Article
Public, Environmental & Occupational Health
Jian Zhou, Yuxin Chen, Hui Chen, Manoj Khandelwal, Masoud Monjezi, Kang Peng
Summary: Pillar stability is crucial for safe work in mines. Accurate estimation of induced stresses in pillars is important for design and guaranteeing stability. Machine learning algorithms, such as back-propagation neural network (BPNN), have been successfully applied to pillar stability assessment with high accuracy.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Engineering, Geological
D. G. Wessels, D. F. Malan
Summary: This study used a limit equilibrium model to simulate the time-dependent scaling of hard rock pillars. The study found that extensive scaling occurs in pillars with a high joint density in manganese mines in South Africa. Contrary to expectations, the study found that almost no additional scaling was recorded during a 3-month monitoring period. Numerical simulations using a displacement discontinuity code and a limit equilibrium constitutive model showed that the decay of rock mass strength at the edges of pillars qualitatively matches the observed underground behavior.
ROCK MECHANICS AND ROCK ENGINEERING
(2023)
Article
Agricultural Engineering
P. C. S. Moncks, E. K. Correa, L. L. C. Guidoni, R. B. Moncks, L. B. Correa, T. Lucia Jr, R. M. Araujo, A. C. Yamin, F. S. Marques
Summary: This study designed a hardware and software model to enable self-adjustment of a low-cost capacitive moisture sensor and improve the measurement accuracy using machine learning techniques. The results demonstrate that the proposed model is efficient and reliable in measuring moisture in compost.
BIORESOURCE TECHNOLOGY
(2022)
Article
Optics
Jianan Feng, Hang Chen, Dahai Yang, Junbo Hao, Jie Lin, Peng Jin
Summary: In this paper, a framework for achieving multi-wavelength D2NN based on weight coefficients is proposed. The classification tasks are conducted using the designed multi-layer and single-layer MW-D2NN, with simulation and experimental results showing high accuracy. The proposed MW-D2NN can be extended to intelligent machine vision systems with multi-wavelength and incoherent illumination.
Article
Gastroenterology & Hepatology
Joon Yeul Nam, Hyung Jin Chung, Kyu Sung Choi, Hyuk Lee, Tae Jun Kim, Hosim Soh, Eun Ae Kang, Soo-Jeong Cho, Jong Chul Ye, Jong Pil Im, Sang Gyun Kim, Joo Sung Kim, Hyunsoo Chung, Jeong-Hoon Lee
Summary: This study developed and validated convolutional neural network-based artificial intelligence models for the differential diagnosis of gastric mucosal lesions, showing good performance in lesion detection, differential diagnosis, and evaluation of invasion depth when compared with visual diagnoses by endoscopists and EUS results. The AI models were comparable with experts and outperformed novice and intermediate endoscopists in the differential diagnosis, while the AI model for invasion depth assessment performed better than EUS.
GASTROINTESTINAL ENDOSCOPY
(2022)
Article
Chemistry, Multidisciplinary
Abdullah K. Alanazi, Seyed Mehdi Alizadeh, Karina Shamilyevna Nurgalieva, Slavko Nesic, John William Grimaldo Guerrero, Hala M. Abo-Dief, Ehsan Eftekhari-Zadeh, Ehsan Nazemi, Igor M. Narozhnyy
Summary: This innovative non-invasive system uses a dual-energy gamma source and two detectors, along with artificial intelligence, to determine the flow pattern and volume percentage of two-phase flow by considering the thickness of scales in the pipelines.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Kerstin N. Vokinger, Urs Gasser
Summary: Regulatory frameworks for artificial intelligence are being developed on both sides of the Atlantic, eagerly anticipated by the scientific and industrial community. Commonalities and differences in approaches to AI in medicine are beginning to emerge.
NATURE MACHINE INTELLIGENCE
(2021)
Editorial Material
Biochemistry & Molecular Biology
Eric Wu, Kevin Wu, Roxana Daneshjou, David Ouyang, Daniel E. Ho, James Zou
Summary: A comprehensive overview of medical AI devices approved by the US Food and Drug Administration sheds light on limitations of the evaluation process that may mask vulnerabilities of devices when deployed on patients.
Article
Multidisciplinary Sciences
Zafer Soydan, Yavuz Saglam, Sefa Key, Yusuf Alper Kati, Murat Taskiran, Seyfullah Kiymet, Tuba Salturk, Ahmet Serhat Aydin, Fuat Bilgili, Cengiz Sen
Summary: Researchers trained a convolutional neural network (CNN) using a unique method to classify Legg-Calve-Perthes disease (LCPD) based on modified hip radiographs, and compared its performance to that of 11 doctors. The CNN model showed good reliability (ICC = 0.868) and achieved a classification performance of 76.54%, surpassing 9 out of 11 doctors.
SCIENTIFIC REPORTS
(2023)
Article
Chemistry, Analytical
Ritesh Kumar Singh, Mohammad Hasan Rahmani, Maarten Weyn, Rafael Berkvens
Summary: This study presents a greenhouse monitoring system utilizing internet of things and low-power wide area network communication, aided by artificial intelligence technology for disease and nutrition detection in plants. The analysis and prediction of crop growth based on collected datasets have improved the efficiency of precision agriculture monitoring.
Article
Engineering, Geological
Prudhvi Raju Gadepaka, Ashok Jaiswal
Summary: A novel approach is proposed for simulating the caving behavior in underground coal mining. The approach resembles the natural caving mechanism and controls the uncontrolled deformation using interface elements. The simulation results are found to match the physical observations and can predict the surface subsidence and stress changes on the working pillars.
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2023)
Article
Multidisciplinary Sciences
Laetitia Coassolo, Tianyun Liu, Yunshi Jung, Nikki P. Taylor, Meng Zhao, Gregory W. Charville, Silas Boye Nissen, Hannele Yki-Jarvinen, Russ B. Altman, Katrin J. Svensson
Summary: Non-alcoholic fatty liver disease (NAFLD) is a complex disease with unclear molecular mechanisms. By using single-cell RNA sequencing, researchers identified distinct clusters of hepatocytes with different expression of the lipid synthesis driver Srebp1. Interestingly, Srebp1 was not a reliable predictor of hepatic lipid accumulation, suggesting the involvement of other factors in lipid metabolism. Computational network analyses revealed a strong association between NAFLD and high constitutive androstane receptor (CAR) expression, which interacted with multiple functional modules related to lipid metabolism. These findings provide insights into the cellular differences in lipid signatures and identify important functional networks involved in hepatic steatosis in both mice and humans.
Article
Optics
Ehsan Eftekhari-Zadeh, Abdallah S. Bensalama, Gholam Hossein Roshani, Ahmed S. Salama, Christian Spielmann, Abdullah M. Iliyasu
Summary: Scale deposition is a significant issue in the oil and gas production system. Our proposed method, using an Artificial Neural Network (ANN) model, accurately classifies flow regimes and predicts scale thickness, providing a platform to improve various areas in the oil industry.
Editorial Material
Health Care Sciences & Services
Mirja Mittermaier, Marium M. Raza, Joseph C. Kvedar
Summary: Artificial intelligence is increasingly used in healthcare, particularly in surgery. While it holds promise in predicting outcomes and guiding surgeons, AI systems can also be biased, exacerbating existing inequalities. This impacts disadvantaged populations, who may receive less accurate algorithmic predictions or underestimate their need for care. Detecting and mitigating bias is crucial for creating fair and generalizable AI technology. This article discusses a recent study that developed a new strategy to address bias in surgical AI systems.
NPJ DIGITAL MEDICINE
(2023)
Article
Health Care Sciences & Services
Roman Zeleznik, Jakob Weiss, Jana Taron, Christian Guthier, Danielle S. Bitterman, Cindy Hancox, Benjamin H. Kann, Daniel W. Kim, Rinaa S. Punglia, Jeremy Bredfeldt, Borek Foldyna, Parastou Eslami, Michael T. Lu, Udo Hoffmann, Raymond Mak, Hugo J. W. L. Aerts
Summary: The study evaluated the use of a deep-learning system for heart segmentation on CT scans in radiation oncology treatment planning. The system, trained with multi-center data and validated in a real-world dataset, showed improved segmentation time and agreement compared to manual methods. The results indicate that deep-learning algorithms can be successfully applied across medical specialties to enhance clinical care.
NPJ DIGITAL MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Amirhossein Mehrdanesh, Masoud Monjezi, Manoj Khandelwal, Parichehr Bayat
Summary: In this paper, various robust techniques were implemented to predict rock fragmentation in open pit mines. Artificial neural network (ANN) was found to be the most precise method for modeling, compared to other techniques. Sensitivity analysis revealed that rock quality designation, Schmidt hardness value, mean in-situ block size were the most influential parameters, while hole diameter and burden had smaller impacts. The advantage of using back propagation neural network technique is its ability to transparently describe complex multivariable problems.
ENGINEERING WITH COMPUTERS
(2023)
Article
Green & Sustainable Science & Technology
Saeed Aligholi, Manoj Khandelwal
Summary: According to chaos theory, certain underlying patterns can reveal the order of disordered systems. This study discusses the intermittency of rough rock fractured surfaces as an orderable disorder at intermediate length scales, which is more complex than simple fractal or multi-scaling behaviors. The introduced parameters effectively capture the systematic behavior and quantify the intermittency of the surfaces, providing a framework for quantifying and modeling the roughness of fractured surfaces and analyzing fluid flow and shear strength in rock media. This framework can also be used in analyzing the intermittency of time series and developing new models for predicting seismic or flood events with higher accuracy in a short time.
Article
Public, Environmental & Occupational Health
Jian Zhou, Yuxin Chen, Hui Chen, Manoj Khandelwal, Masoud Monjezi, Kang Peng
Summary: Pillar stability is crucial for safe work in mines. Accurate estimation of induced stresses in pillars is important for design and guaranteeing stability. Machine learning algorithms, such as back-propagation neural network (BPNN), have been successfully applied to pillar stability assessment with high accuracy.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Metallurgy & Metallurgical Engineering
Jian Zhou, Peixi Yang, Pingan Peng, Manoj Khandelwal, Yingui Qiu
Summary: Three hybrid support vector machine (SVM) models optimized by particle swarm optimization (PSO), Harris hawk optimization (HHO), and moth flame optimization (MFO) are proposed to predict rockburst hazard level (RHL), achieving better accuracy and performance than the unoptimized SVM model.
MINING METALLURGY & EXPLORATION
(2023)
Article
Engineering, Multidisciplinary
Dakshith Ruvin Wijesinghe, Sundararajan Natarajan, Greg You, Manoj Khandelwal, Ashley Dyson, Chongmin Song, Ean Tat Ooi
Summary: A scaled boundary finite element-based phase field formulation is proposed for modeling 2D fracture in saturated poroelastic media. An adaptive refinement strategy based on quadtree meshes is adopted to avoid the constraints of fine uniform meshes when using phase field models. The unique advantage of the scaled boundary finite element method allows for efficient computation on quadtree meshes without special treatment of hanging nodes. The proposed model is validated and demonstrated through numerical examples of hydraulic fractures.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Review
Energy & Fuels
Rahil Parag Sheth, Narendra Singh Ranawat, Ayon Chakraborty, Rajesh Prasad Mishra, Manoj Khandelwal
Summary: Since their introduction in the 1970s, lithium-ion batteries (LIBs) have seen a significant increase in demand due to their applications in electric vehicles, smartphones, and energy storage systems. To address the environmental effects of excessive mining activities and waste production, it is essential to explore ways of manufacturing LIBs from already extracted resources through re-usage, refurbishing, and recycling, as well as adopting the circular economy model. A literature review reveals that the current focus in the battery industry is mostly on recycling, and further understanding is needed to adapt to other circular economy practices such as reuse, remanufacture, and refurbishment. The review also provides insights into the recycling process and presents case studies showcasing different approaches to battery recycling, contributing to a comprehensive understanding of the current state of LIB recycling and CE adoption.
Article
Engineering, Mechanical
Dakshith Ruvin Wijesinghe, Ashley Dyson, Greg You, Manoj Khandelwal, Ean Tat Ooi
Summary: Accurate interpretation of stratigraphic profiles, the phreatic surface, and the spatial variability of geomaterials are crucial for representative behavior of geomechanical systems. This paper presents an image-based technique for generating continuous stratigraphic profiles with random fluctuations. The technique uses Brownian bridges and quadtree decomposition to discretize and integrate material properties for slope stability analysis with the Scaled Boundary Finite Element Method.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Mechanics
Shiming Wang, Jiaqi Wang, Xianrui Xiong, Zhongjun Ren, Lei Weng, Manoj Khandelwal, Jian Zhou
Summary: Thin Spray-On Liner (TSL) is widely used in underground engineering support like mining due to its ease of operation and effective support. A series of uniaxial compression experiments were conducted on TSL-coated specimens under static and dynamic loads to study the support effect. The results showed that the TSL improves the strength and peak strain of sandstone, with a more significant improvement observed with increased coating thickness. TSL provides good bonding ability and tensile properties to support the rock. Simulation results confirmed the experimental findings, demonstrating that TSL delays failure time and reduces cracks.
MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES
(2023)
Article
Mechanics
Lei Zhou, Hadi Haeri, Vahab Sarfarazi, Soheil Abharian, Manoj Khandelwal, Mohammad Fatehi Marji
Summary: The effects of porosity and its geometry on the tensile features of concrete were investigated using the Brazilian test and three-dimensional PFC model. The study found that the porosity geometry plays an important role in the fracturing pattern, with different pore shapes leading to different fracture energies and crack initiation stresses. The results highlight the significance of considering porosity geometry in understanding the mechanical behavior of concrete.
MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES
(2023)
Article
Engineering, Geological
Jian Zhou, Rui Zhang, Yingui Qiu, Manoj Khandelwal
Summary: Rock strength is crucial for underground projects, and this study utilizes a GEP algorithm-based model to predict true triaxial strength, considering the influence of rock genesis. The proposed criterion shows superior prediction accuracy and stability compared to existing models.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2023)
Article
Energy & Fuels
Mostafa Hosseini, Manoj Khandelwal, Rahman Lotfi, Mohsen Eslahi
Summary: Bench blasting is a typical method used in surface mines to excavate hard rock mass. However, improper blasting leads to backbreak, massive rock fragmentation, and high-intensity ground vibrations, resulting in increased production costs and decreased productivity. This study conducted a sensitivity analysis on various blast design parameters using the Taguchi method, and found that blast hole diameter is the most important factor influencing blasting outcomes.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2023)
Article
Engineering, Multidisciplinary
Jian Zhou, Yong Dai, Ming Tao, Manoj Khandelwal, Mingsheng Zhao, Qiyue Li
Summary: In this research, a novel intelligent model based on random forest algorithm and salp swarm algorithm has been developed to predict the mean cutting force of conical picks. The model demonstrates higher accuracy and reliability compared to other prediction tools.
RESULTS IN ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Gaurav Verma, Brind Kumar, Chintoo Kumar, Arunava Ray, Manoj Khandelwal
Summary: The study utilizes novel computational approaches to predict the soaked CBR value of soils as an alternative solution to the rigorous and time-taking laboratory-performed CBR test. The results show that sand, fine content, plastic limit, plasticity index, maximum dry density, and optimum moisture content are the most influencing input parameters in developing the soaked CBR of fine-grained plastic soils. The GPR model developed through FCM and K-Fold data division approaches demonstrates good predictive ability and helps remove overfitting.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Civil
Jian Zhou, Shuai Huang, Ming Tao, Manoj Khandelwal, Yong Dai, Mingsheng Zhao
Summary: This study proposes a new prediction method based on machine learning to scientifically adjust the critical span graph. The prediction performance of the proposed PSO-GBDT model is the most reliable among the other eight models, with a classification accuracy of 0.93. It has great potential to provide a more scientific and accurate choice for the stability prediction of underground excavations.
Article
Geosciences, Multidisciplinary
Masoud Monjezi, Hamed Amiri, Mir Naser Seyed Mousavi, Jafar Khademi Hamidi, Manoj Khandelwal
Summary: Blasting operation is crucial in mining industry for efficient rock fragmentation. Optimizing blasting techniques can reduce undesirable side effects and improve rock fragmentation. This study found that using a top air deck instead of a bottom one significantly decreased specific charge, back break, and flyrock while increasing the average size of fragments obtained from blasting.