检索结果-内蒙古大学图书馆

Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing

引用

Multimedia Tools and Applications 2025年第17期84卷 18071-18093页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. T

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Ensemble Technique for Imputing Missing Values in MAR Missingness 6

Ensemble Technique for Imputing Missing Values in MAR Missin...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Tiwaskar, Shweta Rashid, Mamoon Gokhale, Prasad Vishwakarma University Faculty of Science and Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350304480

Missing data is a widespread problem across many research fields, and it can have a major impact on the precision of statistical analyses. Imputation is one method for handling missing data, in which missing values are imputed based on the available data. A promising method for handling missing data is ensemble imputation, which uses the advantages of various imputation models. This paper aims to provide an ensemble imputation method for missingness at random (MAR) mechanism in multivariate configuration (missingness in more than one variable). We consider three popular imputation models-k-Nearest Neighbours (KNNI), Multiple Imputation by Chained Equations (MICE), and MissForest (MF)-and combine their findings to produce a more reliable imputation technique. To evaluate the performance of our proposed ensemble imputation method, we employ four commonly used evaluation criteria namely Standard Deviation (SD), Coefficient of Determination (R2), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) values. By comparing the performance of our proposed ensemble method with the other three imputation methods, the results show that the proposed ensemble imputation method performed better than MF, KNNI, and MICE in 83.33% of the cases, achieving lower values of MAE, RMSE, and higher R-Squared values and lower SD values in 66.66% of the cases. © 2023 IEEE.

关键词： Ensemble Imputation Missing Data Modelling

来源：评论

学校读者我要写书评

暂无评论

Indoor Positioning System Based on BSSID on Office Wi-Fi Network

Indoor Positioning System Based on BSSID on Office Wi-Fi Net...

引用

2023 International Conference on computer Science, Information technology and engineering, ICCoSITE 2023

作者： Aisuwarya, Ratna Ferdian, Rian Yulianti, Indah Hestina Universitas Andalas Faculty of Information Technology Computer Engineering Department Padang Indonesia

ISBN: (纸本)9798350320954

Indoor positioning system determine the position of objects in a closed room or story building. This system can determine not only the position but also the orientation and direction of a person's movement. This research uses Wi-Fi (Wireless Fidelity) a network technology that utilizes wireless technology and can work at frequencies of 2.4 GHz and 5.8 GHz. The aims to produce a system that can monitor the presence of employees. This makes the supervisor's work more effective because it can unify based on the information displayed on the android application. Based on observation and testing that has been done, the proposed system can display BSSID as MAC address and SSID from user data by authentication by admin. The system can monitor the user's position in the faculty office area with the application of the K-Nearest Neighbor (KNN) algorithm and the calculation of Received Signal Strength Indication (RSSI) and using the Fingerprinting method with an average Euclidean distance accuracy of 2.37 meters and able to display the user's position with a 100% success percentage. Then, the system is able to read the value of RSSI with 2.08% error. © 2023 IEEE.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

Improved channel estimation for underwater wireless optical communication OFDM systems by combining deep learning and machine learning models

引用

Optical and Quantum Electronics 2025年第3期57卷 1-21页

作者： Salama, Wessam M. Aly, Moustafa H. Department of Computer Engineering Faculty of Engineering Pharos University Canal El Mahmoudia Street Beside Green Plaza Complex 21648 Alexandria Egypt OSA Member Department of Electronics and Communications Engineering College of Engineering and Technology Arab Academy for Science Technology and Marine Transport Alexandria1029 Egypt

Recent studies on channel estimation in wireless communication systems have focused on deep learning methods. Our primary contribution is based on the use of DenseNet121 hybrid with Random Forest (RF), Gated Recurrent Units (GRU), Long Short-Term Memory Networks (LSTM), and Recurrent Neural Networks (RNN) to improve the channel estimation and lower the error rate. In order to mitigate inter-symbol interference and map the datasets, this paper introduces M-quadrature amplitude modulation (16-QAM) and orthogonal frequency division multiplexing (OFDM), which is based on quadrature phase shift keying (QPSK). Additionally, the existence or lack of cyclic prefixes forms the basis of our simulation. Additionally, the suggested models are investigated using pilot samples 2, 4, 8, and 64. Labeled OFDM signal samples, where the labels match the signal received after applying OFDM and passing through the medium, are used to train the proposed models. The DenseNet121 functions as a powerful feature extractor to extract intricate spatial information from received signal data. Sequential models like as RNN, LSTM, and GRU are used to model temporal dependencies in the retrieved features. RF is also utilized to exploit non-linear relationships and interactions between features to further increase prediction accuracy and reduce bit error rate (BER). By comparing the models using key metrics like accuracy, bit error rate (BER), and mean squared error (MSE), superior performance is attained based on the DenseNet121_RNN_GRU_RF model. Additionally, the DLMs are assessed against traditional methods like minimal mean square error (MMSE) and least squares (LS). Using the DenseNet121_RNN_GRU_RF model indicates a considerable gain over alternative architectures, with an improvement of 36.3% over DensNet121-RNN-LSTM-RF, according to a comparison of the suggested models without cyclic prefix for OFDM_QPSK. The improvement in percentages of roughly 63.3% over DensNet121-RNN-LSTM, 68.18% over De

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Graph-RAG for Enhanced Diagnostic and Treatment Strategies in Dentistry 8

Leveraging Graph-RAG for Enhanced Diagnostic and Treatment S...

引用

8th International Conference on Information technology, InCIT 2024

作者： Sophaken, Chotanansub Vongpanich, Kantapong Intaphan, Wachirawit Utasri, Tharathon Deepho, Chutamas Takhom, Akkharawoot King Mongkut's University of Technology Thonburi Faculty of Engineering Bangkok Thailand National Electronics and Computer Technology Center Pathum Thani Thailand Naresuan University Faculty of Dentistry Phitsanulok Thailand Thammasat University Faculty of Engineering Thammasat School of Engineering Thailand

ISBN: (纸本)9798350366303

This paper presents a method for extracting and interpreting information from diverse, unstructured dental literature using advanced AI techniques. By integrating information extraction, ontologies, and knowledge graphs, the approach enhances the efficiency and accuracy of dental data analysis. Named Entity Recognition (NER) and a Large Language Model (LLM) are employed to extract relevant entities and relationships, which are then structured into triples and integrated with a dental ontology to ensure contextual relevance. This enriched ontology supports Retrieval-Augmented Generation (RAG) applications, enabling advanced querying and analysis. The methodology improves the identification and categorization of dental conditions, treatments, and anatomical terms, providing a structured representation of dental knowledge. Knowledge graphs facilitate the representation and analysis of relationships between entities, fostering insightful interpretations and supporting hypothesis generation, thereby enhancing the accessibility and usability of dental knowledge. Experimental results demonstrate the effectiveness of this approach in managing complex dental information, showcasing the benefits of combining Knowledge Representation (KR) with Machine Learning (ML). This research contributes to dental studies by offering a robust framework for extracting and utilizing knowledge from diverse and extensive datasets. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Binary and Multi Classification Model on Tax Evasion:A Comparative Study 1

A Binary and Multi Classification Model on Tax Evasion:A Com...

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Shujaaddeen, Abeer Abdullah Ba-Alwi, Fadl Mutaher Zahary, Ammar T. Alhegami, Ahmed Sultan Alsabry, Ayman Al-Badani, Abdulkader M. Faculty of Computer and Information Technology Sana’a University Sana’a Yemen International University of Technology Twintech Malaysia Department of Computer Science Faculty of Computing and Information Technology University of Science and Technology Sana’a University Sana’a Yemen Department of Computer Science International University of Technology Twintech Sana’a Yemen Faculty of Science and Engineering Department of Computers Aljazeera University Ibb Yemen

ISBN: (纸本)9798331533557

In this paper, a model was built to compare the performance of the following machine learning (ML) models: DT, RF, SVM, and MLP, using two types of classification: binary classification and multi classification. The researchers concluded that the MLP classifier was the most efficient using multi classifications, as the classifier gave an accuracy of 99.77%, a recall of 93.25%, a precision of 92.02%, and an F-score of 92.63%. Using the dataset provided by the Tax Authority of Yemen, which is related to the commercial and industrial profits tax explained in detail in other papers for the same authors, which consists of 1083 record, after the preprocessing of data. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Geometric Autoencoder with Manifold Learning 29

Geometric Autoencoder with Manifold Learning

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Farahat, Mahboubeh Ahmadi, Ali Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran

ISBN: (纸本)9798331523114

Autoencoders are widely recognized as non-probabilistic learning models for extracting useful information from data. Most autoencoder models assume a Euclidean geometry for the underlying nature of the data. However, recent advancements in geometric learning suggest that incorporating curvature information of the intrinsic manifold of data may yield richer representations. In this work, we investigate the performance of a learning method that embeds data under curved geometric constraints. Our method assumes that the data manifold consists of both curved and Euclidean spaces. Experimental results demonstrate that our method achieves performance comparable to state-of-the-art techniques. © 2025 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Identification and Classification of Crowd Activities

引用

computers, Materials & Continua 2022年第7期72卷 815-832页

作者： Manar Elshahawy Ahmed O.Aseeri Shaker El-Sappagh Hassan Soliman Mohammed Elmogy Mervat Abu-Elkheir Department of Information Technology Faculty of Computers and InformationMansoura UniversityEgypt Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Systems Faculty of Computers and Artificial IntelligenceBenha UniversityEgypt Faculty of Computer Science and Engineering Galala University435611SuezEgypt Department of Computer Science Faculty of Media Engineering and TechnologyGerman UniversityEgypt

The identification and classification of collective people’s activities are gaining momentum as significant themes in machine learning,with many potential applications *** need for representation of collective human behavior is especially crucial in applications such as assessing security conditions and preventing crowd *** paper investigates the capability of deep neural network(DNN)algorithms to achieve our carefully engineered pipeline for crowd *** includes three principal stages that cover crowd analysis ***,individual’s detection is represented using the You Only Look Once(YOLO)model for human detection and Kalman filter for multiple human tracking;Second,the density map and crowd counting of a certain location are generated using bounding boxes from a human detector;and Finally,in order to classify normal or abnormal crowds,individual activities are identified with pose *** proposed system successfully achieves designing an effective collective representation of the crowd given the individuals in addition to introducing a significant change of crowd in terms of activities *** results onMOT20 and SDHA datasets demonstrate that the proposed system is robust and *** framework achieves an improved performance of recognition and detection peoplewith a mean average precision of 99.0%,a real-time speed of 0.6ms non-maximumsuppression(NMS)per image for the SDHAdataset,and 95.3%mean average precision for MOT20 with 1.5ms NMS per image.

关键词： Crowd analysis individual detection You Only Look Once(YOLO) multiple object tracking kalman filter pose estimation

来源：评论

学校读者我要写书评

暂无评论

A 69MHz-Bandwidth 40V/μ s-Slew-Rate 3n V/√Hz-Noise 4.5 μ V-Offset Chopper Operational Amplifier

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2024年第7期71卷 2977-2988页

作者： Koolivand, Yarallah Rezaeiyan, Yasser Zamani, Milad Akbari, Meysam Shoaei, Omid Tang, Kea-Tiong Moradi, Farshad Khajeh Nasir Toosi University of Technology Faculty of Electrical Engineering Tehran16317-14191 Iran Aarhus University Department of Electrical and Computer Engineering Aarhus8000 Denmark University of Kurdistan Department of Engineering Sanandaj66177-15177 Iran University of Tehran Department of Electrical and Computer Engineering Tehran*** Iran National Tsing Hua University Faculty of Electrical Engineering Hsinchu300044 Taiwan

This paper presents a chopper-stabilized three-stage operational amplifier (OpAmp) with a unity gain bandwidth of 69 MHz and an input referred noise density of 3 nV√Hz. The proposed design achieves a stable unity gain by proposing a new pole and zero scheme with very low power consumption, drawing only 3.3 mA from a 1.8 V power supply while driving a load capacitor as large as 100pF. To achieve rail-to-rail input swing, the design uses both NMOS and PMOS differential pairs at the input and biases them in the subthreshold region to provide an identical net trans-conductance over the rail-to-rail input common mode. Furthermore, an adaptive biasing is employed and the current sources are kept ON during large signal transitions at the input, thus eliminating crossover distortion and providing a high slew rate of 40 V/μs at a 100 pF load capacitor. The design employs chopping at 2.5 MHz and is enhanced with a local ripple reduction loop, making the OpAmp suitable for high gain and wide bandwidth applications with less filtering required. The design also reduces the input bias current significantly from 500 nA to 1.5 nA by buffering the input and applying it to the modified bootstrap switches. The proposed OpAmp, fabricated in a 0.18μm CMOS process, exhibits a maximum offset of 4.5μV , a flicker noise corner frequency of 246 Hz, a DC gain of 146 dB, a power supply rejection ratio of 123 dB, and a common mode rejection ratio of 116 dB. © 2004-2012 IEEE.

关键词： Operational amplifiers

来源：评论

学校读者我要写书评

暂无评论

Secure speaker identification in open and closed environments modeled with symmetric comb filters

引用

Multimedia Tools and Applications 2025年第18期84卷 19147-19189页

作者： Shafik, Amira Monir, Mohamad El-Shafai, Walid Khalaf, Ashraf A. M. Nassar, M.M. El-Fishawy, Adel S. El-Din, M. A. Zein Dessouky, Moawad I. El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Minia University Minia61519 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Speech is a fundamental means of human interaction. Speaker Identification (SI) plays a crucial role in various applications, such as authentication systems, forensic investigation, and personal voice assistance. However, achieving robust and secure SI in both open and closed environments remains challenging. To address this issue, researchers have explored new techniques that enable computers to better understand and interact with humans. Smart systems leverage Artificial Neural Networks (ANNs) to mimic the human brain in identifying speakers. However, speech signals often suffer from interference, leading to signal degradation. The performance of a Speaker Identification System (SIS) is influenced by various environmental factors, such as noise and reverberation in open and closed environments, respectively. This research paper is concerned with the investigation of SI using Mel-Frequency Cepstral Coefficients (MFCCs) and polynomial coefficients, with an ANN serving as the classifier. To tackle the challenges posed by environmental interference, we propose a novel approach that depends on symmetric comb filters for modeling. In closed environments, we study the effect of reverberation on speech signals, as it occurs due to multiple reflections. To address this issue, we model the reverberation effect with comb filters. We explore different domains, including time, Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Discrete Sine Transform (DST) domains for feature extraction to determine the best combination for SI in case of reverberation environments. Simulation results reveal that DWT outperforms other transforms, leading to a recognition rate of 93.75% at a Signal-to-Noise Ratio (SNR) of 15 dB. Additionally, we investigate the concept of cancelable SI to ensure user privacy, while maintaining high recognition rates. Our simulation results show a recognition rate of 97.5% at 0 dB using features extracted from speech signals and their DCTs. Fo

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：