Article
Statistics & Probability
Koen Jochmans
Summary: This article investigates inference in linear regression models that are robust to heteroscedasticity and the presence of many control variables. The usual heteroscedasticity-robust estimators of the covariance matrix are inconsistent when the number of control variables increases at the same rate as the sample size. An alternative covariance-matrix estimator for such a setting is proposed, and high-level conditions for size-correct inference as well as more primitive conditions for three special cases are provided.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Physics, Multidisciplinary
Amichai Painsky, Meir Feder
Summary: The study explores an alternative approach for learning from a finite set of samples, utilizing a minimax estimator to control worst-case performance in a class of reasonable models. The suggested scheme shows significant improvement in worst-case performance compared to currently known alternatives.
Article
Automation & Control Systems
Jiyuan Tu, Weidong Liu, Xiaojun Mao, Xi Chen
Summary: The paper introduces an efficient distributed inference algorithm that is robust against Byzantine failures, achieving better statistical and computational efficiency than traditional methods. Experimental results demonstrate the effectiveness and performance of the algorithm.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Engineering, Manufacturing
Wei-Tai Huang, Shih-Cheng Yang, Wen-Hsien Ho, Jinn-Tsong Tsai
Summary: The study investigates multiple performance objectives in turn-mill multitasking machining using the Taguchi method combined with fuzzy theory. Optimized processing parameters were rapidly identified to obtain improved dimensional accuracy and geometrical shape angle, reducing machining cost and time. The optimized parameters showed dimensional accuracy of 0.005 mm and geometrical shape angle of 0.004 degrees.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2022)
Article
Computer Science, Artificial Intelligence
Nataliya Chukhrova, Arne Johannssen
Summary: The extended sign test, based on fuzzy categories and fuzzy hypotheses, improves the performance of the common sign test by addressing its drawbacks and avoiding common disadvantages associated with fuzzy tests. This method enhances the generality, versatility, and practicability of the sign test.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Statistics & Probability
Marco Avella-Medina
Summary: This research introduces the concept of differential privacy and its application in parametric inference, ensuring privacy through the introduction of noise terms and providing statistical guarantees. The results show a connection between differential privacy and robust statistics, with the former having a weaker stability requirement towards data contamination.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2021)
Article
Construction & Building Technology
Omid Ghaderi, Mohammad Abedini
Summary: This study compared different digital image processing techniques for evaluating the macro-texture of asphalt pavement, finding that image processing provides a faster, more reliable, and cost-effective method compared to conventional tests with lower computational complexity. Regression models of edge pixel count and fuzzy logic edge detection methods showed good correlation with MTD data.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2022)
Article
Management
Amir Homayoun Sarfaraz, Amir Karbassi Yazdi, Thomas Hanne, Peter Fernandes Wanke, Raheleh Sadat Hosseini
Summary: This paper investigates the efficiency indices of Tehran water utility maintenance teams using different DEA models and then assesses the efficiency of these maintenance units using a FIS. Two performance indicators, Availability efficiency and Repair time efficiency, are introduced for performance assessment. In addition, a new index named MRRW is suggested by combining DEA efficiency with the RRW index. The study presents future improvement strategies based on the output of the FIS.
OPERATIONS MANAGEMENT RESEARCH
(2023)
Article
Computer Science, Hardware & Architecture
Eht E. Sham, Deo Prakash Vidyarthi
Summary: This paper proposes an admission control manager using a modified fuzzy inference system to address the uncertainty in resource provisioning of fog-integrated cloud. By analyzing the parameters of requests, the fog-integrated cloud nodes are classified into fog nodes, aggregated fog nodes, and cloud nodes based on a modified fuzzy inference system model. Extensive simulation experiments on real Google trace and comparisons with other methods have been conducted to evaluate the performance of the proposed approach.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Yi Wen Kerk, Chin Ying Teh, Kai Meng Tay, Chee Peng Lim
Summary: This article aims to establish the parametric conditions for the Takagi-Sugeno-Kang (TSK) FIS model to operate as an n-ary aggregation function, through the specifications of fuzzy membership functions and fuzzy rules. An absorption property with fuzzy rules interpretation is outlined, and the use of n-TSK-FIS as a uninorm is explained.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Computer Science, Information Systems
Kamal Das, Rajarshi Ray, Soumen Moulik
Summary: Wireless body area networks (WBANs) are a promising technology that supports a variety of applications. We propose an optimal relaying nodes selection mechanism to enhance reliability, network lifetime, and throughput. We use the TOPSIS method to calculate the fitness value of relaying capable nodes and the Mamdani fuzzy inference system to determine the link quality index. We also design a schedule slot allocation mechanism based on packet generation rate (PGR).
INTERNET OF THINGS
(2023)
Article
Computer Science, Theory & Methods
Thierry Denaeux
Summary: This paper presents the theory of epistemic random fuzzy sets, which is a general theory of uncertainty that includes possibility theory and the Dempster-Shafer theory. The authors extend the theory by introducing Gaussian random fuzzy numbers to represent various beliefs encountered in applications. They also study the properties of one-to-one transformations and mixtures of random fuzzy variables, and demonstrate the practical applications of these models through two case studies.
FUZZY SETS AND SYSTEMS
(2023)
Article
Environmental Sciences
Tjalling Jager
Summary: TKTD models provide mechanistic understanding of individual-level toxicity over time and have great potential for ecotoxicological studies. Robust software tools are needed for automatically extracting best-fitting model parameters and quantifying their uncertainty, especially in the context of environmental risk assessment.
INTEGRATED ENVIRONMENTAL ASSESSMENT AND MANAGEMENT
(2021)
Article
Materials Science, Textiles
Chung-Feng Jeffrey Kuo, Chang-Chiun Huang, Cheng-Han Yang, Sung-Hua Chen
Summary: The study utilized multivariate statistical process control to analyze abnormal samples, effectively identifying them and establishing a fault processing parameter diagnosis system for melt spinning machines.
TEXTILE RESEARCH JOURNAL
(2021)
Article
Engineering, Geological
Adeyemi Emman Aladejare, Toochukwu Ozoji, Abiodun Ismail Lawal, Zongxian Zhang
Summary: This study proposed two soft computing models (ANN and ANFIS) for better predictions of characteristic impedance of igneous rocks, and compared them with multiple linear regression (MLR) model. The results showed that the ANN and ANFIS models had better prediction performance and could be used to predict the characteristic impedance of igneous rocks.
ROCK MECHANICS AND ROCK ENGINEERING
(2022)
Article
Engineering, Manufacturing
Din Bandhu, Jay J. Vora, Subhash Das, Ashish Thakur, Soni Kumari, Kumar Abhishek, M. Nagaphani Sastry
Summary: In this study, the regulated metal deposition (RMD) technique was used to weld ASTM A387-11-2 low alloy steel plates. After the recommended heat-treatment process, the mechanical behavior and microstructure of the welded joints were experimentally investigated. The regulated metal deposition weldments exhibited better microstructure and mechanical properties compared to gas metal arc weldments.
MATERIALS AND MANUFACTURING PROCESSES
(2022)
Article
Engineering, Multidisciplinary
Sarthak Prasad Sahoo, Saurav Datta
Summary: Ti-6Al-4V alloy is a potential material for aerospace and biomedical engineering due to its high temperature strength, corrosion resistance, and strength-to-weight ratio. However, its low thermal conductivity and chemical properties often lead to aggressive cutting conditions and poor surface quality in conventional machining. Therefore, selecting proper cutting tools is crucial for achieving desired machining performance without using coolants.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2022)
Article
Materials Science, Composites
Jogendra Kumar, Kumar Abhishek, Jinyang Xu, Rajesh Kumar Verma
Summary: Fiber laminate composites are widely used in aerospace, aircraft, and automotive components due to their unique features. In this study, the machining behavior and damage generation during milling of graphene-modified carbon-fiber reinforced polymer nanocomposites were investigated. The results showed that the cutting parameters and graphene nanomaterial have a significant influence on the milling responses. The optimal addition of graphene improves the machinability of the nanocomposites, but excessive addition can reduce machining efficiency.
JOURNAL OF COMPOSITES SCIENCE
(2022)
Article
Materials Science, Multidisciplinary
Din Bandhu, E. Venugopal Goud, Jay J. Vora, Subhash Das, Kumar Abhishek, Ramendra Kumar Gupta, Ashish Thakur, Soni Kumari, K. Devaki Devi
Summary: This study performed butt welding experiments using the processes of resistance metal powder welding (RMD) and gas metal arc welding (GMAW), and conducted macroscopic and microscopic analysis of the welds. The results showed that RMD welding produced better weld quality, smaller heat-affected zone, and finer grain refinement.
JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE
(2023)
Article
Engineering, Mechanical
Sarthak Prasad Sahoo, Saurav Datta
Summary: During dry machining of Ti-6Al-4V alloy, the use of HSN2 coated carbide tool reduces cutting forces, tool-tip temperature, and wear severity, resulting in the production of better machined surface quality with reduced chip segmentation ratio.
JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING
(2022)
Review
Materials Science, Multidisciplinary
Soni Kumari, Meet Shah, Yug Modi, Din Bandhu, Kishan Zadafiya, Kumar Abhishek, Kuldeep K. Saxena, Velaphi Msomi, Kahtan A. Mohammed
Summary: In recent years, researchers have proposed sustainable ways to achieve maximum lubricant efficacy with minimal usage. This paper provides a comprehensive review of modern cooling/lubrication technologies and their impact on titanium alloy machining. The study examines selected research on lubrication systems, including power consumption, cutting forces, surface finish, and investigates the effects of different cutting fluids on titanium alloy processing.
Article
Materials Science, Multidisciplinary
Soni Kumari, Din Bandhu, Amit Muchhadiya, Kumar Abhishek
Summary: Friction stir welding (FSW) of polymers and composites has attracted significant attention in recent years. Efforts have been made to explore current trends and optimize FSW processing settings for better joint efficiency. The application of ANOVA in analyzing the parametric effect of welding factors has been highlighted. Further research is needed to address the issue of holes as defects in FSW. This review study also provides recommendations for tool setup, microstructure analysis, and best practices.
ADVANCES IN MATERIALS AND PROCESSING TECHNOLOGIES
(2023)
Article
Engineering, Multidisciplinary
Soni Kumari, Rakesh Gupta, Gopal Krishna, Kumar Abhishek, Naveenkrishna Alla, Kuldeep Kr. Saxena
Summary: Manufacturing and production have experienced rapid development through the combination of additive manufacturing (AM) and other digitally driven machines, creating hybrid additive manufacturing (hybrid-AM). However, hybrid-AM has not gained industrial acceptance due to certain limitations. This article provides the latest information on hybrid-AM, discussing research trends, challenges, and future directions for development.
INNOVATION AND EMERGING TECHNOLOGIES
(2023)
Article
Engineering, Multidisciplinary
Soni Kumari, Kumar Abhishek, Din Bandhu, B. D. Y. Pardeep, B. D. Y. Sunil, Manish Gupta
Summary: In the realm of manufacturing, the use of hybrid manufacturing, which combines additive manufacturing with other digitally driven machines, has led to high-speed production. However, the acceptance of hybrid AM within the industry has been limited due to various constraints. To address this, recent developments in integration of AM processes, improved integrated technical planning, and understanding the mixed supplement production industry are crucial. Emphasizing advances in these areas is essential to meet the demands of a rapidly evolving manufacturing sector.
INNOVATION AND EMERGING TECHNOLOGIES
(2023)
Article
Multidisciplinary Sciences
Nimai Haldar, Sameer Anand, Saurav Datta, Atanu Das
Summary: A slab with dimensions of (152 x 25 x 18) mm(3) was successfully fabricated using Cold Metal Transfer + Metal Inert Gas-based Wire Arc Additive Manufacturing (WAAM), achieving a deposition rate of 4.3 kg/h. The WAAMed Inconel 718 exhibited a dendritic microstructure that grew along the build direction. Different phases, such as Laves phase, Nb-rich MC-type carbides, and delta (d) phases, were detected in the solid solution matrix of Ni-Cr-Fe. The average tensile strength in the horizontal direction was approximately 824 MPa. The microstructure evolution at specific locations caused significant anisotropy in properties, primarily along the build direction.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Akshay Kumar, Saurav Datta, Tarapada Roy, Siba Sankar Mahapatra
Summary: Auxetic metamaterials, with cellular structures and better mechanical properties, have wide engineering applications. In this study, the auxetic behavior of chiral honeycomb structures was investigated using the Finite Element Method, and tensile specimens were fabricated using Fused Filament Fabrication (FFF). The effects of FFF parameters on part quality and build time were analyzed, and an optimal combination of FFF parameters was determined.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2022)
Article
Engineering, Multidisciplinary
Sarthak Prasad Sahoo, Kshitij Pandey, Saurav Datta
Summary: In this study, the machinability of difficult-to-cut Inconel 718 aerospace superalloy is investigated under vegetable oil-based minimum quantity lubrication (MQL) with different cutting tool materials. Coated tools show lower tool-tip temperature and cutting forces compared to uncoated tools.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2022)
Proceedings Paper
Materials Science, Multidisciplinary
Naveen Kumar, Soni Kumari, Kumar Abhishek, Goutam Nandi, Nabendu Ghosh
Summary: Wire Electro Discharge Machining (WEDM) is a nonconventional machining method used for cutting hard conductive materials. This paper reviews recent research and focuses on the effect of different optimization techniques on hard to cut materials. The study examines various input parameters to optimize the process parameters of WEDM, including metal removal rate and surface roughness. The paper also covers single response and multi-response techniques.
MATERIALS TODAY-PROCEEDINGS
(2022)
Article
Engineering, Multidisciplinary
Kshitij Pandey, Saurav Datta, Tarapada Roy
Summary: This study investigates the turning performance of Inconel 825 superalloy under Nanofluid Minimum Quantity Lubrication (NFMQL), revealing that NFMQL machining exhibits lower cutting force, reduced tool-tip temperature, and less severe tool wear compared to dry machining. Additionally, NFMQL produces thinner chips with shorter segmentation spacing and wider shear angle.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2022)
Article
Computer Science, Information Systems
Soni Kumari, Bhavdeep Nakum, Din Bandhu, Kumar Abhishek
Summary: This article is a case study that uses fuzzy logic and the VIKOR method to solve a car purchasing problem.
INTERNATIONAL JOURNAL OF DECISION SUPPORT SYSTEM TECHNOLOGY
(2022)