YOLOv8A-SD: A Segmentation-Detection Algorithm for Overlooking Scenes in Pig Farms by Yiran Liao, Yipeng Qiu, Bo Liu, Yibin Qin, Yuchao Wang, Zhijun Wu, Lijia Xu, Ao Feng

Get full text

Disease Detection Algorithm for Tea Health Protection Based on Improved Real-Time Detection Transformer by Zhijie Lin, Zilong Zhu, Lingling Guo, Jingjing Chen, Jiyi Wu

“…Faster-LTNet employs partial convolution and hierarchical design to optimize computational resources, while the CG Attention Module enhances multi-head self-attention by introducing grouped feature inputs and cascading operations to reduce redundancy and increase attention diversity. …”
Get full text

Estimation of the Ultimate Bearing Capacity of the Rocks via Utilization of the AI-Based Frameworks by Bianca Damico, Matteo Conti

“…The approach adopted here is new and solves the problem using KNN combined with two modern nature-inspired optimization frameworks, namely the Honey Badger Algorithm (HBA) and Equilibrium Slime Mould Algorithm (ESMA). …”
Get full text

Can Integrating SoC Management in Economic Dispatch Enhance Real-Time Operation of a Microgrid? by Alessia Cagnano

“…To enable real-time adaptability, the methodology employs a Lyapunov-based optimization algorithm combined with a sensitivity analysis, ensuring rapid convergence to optimal solutions, even under rapidly changing conditions. …”
Get full text

Resource allocation strategy based on optimal matching auction in the enterprise network by Xin CONG, Lingling ZI, Xueli SHEN

“…To address the issue that the owners of computer are selfish in the enterprise networks,which caused the low available number of resource nodes and low efficiency of resource allocation,an optimized matching resource allocation strategy OMRA was proposed and its core was the auction mechanism.Selfishness was restrained and the number of available resources was increased by OMRA,so as the operating efficiency of the whole auction market was improved.First,the initial prices were determined by normalizing the costs of different type of resources on the beginning of auction.Secondly,an optimal matching auction algorithm was designed to maximize the interests of the auction markets.Then,service perfecting algorithm was performed such that the sellers could get more services at the current transaction value,thus ensuring the benefits of resource providers.At last,a request price updating algorithm was adopted to assurance that both sellers and buyers could get priorities in the next auction processing.Compared with the cloud resource allocating algorithm via fitness-enabled auction (CRAA/FA),the experiment results indicate that the efficiency of resource allocation improves by 10% and the benefits of market increase by 11.4%.…”
Get full text

DNN-based Sub-6 GHz assisted millimeter wave network power allocation algorithm by Changyin SUN, Liyan LIU, Fan JIANG, Jing JIANG

“…Aimed at the problems of the signaling cost and power consumption in the power control measurement of the millimeter wave system, as well as the complexity caused by iteration operations, a millimeter wave link power allocation prediction algorithm using the Sub-6 GHz frequency band was proposed.Firstly, the mapping between the Sub-6 GHz band channel information and the optimal power allocation of the millimeter wave band was analyzed.Then, a deep neural network (DNN) model was utilized to realize this mapping function.To predict the power allocation of millimeter wave channel with Sub-6 GHz channel as input, the neural network was trained with the weighted mean square error minimization method (WMMSE) as the supervisor in different scenarios.The simulation results show that compared with the WMMSE algorithm in millimeter wave band, the proposed algorithm can obtain more than 97% of its sum-rate performance while taking less than 0.1% of the time.…”
Get full text

MPDCGA: a real-coded multi-population dynamic competitive genetic algorithm for feature selection by Chuantao Li, Chen Huang, Ruihan Chen, Zhuohong Yu, Sheng Li

“…To mitigate these limitations, this study proposes a real-coded multi-population dynamic competitive genetic algorithm (MPDCGA) for feature selection. In this innovative framework, the population initialization mechanism based on mRMR and cosine similarity furnishes a diverse initial solution, the dynamic competition operator explores the optimal feature subset through coevolutionary processes, and the adaptive similarity crossover operator improves the global search efficiency while augmenting the capability to extract potentially salient features. …”
Get full text

Research on Static/Dynamic Global Path Planning Based on Improved A∗ Algorithm for Mobile Robots by Huifang Bao, Jie Fang, Chaohai Wang, Zebin Li, Jinsi Zhang, Chuansheng Wang

“…In addition, we combine the improved A∗ algorithm with the dynamic window algorithm to enable mobile robots to realize real-time dynamic obstacle avoidance while ensuring the optimality of global path planning.…”
Get full text

BDCOA: Wavefront Aberration Compensation Using Improved Swarm Intelligence for FSO Communication by Suhas Shankarnahalli Krishnegowda, Arvind Kumar Ganesh, Parameshachari Bidare Divakarachari, Veena Yadav Shankarappa, Nijaguna Gollara Siddappa

“…In this research, the compensation of WA in SLAO is obtained by proposing the Brownian motion and Directional mutation scheme-based Coati Optimization Algorithm, BDCOA. Here, the BDCOA is developed to search for an optimum control signal value of actuators in Deformable Mirror (DM). …”
Get full text

Denoising of Inflow of Pingzhai Reservoir Based on Fusion Algorithm of Wavelet Transform and Savitzky-Golay Filter by GAO Lin, SONG Jinwei, LI Zuoxiao

“…According to the results, compared with the five point three order smoothing method, sliding average method, and wavelet threshold denoising method, the wavelet transform SG filtering fusion algorithm significantly improves the smoothness and denoising effect while ensuring the characteristics of the reverse flow peak information of the inflow. …”
Get full text

Denoising of Inflow of Pingzhai Reservoir Based on Fusion Algorithm of Wavelet Transform and Savitzky-Golay Filter by GAO Lin, SONG Jinwei, LI Zuoxiao

“…According to the results, compared with the five point three order smoothing method, sliding average method, and wavelet threshold denoising method, the wavelet transform SG filtering fusion algorithm significantly improves the smoothness and denoising effect while ensuring the characteristics of the reverse flow peak information of the inflow. …”
Get full text

Novel algorithm for multifocus image fusion: integration of convolutional neural network and partial differential equation by Gargi J Trivedi, Rajesh Sanghvi

“…Furthermore, we aim to enhance our approach by incorporating machine learning techniques to optimize the parameters of the image fusion algorithm. …”
Get full text

A mathematical PAPR estimation of OTFS network using a machine learning SVM algorithm by Arun Kumar, Nishant Gaur, Aziz Nanthaamornphong

“…The article presents a Support Vector Machine (SVM) algorithm to lower the peak-to-average power ratio (PAPR) in networks that work in orthogonal time frequency space (OTFS). …”
Get full text

Mathematical Background and Algorithms of a Collection of Android Apps for a Google Play Store Page by Roland Szabo

“…The first application unveils an innovative SMS messaging system that substitutes manual typing with voice interaction. The key algorithm facilitates real-time conversion from speech to text for message creation and from text to speech for message playback, thus turning SMS communication into an audio-focused exchange while preserving conventional messaging standards. …”
Get full text

Vehicular cache nodes selection algorithm under load constraint in C-V2X by Zhexin XU, Kaimeng GAO, Wenkang JIA, Yi WU

“…In order to solve the problem that the C-V2X vehicle topology in urban environment was highly dynamic and the load capacity of vehicle nodes was limited, and improve the utilization of vehicular cache resources and reduce the load of base station, a vehicle cache nodes selection algorithm under load constraints was proposed.Firstly, by defining the link stability metric, the predicted weight adjacency matrix was constructed to describe the vehicular micro-topology in essence.Next, the objective function was further constructed under the load constraints and non-overlapping coverage constraint, which maximized the average link weight of the clusters by using the least cache nodes.Finally, the greedy concept was then introduced and the node states were reasonably defined.As a result, the minimum dominating set of the vehicle topology was figured out under the load constraints.Besides, the serviced neighbor nodes were then determined preferentially.The simulation results show that the proposed algorithm is close to the global optimal results in terms of the number of cache nodes and the average weight of cluster links.Moreover, the repeated response ratio of the proposed algorithm is always zero while the request response ratio can achieve the theoretical upper bound.Furthermore, the response times of cache resources can be also effectively improved.…”
Get full text

Modeling and Evolutionary Optimization on Multilevel Production Scheduling: A Case Study by Ruifeng Shi, Chunxia Shangguan, Hong Zhou

“…An integrated model, which can cope with the whole multilevel scheduling information simultaneously, is proposed in this paper, and a specific evolutionary algorithm is designed to solve the integrated model with a twin-screw coding strategy. …”
Get full text

Short-Term Electric Load Forecasting for an Industrial Plant Using Machine Learning-Based Algorithms by Oğuzhan Timur, Halil Yaşar Üstünel

“…The integration of calendar, meteorological, and lagging electrical variables, along with machine learning-based algorithms, is employed to boost forecasting accuracy and optimize energy utilization. …”
Get full text

Simulation of a scalable corridor waning radiance system using fuzzy PID and genetic algorithm by Abdallah Awamu, Jimmy Nabende Wanzala, Michael Robson Atim, Cosmos Dumba

Get full text

Significance of Machine Learning-Driven Algorithms for Effective Discrimination of DDoS Traffic Within IoT Systems by Mohammed N. Alenezi

“…Findings revealed that the RF model outperformed other models by delivering optimal detection speed and remarkable performance across all evaluation metrics, while KNN (K = 7) emerged as the most efficient model in terms of training time.…”
Get full text

Lightweight Transformer traffic scene semantic segmentation algorithm integrating multi-scale depth convolution by Gang XIE, Quanyi WANG, Xinlin XIE, Jian’an WANG

“…Aiming at the problems of discontinuous segmentation of thin strip objects that were easy to blend into the surrounding background and a large number of model parameters in the semantic segmentation algorithm of traffic scenes, a lightweight Transformer traffic scene semantic segmentation algorithm integrating multi-scale depth convolution was proposed.First, a multi-scale strip feature extraction module (MSEM) was constructed based on deep convolution to enhance the representation ability of thin strip target features at different scales.Secondly, a spatial detail auxiliary module (SDAM) was designed using the convolutional inductive bias feature in the shallow network to compensate for the loss of deep spatial detail information to optimize object edge segmentation.Finally, an asymmetric encoding-decoding network based on the Transformer-CNN framework (TC-AEDNet) was proposed.The encoder combined Transformer and CNN to alleviate the loss of detail information and reduce the amount of model parameters; while the decoder adopted a lightweight multi-level feature fusion design to further model the global context.The proposed algorithm achieves the mean intersection over union (mIoU) of 78.63% and 81.06% respectively on the Cityscapes and CamVid traffic scene public datasets.It can achieve a trade-off between segmentation accuracy and model size in traffic scene semantic segmentation and has a good application prospect.…”
Get full text