Article
Environmental Sciences
Zahra Pashaei, Eric Guilbert, Thierry Badard
Summary: Airborne LiDAR scanning is a promising method for providing high-resolution products. However, the accuracy of LiDAR point clouds varies in space. This article proposes a method using geostatistical ordinary kriging to estimate local accuracy, which proves to be more reliable than traditional approaches.
Article
Agriculture, Multidisciplinary
Bernat Lavaquiol, Ricardo Sanz, Jordi Llorens, Jaume Arno, Alexandre Escola
Summary: This study presents a methodology for obtaining 3D point clouds of fruit trees using stereo-photogrammetry techniques, validating the accuracy of the resulting digital models. The methodology also allows for detection of small changes in the trees, serving as a basis for validating other sensing systems for 3D vegetation characterization and making more informed management decisions.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Robotics
Yuchen Liu, Wei Gao, Zhanyi Hu
Summary: This article introduces a challenging new dataset for indoor localization research, including RGB-D panoramas, query images, and aligned 3D point cloud, with a method for generating high-resolution depth images. Additionally, it provides a benchmark for indoor visual localization and the complete dataset can be downloaded from the given link.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2022)
Article
Engineering, Industrial
Jiazhen Pang, Pai Zheng, Shufei Li, Shimin Liu
Summary: This paper proposes a verification-oriented and part-focused monitoring system based on multi-layered digital twin for manual assembly assistance. It constructs a physical twin scene and a digital twin scene using digital twin technology to represent the theoretical status of the assembly in real time. By generating the newly assembled part and its corresponding template, and evaluating its position using a matching algorithm, potential assembly errors can be detected. The experimental result shows that this monitoring system is significant for human-centric intelligent manufacturing system development.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yirui Wu, Hao Cao, Guoqiang Yang, Tong Lu, Shaohua Wan
Summary: This article aims to construct a cyber-manufacturing system to achieve a digital twin solution for small surface defect detection. By using an Edge Cloud architecture and a deep learning algorithm, data can be collected, processed, analyzed, and stored efficiently to achieve smart manufacturing.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Xu Han, Hua Yu, Wenhao You, Chengxu Huang, Baohua Tan, Xingru Zhou, Neal N. Xiong
Summary: This research proposes the use of digital twin technology to construct virtual campus scenes and develop a spiral optimization system life cycle. Experimental results demonstrate that the virtual-real campus system can enhance school management and teaching.
Article
Computer Science, Interdisciplinary Applications
Ke Wang, Daxin Liu, Zhenyu Liu, Qide Wang, Jianrong Tan
Summary: This paper presents an assembly precision analysis method based on a general part digital twin model (PDTM). The method improves the efficiency of assembly simulation by mapping assembly information from assembly semantics to geometry elements, allowing automatic assembly positioning of parts. The study considers the impact of assembly-positioning error and mating-surface deformation on the key characteristics of the assembled product, enhancing the reliability of the analytical results.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Geochemistry & Geophysics
Tito Arevalo-Ramirez, Fernando Auat Cheein
Summary: Forest regions pose challenges for measuring terrain information through aerial surveys due to occlusion caused by tree canopies. This study proposes a method to compute the elevation of occluded ground points using canopy data and estimated tree height. The results show improved accuracy compared to traditional methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Biochemical Research Methods
Yadong Liu, Hongbo Yuan, Xin Zhao, Caihu Fan, Man Cheng
Summary: The study presents a reconstruction method based on dual RGB-D cameras for quickly and accurately establishing a 3D model of the peanut plant. The method is 2.54 times faster than the widely used ICP algorithm with approximate accuracy. It offers a potential tool for improving traits and agronomic qualities of plants.
Article
Engineering, Industrial
Wenjun Xu, Jia Cui, Lan Li, Bitao Yao, Sisi Tian, Zude Zhou
Summary: This paper introduces the application of digital twin technology in the field of industrial cloud robotics, encapsulating robot control capabilities as cloud services and implementing fine sensing control of physical manufacturing systems using digital twin technology. This technology is capable of synchronizing and merging digital models with physical robots to achieve accurate control, and it has flexibility and scalability by utilizing ontology models.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Engineering, Multidisciplinary
Chuanfa Chen, Jiaojiao Guo, Yanyan Li, Lianzhong Xu
Summary: In order to improve the accuracy of filtering in complex environments, this paper proposes a segmentation-based hierarchical interpolation filter that utilizes both geometric and radiometric features. The method involves segmenting the raw point cloud using DBSCAN and selecting initial ground seeds based on terrain features. Ground points are then detected using an enhanced multiresolution hierarchical filter with three reference ground surfaces and slope-adaptive thresholds. Experimental results demonstrate that the proposed method outperforms state-of-the-art filtering methods, achieving significant reductions in average type I, II, and total errors, as well as an improvement in the kappa coefficient.
Review
Engineering, Industrial
Fei Tao, Bin Xiao, Qinglin Qi, Jiangfeng Cheng, Ping Ji
Summary: This paper provides a systematic research on the current studies of digital twin modeling and conducts a comprehensive and insightful analysis of digital twin models. It also investigates and summarizes the enabling technologies and tools for digital twin modeling and presents observations and future research recommendations.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Chemistry, Analytical
Xinming Pu, Shu Gan, Xiping Yuan, Raobo Li
Summary: This study combines the advantages of different point cloud acquisition methods to provide high-quality basic data for structure measurement and modeling. By analyzing the mechanisms of different sensors, the integrity of point cloud data, and the single-point geometric characteristics, the advantages and disadvantages of different methods for collecting point clouds of special-shaped structures are compared. Additionally, a point cloud void repair technology based on TLS point cloud is proposed to generate high-quality basic point cloud data of special-shaped structures.
Article
Engineering, Industrial
Xin Ma, Qinglin Qi, Jiangfeng Cheng, Fei Tao
Summary: Human-robot collaboration has broad applications and digital twin plays a critical role in enhancing physical-virtual interaction. However, there are challenges in the dynamic implementation of digital twin, such as building a model and maintaining consistency.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Environmental Sciences
Yijie Wu, Jianga Shang, Fan Xue
Summary: The study proposed a new method RegARD to address the challenge of data set registration by detecting architectural reflection symmetries, achieving high-quality coarse registration and low-cost digital twin buildings creation. Experiments showed that the method outperformed existing methods significantly in both efficiency and effectiveness.
Article
Computer Science, Hardware & Architecture
Bhuvaneswari Swaminathan, Saravanan Palani, Subramaniyaswamy Vairavasundaram, Ketan Kotecha, Vinay Kumar
Summary: Smart farming systems utilize modern technologies like the Internet of Things, Cloud, and Artificial Intelligence (AI) to enhance agricultural practices and increase crop production. Previous works lacked the integration of AI and sensor technology, hindering the development of successful agricultural approaches. To address this, we propose an architectural model consisting of sensor, network, service, and application layers, which enables the deployment of a smart farming system with limited energy consumption. Additionally, we focus on the application layer and present a deep learning approach to create a fertilizer recommendation system that aligns with expert opinions. Ultimately, the entire system is presented as a user-friendly mobile application for farmers.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Computer Science, Artificial Intelligence
E. Rajalakshmi, R. Elakkiya, Alexey L. Prikhodko, M. G. Grif, Maxim A. Bakaev, Jatinderkumar R. Saini, Ketan Kotecha, V Subramaniyaswamy
Summary: The article discusses a Sign Language Recognition system for the hearing and vocally impaired population. A hybrid neural network architecture is proposed to address the challenges in recognizing isolated sign language from static and dynamic gestures. A novel dataset is created and experimental results show high accuracy in static and dynamic isolated sign recognition.
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
(2023)
Article
Engineering, Manufacturing
A. Sasikumar, N. Senthilkumar, V Subramaniyaswamy, Ketan Kotecha, V Indragandhi, Logesh Ravi
Summary: This article discusses the integration of blockchain with industrial IoT systems, presents a DAG-based consensus model to improve the security of industrial IoT, and introduces the key challenges and evaluation results of integrating DAG-based blockchain technology with industrial IoT.
INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM
(2023)
Article
Computer Science, Information Systems
E. Rajalakshmi, R. Elakkiya, V. Subramaniyaswamy, L. Prikhodko Alexey, Grif Mikhail, Maxim Bakaev, Ketan Kotecha, Lubna Abdelkareim Gabralla, Ajith Abraham
Summary: A novel vison-based hybrid deep neural net methodology is proposed in this study for recognizing Indian and Russian sign gestures. The proposed framework aims to establish a single framework for tracking and extracting multi-semantic properties, such as non-manual components and manual co-articulations. By using a 3D deep neural net with atrous convolutions for spatial feature extraction, attention-based Bi-LSTM for temporal and sequential feature extraction, modified autoencoders for abstract feature extraction, and a hybrid attention module for discriminative feature extraction, the proposed sign language recognition framework yields better results than other state-of-the-art frameworks.
Article
Social Sciences, Interdisciplinary
P. Hema, N. R. Rejin Paul, Lenka Cepova, Bhola Khan, Kailash Kumar, Vladimira Schindlerova
Summary: This study proposes a model, named Non-Cooperative Game Resource Allocation Algorithm (NCGRAA), for allocating cloud computing resources based on economic considerations using game theory tools. Additionally, an existing system is improved with the introduction of the Bargaining Game Resource Allocation Algorithm (BGRAA) to develop the billing process while considering availability and fairness. Both algorithms aim to converge on and improve the Nash Equilibrium and Nash Bargaining solutions. Cloud computing has emerged as a popular method for managing computing services and facilitating interactions between producers and consumers. The research investigates the economic operation monitoring of cloud computing using a game theory model.
Article
Computer Science, Artificial Intelligence
Bhuvaneswari Swaminathan, Saravanan Palani, Subramaniyaswamy Vairavasundaram
Summary: In this study, a nutrient-centered deep collaborative filtering technique is proposed to determine the required amount of fertilizers for sustainable crop growth. The data sparsity problem of the undetermined fertilizer's amount is solved by adding side features such as soil fertilizer level, land size, and soil chemical properties. The method exhibits superior performance in predicting nutrient data for precise fertilizer recommendation and increasing crop yield.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Kailash Kumar, Suyog Vinayak Pande, T. Ch. Anil Kumar, Parvesh Saini, Abhay Chaturvedi, Pundru Chandra Shaker Reddy, Krishna Bikram Shah
Summary: A solid state transformer and an optimization coordinated controller are used in a solar power plant to improve transient responsiveness. Transient stability issues in modern electrical power systems due to uncertain renewable energy sources can be addressed by utilizing these devices, which are commonly used to interact between renewable energy sources and the power grid. The solid state transformer features regulated converters to maintain necessary voltage levels, thereby reducing power fluctuations and improving transient responsiveness.
INTERNATIONAL TRANSACTIONS ON ELECTRICAL ENERGY SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Kailash Kumar, M. Pradeepa, Miroslav Mahdal, Shikha Verma, M. V. L. N. RajaRao, Janjhyam Venkata Naga Ramesh
Summary: Chronic kidney disease (CKD) is a disease that gradually impairs kidney function. Detecting CKD at various stages using routine doctor consultation data can facilitate early intervention. Researchers propose an optimization technique inspired by the learning process to categorize CKD.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
M. Anousouya Devi, R. Ezhilarasie, K. Suresh Joseph, Ketan Kotecha, Ajith Abraham, Subramaniyaswamy Vairavasundaram
Summary: In this paper, an Improved Boykov's Graph Cut-based Conditional Random Fields and Superpixel imposed Semantic Segmentation Technique (IBGC-CRF-SPSST) is proposed for efficient cervical cancer detection. This technique combines constraint association among pixels and superpixel edge data to accurately determine the nuclei and cytoplasmic boundaries, achieving effective differentiation of healthy and unhealthy cancer cells. The inclusion of pixel-level forecasting potential of Conditional Random Fields further enhances the semantic-based segmentation accuracy. Experimental results show that the proposed IBGC-CRF-SPSST achieves excellent performance comparable to existing detection techniques, with an accuracy of 99.78%, mean processing time of 2.18 seconds, precision of 96%, sensitivity of 98.92%, and specificity of 99.32%.
Article
Computer Science, Information Systems
S. Saravanan, Kannan Ramkumar, K. Narasimhan, Subramaniyaswamy Vairavasundaram, Ketan Kotecha, Ajith Abraham
Summary: Parkinson's disease is a rapidly growing neurodegenerative disorder that primarily affects the elderly population. Diagnosing Parkinson's disease in its early stages is difficult, and there is currently no antidote for the disease. This study aims to use deep learning models to improve early diagnosis accuracy and increase transparency and trustworthiness.
Article
Computer Science, Information Systems
A. Sasikumar, Logesh Ravi, Ketan Kotecha, Ajith Abraham, Malathi Devarajan, Subramaniyaswamy Vairavasundaram
Summary: Data security and integrity are crucial as data volume grows. Blockchain technology addresses challenges and safeguards personal information. This study introduces a new approach using blockchain and a highway protocol for real-time big data storage security. The proposed protocol allows blocks to configure security thresholds and achieve finality more quickly. The framework dynamically controls data manipulation and supports data-sharing. The highway protocol outperforms baseline models in terms of hit ratio, data processing period, and energy consumption.
Article
Computer Science, Cybernetics
Sudhakar Sengan, Subramaniyaswamy Vairavasundaram, Logesh Ravi, Ahmad Qasim Mohammad AlHamad, Hamzah Ali Alkhazaleh, Meshal Alharbi
Summary: Public and governmental concerns over the widespread diffusion and deceptive impact of online rumors on social media have increased. Finding and controlling social media rumors is challenging in order for users to obtain accurate information and preserve social peace. This article proposes Fakefind, a hybrid model that combines CNN and RNN to efficiently detect rumors using multimodal features.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Information Systems
B. Srinivasan, R. Venkatesan, Belqasem Aljafari, Ketan Kotecha, V. Indragandhi, Subramaniyaswamy Vairavasundaram
Summary: In VLSI circuit design, physical design is a crucial step that involves placing the circuit into the chip area. Floorplanning, which generates a blueprint for circuit module placement, plays a key role in the physical design. The proposed HMAC-FO technique combines the Hybridized Multicriteria Ant Colony and Firefly Optimization algorithms to generate an optimized floorplan. By using an initial population generated by the Ant Colony Optimization algorithm, the firefly algorithm produces globally optimal results. Experimental results on standard MCNC benchmark circuits show that the proposed algorithm achieves reductions in area, wire length, and temperature compared to existing methodologies.
Article
Multidisciplinary Sciences
Sreekumar Krishnan Nair, Sathiya Kumar Chinnappan, Anil Kumar Dubey, Arjun Subburaj, Shanthi Subramaniam, Vivekanandam Balasubramaniam, Sudhakar Sengan
Summary: This article introduces a new method for face detection in surveillance videos. The method combines biometric techniques and deep recurrent neural learning to extract keyframes from video sequences and remove facial features using an edge detector, achieving accurate face recognition. Experimental results show that this method can effectively identify faces while reducing false-positive rates.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Sudhakar Sengan, Kanmani Palaniappan, Nirmala Devi Kathamuthu, Rashid Amin, Rajesh Babu Mariappan, Nik Alif Amri Nik Hashim, Eni Noreni Mohamad Zain, Pankaj Dadheech
Summary: This article investigates the game theory modeling for E-Waste and presents a framework to analyze stakeholders' behavior and determine the best game plan. The findings suggest that using recycled materials is the optimal choice and implementing incentives and penalties can effectively discourage improper disposal of electronic waste.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
