Article
Engineering, Biomedical
Yeguo Xu, Yuhang Wang, Navid Razmjooy
Summary: This study proposes a new diagnosis system for lung cancer based on image processing and artificial intelligence from CT-scan images. The proposed method shows high accuracy and recall rates, and can serve as an efficient tool for optimal diagnosis of lung cancer.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Mathematics
Chun-Yao Lee, Guang-Lin Zhuo
Summary: This study introduces a hybrid whale optimization algorithm that combines genetic and thermal exchange optimization methods, enhancing global optimization capability. The algorithm demonstrates accuracy and competitiveness on benchmark test functions and datasets, performing excellently in solving optimization problems.
Article
Engineering, Biomedical
Zhaoyu Hu, Leyin Li, An Sui, Guoqing Wu, Yuanyuan Wang, Zhifeng Shi, Jinhua Yu, Liang Chen, Guiguan Yang, Yuhao Sun
Summary: In this study, a new network search framework, OCIF, is proposed to integrate low-dimensional clinical information with high-dimensional network features. The use of Gaussian process optimization and transfer learning effectively improves computer-aided diagnosis accuracy.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2023)
Article
Forestry
Demiao Chu, Redzo Hasanagic, Atif Hodzic, Davor Krzisnik, Damir Hodzic, Mohsen Bahmani, Marko Petric, Miha Humar
Summary: This study aims to investigate the influence of thermal modification on the physical and mechanical properties of wood. Experimental results show that stochastic modeling and evolutionary algorithms can be used to obtain models that accurately describe the experimental data.
Article
Automation & Control Systems
Zhenya Wang, Ligang Yao, Gang Chen, Jiaxin Ding
Summary: This paper proposes a novel intelligent fault-diagnosis method for rolling bearing fault diagnosis, utilizing generalized composite multiscale weighted permutation entropy and supervised Isomap algorithm for feature extraction and dimensionality reduction, and employing a support vector machine for diagnosis and identification, confirming the effectiveness of the proposed method through experiments.
Article
Engineering, Multidisciplinary
Hailun Wang, Fei Wu, Lu Zhang
Summary: This paper proposes a failure diagnosis method based on variational mode decomposition (VMD) optimized by the improved whale optimization algorithm (IWOA), and verifies its effectiveness through experiments. The method can effectively extract the early failure features of rolling bearings, improving the quality of information.
ALEXANDRIA ENGINEERING JOURNAL
(2021)
Article
Automation & Control Systems
Shuzhi Gao, Lintao Xu, Yimin Zhang, Zhiming Pei
Summary: An innovative optimized adaptive deep belief network (SADBN) is proposed to address the problem of rolling bearing fault identification. By utilizing an intelligent optimization method and experience of deep learning network structure, the classification accuracy is effectively improved.
Article
Biology
Shervan Fekri-Ershad, S. Ramakrishnan
Summary: This paper presents a two-stage method for pap smear image classification, improving the accuracy of cervical cancer diagnosis. The method uses texture information and a deep neural network for image classification, and improves performance through an optimization algorithm. The results show high detection accuracy, insensitivity to image rotation, and short runtime for the proposed method.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Biomedical
Mohammad Hosein Sabzalian, Farzam Kharajinezhadian, AmirReza Tajally, Reza Reihanisaransari, Hamzah Ali Alkhazaleh, Dmitry Bokov
Summary: The early detection of lung cancer using medical imaging techniques, such as CT-scan, lowers the risk of cancer growth and spreading. Therefore, the development of computer image processing and diagnostic systems, as well as the classification of lung cancer into malignant and benign, are crucial for improving treatment and saving lives. This study proposes a new methodology using an improved Bidirectional Recurrent Neural Network and an optimized search algorithm for accurate lung cancer diagnosis. Preprocessing techniques are applied before utilizing the diagnosis system, and the results are compared to existing works, demonstrating the superiority of the proposed method.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Energy & Fuels
K. Venkateshwar, S. H. Tasnim, S. A. Gadsden, S. Mahmud
Summary: This study aims to enhance the performance of Thermal Energy Storage (TES) system by optimizing the porosity distribution of graded metal foam. A numerical model is used to quantify the influence of graded metal foam on heat transfer rate, and an Artificial Neural Network (ANN) model is trained to optimize the porosity distribution using a Genetic algorithm. The results demonstrated significant heat transfer enhancement with the optimal porosity distribution.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Engineering, Environmental
Kanglei Song, Haiqing Yang, Zhihui Wang
Summary: A new hybrid intelligent model named Stacking-WOA was developed to predict TBM penetration rate (PR) using the whale optimization algorithm. The results showed that the Stacking-WOA model outperformed the single algorithm models in predicting TBM PR and had stronger learning and generalization ability for a small number of samples.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2023)
Article
Multidisciplinary Sciences
Bing Wang, Asad Rezaei
Summary: Sports image classification using image processing and machine vision is a growing field with wide applications. This paper proposes a hybrid framework of deep learning and optimization, using an optimization algorithm for feature selection, which effectively improves the accuracy and dimensionality reduction in sports image classification.
Article
Computer Science, Artificial Intelligence
Kishore Balasubramanian, N. P. Ananthamoorthy
Summary: Computer aided systems have gained popularity in medical diagnosis for their reduced computational time and cost, and improved accuracy. This paper proposes a glaucoma diagnostic approach using bio-inspired algorithms and a Kernel-Extreme Learning Machine classifier, achieving high accuracy and robustness.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Rishav Pramanik, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is a leading cause of premature death among women globally, but early detection and diagnosis can save lives. Hence, computer scientists are working to develop reliable models to tackle this disease. A proposed lightweight model combines transfer learning-based deep learning (DL) with feature selection to detect abnormalities in breast thermograms. This model performs well in detecting and differentiating malignant and healthy breasts.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Narendra Kumar Rout, Mitul Kumar Ahirwal, Mithilesh Atulkar
Summary: This paper presents an assistive system for accurate identification of melanoma, using dynamic weights and optimization algorithms to improve the recognition accuracy.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Computer Science, Hardware & Architecture
Fujia Ren, Chenhui Yang, Y. A. Nanehkaran
Summary: This study presents a deep zero-shot transfer learning model for predicting mild cognitive impairment in Alzheimer's disease patients, which achieves improved accuracy compared to existing approaches.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Chemistry, Analytical
K. Suresh Manic, Venkatesan Rajinikanth, Ali Saud Al-Bimani, David Taniar, Seifedine Kadry
Summary: This research aims to develop a reliable disease screening framework for the automatic identification of schizophrenia (SCZ) conditions from brain MRI slices. The study verifies that the schizophrenia screening accuracy with DF+HF (deep features + handcrafted features) is superior compared with other methods. This framework is clinically significant and can be used to inspect actual patients' brain MRI slices in the future.
Article
Chemistry, Multidisciplinary
Yaser A. Nanehkaran, Zhu Licai, Jin Chengyong, Junde Chen, Sheraz Anwar, Mohammad Azarafza, Reza Derakhshani
Summary: This study conducted a comparative analysis to assess/predict the safety factor (F.S) of earth slopes using MLP, SVM, DT, and RF learning methods. The results showed that MLP provides the most accurate F.S predictions, followed by the SVM algorithm.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Kusum Yadav, Kawther A. Al-Dhlan, Hamad A. Alreshidi, Gaurav Dhiman, Wattana Golf Viriyasitavat, Abdullah Zaid Almankory, Kadiyala Ramana, S. Vimal, Venkatesan Rajinikanth
Summary: Cephalometric analysis plays a crucial role in treating patients with craniofacial and dentofacial deformities. It quantifies and derives human geometric relationships through linear and angular measurements. This analysis is necessary to be performed on the patient's Head X-ray image for treatment purposes.
Review
Green & Sustainable Science & Technology
Amogh Gyaneshwar, Anirudh Mishra, Utkarsh Chadha, P. M. Durai Raj Vincent, Venkatesan Rajinikanth, Ganapathy Pattukandan Ganapathy, Kathiravan Srinivasan
Summary: Deep learning models have proven to be effective in drought forecasting, providing more accurate and timely predictions to mitigate the impacts of drought on crop failure, water shortages, and economic losses.
Article
Medicine, General & Internal
Venkatesan Rajinikanth, P. M. Durai Raj Vincent, C. N. Gnanaprakasam, Kathiravan Srinivasan, Chuan-Yu Chang
Summary: This research aims to develop an efficient deep-learning-based brain-tumor detection scheme using FLAIR- and T2-modality MRI slices. The scheme includes preprocessing, deep-feature extraction, tumor segmentation, feature optimization, and binary classification. Experimental results show that the integrated feature-based scheme achieves a classification accuracy of 99.6667% when using a support-vector-machine classifier.
Article
Environmental Sciences
Ahmed Cemiloglu, Licai Zhu, Biyun Chen, Li Lu, Yaser A. Nanehkaran
Summary: Rapid urban development and increase in construction have led to an increase in impervious surfaces, which hinders rainwater infiltration and causes a rise in surface runoff. Managing surface runoff is crucial in civil engineering and urban planning, and there is a need for cost-effective alternatives. This research proposes an innovative approach that combines a metaheuristic algorithm with a storm water management model to design efficient surface runoff collection networks.
Article
Environmental Sciences
Yimin Mao, Liang Chen, Yaser A. Nanehkaran, Mohammad Azarafza, Reza Derakhshani, Achim A. Beylich
Summary: This study explores the integration of artificial intelligence (AI) and empirical techniques for evaluating rock slope stability, using the Q(slope) system as a framework. By incorporating fuzzy set theory into the Q(slope) classification, a novel approach is proposed to effectively quantify and accommodate uncertainties in coastal regions. The preliminary tests conducted on slope instabilities within coastal zones indicate promising results, affirming the precision and dependability of the proposed AI-based approach. However, further validation efforts are required to establish the reliability and effectiveness of this innovative method across diverse scenarios.
Article
Environmental Sciences
Ahmed Cemiloglu, Zhu Licai, Abbas Ugurenver, Yaser A. Nanehkaran
Summary: Urban water distribution networks are essential infrastructures for providing vital services to society. Optimizing these networks is crucial due to their high costs and limited resources. This study aimed to minimize costs and network pressure in the water distribution network by employing the NSDE multi-objective metaheuristic algorithm as the optimization tool. Through the use of computer programs written in MATLAB and hydraulic simulation using EPANET software, the efficiency and capabilities of the optimization models were tested in the case study of Mashhad, Iran. The results showed significant improvements in achieving desired goals, particularly in reducing network pressure, with a 56.12% reduction compared to the case without a plan, considering five pressure-relief valves.
Review
Environmental Sciences
Yaser A. A. Nanehkaran, Biyun Chen, Ahmed Cemiloglu, Junde Chen, Sheraz Anwar, Mohammad Azarafza, Reza Derakhshani
Summary: Riverside landslides pose significant threats to infrastructure and human lives globally. Professionals have developed various methodologies to analyze, assess, and predict landslides, with artificial neural networks (ANNs) emerging as the preferred method for these assessments. The application of ANNs aligns with the United Nations' Sustainable Development Goals (SDGs), particularly Goal 11: Sustainable Cities and Communities. By effectively assessing riverside landslide susceptibility using ANNs, communities can better manage risks and enhance resilience. This review aims to contribute to the development of improved risk management strategies, sustainable urban planning, and resilient communities in the face of riverside landslides, in line with the SDGs.
Article
Biochemistry & Molecular Biology
Ramya Mohan, Arunmozhi Rama, Ramalingam Karthik Raja, Mohammed Rafi Shaik, Mujeeb Khan, Baji Shaik, Venkatesan Rajinikanth
Summary: With the increasing incidence of cancer, the importance of early diagnosis, treatment, and follow-up clinical protocols is emphasized. Oral cancer, as a type of head and neck cancer, requires effective screening for timely detection. This study proposes a framework called OralNet for oral cancer detection using histopathology images. Experimental results show that OralNet achieved an accuracy exceeding 99.5% in detecting oral cancer presence in histology slides, confirming the clinical significance of the proposed technique.
Article
Environmental Studies
Ahmed Cemiloglu, Licai Zhu, Agab Bakheet Mohammednour, Mohammad Azarafza, Yaser Ahangari Nanehkaran
Summary: Landslide susceptibility assessment is a globally approved procedure for preparing geo-hazard maps, which are important for urban management and disaster prevention. This study used logistic regression to assess the hazard risk in Maragheh County and found it to be in a moderate to high-hazard risk zone. The performance of the logistic regression model was considered reasonable.
Article
Engineering, Electrical & Electronic
Junde Chen, Yuxin Wen, Yaser Ahangari Nanehkaran, Defu Zhang, Adnan Zeb
Summary: The researchers propose a multiscale mobile attention-based network called MANet to automatically detect pavement defects. The approach utilizes an encoder-decoder architecture with MobileNet as the backbone network and incorporates multiscale convolution kernels and hybrid attention mechanisms. The proposed approach achieves state-of-the-art performance on benchmark datasets and provides satisfactory results in practical scenarios. Rating: 9/10
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Venkatesan Rajinikanth, Seifedine Kadry, Pablo Moreno Ger
Summary: The lung is vital in human physiology, and lung disease causes various health issues. Tuberculosis (TB) is a common lung disease, and early diagnosis and treatment are crucial. This study proposes a TB detection framework using integrated optimal deep and handcrafted features. The research process includes data collection and processing, feature mining using pre-trained deep learning schemes, feature extraction with LBP and DWT, feature optimization with the Firefly-Algorithm, feature ranking and concatenation, and classification using a 5-fold cross-validation. The results show that the ResNet18 scheme with SoftMax classifier achieves a better accuracy of 95.2%, while the Decision Tree Classifier reaches 99% accuracy with deep and concatenated features. Overall, the Decision Tree performs better compared to other classifiers.
INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Navid Razmjooy, Danial Bahmanyar, V. Rajinikanth, Gabriel Gomes de Oliveira
Summary: Lack of knowledge on proper energy usage has led to increased energy demand. In this study, an optimized home energy management scheme is proposed to reduce energy cost by implementing variable pricing and load shifting. Simulation results show the advantages of using this scheme in home energy management systems.
PROCEEDINGS OF THE 7TH BRAZILIAN TECHNOLOGY SYMPOSIUM (BTSYM 21): EMERGING TRENDS IN HUMAN SMART AND SUSTAINABLE FUTURE OF CITIES, VOL 1
(2023)