Article
Environmental Sciences
Taek-Lim Kim, Saba Arshad, Tae-Hyoung Park
Summary: Object detection is crucial for autonomous navigation in dynamic environments and camera and lidar sensors are commonly used for efficient object detection. However, they are affected by adverse weather conditions and illumination changes. To address this challenge, this study proposes an adaptive feature attention module (AFAM) for robust multisensory data fusion-based object detection. The AFAM computes uncertainty among camera and lidar features and adaptively refines them via attention. Experimental results demonstrate that the AFAM significantly enhances the overall detection accuracy of an object detection network.
Article
Computer Science, Information Systems
Zihang Lei, Mengxi Jiang, Guangsong Yang, Tianmin Guan, Peng Huang, Yu Gu, Zhenghua Xu, Qiubo Ye
Summary: This paper proposes a novel multi-path features fusion network based on deep learning for automatic modulation recognition. The approach effectively utilizes both refined and rough features, achieving high accuracy in the experiments, especially in high SNR conditions.
Article
Robotics
Wen Qi, Salih Ertug Ovur, Zhijun Li, Aldo Marzullo, Rong Song
Summary: In this letter, we propose a novel multi-sensor guided hand gesture recognition system for surgical robot teleoperation, using a multi-sensor data fusion model and a multilayer Recurrent Neural Network for multiple hand gestures classification to achieve human-robot collaboration tasks. Results show that the proposed model can achieve higher recognition rate and faster inference speed.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Chemistry, Analytical
Pawel Mazurek
Summary: This paper investigates the usability of feedforward and recurrent neural networks for fusing data from impulse-radar sensors and depth sensors in the context of healthcare monitoring of elderly individuals. Two methods of data fusion are compared, one based on a multilayer perceptron and another based on a nonlinear autoregressive network. The experiments show that the method based on a nonlinear autoregressive network with exogenous inputs outperforms other methods in decreasing estimation uncertainty and enabling useful inferences on health conditions.
Article
Engineering, Electrical & Electronic
Zeeshan Ahmad, Naimul Khan
Summary: In this paper, a novel Multistage Gated Average Fusion (MGAF) network is proposed to extract and fuse features from all layers of Convolutional Neural Network (CNN) using Gated Average Fusion (GAF) network, improving Human Action Recognition (HAR) using depth and inertial sensors. Experimental results show that the proposed MGAF outperforms previous fusion methods in terms of recognition accuracy while being more computationally efficient.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Carmen Bisogni, Aniello Castiglione, Sanoar Hossain, Fabio Narducci, Saiyed Umer
Summary: This article proposes a facial expression recognition system that can provide quick assistance to the healthcare system and exceptional services to the patients. The system utilizes multi-resolution image processing techniques and has been proven superior through experiments.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Chemistry, Analytical
Xin Chang, Wladyslaw Skarbek
Summary: The study investigates the application of deep neural networks in audio-video emotion recognition, proposing a multi-modal residual perceptron network that improves recognition rates. By utilizing end-to-end learning and time augmentation techniques, it achieves outstanding recognition results across various datasets including emotional speech and song.
Article
Optics
Santosh Kumar, Ting Bu, He Zhang, Irwin Huang, Yuping Huang
Summary: A hybrid image classifier utilizing feature-sensitive image upconversion, single pixel photodetection, and deep learning is proposed in this study for fast processing of high-resolution images. The classifier improves classification accuracy and robustness by using partial Fourier transform to extract signature features in both the original and Fourier domains. Test results show significant accuracy enhancement, especially for highly contaminated images with low signal-to-noise ratio. This approach holds potential for applications in fast lidar data processing, high-resolution image recognition, occluded target identification, and atmosphere monitoring.
Article
Computer Science, Artificial Intelligence
Wei Gao, Yangming Wu, Cui Hong, Rong-Jong Wai, Cheng-Tao Fan
Summary: This paper proposes a new bird damage recognition network, RCVNet, which addresses the issue of environmental interference in identifying birds around power towers using cameras alone by fusing radio-frequency (RF) images and visual images. The network accurately identifies bird damages in the monitoring area by employing a feature layer fusion approach and incorporating various improved modules and strategies. The experiments conducted using a newly gathered bird dataset called CRB2022 demonstrate that RCVNet achieves a high precision and recall rate in bird identification and an excellent discrimination rate in bird damage recognition.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Said Yacine Boulahia, Abdenour Amamra, Mohamed Ridha Madi, Said Daikh
Summary: Multimodal action recognition techniques combine multiple image modalities, including early fusion, intermediate fusion, and late fusion methods for more robust recognition. By deeply investigating different fusion levels, new schemes are proposed to better combine features from different modalities and achieve better recognition results than traditional methods.
MACHINE VISION AND APPLICATIONS
(2021)
Article
Robotics
Russell Buchanan, Varun Agrawal, Marco Camurri, Frank Dellaert, Maurice Fallon
Summary: This paper proposes a deep learning-based VIO algorithm that trains a neural network to learn the evolution of IMU bias, aiming to improve state estimation in visually challenging situations. The experiments demonstrate the effectiveness of the proposed method across different motion patterns.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Minjung Lee, Jinsoo Bae, Seoung Bum Kim
Summary: Data-driven soft sensors using deep learning models have shown superior predictive performance, but may face trustworthiness issues when dealing with unexpected situations or noisy input data. By introducing uncertainty-aware soft sensors based on Bayesian recurrent neural networks, the reliability of predictive uncertainty can be increased, allowing for interval prediction without compromising the predictive performance of the soft sensor.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Computer Science, Information Systems
Xiaoyu Chen, Hongliang Li, Qingbo Wu, Fanman Meng, Heqian Qiu
Summary: In this study, we propose Bal-(RCNN)-C-2 for high-quality recurrent object detection, with two new components that induce balanced optimization and result in significant improvement over existing solutions, reaching better performance than several state-of-the-art methods on evaluation datasets like PASCAL VOC and MSCOCO.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Biodiversity Conservation
Chih-Wei Lin, Zhongsheng Chen, Mengxiang Lin
Summary: This paper proposes a transposed non-local module based on a time pyramid network for automatically recognizing bird behavior. Compared with existing methods, the model performs better in terms of classification accuracy and various metrics for bird behavior.
ECOLOGICAL INDICATORS
(2022)
Article
Computer Science, Artificial Intelligence
Ehtesham Hassan
Summary: This paper investigates the use of LSTM networks for human action recognition in videos. By learning the fusion of spatial and temporal feature streams with LSTM, a novel two-stream deep network is proposed, efficiently capturing long range temporal dependencies in video streams.
PATTERN RECOGNITION LETTERS
(2021)
Article
Computer Science, Information Systems
Muhammad Umair Hassan, Dongmei Niu, Mingxuan Zhang, Xiuyang Zhao
Summary: This research proposes a novel asymmetric learning-based generative adversarial network (AGAN) for image retrieval, integrating feature learning with hashing and introducing three loss functions that significantly improve retrieval performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Ke Wang, Zicong Chen, Mingjia Zhu, Siu-Ming Yiu, Chien-Ming Chen, Mohammad Mehedi Hassan, Stefano Izzo, Giancario Fortino
Summary: Artificial intelligence-driven automation is becoming the technical trend in the new automation era. Convolutional neural network (CNN) technology has been widely used in industrial automation for defect detection and machine vision-driven automation for robot-human tracking. However, the high dependence on neural networks can lead to potential failures in defect detection system.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Civil
Kashif Naseer Qureshi, Gwanggil Jeon, Mohammad Mehedi Hassan, Md. Rafiul Hassan, Kuljeet Kaur
Summary: Intelligent Transportation Systems (ITS) have gained popularity due to their smart services, but the increasing number of users has raised concerns over data processing, storage, security, and privacy. To address these concerns, this paper proposes a Blockchain-based Privacy-Preserving Authentication (BPPAU) model that uses smart contracts, access control policies, and on-demand functions to manage data while maintaining user privacy. The model's performance is evaluated through simulation tests analyzing transaction cost, transaction per second, and computational time with various data sizes and block times.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Jia Hu, Kuljeet Kaur, Hui Lin, Xiaoding Wang, Mohammad Mehedi Hassan, Imran Razzak, Mohammad Hammoudeh
Summary: This paper proposes a Transfer Learning based Trajectory Anomaly Detection strategy, named TLTAD, for IoT-empowered Maritime Transportation Systems (IoT-MTS). Experimental results show that TLTAD can accurately detect anomalies in ships' trajectories and reduce model training time.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Md. Adyelullahil Mamun, Hasnat Md. Abdullah, Md. Golam Rabiul Alam, Muhammad Mehedi Hassan, Md. Zia Uddin
Summary: This research proposes an anthropomorphic intelligent system that can hold a proper human-like conversation with emotion and personality. It also introduces a voice style transfer method. Through tests and user feedback, the system's effectiveness has been demonstrated.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Wajid Ali, Tanzeela Shaheen, Iftikhar Ul Haq, Hamza Ghazanfar Toor, Faraz Akram, Saeid Jafari, Md. Zia Uddin, Mohammad Mehedi Hassan
Summary: This article explores the combination of the intuitionistic hesitant fuzzy set (IHFS) and set pair analysis (SPA) theories in multi-attribute decision making (MADM) and presents a hybrid model named intuitionistic hesitant fuzzy connection number set (IHCS). A few averaging and geometric aggregation operators are developed on IHCS to facilitate the design of a novel MADM algorithm. Additionally, the benefits of the proposed work are highlighted through a comparative examination with other models and a graphical interpretation of the devised attempt.
Article
Mathematics
Mohammad Mehedi Hassan, Mabrook S. AlRakhami, Amerah A. Alabrah, Salman A. AlQahtani
Summary: This study proposes a secure edge-assisted deep learning-based framework for automatic COVID-19 detection, utilizing cloud and edge computing assistance with 5G network and blockchain technologies. The use of edge services in artificial intelligence methods has played a significant role in various applications. DL approaches have been successful in COVID-19 detection using chest X-ray images in cloud and edge computing environments, but they have limitations in training dataset size. To overcome this, the study collects data from different hospitals to train a DL model on a global cloud, integrates the trained models for automatic COVID-19 detection, and retrain them locally at hospitals to improve the model.
Review
Multidisciplinary Sciences
Walaa N. Ismail, Hessah A. Alsalamah, Mohammad Mehedi Hassan, Ebtesam Mohamed
Summary: Convolutional neural networks have shown exceptional performance in human activity recognition. By using neural architecture search, network architectures can be designed and optimized automatically. This study proposes a novel encoding structure and search space for selecting the optimal CNN architecture.
Article
Acoustics
Rafeed Rahman, Md. Golam Rabiul Alam, Md. Tanzim Reza, Aminul Huq, Gwanggil Jeon, Md. Zia Uddin, Mohammad Mehedi Hassan
Summary: Ultrasound imaging is a valuable tool for assessing fetal development during pregnancy, but manual interpretation of ultrasound images is time-consuming and subjective. Automated image categorization using machine learning algorithms can simplify the interpretation process by identifying stages of fetal development. This research aimed to improve the precision of detecting fetal planes in ultrasound images through training convolutional neural networks on a dataset of 12400 images. Results showed noteworthy performance of each classifier, with PreLUNet achieving the highest accuracy of 91.03%. LIME and GradCam were used to provide explainability for the classifiers' outputs. The findings demonstrate the potential of automated image categorization in large-scale retrospective assessments of fetal development using ultrasound imaging.
Article
Engineering, Multidisciplinary
Ankita Sharma, Shalli Rani, Syed Hassan Shah, Rohit Sharma, Feng Yu, Mohammad Mehedi Hassan
Summary: This article discusses the importance of security in the Cyber-Physical Systems (CPS) model for smart healthcare networks, as well as the use of a deep learning-based CNN-Bidirectional LSTM for DDoS detection. The results of the study show that this method, with four convolutional layers, Maximum Pooling, and Dense Layer, achieved success in Python.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Siyuan Liang, Mengna Xie, Sahil Garg, Georges Kaddoum, Mohammad Mehedi Hassan, Salman A. AlQahtani
Summary: In this paper, a UV positioning system REW_SLAM based on lidar and stereo camera is proposed, which achieves real-time online pose estimation of UV by using high-precision lidar pose correction visual positioning data. A six-element extended Kalman filter (6-element EKF) is proposed to fusion lidar and stereo camera sensors information, effectively improving the accuracy of data fusion. Meanwhile, a modified wavelet denoising method is introduced to preprocess the original lidar data to improve its quality. Experimental results show that compared with the other two algorithms, the relative pose error and absolute trajectory error of this algorithm increased by 0.26 m and 2.36 m on average, respectively, while the CPU occupancy rate increased by 6.685% on average, thus proving the robustness and effectiveness of the algorithm.
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Rabeya Khatun Muna, Muhammad Iqbal Hossain, Md. Golam Rabiul Alam, Mohammad Mehedi Hassan, Michele Ianni, Giancarlo Fortino
Summary: This research aims to detect large-scale attacks on IoT devices using the Extreme Gradient Boosting (XG-Boost) classifier and Explainable Artificial Intelligence (XAI) approaches. The results demonstrate that the proposed model can efficiently identify malicious attacks and threats, reducing IoT cybersecurity threats in smart cities.
INTERNET OF THINGS
(2023)
Article
Engineering, Civil
Prabhat Kumar, Govind P. Gupta, Rakesh Tripathi, Sahil Garg, Mohammad Mehedi Hassan
Summary: The recent growth of IoT technologies in the maritime industry has digitalized Maritime Transportation Systems (MTS), but also introduced cybersecurity threats. Cyber Threat Intelligence (CTI) is an effective security strategy, but existing solutions have low detection rates and high false alarm rates. To address these challenges, an automated framework called DLTIF has been proposed, which can accurately identify threat types.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
C. Lopez-Molina, S. Iglesias-Rey, B. De Baets
Summary: Quantitative image comparison is a critical topic in image processing literature, with diverse applications. Existing measures of comparison often overlook the context in which the comparison takes place. This paper presents a context-aware comparison method for binary images, tested on the BSDS500 benchmark.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Lorenz Linhardt, Klaus-Robert Mueller, Gregoire Montavon
Summary: This paper investigates the issue of mismatches between the decision strategy of the explainable model and the user's domain knowledge, and proposes a new method EGEM to mitigate hidden flaws in the model. Experimental results demonstrate that the approach can significantly reduce reliance on Clever Hans strategies and improve the accuracy of the model on new data.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Zhimin Shao, Weibei Dou, Yu Pan
Summary: This paper proposes a novel algorithm, Dual-level Deep Evidential Fusion (DDEF), to integrate multimodal information at both the BBA level and multimodal level, aiming to enhance accuracy, robustness, and reliability. The DDEF approach utilizes the Dirichlet framework and BBA methods for effective uncertainty estimation and employs the Dempster-Shafer Theory for dual-level fusion. The experimental results show that the proposed DDEF outperforms existing methods in synthetic digit classification and real-world medical prognosis after BCI treatment.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Abhishek K. Ghosh, Danilo S. Catelli, Samuel Wilson, Niamh C. Nowlan, Ravi Vaidyanathan
Summary: The inability of current FM monitoring methods to be used outside clinical environments has made it challenging to understand the nature and evolution of FM. This investigation introduces a novel wearable FM monitor with a heterogeneous sensor suite and a data fusion architecture to efficiently capture and separate FM from interfering artifacts. The performance of the device and architecture were validated through at-home use, demonstrating high accuracy in detecting and recognizing FM events. This research is a major milestone in the development of low-cost wearable FM monitors for pervasive monitoring of FM in unsupervised environments.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jianlei Kong, Xiaomeng Fan, Min Zuo, Muhammet Deveci, Xuebo Jin, Kaiyang Zhong
Summary: In this study, we propose an intelligent traffic flow prediction framework based on the adaptive dual-graphic transformer with a cross-fusion strategy, aiming to uncover latent graphic feature representations that transcend temporal and spatial limitations. By establishing a traffic spatiotemporal prediction model using a cross-fusion attention mechanism, our proposed model achieves superior prediction performance on practical urban traffic flow datasets, particularly for long-term predictions.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huilai Zhi, Jinhai Li
Summary: This article addresses the issue that conflict analysis based on single-valued information systems is no longer valid. It proposes a conflict analysis method based on component similarity, which uses three-way n-valued concept lattices to handle set-valued formal contexts and realizes fast conflict analysis from an information fusion viewpoint. Experimental results verify the effectiveness of this method in reducing time consumption.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Huchang Liao, Jiaxin Qi, Jiawei Zhang, Chonghui Zhang, Fan Liu, Weiping Ding
Summary: In this paper, a hospital selection approach based on a fuzzy multi-criterion decision-making method is proposed. This approach considers sentiment evaluation values of unstructured data from online reviews and structured data of public indexes simultaneously. The methodology involves collecting and processing online reviews, classifying topics and sentiments, quantifying sentiment analysis results using fuzzy numbers, and obtaining final preference scores of hospitals based on patients' preferences. A case study and robustness analysis are conducted to validate the effectiveness of the method.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Faramarz Farhangian, Rafael M. O. Cruz, George D. C. Cavalcanti
Summary: The proliferation of social networks has posed challenges in combating fake news, but automatic fake news detection using artificial intelligence has become more feasible. This paper revisits the definitions and perspectives of fake news and proposes an updated taxonomy, based on multiple criteria, for the field. The study finds that optimal feature extraction techniques vary depending on the dataset, and context-dependent models based on transformer models consistently exhibit superior performance.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Mariana A. Souza, Robert Sabourin, George D. C. Cavalcanti, Rafael M. O. Cruz
Summary: In this study, a dynamic selection technique is proposed to handle sparse and overlapped data. The technique leverages the relationships between instances and classifiers to learn a dynamic classifier combination rule. Experimental results show that the proposed method outperforms static selection and other dynamic selection techniques.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Bin Yu, Ruihui Xu, Mingjie Cai, Weiping Ding
Summary: This paper introduces a clustering method based on non-Euclidean metric and multi-granularity staged clustering to address the challenges posed by complex spatial structure data to traditional clustering methods. The method improves the similarity measure and employs an attenuation-diffusion pattern for local to global clustering, achieving good clustering results.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Jian Zhu, Pengbo Hu, Bingqian Li, Yi Zhou
Summary: The acquisition of multi-view hash representation for heterogeneous data is highly important for multimedia retrieval. Current approaches suffer from limited retrieval precision due to insufficient integration of multi-view features and failure to effectively utilize metric information from diverse samples. In this paper, we propose an innovative method called Fast Metric Multi-View Hashing (FMMVH), which demonstrates the superiority of gate-based fusion over traditional methods. We also introduce a novel deep metric loss function to leverage metric information from dissimilar samples. By optimizing and employing model compression techniques, our FMMVH method significantly outperforms existing state-of-the-art methods on benchmark datasets, with up to 7.47% improvement in mean Average Precision (mAP).
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Fayaz Ali Dharejo, Iyyakutti Iyappan Ganapathi, Muhammad Zawish, Basit Alawode, Moath Alathbah, Naoufel Werghi, Sajid Javed
Summary: The resource-limited nature of underwater vision equipment affects underwater robotics and ocean engineering tasks. Super-resolution methods, particularly using Vision Transformers (ViTs), have emerged to enhance low-resolution underwater images. However, ViTs face challenges in handling severe degradation in underwater imaging. In contrast, Multi-scale ViTs (MViTs) overcome these challenges by preserving long-range dependencies through evolving channel capacity. This study proposes a novel algorithm, SwinWave-SR, for efficient and accurate multi-scale super-resolution for underwater images.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Weiwei Jiang, Haoyu Han, Yang Zhang, Jianbin Mu
Summary: This study incorporates federated learning and split learning paradigms with satellite-terrestrial integrated networks and introduces a split-then-federated learning framework and federated split learning with long short-term memory to handle sequential data in STINs. The proposed solution is demonstrated to be effective through a case study of electricity theft detection based on a real-world dataset.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Najah Abuali, Mohammad Bilal Khan, Farman Ullah, Mohammad Hayajneh, Hikmat Ullah, Shahid Mumtaz
Summary: The demand for innovative solutions in biomedical systems for precise diagnosis and management of critical diseases is increasing. A promising technology, non-invasive and intelligent Internet of Medical Things (IoMT) system, emerges to assess patients with reduced health risks. This research introduces a comprehensive framework for early diagnosis of respiratory abnormalities through RF sensing and SDR technology. The results highlight the superior performance of deep learning frameworks in classifying respiratory anomalies.
INFORMATION FUSION
(2024)
Article
Computer Science, Artificial Intelligence
Shichen Huang, Weina Fu, Zhaoyue Zhang, Shuai Liu
Summary: In the era of adversarial machine learning (AML), developing robust and generalized algorithms has become a key research topic. This study proposes a global similarity matching module and a global-local cognition fusion training mechanism based on relationship adversarial sample generation to improve image-text matching algorithm. Experimental results show significant improvements in accuracy and robustness, performing well in facing security challenges and promoting the fusion of visual and linguistic modalities.
INFORMATION FUSION
(2024)