Article
Agriculture, Dairy & Animal Science
Zhuang Wan, Fang Tian, Cheng Zhang
Summary: In this study, a new sheep face recognition model was constructed, which uses a bilinear feature extraction network to extract important features of sheep faces and a feature fusion method for recognition. The experimental results demonstrate a recognition accuracy of 99.43%, achieving individual recognition of sheep while reducing the influence of pose and angle.
Article
Computer Science, Information Systems
Alaa Eleyan
Summary: This study investigates the impact of feature fusion on face recognition performance by fusing different feature descriptors. The results show that fused feature descriptors can significantly improve performance, especially when the training set is limited.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Chemistry, Multidisciplinary
Younghun Seo, Nam Yul Yu
Summary: This paper proposes a novel loss function called the additive orthant loss (Orthant loss) for deep face recognition. It improves the feature-discriminative capability by using the rescaled softplus function and an additive margin to make features away from the origin. Additionally, it compresses feature spaces by mapping features to an orthant of each class using element-wise operation and 1-bit quantization, enhancing the inter-class separabilty and the intra-class compactness.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Theory & Methods
Bingyao Yu, Jiwen Lu, Xiu Li, Jie Zhou
Summary: The proposed SAFPAD approach utilizes deep reinforcement learning to identify discriminative salient parts in face images, focusing on them to enhance the accuracy and robustness of face presentation attack detection. By jointly training with deep reinforcement learning, the model achieves competitive performance by concentrating on salient local information.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Chenggang Yan, Lixuan Meng, Liang Li, Jiehua Zhang, Zhan Wang, Jian Yin, Jiyong Zhang, Yaoqi Sun, Bolun Zheng
Summary: This article introduces a new method for age-invariant face recognition called Multi-feature Fusion and Decomposition (MFD) framework. The method samples multiple face images of different ages with the same identity and uses multi-head attention to capture contextual information from facial feature series. It combines feature decomposition and fusion techniques to ensure that the final features effectively represent the identity information of the face and have stronger robustness against the aging process.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Chemistry, Analytical
Faseela Abdullakutty, Pamela Johnston, Eyad Elyan
Summary: This paper presents a feature-fusion method that combines features extracted by pre-trained deep learning models with traditional color and texture features to improve the performance of face presentation attack detection. Extensive experiments show that enriching the feature space can enhance the detection rate, opening up future research directions for exploring new characterizing features and fusion strategies.
Article
Computer Science, Hardware & Architecture
Shuhuan Zhao, Wen Liu, Shuaiqi Liu, Jiaqi Ge, Xiaolin Liang
Summary: The study presents a hybrid-supervision learning frame that combines the advantages of supervised and unsupervised features, featuring an effective feature learning method and local information extraction through PCANet, culminating in a SVM final classifier for addressing challenges in face recognition. This method is practical for small communities due to its low storage requirement and has demonstrated effectiveness and efficiency through experiments on four databases.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Guangwei Gao, Yi Yu, Jian Yang, Guo-Jun Qi, Meng Yang
Summary: This paper introduces the problem of cross-resolution face recognition and proposes a method to address it using multi-level deep convolutional neural network feature set. The method adaptively fuses contextual features, utilizes feature set-based representation learning and fuses hierarchical recognition outputs to achieve more robust and accurate face recognition.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Kui Jiang, Zhongyuan Wang, Peng Yi, Tao Lu, Junjun Jiang, Zixiang Xiong
Summary: This article introduces a new dual-path deep fusion network (DPDFN) for face image super-resolution (SR) without requiring additional face prior. It learns the global facial shape and local facial components through two individual branches and achieves high-quality face images.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Psychology, Multidisciplinary
Weiwei Cai, Ming Gao, Runmin Liu, Jie Mao
Summary: The paper introduces a novel multi-layer interactive feature fusion network model with angular distance loss to improve the accuracy of computer recognition of human facial emotions. By addressing the issues of subtle differences and less distinguishable expression features, the proposed model demonstrates strong competitiveness in facial emotion recognition tasks.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Computer Science, Software Engineering
Liangqin Chen, Jiwang Chen, Zhimeng Xu, Yipeng Liao, Zhizhang Chen
Summary: Face recognition in surveillance is challenging due to the disparity between low-resolution camera images and high-resolution database images. This paper proposes a two-stage dual-resolution face network to learn resolution-invariant representations. The network is pre-trained using high-resolution images and then fine-tuned using the triplet loss and competence-based curriculum learning. Experimental results show remarkable face verification accuracy.
Article
Computer Science, Theory & Methods
Yingfan Tao, Wenxian Zheng, Wenming Yang, Guijin Wang, Qingmin Liao
Summary: A novel Frontal-Centers Guided Loss (FCGFace) is proposed for face recognition, which achieves better performance in handling profile faces. Compared to existing methods, FCGFace takes viewpoints into consideration and can adaptively adjust feature distribution to form compact identity clusters.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Alaa Eleyan
Summary: The use of local statistical descriptors for image representation has become a powerful approach. In this study, the effect of different histogram-based local feature extraction algorithms on face recognition performance is investigated. The fusion of descriptors is found to significantly enhance system performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Lucia Cimmino, Michele Nappi, Fabio Narducci, Chiara Pero
Summary: This study explores the impact of wearing masks on face recognition and proposes a robust recognition approach for mobile devices by analyzing the spatio-temporal features of the periocular region. Machine learning techniques are used to classify and analyze the periocular region, and the experimental results show promising performance.
Article
Computer Science, Software Engineering
Jiwei Zhang, Xiaodan Yan, Zelei Cheng, Xueqi Shen
Summary: The translation introduces how face recognition can be applied to the transformation of enterprises, communities, and parks in the process of building a smart city to improve security experience. It also proposes a hierarchy feature fusion method to enhance face recognition accuracy by fusing shallow and deep facial features.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Saiyed Umer, Ranjeet Kumar Rout, Chiara Pero, Michele Nappi
Summary: In this paper, a novel facial expression recognition system utilizing deep learning and data augmentation techniques has been proposed to recognize different types of expressions. The performance of the proposed system outperforms existing state-of-the-art methods.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2022)
Article
Engineering, Biomedical
Ranjeet Kumar Rout, Saiyed Umer, Sabha Sheikh, Sanchit Sindhwani, Smitarani Pati
Summary: This research introduces an efficient alignment-free tool, EightyDVec, for protein sequence comparison. The method generates feature vectors based on physiochemical properties of amino acids to conveniently compare sequences. Validation on four datasets demonstrated the great effectiveness of EightyDVec in similarity analysis of protein sequences.
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION
(2022)
Article
Computer Science, Information Systems
Anay Ghosh, Saiyed Umer, Muhammad Khurram Khan, Ranjeet Kumar Rout, Bibhas Chandra Dhara
Summary: In this paper, a sentiment analysis system for pain detection is proposed using cutting edge techniques in a smart healthcare framework. The system analyzes facial expressions to detect pain sentiments and is divided into four components: face region detection, feature analysis, pain intensity prediction, and performance enhancement. Experimental results comparing the system with existing methods using two benchmark facial pain expression databases demonstrate the superiority of the proposed system.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Biology
Ranjeet Kumar Rout, Sk Sarif Hassan, Sabha H. Sheikh, Saiyed Umer, Kshira Sagar Sahoo, Amir Gandomi
Summary: This study examined the spatial distribution of amino acids in the primary protein sequences of SARS-CoV-2 and compared them with SARS-CoV proteins. The differences in amino acid spatial distribution between SARS-CoV-2 and SARS-CoV proteins were identified, enabling researchers to differentiate between the two types of coronavirus. The study also revealed similarities and differences among important structural proteins, E, M, N, and S, which are crucial for establishing an evolutionary tree with other coronavirus strains.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Alamgir Sardar, Saiyed Umer, Ranjeet K. R. Rout, Shui-Hua Wang, M. Tanveer
Summary: This article proposes a secure face recognition system for IoT-enabled Healthcare, which provides reliable security and smart treatment through face biometrics and template protection techniques. The system has been tested on benchmark face databases and compared with state-of-the-art methods, showing its novelty.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2023)
Article
Computer Science, Artificial Intelligence
Ramanath Datta, Sekhar Mandal, Saiyed Umer, Ahmad Ali AlZubi, Abdullah Alharbi, Jazem Mutared Alanazi
Summary: The paper proposes a fast and novel method for single-image reconstruction using super-resolution technique, which divides the image into homogeneous or non-homogeneous regions for reconstruction. The method results in a better reconstructed SR image compared to state-of-the-art methods.
Article
Mathematics
Monika Khandelwal, Sabha Sheikh, Ranjeet Kumar Rout, Saiyed Umer, Saurav Mallik, Zhongming Zhao
Summary: Aldehyde dehydrogenase 2 (ALDH2) is a key enzyme for alcohol detoxification. Its deficiency in East Asians leads to Alcohol Flushing Syndrome and increased susceptibility to diseases. By analyzing ALDH2 sequences of different species using machine learning, Homo sapiens is found to be closely related to Bos taurus and Sus scrofa.
Article
Chemistry, Analytical
Arindam Saha, Bibhas Chandra Dhara, Saiyed Umer, Kulakov Yurii, Jazem Mutared Alanazi, Ahmad Ali AlZubi
Summary: This paper proposes an efficient obstacle detection and tracking method using depth images. The method uses a u-depth map for obstacle detection with dynamic thresholding facilities and a post-processing restricted v-depth map for better obstacle dimension prediction. The proposed method outperforms vision-based methods in terms of state estimation of dynamic obstacles and execution time.
Article
Computer Science, Information Systems
Arindam Saha, Bibhas Chandra Dhara, Saiyed Umer, Ahmad Ali AlZubi, Jazem Mutared Alanazi, Kulakov Yurii
Summary: In this study, a collaborative SLAM framework called CORB2I-SLAM is proposed for generating robust global maps of unknown cluttered environments through the collaboration of multiple robots. The framework utilizes well-established Visual-Inertial Odometry (VIO) technology and can adapt to use Visual Odometry (VO) when the measurements from inertial sensors are noisy, resulting in more accurate results. Feasibility tests and extensive validation on benchmark data sequences demonstrate the effectiveness and accuracy of the framework, as well as its scalability and applicability in terms of the number of participating robots and network requirements.
Article
Computer Science, Artificial Intelligence
Sanoar Hossain, Saiyed Umer, Ranjeet Kr. Rout, M. Tanveer
Summary: Facial expressions reflect people's feelings, emotions, and motives, attracting researchers to develop a self-acting automatic facial expression recognition system. This research proposed a deep learning framework using fine-grained facial action unit detection to identify facial activity, behavior, and mood and recognize a person's emotions based on these individual patterns.
APPLIED SOFT COMPUTING
(2023)
Article
Automation & Control Systems
Monika Khandelwal, Ranjeet Kumar Rout, Saiyed Umer, Kshira Sagar Sahoo, N. Z. Jhanjhi, Mohammad Shorfuzzaman, Mehedi Masud
Summary: This paper introduces an optimal fuzzy nearest neighbor model for pattern classification. The model classifies unknown patterns through a fuzzification process and forms a membership matrix. The model achieves high accuracy on a Telugu vowel data set and learns well with a small amount of training data.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Alamgir Sardar, Saiyed Umer, Ranjeet Kumar Rout, Chiara Pero
Summary: This paper introduces a secure face recognition system with advanced template protection schemes for Cyber-Physical-Social Services (CPSS), which includes components for image preprocessing, feature extraction, clustering, cancelable feature generation, bio-cryptographic storage, and classification. The system achieves 100% identification accuracy for 200-dimensional cancelable feature vectors when evaluated on benchmark databases. Performance and security comparisons show the superiority of this system over existing methods.
PATTERN RECOGNITION LETTERS
(2023)
Article
Health Care Sciences & Services
Saiyed Umer, Ranjeet Kumar Rout
Summary: This paper predicts the status of Parkinson's disease based on the analysis of two symptoms: Dysphonia and Dysarthria. Statistical and discriminant feature analysis are used to derive effective features and build prediction models, which outperform existing methods. The proposed approach achieved a prediction accuracy of 93.50% for Dysphonia and 87.63% for Dysarthria symptoms datasets.
HEALTH SERVICES AND OUTCOMES RESEARCH METHODOLOGY
(2023)
Article
Computer Science, Information Systems
Chinmay Maiti, Bibhas Chandra Dhara, Saiyed Umer, Vijayan Asari
Summary: In this article, we propose an efficient and secure image encryption method using Fibonacci Transformation and Tribonacci Transformation. The method confuses the plain image and modifies pixel values to achieve encryption. The Fibonacci and Tribonacci numbers for the transformations are determined using the hash value of the plain image. This method is the first to use Tribonacci Transformation in image encryption and has a high key space and sensitivity to the plain image. It is also robust against various attacks and has performance comparable to state-of-the-art methods, demonstrating its applicability.
Article
Engineering, Multidisciplinary
Saiyed Umer, Ranjeet Kumar Rout, Shailendra Tiwari, Ahmad Ali AlZubi, Jazem Mutared Alanazi, Kulakov Yurii
Summary: A deep fusion model is proposed for facial expression-based human-computer interaction. The system extracts facial regions, utilizes deep learning features, and fuses the performance of multiple CNN models. The proposed system outperforms state-of-the-art methods in terms of various performance metrics.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2023)
Article
Engineering, Multidisciplinary
Sicheng Jiao, Shixiang Wang, Minge Gao, Min Xu
Summary: This paper presents a non-contact method of thickness measurement for thin-walled rotary shell parts based on a chromatic confocal sensor. The method involves using a flip method to obtain surface profiles from both sides of the workpiece, measuring the decentration and tilt errors of the workpiece using a centering system, establishing a unified reference coordinate system, reconstructing the external and internal surface profiles, and calculating the thickness. Experimental results show that the method can accurately measure the thickness of a sapphire spherical shell workpiece and is consistent with measurements of other materials.
Article
Engineering, Multidisciplinary
Rajeev Kumar, Sajal Agarwal, Sarika Pal, Alka Verma, Yogendra Kumar Prajapati
Summary: This study evaluated the performance of a CaF2-Ag-MXene-based surface plasmon resonance (SPR) sensor at different wavelengths. The results showed that the sensor achieved the maximum sensitivity at a wavelength of 532 nm, and higher sensitivities were obtained at shorter wavelengths at the expense of detection accuracy.
Article
Engineering, Multidisciplinary
Attilio Di Nisio, Gregorio Andria, Francesco Adamo, Daniel Lotano, Filippo Attivissimo
Summary: Capacitive sensing is a widely used technique for a variety of applications, including avionics. However, current industry standard Capacitive Level Sensors (CLSs) used in helicopters perform poorly in terms of sensitivity and dynamic characteristics. In this study, novel geometries were explored and three prototypes were built and tested. Experimental validation showed that the new design featuring a helicoidal slit along the external electrode of the cylindrical probe improved sensitivity, response time, and linearity.
Article
Engineering, Multidisciplinary
Kai Yang, Huiqin Wang, Ke Wang, Fengchen Chen
Summary: This paper proposes an effective measurement method for dynamic compaction construction based on time series model, which enables real-time monitoring and measurement of anomalies and important construction parameters through simulating motion state transformation and running time estimation.
Article
Engineering, Multidisciplinary
Hui Fu, Qinghua Song, Jixiang Gong, Liping Jiang, Zhanqiang Liu, Qiang Luan, Hongsheng Wang
Summary: An automatic detection and pixel-level quantification model based on joint Mask R-CNN and TransUNet is developed to accurately evaluate microcrack damage on the grinding surfaces of engineering ceramics. The model is effectively trained on actual micrograph image dataset using a joint training strategy. The proposed model achieves reliable automatic detection and fine segmentation of microcracks, and a skeleton-based quantification model is also proposed to provide comprehensive and precise measurements of microcrack size.
Review
Engineering, Multidisciplinary
Sang Yeob Kim, Da Yun Kwon, Arum Jang, Young K. Ju, Jong-Sub Lee, Seungkwan Hong
Summary: This paper reviews the categorization and applications of UAV sensors in forensic engineering, with a focus on geotechnical, structural, and water infrastructure fields. It discusses the advantages and disadvantages of sensors with different wavelengths and addresses the challenges of current UAV technology and recommendations for further research in forensic engineering.
Article
Engineering, Multidisciplinary
Anton Nunez-Seoane, Joaquin Martinez-Sanchez, Erik Rua, Pedro Arias
Summary: This article compares the use of Mobile Laser Scanners (MLS) and Aerial Laser Scanners (ALS) for digitizing the road environment and detecting road slopes. The study found that ALS data and its corresponding algorithm achieved better detection and delimitation results compared to MLS. Measuring the road from a terrestrial perspective negatively impacted the detection process, while an aerial perspective allowed for scanning of the entire slope structure.
Article
Engineering, Multidisciplinary
Nur Luqman Saleh, Aduwati Sali, Raja Syamsul Azmir Raja Abdullah, Sharifah M. Syed Ahmad, Jiun Terng Liew, Fazirulhisyam Hashim, Fairuz Abdullah, Nur Emileen Abdul Rashid
Summary: This study introduces an enhanced signal processing scheme for detecting mouth-click signals used by blind individuals. By utilizing additional band-pass filtering and other steps, the detection accuracy is improved. Experimental results using artificial signal data showed a 100% success rate in detecting obstacles. The emerging concepts in this research are expected to benefit radar and sonar system applications.
Article
Engineering, Multidisciplinary
Jiqiang Tang, Shengjie Qiu, Lu Zhang, Jinji Sun, Xinxiu Zhou
Summary: This paper studies the magnetic noise level of a compact high-performance magnetically shielded room (MSR) under different operational conditions and establishes a quantitative model for magnetic noise calculation. Verification experiments show the effectiveness of the proposed method.
Review
Engineering, Multidisciplinary
Krzysztof Bartnik, Marcin Koba, Mateusz Smietana
Summary: The demand for miniaturized sensors in the biomedical industry is increasing, and optical fiber sensors (OFSs) are gaining popularity due to their small size, flexibility, and biocompatibility. This study reviews various OFS designs tested in vivo and identifies future perspectives and challenges for OFS technology development from a user perspective.
Article
Engineering, Multidisciplinary
Yue Wang, Lei Zhou, Zihao Li, Jun Wang, Xuangou Wu, Xiangjun Wang, Lei Hu
Summary: This paper presents a 3-D reconstruction method for dynamic stereo vision of metal surface based on line structured light, overcoming the limitation of the measurement range of static stereo vision. The proposed method uses joint calibration and global optimization to accurately reconstruct the 3-D coordinates of the line structured light fringe, improving the reconstruction accuracy.
Article
Engineering, Multidisciplinary
Jaafar Alsalaet
Summary: Order tracking analysis is an effective tool for machinery fault diagnosis and operational modal analysis. This study presents a new formulation for the data equation of the second-generation Vold-Kalman filter, using separated cosine and sine kernels to minimize error and provide smoother envelopes. The proposed method achieves high accuracy even with small weighting factors.
Article
Engineering, Multidisciplinary
Tonglei Cao, Kechen Song, Likun Xu, Hu Feng, Yunhui Yan, Jingbo Guo
Summary: This study constructs a high-resolution dataset for surface defects in ceramic tiles and addresses the scale and quantity differences in defect distribution. An improved approach is proposed by introducing a content-aware feature recombination method and a dynamic attention mechanism. Experimental results demonstrate the superior accuracy and efficiency of the proposed method.
Article
Engineering, Multidisciplinary
Qinghong Fu, Yunxi Lou, Jianghui Deng, Xin Qiu, Xianhua Chen
Summary: Measurement and quantitative characterization of aging-induced gradient properties is crucial for accurate analysis and design of asphalt pavement. This research proposes the composite specimen method to obtain asphalt binders at different depths within the mixture and uses dynamic shear rheometer tests to measure aging-induced gradient properties and reveal internal mechanisms. G* master curves are constructed to investigate gradient aging effects in a wide range. The study finds that the composite specimen method can effectively restore the boundary conditions and that it is feasible to study gradient aging characteristics within the asphalt mixture. The study also observes variations in G* and delta values and the depth range of gradient aging effects for different aging levels.
Article
Engineering, Multidisciplinary
Min Li, Kai Wei, Tianhe Xu, Yali Shi, Dixing Wang
Summary: Due to the limitations of ground monitoring stations in China for the BDS, the accuracy of BDS Medium Earth Orbit (MEO) satellite orbits can be influenced. To overcome this, low Earth orbit (LEO) satellites can be used as additional monitoring stations. In this study, data from two LEO satellites were collected to improve the precise orbit determination of the BDS. By comparing the results with GPS and BDS-2/3 solutions, it was found that including the LEO satellites significantly improved the accuracy of GPS and BDS-2/3 orbits.
