Article
Computer Science, Interdisciplinary Applications
Mario Miguel Valero, Lluis Jofre, Ricardo Torres
Summary: Predictions of wildfire behavior are often uncertain, with modeling uncertainties largely unquantified in the literature due to computing constraints. However, new multifidelity techniques show promise in overcoming these limitations, as demonstrated in this study's exploration of their applicability to wildland fire spread prediction. The study achieved notable speedups in performance compared to standard methods, allowing for the quantification of uncertainties and sensitivity analysis in a cost-effective manner.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Thermodynamics
Abdelrahman Abouali, Domingos Xavier Viegas, Jorge Rafael Raposo
Summary: This study examines unexpected or unusual fire behaviors on a sloped ridgeline hill, caused by the interaction between terrain-modified flow mechanisms and fire. Accelerated wind flows resulting from this interaction are found to drive the indicated unexpected behavior.
COMBUSTION AND FLAME
(2021)
Article
Computer Science, Interdisciplinary Applications
K. C. Ujjwal, Jagannath Aryal, Saurabh Garg, James Hilton
Summary: Environmental models often involve inherent uncertainties, which can be quantified using global sensitivity analysis (GSA) methods such as Morris, Sobol, FAST, and PAWN. The choice of GSA method depends on the model complexity and computational constraints, with a trade-off between convergence and computational costs. Sobol method is recommended for detailed sensitivity information, while Morris or PAWN methods are preferred for balanced trade-off under computational constraints.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Environmental Sciences
Gavin M. Schag, Douglas A. Stow, Philip J. Riggan, Atsushi Nara
Summary: The study evaluates the spatial sampling and statistical aspects of landscape-level wildfire rate of spread (ROS) estimates derived from airborne thermal infrared imagery. The findings reveal that the relationships between covariates and ROS estimates are substantially non-stationary on landscape scales. The study highlights the importance of directional slope as the most strongly associated covariate of ROS for the analyzed imagery sequences, regardless of the size of landscape sampling unit.
Article
Environmental Sciences
Darud E. Sheefa, Robert M. Handler, Brian D. Barkdoll
Summary: Flushing the water distribution system with fire hydrants is a common method for decontamination, but it causes environmental impact by discharging contaminated water to the surroundings. To reduce this impact, using a containment pond as an alternative was studied. The results showed that environmental impacts can be significantly reduced in different areas, and the time needed for decontamination and the area of land exposed to contaminated water discharge are the most sensitive variables affecting the impact.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2022)
Article
Thermodynamics
Guanjie Hou, Quanwang Li, Zhigang Song, Hao Zhang
Summary: This study proposes an innovative procedure to determine optimal fire station locations considering unique fire development patterns and potential losses from daily fires and post-earthquake fires. By simulating fire spread processes and utilizing a non-dominated sorting genetic algorithm, the method aims to reduce fire losses and account for uncertainties in estimating arrival times and acceptable fire loss changes.
CASE STUDIES IN THERMAL ENGINEERING
(2021)
Article
Environmental Sciences
Xingdong Li, Hewei Gao, Mingxian Zhang, Shiyu Zhang, Zhiming Gao, Jiuqing Liu, Shufa Sun, Tongxin Hu, Long Sun
Summary: The article introduces three network models based on Long Short-Term Memory (LSTM) to predict fire spread rate, and experimentally validates their effectiveness. The results show that the FNU-LSTM model performs best in both training and prediction stages, successfully predicting real fire spread scenarios.
Article
Urban Studies
Ye Wei, Jiaoe Wang, Wei Song, Chunliang Xiu, Li Ma, Tao Pei
Summary: This study constructed a city-based epidemic and mobility model to simulate the spatiotemporal spread of COVID-19, emphasizing the role of intercity population mobility. Results showed high precision in simulating the inter-city spread of COVID-19 in China. Scenario simulations quantitatively evaluated the effect of control measures such as city lockdown and decreasing population mobility on containing the spatial spread of the COVID-19 epidemic.
Article
Ecology
Jose Ramon Gonzalez-Olabarria, Jaime Carrasco, Cristobal Pais, Jordi Garcia-Gonzalo, David Palacios-Meneses, Rodrigo Mahaluf-Recasens, Olena Porkhum, Andres Weintraub
Summary: The use of fire simulation tools in landscape-level fuel management decisions is common practice. Incorporating fire simulation tools in forest management planning allows for evaluation of fire risk and definition of fire mitigation goals considering the spatial nature of fires. By combining fire simulation tools, growth and yield simulators, and optimization modules, it is possible to minimize fire impact and maximize ecosystem service yield over time.
FRONTIERS IN FORESTS AND GLOBAL CHANGE
(2023)
Article
Construction & Building Technology
Qing He, Zhilei Cao, Fei Tang, Mingyan Gu, Tingting Zhang
Summary: This study experimentally investigates the behavior of carriage flame propagation, evolutionary mechanism, and internal temperature distribution caused by carriage fire in a 1/8 model tunnel. The effects of heat release rates, longitudinal wind speeds, and opening sizes on tunnel safety are comprehensively considered. Machine learning methods, such as BP neural network, are utilized to derive heat release rates from video data for fast operational tunnel management.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
Anabelle W. Cardoso, Sally Archibald, William J. Bond, Corli Coetsee, Matthew Forrest, Navashni Govender, David Lehmann, Loic Makaga, Nokukhanya Mpanza, Josue Edzang Ndong, Aurelie Flore Koumba Pambo, Tercia Strydom, David Tilman, Peter D. Wragg, A. Carla Staver
Summary: This study demonstrates that an infection model captures the spreading pattern of individual fires better than competing models. The proportion of burned landscape can be described by measurements of grass biomass, fuel moisture, and vapor pressure deficit. Averaging across variability results in quasi-linear patterns regionally.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Construction & Building Technology
Kun He, Ying Zhen Li, Haukur Ingason, Xudong Cheng
Summary: The characteristics of fire spread among multiple vehicles in tunnels using longitudinal ventilation were investigated. A simple theoretical model for gas temperature in a tunnel with multiple fire sources was proposed and validated against both model and full-scale tunnel fire tests. The results showed that the critical fire spread distance monotonously increases with the heat release rate, and decreases with the tunnel perimeter. Moreover, the separation distance between the first two fire sources affects the critical fire spread distance from the second fire source to the third fire source and the total fire spread distance from the first fire source to the third one.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2023)
Article
Forestry
Domingos Xavier Filomeno Carlos Viegas, Jorge Rafael Nogueira Raposo, Carlos Fernando Morgado Ribeiro, Luis Carlos Duarte Reis, Abdelrahman Abouali, Carlos Xavier Pais Viegas
Summary: A conceptual model based on the dynamic interaction between fire, the fuel bed, and the surrounding flow is proposed to explain the non-monotonic or intermittent behavior of fires. Experimental results show that the evolution of fire properties exhibits high-frequency oscillations superimposed on low-frequency fire growth cycles.
INTERNATIONAL JOURNAL OF WILDLAND FIRE
(2021)
Article
Computer Science, Interdisciplinary Applications
Sadegh Khanmohammadi, Mehrdad Arashpour, Emadaldin Mohammadi Golafshani, Miguel G. Cruz, Abbas Rajabifard, Yu Bai
Summary: This study examines the applicability of various machine learning methods in predicting the rate of spread of grassfires and develops and evaluates models using a dataset from wildfires and experimental fires.
ENVIRONMENTAL MODELLING & SOFTWARE
(2022)
Article
Thermodynamics
Jiaming Zhao, Zhisheng Xu, Houlin Ying, Xueqi Guan, Kunkun Chu, Sylvain Marcial Sakepa Tagne, Haowen Tao
Summary: This study analyzed the temperature, velocity field, and visibility changes in subway carriages during fires using the fire dynamics simulator (FDS). The results showed that the distribution pattern of ceiling temperature and velocity field remains the same for different subway carriages fires. These findings support the formulation of operational safety management regulations and guidelines for long-distance intervals.
CASE STUDIES IN THERMAL ENGINEERING
(2022)
Article
Automation & Control Systems
Shifa Siddiqui, Muhammad Shahzad Faisal, Shahzada Khurram, Azeem Irshad, Mohammed Baz, Habib Hamam, Naeem Iqbal, Muhammad Shafiq
Summary: Play Store reviews are crucial for understanding mobile app quality and helping developers build better apps. Low-quality apps and spam reviews harm user experience and trust, damaging the reputation of Play Store. Therefore, analyzing review content and developing suitable regression models for wearable apps is of great importance.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Review
Chemistry, Physical
Imran, Faiza Qayyum, Do-Hyeun Kim, Seon-Jong Bong, Su-Young Chi, Yo-Han Choi
Summary: Interdisciplinary research has become more common in recent years, with a focus on the application of artificial intelligence and machine learning in the physical sciences. This study presents a comprehensive survey of state-of-the-art methods for material discovery, including benchmark data sets, pre-processing and analysis techniques, learning model mechanisms, and simulation techniques. The analysis provides promising directions for young interdisciplinary researchers in the computing and material science fields, and aims to contribute to the material industry by reducing manual effort and improving modeling techniques.
Article
Computer Science, Artificial Intelligence
Ahmad Naeem, Tayyaba Anees, Khawaja Tehseen Ahmed, Rizwan Ali Naqvi, Shabir Ahmad, Taegkeun Whangbo
Summary: This paper proposes a novel deep learning technique for image retrieval, which combines convolutional neural network with auto-correlation, gradient computation, and other techniques to achieve highly accurate results. The experiments demonstrate outstanding performance of the proposed method on various datasets.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Harun Jamil, Faiza Qayyum, Naeem Iqbal, Faisal Jamil, Do Hyeun Kim
Summary: This research proposes an optimal ensemble HAR and floor detection scheme based on automated learning and weighted soft voting using smartphone-based sensors to improve the recognition rate. The proposed scheme combines multiple supervised models to classify human activities and detect floor height in multistory buildings. Experimental results demonstrate that the proposed scheme outperforms existing standalone models in terms of recognition accuracy.
IEEE SENSORS JOURNAL
(2023)
Review
Computer Science, Information Systems
Tehseen Mazhar, Hafiz Muhammad Irfan, Inayatul Haq, Inam Ullah, Madiha Ashraf, Tamara Al Shloul, Yazeed Yasin Ghadi, Imran, Dalia H. Elkamchouchi
Summary: With the help of machine learning, difficult tasks can be automated. In a smart grid, computers and mobile devices make it easier to control the interior temperature, monitor security, and perform routine maintenance. The Internet of Things (IoT) connects the components of smart buildings, improving the quality of life for everyone.
Article
Computer Science, Hardware & Architecture
Murad Ali Khan, Naeem Iqbal, Imran, Harun Jamil, Do-Hyeun Kim
Summary: Traditional ML based IDS cannot handle high-speed and ever-evolving attacks. This study proposes an OE-IDS model using AutoML based on a soft voting method for detecting intrusion in the network environment. The proposed model achieves high accuracy and minimizes false alarm rates through optimal ensemble strategy and different sampling methods.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2023)
Article
Mathematics
Faisal Mehmood, Shabir Ahmad, Taeg Keun Whangbo
Summary: Deep learning is a branch of AI that trains neural networks to acquire knowledge. It has various applications in different industries. It is effective in solving complex tasks related to computer vision, such as image classification and object detection.
Article
Biochemistry & Molecular Biology
Tariq Sadad, Raja Atif Aurangzeb, Imran, Mejdl Safran, Sultan Alfarhood, Jungsuk Kim
Summary: This study proposes a genome analysis system that uses advanced deep learning to identify dozens of viruses. The system utilizes nucleotide sequences from the NCBI GenBank database and a BERT tokenizer to extract features. The system consists of a scratch BERT architecture for DNA analysis and a classifier that identifies important features and understands the relationship between genotype and phenotype. The system achieved an accuracy of 97.69% in identifying viral sequences.
Review
Multidisciplinary Sciences
Muhammad Imran Khan, Humera Qureshi, Suk Joo Bae, Aamer Ali Khattak, Muhammad Shahid Anwar, Sadique Ahmad, Fazal Hassan, Shabir Ahmad
Summary: This study conducted a systematic review and meta-analysis on malaria prevalence in Pakistan from 2006 to 2021. Out of the 315 studies collected, only 45 full-text articles were included in the final meta-analysis. The pooled malaria prevalence in Pakistan was 23.3%, with Plasmodium vivax, Plasmodium falciparum, and mixed infection rates of 79.13%, 16.29%, and 3.98%, respectively.
Article
Computer Science, Theory & Methods
Shah Khalid, Aftab Alam, Muhammad Fayaz, Fakhrud Din, Sehat Ullah, Shabir Ahmad
Summary: Serious games have a significant impact on engaging users in healthy activities. CVEs, as enablers of serious games, are widely used in fields like education, healthcare, and tele-conferencing. Network latency is an overlooked factor that affects user performance in CVE. This study analyzed the effects of network latency on user performance and found that the use of arrows-casting aids improved performance compared to other aids.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Faiza Qayyum, Harun Jamil, Naeem Iqbal, Do-Hyeun Kim
Summary: The Internet of things has revolutionized various domains, but its untapped potential in the energy sector is still a topic of contention. Shifting from traditional electric smart grid systems to IoT-based orchestrated frameworks can significantly improve performance. Our proposed architecture includes energy trading cost and ESS power optimization strategies, as well as an IoT-enabled task orchestration system. Evaluating the model using real data sets demonstrates the significant role of optimization in minimizing energy trading cost and optimizing ESS power utilization.
Article
Computer Science, Information Systems
Taimur Shahzad, Khalid Iqbal, Murad Ali Khan, Imran, Naeem Iqbal
Summary: Facial expressions are crucial for collaboration and effective discourse. This study proposes a zoning-based face expression recognition (ZFER) method that improves accuracy by dividing facial landmarks into regions.
Article
Computer Science, Information Systems
Zineddine Kouahla, Ala-Eddine Benrazek, Mohamed Amine Ferrag, Brahim Farou, Hamid Seridi, Muhammet Kurulay, Adeel Anjum, Alia Asheralieva
Summary: This paper examines and reviews existing indexing techniques for large-scale data, proposes a taxonomy for researchers to select techniques as the basis for designing new indexing schemes, presents real-world applications in various fields, and discusses open problems and research challenges.