Broad learning system based on attention mechanism and tracking differentiator by LIAO Lüchao, ZOU Weidong, YANG Jialong, LU Huihuang, XIA Yuanqing, GAO Jianlei

“…To alleviate these problems, broad learning system based on attention mechanism and tracking differentiator (TD), abbreviated as A-TD-BLS, was proposed. In terms of model structure, A-TD-BLS introduced self-attention mechanism to the original BLS, and further fused and transformed the extracted features through attention weighting to improve the feature learning ability.In terms of model training methods, a weight optimization algorithm based on tracking differentiator was designed.This method effectively alleviates the overfitting phenomenon of the original BLS by limiting the size of the weight values, significantly reduces the influence of the number of hidden layer nodes on model performance and makes the generalization performance more stable.Moreover, the training algorithm was extended to the BLS incremental learning framework, so that the model can improve performance by dynamically adding hidden layer nodes.Multiple experiments conducted on some benchmark datasets show that compared to the original BLS, the classification accuracy of A-TD-BLS is increased by 1.27% on average on classification datasets and the root mean square error of A-TD-BLS is reduced by 0.53 on average on regression datasets.Besides, A-TD-BLS is less affected by the number of hidden layer nodes and has more stable generalization performance. …”
Get full text

Driving Pattern Analysis, Gear Shift Classification, and Fuel Efficiency in Light-Duty Vehicles: A Machine Learning Approach Using GPS and OBD II PID Signals by Juan José Molina-Campoverde, Juan Zurita-Jara, Paúl Molina-Campoverde

“…A multiple linear regression model was developed to estimate instantaneous fuel consumption (in L/100 km) using the gear predicted by the KNN algorithm and other relevant variables. …”
Get full text

Augmented Reality Interactive Guide System and Method for Tourist Attractions Based on Geographic Location by Xueqiu Zhuang, Huihua Jiao, Kai Lu

“…This paper proposes an improved probabilistic algorithm model to accurately locate tourists. …”
Get full text

Dynamic-budget superpixel active learning for semantic segmentation by Yuemin Wang, Ian Stavness

“…A static budget could result in over- or under-labeling images as the number of high-impact regions in each image can vary.MethodsIn this paper, we present a novel dynamic-budget superpixel querying strategy that can query the optimal numbers of high-uncertainty superpixels in an image to improve the querying efficiency of regional active learning algorithms designed for semantic segmentation.ResultsFor two distinct datasets, we show that by allowing a dynamic budget for each image, the active learning algorithm is more effective compared to static-budget querying at the same low total labeling budget. …”
Get full text

Breast Tumor-Like-Masses Segmentation From Scattering Images Obtained With an Ultrahigh-Sensitivity Talbot-Lau Interferometer Using Convolutional Neural Networks by Ionut-Cristian Ciobanu, Nicoleta Safca, Elena Anghel, Dan Popescu

“…Future work will focus on optimizing CNN architecture and expanding the dataset to improve the segmentation of small tumor-like masses.…”
Get full text

Exploring a QoS Driven Scheduling Approach for Peer-to-Peer Live Streaming Systems with Network Coding by Laizhong Cui, Nan Lu, Fu Chen

“…The main contributions of this paper are: (i) We introduce a new network coding method to increase the content diversity and reduce the complexity of scheduling; (ii) we formulate the push scheduling as an optimization problem and transform it to a min-cost flow problem for solving it in polynomial time; (iii) we propose a push scheduling algorithm to reduce the coding overhead and do extensive experiments to validate the effectiveness of our approach. …”
Get full text

Real-time torque distribution simulation of parallel hybrid vehicle engine by Jing Wang

“…Validation employed the Gamma Technologies Suite simulation platform and the Next Generation Simulation dataset, with benchmark comparisons against Equivalent Consumption Minimization Strategy, Fuzzy Logic Control, and Thermostat Strategy models.ResultsThe optimized Proximal Policy Optimization algorithm achieved 93.2% accuracy and 1.0% loss rate upon convergence, with an average feedback time of 32 milliseconds. …”
Get full text

Research on caching strategy based on transmission delay in Cell-Free massive MIMO systems by Rui WANG, Min SHEN, Yun HE, Xiangyan LIU

“…To meet the ultra-low latency and ultra-high reliability requirements of users in the future mobile Internet， the wireless caching technology was combined with Cell-Free massive MIMO systems.The caching model was designed based on AP cooperative caching and regional popularity evaluation.The transmission delay expression involving AP clustering， cooperative caching， and regional popularity was derived， and the content placement problem was expressed as total content transmission delay minimization.Through the demonstration of the NP-hard and submodular monotony of the optimization problem， the greedy algorithm-based optimization strategy was proposed.Simulation results show that the proposed strategy can effectively reduce the content transmission delay and improve the cache hit rate.…”
Get full text

Outdoor location scheme with fingerprinting based on machine learning of mobile cellular network by Zhichao ZHOU, Yi FENG, Xiaohan XIA, Yuyao FENG, Chao CAI, Jiahui QIU, Lihui YANG, Yunxiao WU

“…The positioning scheme based on mobile cellular network technology is one of the important technical approaches to provide network optimization, emergency rescue, police patrol and location services.The traditional positioning scheme based on cell base station location information has low positioning accuracy and large positioning error, so it cannot meet the requirements of some positioning applications.The scheme based on fingerprint location can greatly improve the location accuracy, save computational cost and enhance the usability based on the coarse location scheme of the cell and become the hotspot of the research.Rasterization and non-rasterization of outdoor fingerprint location scheme based on machine learning were studied and analyzed to meet the business requirements of outdoor fingerprint location.By means of parameter weighting, data fitting and other methods, large-scale fingerprint data were cleaned to improve the effectiveness of data sources.Through the realization of sub-modules such as demarcating research area, rasterizing, constructing fingerprint database, training model, correcting model, non-rasterizing, rough positioning coupling, matching parameter and training parameter, the operation efficiency and positioning accuracy of the algorithm were analyzed and optimized, and the key indexes affecting the algorithm performance were determined.Then, the performance of two fingerprint-based localization schemewas analyzed based on the simulation results.Finally, the typical scenarios of the fingerprint location scheme based on machine learning in practical application were presented.…”
Get full text

HUMAN-ORIENTED QUALITY MANAGEMENT SYSTEM OF ENTERPRISE: CONTROL OF NON-CONFORMING PRODUCT AND UTILIZATION by Vyacheslav Feoktistovich Bezyazychny, Maria Evgenyevna Ilyina

“…The presented model algorithm reflects all possible action variants directed on the improvement and the most effective use of non-conforming product. …”
Get full text

Smart estimation of protective antioxidant enzymes’ activity in savory (Satureja rechingeri L.) under drought stress and soil amendments by Amin Taheri-Garavand, Mojgan Beiranvandi, Abdolreza Ahmadi, Nikolaos Nikoloudakis

“…The current research was carried out to develop a genetic algorithm-based artificial neural network (ΑΝΝ) model able of simulating the levels of antioxidants in savory when using soil amendments [biochar (BC) and superabsorbent (SA)] under drought. …”
Get full text

Research on automatic identification method for pipeline girth weld defects based on X-ray images and sparse representation by Shaohui JIA, Yaping LI, Weixin GAO, Yunchao PENG, Xinjian ZHANG, Yuxia WANG

“…To maximize the library of image features within the dictionary matrix, an optimal model was established for X-ray SDR images of welds based on orthogonal optimization, along with a dictionary matrix solving algorithm featuring orthogonal optimization. …”
Get full text

Investigation on the Aerodynamic Parameters of the Triangle Shape of Tall Buildings by Using of CFD Method by Mehdi Noormohamadian, Eysa Salajegheh

“…Nowadays, the neural network algorithm is one of the most famous numerical methods for optimizing hull shapes. …”
Get full text

A Generalized Shape Function for Vibration Suppression Analysis of Acoustic Black Hole Beams Based on Fractional Calculus Theory by Jun Xu, Ning Chen

“…To obtain the best parameters of the shape function under various parameters, the Particle Swarm Optimization (PSO) algorithm is employed. The results demonstrate that by selecting appropriate ML parameters and viscoelastic materials, the dissipation characteristics of the structure can be significantly improved. …”
Get full text

A Robust Enhanced Ensemble Learning Method for Breast Cancer Data Diagnosis on Imbalanced Data by Zhenzhen Wang, Junde Xie, Jia Zhang

“…Specifically, a double-level over-sampling technology is developed to increase the diversity of synthesized minority breast cancer samples before model training, and an improved Random Forest is proposed to reconcile the bias and variance. …”
Get full text

Performance Analysis of CO2 Systems Integrated with Ejector and Dedicated Mechanical Subcooling by Dai Baomin, Zhao Ruirui, Liu Shengchun, Qian Jiabao, Xu Tianyahui, Liu Chen, Yang Peifang

“…A thermodynamic model of the system was devised. Then, the discharge pressure and subcooling degree were optimized using a genetic algorithm by considering the coefficient of performance (COP) as the objective function. …”
Get full text

Soft Measurement of Wastewater Treatment System Based on PSOGA-WNN by LIU Yuhui, MAI Wenjie, LI Xiaoyong, ZHAO Yinzhong, HE Xinzhong, HUANG Mingzhi

“…To accurately predict the SS_eff (effluent SS) content and COD_eff (effluent COD) concentration in water quality parameters and further improve the water quality early warning mechanism,this paper proposes the PSOGA-WNN soft measurement model of paper wastewater effluent quality to obtain the main water quality technical parameters,COD_inf (influent COD),Q (influent flow),pH (influent pH),SS_inf (influent SS),T (influent temperature),DO (influent dissolved oxygen),COD_eff,and SS_eff, for predicting the quality of wastewater from the wastewater treatment plant.Among them,the prediction results of PSOGA-WNN are compared with the neural networks of PSO-WNN,GA-WNN,and PSOGA-BP.The results show that the PSOGA-WNN neural network has the highest prediction accuracy,which indicates that the PSOGA hybrid parameter optimization algorithm based on the genetic algorithm and particle swarm algorithm has obvious superiority in optimizing the prediction accuracy of the model.The WNN neural network has certain advantages over BP neural network in terms of fitting degree as well as error accuracy and is an effective means of simulation prediction.…”
Get full text

Nitrous oxide prediction through machine learning and field-based experimentation: A novel strategy for data-driven insights by Muhammad Hassan, Khabat Khosravi, Travis J. Esau, Gurjit S. Randhawa, Aitazaz A. Farooque, Seyyed Ebrahim Hashemi Garmdareh, Yulin Hu, Nauman Yaqoob, Asad T. Jappa

“…The study found that combining soil and climatic variables improved prediction accuracy, with ST, AT, and soil EC being the most influential variables. …”
Get full text

A Hierarchical Control Framework for Coordinating CAV-Dedicated Lane Allocation and Signal Timing at Isolated Intersections in Mixed Traffic Environments by Feng Chen, Cunbao Zhang, Yu Cao

“…With the rapid development of connected and automated vehicles (CAVs), numerous studies have demonstrated that CAV-dedicated lanes (CAV-DLs) can significantly enhance traffic efficiency. However, most existing studies primarily focus on optimizing either CAV trajectory planning or traffic signal control, and the integration of CAV-DLs and signal control for improved spatiotemporal resource utilization remains underexplored. …”
Get full text

Flight Endurance Increasing Technology of New Energy UAV Based on a Strut-Braced Wing by Li Liu, Wencan Bai, Dun Yang

“…Surrogate model technology and multiobjective genetic algorithm are used to optimize the SBW configuration. …”
Get full text