Personalized trajectory inference framework integrating driving behavior recognition and temporal dependency learning. by Jinhao Yang, Junwen Cao, Mingyu Fang

“…The model achieves a mean RMSE of 4.46 and NLL of 3.89 across varying prediction horizons, with 35.8% error reduction attained after 100 hyperparameter optimization iterations. …”
Get full text

Experimental and Finite Element Analysis on the Structural Performance of Lightweight Hollow Slab Prefabricated Staircases by Jingmin Liu, Yiming Bao, Kang Qin

“…Furthermore, it achieves a 16% reduction in weight, a 28.6% improvement in load capacity, and a maximum error of 9.9% between the model and experimental results. …”
Get full text

Advancing precision dentistry: the integration of multi-omics and cutting-edge imaging technologies—a systematic review by Neelam Das

“…CBCT reduced diagnostic error by 35% (CI: 30%–40%), while MRI improved soft-tissue evaluation by 25% (CI: 18%–32%). …”
Get full text

RESEARCH ON THE OPTIMAL DESIGN METHOD OF U-SHAPED SECTION CONTAINMENT RING

“…U-shaped containment ring is usually used as protection device for turbine starters.Under the condition that the turbine rotor is contained,structural optimization of the U-shaped section containment ring was carried out to obtain a light and inclusive structure,which improved aircraft safety and thrust-to-weight ratio.An optimal design method for U-shaped cross section containment ring was proposed.The method adopted the optimal Latin hypercube design,numerical simulation,response surface modeling,and multi-island genetic algorithm to achieve the optimal design of multiple parameters of containment rings cross section.By combining simulation and experiment,the influence weights of different structural parameters on the residual kinetic energy of debris and the volume of containment rings were analyzed.The influence of different structural parameters of Ushaped containment ring on the containment results was studied.Containment test was carried out to verify the optimized containment ring.The results show that the thickness of the containment ring has the greatest influence on the residual kinetic energy of the debris,and the weight ratio is 38%.The main structural parameters affect the inclusion effect are thickness and groove depth.The error of inclusion ring deformation is less than 2%in the comparison between simulation and test results,which indicates that the optimization design method proposed is reasonable and reliable.The research results can provide prior knowledge and optimization methods for the quality reduction of U-shaped containment ring structures.…”
Get full text

A Study of Engine Intake Noise Control Based on the Improved Filtered-x Least Mean Square Algorithm by Chaofeng Lan, Lei Zhang, Shou Lv, Pengwei Jiang

“…The results show that the algorithm proposed can effectively reduce the intake noise of the engine at each speed and the noise reduction effect can reach 23.11 dB at a certain frequency. …”
Get full text

Risk Assessment and Enhancement Suggestions for Automated Driving Systems through Examining Testing Collision and Disengagement Reports by Kuo-Wei Wu, Wen-Fang Wu, Chung-Chih Liao, Wei-Ann Lin

“…Finally, we propose a workable risk reduction solution according to the characteristics of accidents.…”
Get full text

CO2 emissions response to GDP and crude oil price shocks: Evidence from India and China using SVAR Model by Matali Mahajan, Dr. Ash Narayan Sah

“…Global CO₂ emissions and warming remain critical challenges worldwide, with emission reduction central to attaining the UN Sustainable Development Goals. …”
Get full text

Hybrid Fuzzy Centroid with MDV-Hop BAT Localization Algorithms in Wireless Sensor Networks by Chakchai So-In, Weerat Katekaew

“…These combinations demonstrate the effectiveness in the simulation and location error reduction with time complexity trade-off.…”
Get full text

Improving Wireless Sensor Network Security Using Quantum Key Distribution by Laith H. Alhasnawy, Ameer K. AL-Mashanji

“…The efficiency of the work increased to 0.704 after using the Quantum Bit Error Rate equation, eventually increasing the network performance. …”
Get full text

Sensor placement optimization for critical-grid coverage problem of indoor positioning by Hui Wu, Zhe Liu, Jin Hu, Weifeng Yin

“…The results showed that the optimized schemes obtain a lower error (1.13, 1.21 m) and a higher reduction of sensor deployment cost than the uniform deployment scheme (1.44 m). …”
Get full text

Any-to-any voice conversion using representation separation auto-encoder by Zhihua JIAN, Zixu ZHANG

“…In view of the problem that it was difficult to separate speaker personality characteristics from semantic content information in any-to-any voice conversion under non-parallel corpus, which led to unsatisfied performance, a voice conversion method, called RSAE-VC (representation separation auto-encoder voice conversion) was proposed.The speaker’s personality characteristics in the speech were regarded as time invariant and the content information as time variant, and the instance normalization and activation guidance layer were used in the encoder to separate them from each other.Then the content information of the source speech and the personality characteristics of the target one was utilized to synthesize the converted speech by the decoder.The experimental results demonstrate that RSAE-VC has an average reduction of 3.11% and 2.41% in Mel cepstral distance and root mean square error of pitch frequency respectively, and has an increasement of 5.22% in MOS and 8.45% in ABX, compared with the AGAIN-VC (activation guidance and adaptive instance normalization voice conversion) method.In RSAE-VC, self-content loss is applied to make the converted speech reserve more content information, and self-speaker loss is used to separate the speaker personality characteristics from the speech better, which ensure the speaker personality characteristics be left in the content information as little as possible, and the conversion performance is improved.…”
Get full text

LX-mixers for QAOA: Optimal mixers restricted to subspaces and the stabilizer formalism by Franz G. Fuchs, Ruben Pariente Bassa

“…The numerical examples provided show a dramatic reduction of CX gates when compared to previous results. …”
Get full text

Quantum-enhanced intelligent system for personalized adaptive radiotherapy dose estimation by Radhey Lal, Rajiv Kumar Singh, Dinesh Kumar Nishad, Saifullah Khalid

“…Validation on simulated datasets demonstrates a 50–70% reduction in mean absolute error and 2–3% improvements in gamma index metrics compared to conventional approaches. …”
Get full text

Scaling Laws for Emulation of Stellar Spectra by Tomasz Różański, Yuan-Sen Ting

“…Specifically, given a tenfold increase in training compute, achieving an optimal seven-fold reduction in mean squared error necessitates an approximately 2.5-fold increase in dataset size and a 3.8-fold increase in model size. …”
Get full text

Development of regional mixed-effects height–diameter models for natural black pine stands by Ramazan Ozçelik, Onur Alkan

“…Compared to the fixed-effects model, the mixed-effects model achieved a 32% reduction in the root mean square error (RMSE). The findings suggest that the proposed model is highly suitable for forest inventory studies to predict tree heights in black pine stands.…”
Get full text

Medium- and Long-term Runoff Prediction Based on SMA-LSSVM by TIAN Jinghuan, LI Congxin, LI Ang

“…Medium-and long-term runoff prediction is extremely important for flood control,disaster reduction and the utilization efficiency improvement of water resources.To avoid the influence of prediction model parameters on prediction accuracy,this paper proposes a medium-and long-term runoff prediction model based on least squares support vector machine (LSSVM) optimized by the slime mold algorithm (SMA).Firstly,five standard test functions are selected to compare the simulation results of SMA and particle swarm optimization (PSO) algorithms in different dimensions.Secondly,SMA is used to optimize the penalty parameters and kernel parameters of LSSVM,and the comparison models of LSSVM and PSO-LSSVM are constructed.Finally,the models are verified with the monthly runoff of Manwan Hydropower Station Reservoir and Yingluoxia Hydrological Station as prediction examples.The results show that the mean square error of the SMA-LSSVM model is 29.26% and 7.42% lower than those of the LSSVM and PSO-LSSVM models,respectively,in the monthly runoff prediction of the Manwan station,and 32.61% and 6.61% lower,respectively,in the monthly runoff prediction of the Yingluoxia station.The proposed SMA-LSSVM model has better comprehensive prediction performance and also provides a new method for medium- and long-term runoff prediction.…”
Get full text

AHerfReLU: A Novel Adaptive Activation Function Enhancing Deep Neural Network Performance by Abaid Ullah, Muhammad Imran, Muhammad Abdul Basit, Madeeha Tahir, Jihad Younis

“…We propose AHerfReLU, a novel activation function that combines the rectified linear unit (ReLU) function with the error function (erf), complemented by a regularization term 1/1+x2, ensuring smooth gradients even for negative inputs. …”
Get full text

Market Phases and Price Discovery in NFTs: A Deep Learning Approach to Digital Asset Valuation by Ho-Jun Kang, Sang-Gun Lee

“…Analyzing 26,287 h of transaction data across major marketplaces, the model demonstrates superior predictive accuracy compared to conventional approaches, achieving a 33.5% reduction in Mean Absolute Error versus LSTM models, a 29.7% improvement over Transformer architectures, and a 30.1% enhancement compared to LightGBM implementations. …”
Get full text

Adaptive Backstepping Fuzzy Control Based on Type-2 Fuzzy System by Ll Yi-Min, Yue Yang, Li Li

“…This approach adopts type-2 fuzzy system instead of type-1 fuzzy system to approximate the unknown functions. With type-reduction, the type-2 fuzzy system is replaced by the average of two type-1 fuzzy systems. …”
Get full text

Enhancing 4G/LTE Network Path Loss Prediction with PSO-GWO Hybrid Approach by Messaoud Garah, Nabil Boukhennoufa

“…The performance of each optimization method is evaluated using various error metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Standard Deviation (STD), Mean Error (ME), and Mean Absolute Percentage Error (MAPE). …”
Get full text