlation analysis of stock price fluctuations helps to understand market dynamics better and improve the scientific nature of investment decisions and risk management capabilities. Most existing methods use multifractals to explore the correlation between different economic entities. However, the study of multifractals fails to fully consider the weight of each entity’s impact on the market, resulting in an inaccurate description of the overall market dynamics. To address this problem, this paper creatively proposes a weighted multifractal analysis method (WMA). The correlation analysis of government regulation, market supply and demand, and stock price index is performed using the data of A-share listed companies in Shenzhen and Shanghai as samples. First, we consider the amplitude fluctuation information the signal carries and weigh the partition function according to the proportion of variance in the segment for different amplitude changes. Secondly, we derive the theoretical analytical form of the classical multifractal model (SMA) of the scaling indicator under WMA. Finally, through numerical simulation experiments, it is confirmed that WMA is equally effective as SMA. In addition, the re-fractal correlation analysis of real financial time series also confirms that WMA can effectively utilize the amplitude fluctuation information in the series and outperforms the classical SMA method in distinguishing different signals.
研究股价波动的相关性分析有助于更好地了解市场动态，提高投资决策的科学性和风险管理能力。现有方法大多采用多分形来探讨不同经济实体之间的相关性。然而，对多分形的研究未能充分考虑各实体对市场影响的权重，导致对整体市场动态的描述不准确。针对这一问题，本文创造性地提出了加权多分形分析方法（WMA）。以深市和沪市 A 股上市公司数据为样本，对政府调控、市场供求和股价指数进行相关性分析。首先，我们考虑了信号所携带的振幅波动信息，并根据不同振幅变化在分段中的方差比例来权衡分区函数。其次，我们推导出 WMA 下缩放指标的经典多分形模型（SMA）的理论解析形式。最后，通过数值模拟实验，证实 WMA 与 SMA 同样有效。此外，对真实金融时间序列的重分形相关性分析也证实，WMA 可以有效利用序列中的振幅波动信息，在区分不同信号方面优于经典的 SMA 方法。
{"title":"Correlation analysis of multifractal stock price fluctuations based on partition function","authors":"Huan Wang, Wei Song","doi":"10.1016/j.jksuci.2024.102233","DOIUrl":"10.1016/j.jksuci.2024.102233","url":null,"abstract":"<div><div>Studying the correlation analysis of stock price fluctuations helps to understand market dynamics better and improve the scientific nature of investment decisions and risk management capabilities. Most existing methods use multifractals to explore the correlation between different economic entities. However, the study of multifractals fails to fully consider the weight of each entity’s impact on the market, resulting in an inaccurate description of the overall market dynamics. To address this problem, this paper creatively proposes a weighted multifractal analysis method (WMA). The correlation analysis of government regulation, market supply and demand, and stock price index is performed using the data of A-share listed companies in Shenzhen and Shanghai as samples. First, we consider the amplitude fluctuation information the signal carries and weigh the partition function according to the proportion of variance in the segment for different amplitude changes. Secondly, we derive the theoretical analytical form of the classical multifractal model (SMA) of the scaling indicator under WMA. Finally, through numerical simulation experiments, it is confirmed that WMA is equally effective as SMA. In addition, the re-fractal correlation analysis of real financial time series also confirms that WMA can effectively utilize the amplitude fluctuation information in the series and outperforms the classical SMA method in distinguishing different signals.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102233"},"PeriodicalIF":5.2,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-15DOI: 10.1016/j.jksuci.2024.102238
Abdulbasit A. Darem , Tareq M. Alkhaldi , Asma A. Alhashmi , Wahida Mansouri , Abed Saif Ahmed Alghawli , Tawfik Al-Hadhrami
Sixth-generation (6G) communication advancements target massive connectivity, ultra-reliable low-latency communication (URLLC), and high data rates, essential for IoT applications. Yet, in natural disasters, particularly in dense urban areas, 6G quality of service (QoS) can falter when terrestrial networks—such as base stations—become unavailable, unstable, or strained by high user density and dynamic environments. Additionally, high-rise buildings in smart cities contribute to signal blockages. To ensure reliable, high-quality connectivity, integrating low-Earth Orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and reconfigurable intelligent surfaces (RIS) into a multilayer (ML) network offers a solution: LEO satellites provide broad coverage, UAVs reduce congestion with flexible positioning, and RIS enhances signal quality. Despite these benefits, this integration brings challenges in resource allocation, requiring path loss models that account for both line-of-sight (LOS) and non-line-of-sight (NLOS) links. To address these, a joint optimization problem is formulated focusing on resource distribution fairness. Given its complexity, a framework is proposed to decouple the problem into subproblems using the block coordinate descent (BCD) method. These subproblems include UAV placement optimization, user association, subcarrier allocation via orthogonal frequency division multiple access (OFDMA), power allocation, and RIS phase shift control. OFDMA efficiently manages shared resources and mitigates interference. This iterative approach optimizes each subproblem, ensuring convergence to a locally optimal solution. Additionally, we propose a low-complexity solution for RIS phase shift control, proving its feasibility and efficiency mathematically. The numerical results demonstrate that the proposed scheme achieves up to 43.5% higher sum rates and 80% lower outage probabilities compared to the schemes without RIS. The low complexity solution for RIS optimization achieves performance within 1.8% of the SDP approach in terms of the sum rate. This model significantly improves network performance and reliability, achieving a 16.3% higher sum rate and a 44.4% reduction in outage probability compared to joint optimization of SAT-UAV resources. These findings highlight the robustness and efficiency of the ML network model, making it ideal for next-generation communication systems in high-density urban environments.
{"title":"Optimizing resource allocation for enhanced urban connectivity in LEO-UAV-RIS networks","authors":"Abdulbasit A. Darem , Tareq M. Alkhaldi , Asma A. Alhashmi , Wahida Mansouri , Abed Saif Ahmed Alghawli , Tawfik Al-Hadhrami","doi":"10.1016/j.jksuci.2024.102238","DOIUrl":"10.1016/j.jksuci.2024.102238","url":null,"abstract":"<div><div>Sixth-generation (6G) communication advancements target massive connectivity, ultra-reliable low-latency communication (URLLC), and high data rates, essential for IoT applications. Yet, in natural disasters, particularly in dense urban areas, 6G quality of service (QoS) can falter when terrestrial networks—such as base stations—become unavailable, unstable, or strained by high user density and dynamic environments. Additionally, high-rise buildings in smart cities contribute to signal blockages. To ensure reliable, high-quality connectivity, integrating low-Earth Orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and reconfigurable intelligent surfaces (RIS) into a multilayer (ML) network offers a solution: LEO satellites provide broad coverage, UAVs reduce congestion with flexible positioning, and RIS enhances signal quality. Despite these benefits, this integration brings challenges in resource allocation, requiring path loss models that account for both line-of-sight (LOS) and non-line-of-sight (NLOS) links. To address these, a joint optimization problem is formulated focusing on resource distribution fairness. Given its complexity, a framework is proposed to decouple the problem into subproblems using the block coordinate descent (BCD) method. These subproblems include UAV placement optimization, user association, subcarrier allocation via orthogonal frequency division multiple access (OFDMA), power allocation, and RIS phase shift control. OFDMA efficiently manages shared resources and mitigates interference. This iterative approach optimizes each subproblem, ensuring convergence to a locally optimal solution. Additionally, we propose a low-complexity solution for RIS phase shift control, proving its feasibility and efficiency mathematically. The numerical results demonstrate that the proposed scheme achieves up to 43.5% higher sum rates and 80% lower outage probabilities compared to the schemes without RIS. The low complexity solution for RIS optimization achieves performance within 1.8% of the SDP approach in terms of the sum rate. This model significantly improves network performance and reliability, achieving a 16.3% higher sum rate and a 44.4% reduction in outage probability compared to joint optimization of SAT-UAV resources. These findings highlight the robustness and efficiency of the ML network model, making it ideal for next-generation communication systems in high-density urban environments.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102238"},"PeriodicalIF":5.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-14DOI: 10.1016/j.jksuci.2024.102235
Deep Singh , Sandeep Kumar , Chaman Verma , Zoltán Illés , Neerendra Kumar
Image ciphering techniques usually transform a given plain image data into a cipher image data resembling noise, serving as an indicator of the presence of secret image data. However, the transmission of such noise-like images could draw attention, thereby attracting the attackers and may face several possible attacks. This paper presents an approach for generating a visually meaningful image encryption (VMIE) scheme that combines three layers of security protection: encryption, digital signature, and steganography. The present scheme is dedicated to achieving a balanced performance in robustness, security and operational efficiency. First, the original image is partially encrypted by using the RSA cryptosystem and modified Hénon map (MHM). In the second stage, a digital signature is generated for the partially encrypted image by employing a hash function and the RSA cryptosystem. The obtained digital signature is appended to the partially encrypted image produced after implementing the zigzag confusion in the above partially encrypted image. Further, to achieve better confusion and diffusion, the partially encrypted image containing a digital signature undergoes through the application of 3D Arnold cat map ( times), to produce the secret encrypted image . To ensure the security and robustness of the proposed technique against various classical attacks, the hash value obtained from the SHA-256 hash function and carrier images is utilized to generate the initial conditions and for modified Hénon map, and initial position for zigzag confusion. In the proposed algorithm, the digital signature is utilized for both purposes to verify the sender’s authenticity and to enhance the encryption quality. The carrier image undergoes lifting wavelet transformation, and its high-frequency components are utilized in the embedding process through a permuted pattern of MHM, resulting in a visually meaningful encrypted image. The proposed scheme achieves efficient visual encryption with minimal distortion and ensures lossless image quality upon decryption (infinite PSNR), balancing high level of security along with a good computational efficiency.
{"title":"Visually meaningful image encryption for secure and authenticated data transmission using chaotic maps","authors":"Deep Singh , Sandeep Kumar , Chaman Verma , Zoltán Illés , Neerendra Kumar","doi":"10.1016/j.jksuci.2024.102235","DOIUrl":"10.1016/j.jksuci.2024.102235","url":null,"abstract":"<div><div>Image ciphering techniques usually transform a given plain image data into a cipher image data resembling noise, serving as an indicator of the presence of secret image data. However, the transmission of such noise-like images could draw attention, thereby attracting the attackers and may face several possible attacks. This paper presents an approach for generating a visually meaningful image encryption (VMIE) scheme that combines three layers of security protection: encryption, digital signature, and steganography. The present scheme is dedicated to achieving a balanced performance in robustness, security and operational efficiency. First, the original image is partially encrypted by using the RSA cryptosystem and modified Hénon map (MHM). In the second stage, a digital signature is generated for the partially encrypted image by employing a hash function and the RSA cryptosystem. The obtained digital signature is appended to the partially encrypted image produced after implementing the zigzag confusion in the above partially encrypted image. Further, to achieve better confusion and diffusion, the partially encrypted image containing a digital signature undergoes through the application of 3D Arnold cat map (<span><math><mrow><mi>A</mi><msub><mrow><mi>R</mi></mrow><mrow><mi>n</mi><mi>o</mi></mrow></msub></mrow></math></span> times), to produce the secret encrypted image <span><math><mrow><mo>(</mo><msub><mrow><mi>S</mi></mrow><mrow><mi>r</mi><mn>5</mn></mrow></msub><mo>)</mo></mrow></math></span>. To ensure the security and robustness of the proposed technique against various classical attacks, the hash value obtained from the SHA-256 hash function and carrier images is utilized to generate the initial conditions <span><math><mrow><mi>M</mi><msub><mrow><mi>h</mi></mrow><mrow><mn>10</mn></mrow></msub></mrow></math></span> and <span><math><mrow><mi>M</mi><msub><mrow><mi>h</mi></mrow><mrow><mn>20</mn></mrow></msub></mrow></math></span> for modified Hénon map, and initial position <span><math><mrow><msub><mrow><mi>Z</mi></mrow><mrow><mi>i</mi><mi>p</mi></mrow></msub><mo>=</mo><mrow><mo>(</mo><msub><mrow><mi>z</mi></mrow><mrow><mi>r</mi><mi>o</mi><mi>w</mi></mrow></msub><mo>,</mo><msub><mrow><mi>z</mi></mrow><mrow><mi>c</mi><mi>o</mi><mi>l</mi></mrow></msub><mo>)</mo></mrow></mrow></math></span> for zigzag confusion. In the proposed algorithm, the digital signature is utilized for both purposes to verify the sender’s authenticity and to enhance the encryption quality. The carrier image undergoes lifting wavelet transformation, and its high-frequency components are utilized in the embedding process through a permuted pattern of MHM, resulting in a visually meaningful encrypted image. The proposed scheme achieves efficient visual encryption with minimal distortion and ensures lossless image quality upon decryption (infinite PSNR), balancing high level of security along with a good computational efficiency.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102235"},"PeriodicalIF":5.2,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.jksuci.2024.102236
Jie Meng , Yingqi Lu , Wangjiao He , Xiangsuo Fan , Gechen Zhou , Hongjian Wei
The detection of white blood cells provides important information in cellular research regarding infections, inflammation, immune function, and blood pathologies. Effective segmentation of WBCs in blood microscopic images not only aids pathologists in making more accurate diagnoses and early detections but is also crucial for identifying the types of lesions. Due to significant differences among various types of pathological WBCs and the complexities associated with cellular imaging and staining techniques, accurately recognizing and segmenting these different types of WBCs remains challenging. To address these challenges, this paper proposes a WBC segmentation technique based on DenseREU-Net, which enhances feature exchange and reuse by employing Dense Blocks and residual units. Additionally, it introduces mixed pooling and skip multi-scale fusion modules to improve the recognition and segmentation accuracy of different types of pathological WBCs. This study was validated on two datasets provided by DML-LZWH (Liuzhou Workers’ Hospital Medical Laboratory). Experimental results indicate that on the multi-class dataset, DenseREU-Net achieves an average IoU of 73.05% and a Dice coefficient of 80.25%. For the binary classification blind sample dataset, the average IoU and Dice coefficient are 83.98% and 90.41%, respectively. In both datasets, the proposed model significantly outperforms other advanced medical image segmentation algorithms. Overall, DenseREU-Net effectively analyzes blood microscopic images and accurately recognizes and segments different types of WBCs, providing robust support for the diagnosis of blood-related diseases.
{"title":"Leukocyte segmentation based on DenseREU-Net","authors":"Jie Meng , Yingqi Lu , Wangjiao He , Xiangsuo Fan , Gechen Zhou , Hongjian Wei","doi":"10.1016/j.jksuci.2024.102236","DOIUrl":"10.1016/j.jksuci.2024.102236","url":null,"abstract":"<div><div>The detection of white blood cells provides important information in cellular research regarding infections, inflammation, immune function, and blood pathologies. Effective segmentation of WBCs in blood microscopic images not only aids pathologists in making more accurate diagnoses and early detections but is also crucial for identifying the types of lesions. Due to significant differences among various types of pathological WBCs and the complexities associated with cellular imaging and staining techniques, accurately recognizing and segmenting these different types of WBCs remains challenging. To address these challenges, this paper proposes a WBC segmentation technique based on DenseREU-Net, which enhances feature exchange and reuse by employing Dense Blocks and residual units. Additionally, it introduces mixed pooling and skip multi-scale fusion modules to improve the recognition and segmentation accuracy of different types of pathological WBCs. This study was validated on two datasets provided by DML-LZWH (Liuzhou Workers’ Hospital Medical Laboratory). Experimental results indicate that on the multi-class dataset, DenseREU-Net achieves an average IoU of 73.05% and a Dice coefficient of 80.25%. For the binary classification blind sample dataset, the average IoU and Dice coefficient are 83.98% and 90.41%, respectively. In both datasets, the proposed model significantly outperforms other advanced medical image segmentation algorithms. Overall, DenseREU-Net effectively analyzes blood microscopic images and accurately recognizes and segments different types of WBCs, providing robust support for the diagnosis of blood-related diseases.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102236"},"PeriodicalIF":5.2,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-09DOI: 10.1016/j.jksuci.2024.102232
Jidong Ma (继东) , Hairu Wang (王海茹)
Detecting anomalies in multivariate time series data is crucial for maintaining the optimal functionality of control system equipment. While existing research has made significant strides in this area, the increasing complexity of industrial environments poses challenges in accurately capturing the interactions between variables. Therefore, this paper introduces an innovative anomaly detection approach that extends one-dimensional time series into two-dimensions to capture the spatial correlations within the data. Unlike traditional approaches, we utilize the Gramian Angular Field to encode the correlations between different sensors at specific time points into images, enabling precise learning of spatial information across multiple variables. Subsequently, we construct an adversarial generative model to accurately identify anomalies at the pixel level, facilitating precise localization of abnormal points. We evaluate our method using five open-source datasets from various fields. Our method outperforms state-of-the-art anomaly detection techniques across all datasets, showcasing its superior performance. Particularly, our method achieves a 11.5% increase in F1 score on the high-dimensional WADI dataset compared to the baseline method. Additionally, we conduct thorough effectiveness analysis, parameter impact experiments, significant statistical analysis, and burden analysis, confirming the efficacy of our approach in capturing both the temporal dynamics and spatial relationships inherent in multivariate time series data.
检测多变量时间序列数据中的异常情况对于保持控制系统设备的最佳功能至关重要。虽然现有研究在这一领域取得了长足进步，但工业环境的日益复杂性给准确捕捉变量之间的相互作用带来了挑战。因此，本文引入了一种创新的异常检测方法，将一维时间序列扩展到二维，以捕捉数据中的空间相关性。与传统方法不同，我们利用格拉米安角场（Gramian Angular Field）将特定时间点上不同传感器之间的相关性编码成图像，从而实现跨多个变量的空间信息的精确学习。随后，我们构建了一个对抗生成模型，以准确识别像素级别的异常，从而促进异常点的精确定位。我们使用来自不同领域的五个开源数据集对我们的方法进行了评估。在所有数据集上，我们的方法都优于最先进的异常检测技术，展示了其卓越的性能。特别是，与基线方法相比，我们的方法在高维 WADI 数据集上的 F1 分数提高了 11.5%。此外，我们还进行了全面的有效性分析、参数影响实验、重要统计分析和负担分析，证实了我们的方法在捕捉多元时间序列数据中固有的时间动态和空间关系方面的功效。
{"title":"Anomaly detection in sensor data via encoding time series into images","authors":"Jidong Ma (继东) , Hairu Wang (王海茹)","doi":"10.1016/j.jksuci.2024.102232","DOIUrl":"10.1016/j.jksuci.2024.102232","url":null,"abstract":"<div><div>Detecting anomalies in multivariate time series data is crucial for maintaining the optimal functionality of control system equipment. While existing research has made significant strides in this area, the increasing complexity of industrial environments poses challenges in accurately capturing the interactions between variables. Therefore, this paper introduces an innovative anomaly detection approach that extends one-dimensional time series into two-dimensions to capture the spatial correlations within the data. Unlike traditional approaches, we utilize the Gramian Angular Field to encode the correlations between different sensors at specific time points into images, enabling precise learning of spatial information across multiple variables. Subsequently, we construct an adversarial generative model to accurately identify anomalies at the pixel level, facilitating precise localization of abnormal points. We evaluate our method using five open-source datasets from various fields. Our method outperforms state-of-the-art anomaly detection techniques across all datasets, showcasing its superior performance. Particularly, our method achieves a 11.5% increase in F1 score on the high-dimensional WADI dataset compared to the baseline method. Additionally, we conduct thorough effectiveness analysis, parameter impact experiments, significant statistical analysis, and burden analysis, confirming the efficacy of our approach in capturing both the temporal dynamics and spatial relationships inherent in multivariate time series data.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102232"},"PeriodicalIF":5.2,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-07DOI: 10.1016/j.jksuci.2024.102230
Zhu Chen, Fan Li, Yueqin Diao, Wanlong Zhao, Puyin Fan
Infrared and visible image fusion aims at generating high-quality images that serve both human and machine visual perception under extreme imaging conditions. However, current fusion methods primarily rely on datasets comprising infrared and visible images captured under clear weather conditions. When applied to real-world scenarios, image fusion tasks inevitably encounter challenges posed by adverse weather conditions such as heavy fog, resulting in difficulties in obtaining effective information and inferior visual perception. To address these challenges, this paper proposes a Mean Teacher-based Self-supervised Image Restoration and multimodal Image Fusion joint learning network (SIRIFN), which enhances the robustness of the fusion network in adverse weather conditions by employing deep supervision from a guiding network to the learning network. Furthermore, to enhance the network’s information extraction and integration capabilities, our Multi-level Feature Collaborative adaptive Reconstruction Network (MFCRNet) is introduced, which adopts a multi-branch, multi-scale design, with differentiated processing strategies for different features. This approach preserves rich texture information while maintaining semantic consistency from the source images. Extensive experiments demonstrate that SIRIFN outperforms current state-of-the-art algorithms in both visual quality and quantitative evaluation. Specifically, the joint implementation of image restoration and multimodal fusion provides more effective information for visual tasks under extreme weather conditions, thereby facilitating downstream visual tasks.
{"title":"Knowledge-embedded multi-layer collaborative adaptive fusion network: Addressing challenges in foggy conditions and complex imaging","authors":"Zhu Chen, Fan Li, Yueqin Diao, Wanlong Zhao, Puyin Fan","doi":"10.1016/j.jksuci.2024.102230","DOIUrl":"10.1016/j.jksuci.2024.102230","url":null,"abstract":"<div><div>Infrared and visible image fusion aims at generating high-quality images that serve both human and machine visual perception under extreme imaging conditions. However, current fusion methods primarily rely on datasets comprising infrared and visible images captured under clear weather conditions. When applied to real-world scenarios, image fusion tasks inevitably encounter challenges posed by adverse weather conditions such as heavy fog, resulting in difficulties in obtaining effective information and inferior visual perception. To address these challenges, this paper proposes a Mean Teacher-based Self-supervised Image Restoration and multimodal Image Fusion joint learning network (SIRIFN), which enhances the robustness of the fusion network in adverse weather conditions by employing deep supervision from a guiding network to the learning network. Furthermore, to enhance the network’s information extraction and integration capabilities, our Multi-level Feature Collaborative adaptive Reconstruction Network (MFCRNet) is introduced, which adopts a multi-branch, multi-scale design, with differentiated processing strategies for different features. This approach preserves rich texture information while maintaining semantic consistency from the source images. Extensive experiments demonstrate that SIRIFN outperforms current state-of-the-art algorithms in both visual quality and quantitative evaluation. Specifically, the joint implementation of image restoration and multimodal fusion provides more effective information for visual tasks under extreme weather conditions, thereby facilitating downstream visual tasks.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102230"},"PeriodicalIF":5.2,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-06DOI: 10.1016/j.jksuci.2024.102227
Yanxuan Wei , Mingsen Du , Teng Li , Xiangwei Zheng , Cun Ji
In various fields such as healthcare and transportation, accurately classifying time series data can provide important support for decision-making. To further improve the accuracy of time series classification, we propose a Feature-fused Residual Network based on Multi-scale Signed Recurrence Plot (MSRP-FFRN). This method transforms one-dimensional time series into two-dimensional images, representing the temporal correlation of time series in a two-dimensional space and revealing hidden details within the data. To enhance these details further, we extract multi-scale features by setting receptive fields of different sizes and using adaptive network depths, which improves image quality. To evaluate the performance of this method, we conducted experiments on 43 UCR datasets and compared it with nine state-of-the-art baseline methods. The experimental results show that MSRP-FFRN ranks first on critical difference diagram, achieving the highest accuracy on 18 datasets with an average accuracy of 89.9%, making it the best-performing method overall. Additionally, the effectiveness of this method is further validated through metrics such as Precision, Recall, and F1 score. Results from ablation experiments also highlight the efficacy of the improvements made by MSRP-FFRN.
{"title":"Feature-fused residual network for time series classification","authors":"Yanxuan Wei , Mingsen Du , Teng Li , Xiangwei Zheng , Cun Ji","doi":"10.1016/j.jksuci.2024.102227","DOIUrl":"10.1016/j.jksuci.2024.102227","url":null,"abstract":"<div><div>In various fields such as healthcare and transportation, accurately classifying time series data can provide important support for decision-making. To further improve the accuracy of time series classification, we propose a Feature-fused Residual Network based on Multi-scale Signed Recurrence Plot (MSRP-FFRN). This method transforms one-dimensional time series into two-dimensional images, representing the temporal correlation of time series in a two-dimensional space and revealing hidden details within the data. To enhance these details further, we extract multi-scale features by setting receptive fields of different sizes and using adaptive network depths, which improves image quality. To evaluate the performance of this method, we conducted experiments on 43 UCR datasets and compared it with nine state-of-the-art baseline methods. The experimental results show that MSRP-FFRN ranks first on critical difference diagram, achieving the highest accuracy on 18 datasets with an average accuracy of 89.9%, making it the best-performing method overall. Additionally, the effectiveness of this method is further validated through metrics such as Precision, Recall, and F1 score. Results from ablation experiments also highlight the efficacy of the improvements made by MSRP-FFRN.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102227"},"PeriodicalIF":5.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-05DOI: 10.1016/j.jksuci.2024.102234
Zhan Jingchun , Goh Eg Su , Mohd Shahrizal Sunar
Enhancing low-light images in computer vision is a significant challenge that requires innovative methods to improve its robustness. Low-light image enhancement (LLIE) enhances the quality of images affected by poor lighting conditions by implementing various loss functions such as reconstruction, perceptual, smoothness, adversarial, and exposure. This review analyses and compares different methods, ranging from traditional to cutting-edge deep learning methods, showcasing the significant advancements in the field. Although similar reviews have been studied on LLIE, this paper not only updates the knowledge but also focuses on recent deep learning methods from various perspectives or interpretations. The methodology used in this paper compares different methods from the literature and identifies the potential research gaps. This paper highlights the recent advancements in the field by classifying them into three classes, demonstrated by the continuous enhancements in LLIE methods. These improved methods use different loss functions showing higher efficacy through metrics such as Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Naturalness Image Quality Evaluator. The research emphasizes the significance of advanced deep learning techniques and comprehensively compares different LLIE methods on various benchmark image datasets. This research is a foundation for scientists to illustrate potential future research directions.
{"title":"Low-light image enhancement: A comprehensive review on methods, datasets and evaluation metrics","authors":"Zhan Jingchun , Goh Eg Su , Mohd Shahrizal Sunar","doi":"10.1016/j.jksuci.2024.102234","DOIUrl":"10.1016/j.jksuci.2024.102234","url":null,"abstract":"<div><div>Enhancing low-light images in computer vision is a significant challenge that requires innovative methods to improve its robustness. Low-light image enhancement (LLIE) enhances the quality of images affected by poor lighting conditions by implementing various loss functions such as reconstruction, perceptual, smoothness, adversarial, and exposure. This review analyses and compares different methods, ranging from traditional to cutting-edge deep learning methods, showcasing the significant advancements in the field. Although similar reviews have been studied on LLIE, this paper not only updates the knowledge but also focuses on recent deep learning methods from various perspectives or interpretations. The methodology used in this paper compares different methods from the literature and identifies the potential research gaps. This paper highlights the recent advancements in the field by classifying them into three classes, demonstrated by the continuous enhancements in LLIE methods. These improved methods use different loss functions showing higher efficacy through metrics such as Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Naturalness Image Quality Evaluator. The research emphasizes the significance of advanced deep learning techniques and comprehensively compares different LLIE methods on various benchmark image datasets. This research is a foundation for scientists to illustrate potential future research directions.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102234"},"PeriodicalIF":5.2,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-05DOI: 10.1016/j.jksuci.2024.102228
Guanyuan Feng, Yu Liu, Weili Shi, Yu Miao
In recent years, visual localization has gained significant attention as a key technology for indoor navigation due to its outstanding accuracy and low deployment costs. However, it still encounters two primary challenges: the requirement for multiple database images to match the query image and the potential degradation of localization precision resulting from the keypoints clustering and mismatches. In this research, a novel visual localization framework based on a binocular camera is proposed to estimate the absolute positions of the query camera. The framework integrates three core methods: the multi-epipolar constraints-based localization (MELoc) method, the Optimal keypoint selection (OKS) method, and a robust measurement method. MELoc constructs multiple geometric constraints to enable absolute position estimation with only a single database image, while OKS and the robust measurement method further enhance localization accuracy by refining the precision of these geometric constraints. Experimental results demonstrate that the proposed system consistently outperforms existing visual localization systems across various scene scales, database sampling intervals, and lighting conditions
{"title":"Binocular camera-based visual localization with optimized keypoint selection and multi-epipolar constraints","authors":"Guanyuan Feng, Yu Liu, Weili Shi, Yu Miao","doi":"10.1016/j.jksuci.2024.102228","DOIUrl":"10.1016/j.jksuci.2024.102228","url":null,"abstract":"<div><div>In recent years, visual localization has gained significant attention as a key technology for indoor navigation due to its outstanding accuracy and low deployment costs. However, it still encounters two primary challenges: the requirement for multiple database images to match the query image and the potential degradation of localization precision resulting from the keypoints clustering and mismatches. In this research, a novel visual localization framework based on a binocular camera is proposed to estimate the absolute positions of the query camera. The framework integrates three core methods: the multi-epipolar constraints-based localization (MELoc) method, the Optimal keypoint selection (OKS) method, and a robust measurement method. MELoc constructs multiple geometric constraints to enable absolute position estimation with only a single database image, while OKS and the robust measurement method further enhance localization accuracy by refining the precision of these geometric constraints. Experimental results demonstrate that the proposed system consistently outperforms existing visual localization systems across various scene scales, database sampling intervals, and lighting conditions</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102228"},"PeriodicalIF":5.2,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-04DOI: 10.1016/j.jksuci.2024.102226
Mohammed A.M. Elhassan , Changjun Zhou , Ali Khan , Amina Benabid , Abuzar B.M. Adam , Atif Mehmood , Naftaly Wambugu
Real-time semantic segmentation is a crucial component of autonomous driving systems, where accurate and efficient scene interpretation is essential to ensure both safety and operational reliability. This review provides an in-depth analysis of state-of-the-art approaches in real-time semantic segmentation, with a particular focus on Convolutional Neural Networks (CNNs), Transformers, and hybrid models. We systematically evaluate these methods and benchmark their performance in terms of frames per second (FPS), memory consumption, and CPU runtime. Our analysis encompasses a wide range of architectures, highlighting their novel features and the inherent trade-offs between accuracy and computational efficiency. Additionally, we identify emerging trends, and propose future directions to advance the field. This work aims to serve as a valuable resource for both researchers and practitioners in autonomous driving, providing a clear roadmap for future developments in real-time semantic segmentation. More resources and updates can be found at our GitHub repository: https://github.com/mohamedac29/Real-time-Semantic-Segmentation-Survey
实时语义分割是自动驾驶系统的重要组成部分，准确高效的场景解读对确保安全和运行可靠性至关重要。本综述深入分析了最先进的实时语义分割方法，尤其关注卷积神经网络（CNN）、变形器和混合模型。我们系统地评估了这些方法，并根据每秒帧数（FPS）、内存消耗和 CPU 运行时间对其性能进行了基准测试。我们的分析涵盖了各种架构，突出了它们的新特点以及准确性和计算效率之间的内在权衡。此外，我们还确定了新兴趋势，并提出了推动该领域发展的未来方向。这项工作旨在为自动驾驶领域的研究人员和从业人员提供宝贵的资源，为实时语义分割的未来发展提供清晰的路线图。更多资源和更新请访问我们的 GitHub 存储库：https://github.com/mohamedac29/Real-time-Semantic-Segmentation-Survey
{"title":"Real-time semantic segmentation for autonomous driving: A review of CNNs, Transformers, and Beyond","authors":"Mohammed A.M. Elhassan , Changjun Zhou , Ali Khan , Amina Benabid , Abuzar B.M. Adam , Atif Mehmood , Naftaly Wambugu","doi":"10.1016/j.jksuci.2024.102226","DOIUrl":"10.1016/j.jksuci.2024.102226","url":null,"abstract":"<div><div>Real-time semantic segmentation is a crucial component of autonomous driving systems, where accurate and efficient scene interpretation is essential to ensure both safety and operational reliability. This review provides an in-depth analysis of state-of-the-art approaches in real-time semantic segmentation, with a particular focus on Convolutional Neural Networks (CNNs), Transformers, and hybrid models. We systematically evaluate these methods and benchmark their performance in terms of frames per second (FPS), memory consumption, and CPU runtime. Our analysis encompasses a wide range of architectures, highlighting their novel features and the inherent trade-offs between accuracy and computational efficiency. Additionally, we identify emerging trends, and propose future directions to advance the field. This work aims to serve as a valuable resource for both researchers and practitioners in autonomous driving, providing a clear roadmap for future developments in real-time semantic segmentation. More resources and updates can be found at our GitHub repository: <span><span>https://github.com/mohamedac29/Real-time-Semantic-Segmentation-Survey</span><svg><path></path></svg></span></div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 10","pages":"Article 102226"},"PeriodicalIF":5.2,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号