Article
Computer Science, Artificial Intelligence
Jarjish Rahaman, Mihir Sing
Summary: Segmenting satellite images is a challenging task due to their random nature, multiple regions of interest, and weak correlation with pixels. Nature-inspired algorithms can be used to improve segmentation quality, with the adaptive cuckoo search (ACS) algorithm showing superior global convergence compared to other methods. The proposed method offers a more effective approach for image segmentation, showcasing improved results and reduced computational time.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Omar A. Kittaneh
Summary: This paper proposes a new multi-level entropy-based image thresholding method that relies on the minimum of the variance entropy. The method is fully automated and produces segmentation results comparable to the generalized Otsu's method, which requires human intervention. It also outperforms the generalized Kapur's method in benchmarking entropy-based thresholding techniques. The method is successfully applied to various scenarios and its performance is checked using classification measures and quality metrics.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Longzhen Duan, Shuqing Yang, Dongbo Zhang
Summary: An improved cuckoo search algorithm (ICS) is proposed for multilevel thresholding image segmentation in this paper, and the experimental results show that the proposed algorithm is superior to other seven well-known heuristic algorithms.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Leila Esmaeili, Seyed Jalaleddin Mousavirad, Ali Shahidinejad
Summary: A novel image thresholding method, based on an improved human mental search algorithm, is proposed in this paper to address the time complexity issue of the minimum cross-entropy approach. Extensive experiments demonstrate the competitive performance of the proposed algorithm.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Swarnajit Ray, Santanu Parai, Arunita Das, Krishna Gopal Dhal, Prabir Kumar Naskar
Summary: The study aims to enhance the efficiency of the Cuckoo Search algorithm in image segmentation by incorporating mutation strategies of Differential Evolution. Results of the experiment provide valuable insight for developing efficient CS variants using optimal or adaptive mutation strategies of DE.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Mathematics
Jorge Munoz-Minjares, Osbaldo Vite-Chavez, Jorge Flores-Troncoso, Jorge M. Cruz-Duarte
Summary: This paper proposes a strategy for object segmentation based on CSA and GG distribution, and validates its advantages in both synthetic and practical scenarios through experiments. The results show that this strategy outperforms other algorithms in simulated environments and ranks among the best algorithms in real-world scenarios.
Article
Computer Science, Artificial Intelligence
Rutuparna Panda, Leena Samantaray, Akankshya Das, Sanjay Agrawal, Ajith Abraham
Summary: The paper proposes a new normalized local variance (NLV) method for constructing 2D histogram, followed by a novel evolutionary row class entropy (ERCE) method for optimal multi-level image thresholding, which aims to preserve maximum spatial information through normalization of the local variance.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Agriculture, Multidisciplinary
Arun Kumar, A. Kumar, Amit Vishwakarma, Girish Kumar Singh
Summary: This paper presents a crop image multilevel thresholding technique based on the recursive minimum cross entropy method and efficient cuckoo search algorithm. Experimental results demonstrate that the proposed method can accurately and efficiently segment crop images with complex backgrounds.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Food Science & Technology
Rekha Chaturvedi, Abhay Sharma, Anuja Bhargava, Jitendra Rajpurohit, Pushpa Gothwal
Summary: The Internet and its applications have led to a massive amount of data, particularly in the form of images, which has provided researchers with vast opportunities for data analysis. Image processing is crucial for improving the understanding of images, and various image processing steps can enhance images in different application areas. Many applications, such as medical imaging, face recognition, biometric security, fruit quality evaluation, and traffic surveillance, heavily rely on image analysis and segmentation. This paper focuses on multi-level thresholding for accurately segmenting different types of fruits, proposing a modified Firefly Algorithm (FA) that optimizes fuzzy parameters to obtain optimal thresholds. The algorithm utilizes levy flight and local search for improved performance. The proposed method is evaluated quantitatively and qualitatively on apple, banana, mango, and orange images using parameters like peak signal-to-noise ratio (PSNR) and structured similarity index metric (SSIM).
FOOD ANALYTICAL METHODS
(2022)
Article
Physics, Multidisciplinary
Yuanyuan Jiang, Dong Zhang, Wenchang Zhu, Li Wang
Summary: In this paper, a multi-level thresholding image segmentation method based on an improved slime mould algorithm and symmetric cross-entropy is proposed to address the issues of low segmentation accuracy and slow convergence speed of traditional methods. Experimental results demonstrate that the proposed method outperforms other compared algorithms in image segmentation tasks.
Article
Computer Science, Artificial Intelligence
Shouvik Chakraborty, Kalyani Mali
Summary: This article proposes a novel approach for multilevel biomedical image segmentation based on the modified cuckoo search and chaos theory. The modified cuckoo search approach efficiently models the Levy flight, while the incorporation of chaos theory helps maintain diversity in the population. The proposed approach determines optimal threshold values and uses four different objective functions to achieve realistic segmented output, contributing to the field of biomedical image analysis.
Article
Computer Science, Artificial Intelligence
Zhiping Tan, Kangshun Li, Yi Wang
Summary: The improved cuckoo search algorithm (ICS) proposed in this paper for color image segmentation utilizes a modified fuzzy entropy as its objective function, with adaptive control parameter mechanism and hybrid search strategy for enhanced performance. Experimental results demonstrate that the ICS algorithm outperforms others in terms of objective function value, PSNR, FSIM, convergence speed, and statistical tests.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Automation & Control Systems
Monorama Swain, Tanmaya Tapaswini Tripathy, Rutuparna Panda, Sanjay Agrawal, Ajith Abraham
Summary: This paper proposes a multilevel threshold selection method based on differential exponential entropy (DEE) to address the challenges of edge loss, insufficient retention of spatial correlation information, and accuracy reduction due to logarithmic function in traditional approaches. The method uses normalized local variance in histogram construction to suppress high magnitude peaks, and introduces a new objective function and optimizer to maximize DEE. Experimental results show that the proposed method outperforms other techniques in terms of image quality assessment metrics.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mohamed Abd Elaziz, Songfeng Lu, Sibo He
Summary: This paper presents a multilevel thresholding image segmentation method based on enhancing the performance of the whale optimization algorithm (WOA), called the multi-leader whale optimization algorithm (MLWOA). MLWOA integrates different tools with WOA to improve exploration ability and avoid the trap of local optima during the search process.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Biomedical
Shouvik Chakraborty, Kalyani Mali
Summary: The study focuses on addressing the challenge of automated segmentation of digital images using a hybrid approach that combines the modified cuckoo search approach and fuzzy system. The proposed method is evaluated using both qualitative and quantitative approaches and outperforms competitors, achieving significant improvements. The results show that the proposed approach achieves higher SSIM values for different numbers of clusters by optimizing the fuzzy Tsallis entropy, motivating its deployment in real-life scenarios.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Software Engineering
Gyanesh Das, Rutuparna Panda, Leena Samantaray, Sanjay Agrawal
Summary: This paper proposes a multilevel optimal threshold selection method using opposition equilibrium optimizer. The method minimizes the segmentation error function and is independent of the spatial distribution of gray values, resulting in improved threshold selection. Experimental results showed that the proposed method performs well qualitatively and quantitatively, making it valuable for biomedical image segmentation.
INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS
(2023)
Article
Computer Science, Artificial Intelligence
Sidharth Gautam, Tapan Kumar Gandhi, B. K. Panigrahi
Summary: In this research, a novel two-fold method named Weighted Median Channel Prior (WMCP) is proposed, focusing on self-adaptive prior, which resolves the problems caused by using a fixed size local-patch in the dehazing process. WMCP leverages spatially changing haze statistics to estimate depth-map in varying haze conditions. It is a scale-invariant technique that retains most of the information in the local neighborhood of the hazy input image for estimating scene depth, which traditional methods fail to preserve. Additionally, an unsharp-masking based technique called edge-modulation (EM) enhances hidden or missing details lost due to haze, resulting in visually aesthetic and realistic dehazed images. Comparative evaluation shows the superiority of this method in terms of visibility improvement and edge preservation, especially in dense haze regions.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2023)
Article
Computer Science, Information Systems
Arup Anshuman, Bijaya Ketan Panigrahi, Manas Kumar Jena
Summary: This article proposes a method for real-time monitoring of oscillation events, which can visualize and classify low-frequency oscillatory modes in the system. Significant oscillatory modes are extracted and analyzed through a novel algorithm, and presented in the form of time-domain plots to enhance operator understanding. The method is validated and compared, demonstrating its superior performance.
IEEE SYSTEMS JOURNAL
(2023)
Article
Computer Science, Information Systems
Diptak Pal, Bijaya Ketan Panigrahi, Shubhendu Bhasin
Summary: This article introduces a unique design method for an adaptive neural network based backstepping-like control scheme applied in inverter interfaced distributed generators (IIDGs) integrated to an autonomous distribution network. It also presents an optimal distributed secondary control framework for a multiple IIDGs-based autonomous distribution network, which achieves accurate power sharing and regulation of system frequency and voltage. The proposed control framework considers the entire system dynamics of IIDG, including uncertain terms, without relying on system parameters information. Suitable update laws are designed for estimating unknown weights and uncertain system parameters, which are proven to be uniformly ultimately bounded through Lyapunov analysis. Case studies on a typical autonomous distribution network with single and multiple IIDGs are conducted using MATLAB/Simulink platform.
IEEE SYSTEMS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Arjita Pal, Diptak Pal, Bijaya Ketan Panigrahi
Summary: This paper proposes a new current saturation strategy (CSS) for grid-forming (GFM) inverters to comply with low-voltage ride-through (LVRT) capability requirements. The proposed control philosophy limits the output current during LVRT using a new control parameter, the power factor angle (PFA), enabling the GFM inverters to adhere to standardized grid codes. A nonlinear mathematical model capturing the dynamics of a GFM inverter with current limiting control is developed, and a simplified equivalent circuit model is used to analytically evaluate the proposed CSS. Numerical and experimental results validate the accuracy of the CSS in assessing the large-signal stability of a GFM inverter under severe symmetrical grid faults.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Automation & Control Systems
Parul Arora, Seyed Mohammad Jafar Jalali, Sajad Ahmadian, B. K. Panigrahi, P. N. Suganthan, Abbas Khosravi
Summary: Wind power forecasting is crucial for power system planning and scheduling. Optimizing the hyperparameters of deep neural networks (DNNs) using evolutionary algorithms is an effective approach. In this article, a novel evolutionary algorithm based on the grasshopper optimization algorithm is proposed to optimize the hyperparameters of a wind power forecasting model. The proposed model outperforms benchmark DNNs and other neuroevolutionary models in terms of learning speed and prediction accuracy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Geeta Pathak, Bhim Singh, B. K. Panigrahi
Summary: This paper investigates a three-phase wind-solar-photovoltaic microgrid system that can operate in grid-tied and island modes under steady state and in DSTATCOM mode, utility-interactive mode and disconnecting mode under dynamic state. The microgrid uses a single Voltage Source Inverter (VSI) with reduced power converters and switches. A battery bank is utilized at the DC bus of the VSI for load leveling and power balance control. The VSI's control also improves Power Quality (PQ) and provides power backup during abnormal grid conditions.
IETE JOURNAL OF RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Sauvik Biswas, Paresh Kumar Nayak, Bijaya Ketan Panigrahi, Gayadhar Pradhan
Summary: This paper proposes an intelligent relaying scheme for efficient detection and classification of faults in AC transmission lines. This scheme extracts suitable features from locally measured current signals using variational mode decomposition (VMD) and utilizes a deep convolutional neural network (CNN) classifier for fault classification. The proposed scheme is evaluated on a DFIG wind farm and UPFC compensation system, showing fast fault detection time (<10 ms) and high accuracy in fault detection and classification (100% and 99.86%).
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Thermodynamics
Karan Sareen, Bijaya Ketan Panigrahi, Tushar Shikhola, Rajneesh Sharma
Summary: Due to its renewable and ecological attributes, wind energy is gaining global attention, but accurate forecasting of wind speed is challenging due to its variable and stochastic nature. Many wind speed forecasting algorithms neglect missing value imputation, which can significantly affect prediction accuracy. This study proposes a hybrid technique using k-NN-CEEMDAN-BiDLSTM, which combines data imputation, signal denoising, and neural network analysis to achieve better prediction accuracy. Empirical findings show that this hybrid technique outperforms other existing techniques in terms of accuracy.
Review
Computer Science, Artificial Intelligence
Karan Sareen, Bijaya Ketan Panigrahi, Tushar Shikhola
Summary: This study focuses on four Indian cities in the state of Rajasthan, namely Ajmer, Jaipur, Jodhpur, and Kota, and applies a proposed technique for predicting Global Horizontal Irradiance (GHI) using 30-minute ahead data obtained from the National Institute of Wind Energy and Wind Resource (NIWE) data site. Three different signal decomposition algorithms, namely Empirical Mode Decomposition (EMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and Ensemble Empirical Mode Decomposition (EEMD), are used for data preprocessing. The signal reconstruction is based on the comparison of Pearson's Correlation Coefficient (PCC) values of the corresponding Intrinsic Mode Functions (IMFs) and Residuals obtained from the three decomposition algorithms. The selected IMFs and Residuals from each algorithm are then combined to form a single input for solar irradiance forecasting using the Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed technique demonstrates high accuracy with less than 2% Mean Absolute Percentage Error (MAPE) for different seasons and site locations considered.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Marine
Karan Sareen, Bijaya Ketan Panigrahi, Tushar Shikhola, Rita Nagdeve
Summary: The ocean is a potential and limitless source of renewable energy, but the intermittent and irregular characteristic of wave energy is concerning for the stability of the power system. Accurate and trustworthy forecasts of ocean wave height have gained increased attention recently, as it is a crucial parameter for harnessing energy from ocean waves. In this study, a framework combining the CEEMDAN data decomposition algorithm and BiDLSTM deep learning algorithm is proposed to accurately forecast ocean significant wave height and wave energy. The empirical outcomes show that the proposed method is highly accurate compared to recently established forecasting algorithms in literature.
Proceedings Paper
Green & Sustainable Science & Technology
Purusharth Semwal, Vivek Narayanan, Bhim Singh, B. K. Panigrahi
Summary: To reduce water pollution, integrating non-conventional energy sources into the marine sector is an effective solution. This paper evaluates the performance of an emission-free marine microgrid under different operational conditions. Using the MATLAB-Simulink platform, an emission-free ferry is developed with a battery energy storage, solar photovoltaic system, propulsion motors, and service loads, and operated in various sea conditions. By employing a power management system and Black Widow Optimization, stability and regulation of the power system are ensured. The dual second-order generalized integrator and modified quasi type1 phase-locked loop are used for cold ironing mode to synchronize the ferry with the shore power system and provide distortion-free current.
2023 IEEE IAS GLOBAL CONFERENCE ON RENEWABLE ENERGY AND HYDROGEN TECHNOLOGIES, GLOBCONHT
(2023)
Proceedings Paper
Green & Sustainable Science & Technology
Sunaina Singh, Vivek Narayanan, Bhim Singh, B. K. Panigrahi
Summary: The paper presents a standalone system based on solar photovoltaic (PV)-ES energy storage. A battery is used as the energy storage (ES) due to the intermittent nature of solar energy. A bidirectional converter (BDC) is connected with the battery to regulate the DC-link voltage. The system's performance under steady-state and dynamic conditions is validated through simulations in MATLAB/Simulink.
2023 IEEE IAS GLOBAL CONFERENCE ON RENEWABLE ENERGY AND HYDROGEN TECHNOLOGIES, GLOBCONHT
(2023)
Article
Engineering, Electrical & Electronic
Bijay Kumar Sa, Rutuparna Panda, Sanjay Agrawal
Summary: In this study, a new adaptively weighted level-set evolution method based on relevant edge probability is investigated for medical image segmentation. By adjusting the weights according to the image's relative value, the leakage and premature convergence are reduced, leading to improved segmentation accuracy.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Guiliang Gong, Jiuqiang Tang, Dan Huang, Qiang Luo, Kaikai Zhu, Ningtao Peng
Summary: This paper proposes a flexible job shop scheduling problem with discrete operation sequence flexibility and designs an improved memetic algorithm to solve it. Experimental results show that the algorithm outperforms other algorithms in terms of performance. The proposed model and algorithm can help production managers obtain optimal scheduling schemes considering operations with or without sequence constraints.
SWARM AND EVOLUTIONARY COMPUTATION
(2024)
Article
Computer Science, Artificial Intelligence
Daniel Molina-Perez, Efren Mezura-Montes, Edgar Alfredo Portilla-Flores, Eduardo Vega-Alvarado, Barbara Calva-Yanez
Summary: This paper presents a new proposal based on two fundamental strategies to improve the performance of the differential evolution algorithm when solving MINLP problems. The proposal considers a set of good fitness-infeasible solutions to explore promising regions and introduces a composite trial vector generation method to enhance combinatorial exploration and convergence capacity.
SWARM AND EVOLUTIONARY COMPUTATION
(2024)
