Utilizing computer vision and deep learning to detect and monitor insects in real time by analyzing camera trap images DOI Open Access

Debarghya Biswas,

Akash Tiwari

Natural and Engineering Sciences, Год журнала: 2024, Номер 9(2), С. 280 - 292

Опубликована: Окт. 30, 2024

Insect monitoring techniques are often labor-intensive and need significant resources for identifying species after manual field traps. traps usually maintained every week, leading to a low temporal accuracy of information collected that impedes ecological analysis. This study introduces handheld computer vision device attract detect real insects. The research explicitly proposes categorizing by imaging live drawn camera trapping. An Automatic Moth Trapping (AMT) equipped with light elemnets was developed draw observe insects throughout twilight nocturnal periods. Classification Counting (MCC) utilizes Computer Vision (CV) Deep Learning (DL) evaluation pictures monitors. It enumerates insect populations while moth species. Over 48 nights, more than 250k photos were captured, averaging 5.6k daily. A tailored Convolutional Neural Networks (CNN) on 2000 labeled across eight distinct categories. suggested method methodology have shown encouraging outcomes as an economical option automated surveillance

Язык: Английский

A Comparative Analysis Of African Vultures Optimization Algorithm With Current Metaheuristics DOI Creative Commons
Sibel Arslan, Yıldız Zoralioğlu,

Muhammed Furkan Gul

и другие.

Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Год журнала: 2025, Номер 8(1), С. 325 - 352

Опубликована: Янв. 15, 2025

With the increasing complexity of optimization problems, new metaheuristic algorithms are being developed. These show their success by exhibiting superior performances on different problems. In this paper, performance 4 recently proposed algorithms, namely Artificial Hummingbird Algorithm (AHA), African Vultures Optimization (AVOA), Crayfish (COA) and Marine Predators (MPA) 26 test functions compared. As a result comparisons, it was observed that outperformed each other with very small differences functions. At same time, comparison results were evaluated t-test statistical test. AVOA has shown better or comparable to recent metaheuristics in evaluating quality solutions for several It is aimed use problems future research.

Язык: Английский

Процитировано

0
The Application of the SubChain Salp Swarm Algorithm in the Less-Than-Truckload Freight Matching Problem DOI Creative Commons
Yibo Sun, Lei Yue, Yi Liu

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(8), С. 4436 - 4436

Опубликована: Апрель 17, 2025

The less-than-truckload (LTL) freight problem is a general pain point in logistics applications. Its challenge resides the fact that these loads cannot be shipped timely manner due to their relatively small volumes. Traditional LTL matching methods are challenged by delays updating logistic information and higher distribution costs. In order solve challenges, we developed novel SubChain Salp Swarm Algorithm (SSSA) improving traditional with utilization of operation. Our method aims find optimal strategy for maintaining balance between lower operating costs customer satisfaction. SSSA combines multiple disconnected points separate individual chains local optima obtain better convergence results final decision. We have compared our mainstream metaheuristic algorithms using datasets from road company Hangzhou, demonstrate converges faster than other has variance. solves limitation observed optimization improves service relation transportation issue.

Язык: Английский

Процитировано

0
A Wireless Sensor Network-Based Combustible Gas Detection System Using PSO-DBO-Optimized BP Neural Network DOI Creative Commons

Min Zhou,

Sen Wang,

Jianming Li

и другие.

Sensors, Год журнала: 2025, Номер 25(10), С. 3151 - 3151

Опубликована: Май 16, 2025

Combustible gas leakage remains a critical safety concern in industrial and indoor environments, necessitating the development of detection systems that are both accurate practically deployable. This study presents wireless system integrates sensor array, low-power microcontroller with Zigbee-based communication, Back Propagation (BP) neural network optimized via sequential hybrid strategy. Specifically, Particle Swarm Optimization (PSO) is employed for global parameter initialization, followed by Dung Beetle (DBO) local refinement, jointly enhancing network’s convergence speed predictive precision. Experimental results confirm proposed PSO-DBO-BP model achieves high correlation coefficients (above 0.997) low mean relative errors (below 0.25%) all monitored gases, including hydrogen, carbon monoxide, alkanes, smog. The exhibits strong robustness handling nonlinear responses cross-sensitivity effects across multiple sensors, demonstrating its effectiveness complex scenarios under laboratory conditions within embedded networks.

Язык: Английский

Процитировано

0
A review on machine learning driven next generation thermoelectric generators DOI Creative Commons
Uzair Sajjad, Ahsan Ali, Hafız Muhammad Ali

и другие.

Energy Conversion and Management X, Год журнала: 2025, Номер unknown, С. 101092 - 101092

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Hierarchical Learning-Enhanced Chaotic Crayfish Optimization Algorithm: Improving Extreme Learning Machine Diagnostics in Breast Cancer DOI Creative Commons
Jilong Zhang,

Yuan Diao

Mathematics, Год журнала: 2024, Номер 12(17), С. 2641 - 2641

Опубликована: Авг. 26, 2024

Extreme learning machines (ELMs), single hidden-layer feedforward neural networks, are renowned for their speed and efficiency in classification regression tasks. However, generalization ability is often undermined by the random generation of hidden layer weights biases. To address this issue, paper introduces a Hierarchical Learning-based Chaotic Crayfish Optimization Algorithm (HLCCOA) aimed at enhancing ELMs. Initially, to resolve problems slow search premature convergence typical traditional crayfish optimization algorithms (COAs), HLCCOA utilizes chaotic sequences population position initialization. The ergodicity chaos leveraged boost diversity, laying groundwork effective global efforts. Additionally, hierarchical mechanism encourages under-performing individuals engage extensive cross-layer enhanced exploration, while top performers directly learn from elite highest improve local exploitation abilities. Rigorous testing with CEC2019 CEC2022 suites shows HLCCOA’s superiority over both original COA nine heuristic algorithms. Ultimately, HLCCOA-optimized extreme machine model, HLCCOA-ELM, exhibits superior performance reported benchmark models terms accuracy, sensitivity, specificity UCI breast cancer diagnosis, underscoring practicality robustness, as well HLCCOA-ELM’s commendable performance.

Язык: Английский

Процитировано

1
Utilizing computer vision and deep learning to detect and monitor insects in real time by analyzing camera trap images DOI Open Access

Debarghya Biswas,

Akash Tiwari

Natural and Engineering Sciences, Год журнала: 2024, Номер 9(2), С. 280 - 292

Опубликована: Окт. 30, 2024

Insect monitoring techniques are often labor-intensive and need significant resources for identifying species after manual field traps. traps usually maintained every week, leading to a low temporal accuracy of information collected that impedes ecological analysis. This study introduces handheld computer vision device attract detect real insects. The research explicitly proposes categorizing by imaging live drawn camera trapping. An Automatic Moth Trapping (AMT) equipped with light elemnets was developed draw observe insects throughout twilight nocturnal periods. Classification Counting (MCC) utilizes Computer Vision (CV) Deep Learning (DL) evaluation pictures monitors. It enumerates insect populations while moth species. Over 48 nights, more than 250k photos were captured, averaging 5.6k daily. A tailored Convolutional Neural Networks (CNN) on 2000 labeled across eight distinct categories. suggested method methodology have shown encouraging outcomes as an economical option automated surveillance

Язык: Английский

Процитировано

0