pith. sign in

arxiv: 2604.16047 · v1 · submitted 2026-04-17 · 💻 cs.HC · cs.CY· cs.LG

Driving Assistance System for Ambulances to Minimise the Vibrations in Patient Cabin

Abdulaziz Aldegheishem , Nabil Alrajeh , Lorena Parra , Oscar Romero , Jaime Lloret This is my paper

Pith reviewed 2026-05-10 08:11 UTC · model grok-4.3

classification 💻 cs.HC cs.CYcs.LG
keywords ambulancevibration reductionroute recommendationartificial neural networkpatient safetyaccelerometerdriving assistanceemergency transport
0
0 comments X

The pith

An ambulance system recommends the lower-vibration route when time differences between options stay below 6 percent but takes the shortest route above 20 percent.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper builds and evaluates a sensor-based driving assistance system for ambulances that measures cabin vibrations with an accelerometer and pairs the readings with GPS data. An artificial neural network classifies road segments into low, medium, or high vibration categories at 97 percent accuracy after training on one region and validation on another. When two routes reach the same destination, the system computes an index that trades off travel time against cumulative vibration exposure and selects the route that keeps vibrations lower in the patient cabin. This matters because vibrations from normal driving can interfere with medical procedures and patient stability during transport. Tests on new route pairs show the low-vibration choice wins only when the time penalty is modest.

Core claim

The system classifies vibration levels along candidate routes using an artificial neural network trained on accelerometer data, then applies a weighted index to pick the route that minimizes patient-cabin vibrations unless the time difference exceeds 20 percent, in which case the shortest route is selected regardless of vibration levels.

What carries the argument

The ANN vibration classifier that labels segments low-medium-high to feed into a route-scoring index balancing time and vibration exposure.

If this is right

  • When travel times are nearly equal the system steers ambulances onto smoother roads to limit cabin vibrations.
  • Real-time sensor data plus the trained model produces route scores that can be shown on the vehicle display.
  • Validation across regions indicates the approach works for areas sharing similar road vibration profiles.
  • Current time-vibration weights make any route more than 20 percent faster win even if vibrations are higher.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Linking the system to existing ambulance navigation software would let drivers receive vibration-aware guidance without manual route planning.
  • Retraining the classifier on local road data could maintain accuracy when moving between cities with different pavement types.
  • The same sensor-plus-index logic might help other vehicles carrying vibration-sensitive equipment such as blood supplies or lab samples.

Load-bearing premise

Vibration patterns and weighting factors learned from the training region will transfer to new cities while preserving the 97 percent classification accuracy without extra calibration.

What would settle it

Running the deployed system in a city with markedly different road surfaces and measuring whether accuracy on fresh accelerometer data falls below 90 percent or the route choices stop reducing measured vibrations as predicted.

Figures

Figures reproduced from arXiv: 2604.16047 by Abdulaziz Aldegheishem, Jaime Lloret, Lorena Parra, Nabil Alrajeh, Oscar Romero.

Figure 1
Figure 1. Figure 1: Operation mode 1 of the proposed system [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: The first scenario with two possible routes to reach the same destination. The second scenario comprises three different routes, including different urban and interurban areas in different proportions (see [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 6
Figure 6. Figure 6: Used ANN for data classification. First, data in the grey colour of [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Classified points of the three routes of the second scenario using the 15 s buffer [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Classified points of the three routes of the second scenario using the 29 s buffer. The first visible differences in classified data with the different ANN models are found for the A3 and A2 classes. In general terms, the A1 is similar to both models. The route indicated in the black line does not include any point classified as A1. According to data classified with the first model, no point is classified … view at source ↗
Figure 10
Figure 10. Figure 10: Detail of classified points of the second route of the second scenario using the ANN with the 29 s buffer, (a) Urban zone of Daimuz, (b) Urban zone of Miramar [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Detail of classified points of the third route of the second scenario using the ANN with the 15 s buffer, (a) Urban zone of Gandía, (b) Urban zone of Plama de Gandía. Considering the pieces of evidence presented in the validation, we have concluded that using 29 s as a time buffer is the most accurate option. Thus, the validation results indicated that the ANN model with the 29 s buffer should be used to … view at source ↗
Figure 12
Figure 12. Figure 12: Detail of classified points of the third route of the second scenario using the ANN with the 29 s buffer, (a) Urban zone of Gandía, (b) Urban zone of Plama de Gandía. 4.3. Classified Routes for Index and Score Testing The last step is to evaluate the performance of the index and score over two classified routes to recommend the route that minimises the vibration in the patient cabin. The two routes of the… view at source ↗
Figure 13
Figure 13. Figure 13: Classified routes of the first scenario to test the index and score [PITH_FULL_IMAGE:figures/full_fig_p016_13.png] view at source ↗
read the original abstract

The ambulance service is the main transport for diseased or injured people which suffers the same acceleration forces as regular vehicles. These accelerations, caused by the movement of the vehicle, impact the performance of tasks executed by sanitary personnel, which can affect patient survival or recovery time. In this paper, we have trained, validated, and tested a system to assess driving in ambulance services. The proposed system is composed of a sensor node which measures the vehicle vibrations using an accelerometer. It also includes a GPS sensor, a battery, a display, and a speaker. When two possible routes reach the same destination point, the system compares the two routes based on previously classified data and calculates an index and a score. Thus, the index balances the possible routes in terms of time to reach the destination and the vibrations suffered in the patient cabin to recommend the route that minimises those vibrations. Three datasets are used to train, validate, and test the system. Based on an Artificial Neural network (ANN), the classification model is trained with tagged data classified as low, medium, and high vibrations, and 97% accuracy is achieved. Then, the obtained model is validated using data from three routes of another region. Finally, the system is tested in two new scenarios with two possible routes to reach the destination. The results indicate that the route with less vibration is preferred when there are low time differences (less than 6%) between the two possible routes. Nonetheless, with the current weighting factors, the shortest route is preferred when time differences between routes are higher than 20%, regardless of the higher vibrations in the shortest route.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The paper proposes a sensor-based driving assistance system for ambulances consisting of an accelerometer, GPS, battery, display and speaker. An ANN classifies measured vibrations into low/medium/high categories (97% accuracy on training data) and an index is computed to select between two routes to the same destination, balancing travel time against patient-cabin vibrations. The system is trained on three datasets, validated on routes from a second region, and tested in two scenarios; the authors conclude that the lower-vibration route is preferred when time differences are below 6% while the shortest route is chosen for differences above 20% under the current weighting factors.

Significance. If the reported accuracy and route-selection behavior generalize, the work could meaningfully reduce vibration exposure during ambulance transport and thereby improve patient outcomes in emergency medical services. The approach combines readily available sensors with a trained classifier and a practical decision index, offering a deployable prototype that is grounded in real accelerometer data rather than purely simulated conditions.

major comments (3)
  1. [Route index and score calculation (results and methods)] The manuscript never states the exact mathematical definition of the route index or the numerical values of the weighting factors that balance time and vibration. Because the reported preference thresholds (<6% time difference favors lower vibration; >20% favors shortest route) are produced by this index, the central empirical claim cannot be reproduced or tested for robustness without those parameters.
  2. [Validation on second-region routes] No accuracy, confusion matrix, or other performance metric is supplied for the ANN when it is applied to the three routes of the second region, even though the text states that the model is validated on that data. This leaves the generalization claim unsupported by quantitative evidence.
  3. [Training, validation and test datasets] Dataset sizes, number of samples per class, cross-validation procedure, and any error bars or statistical tests accompanying the 97% accuracy figure are omitted. Without these details the reliability of the classifier and the subsequent route recommendations cannot be assessed.
minor comments (1)
  1. [Data labeling] The abstract and text refer to 'three datasets' and 'tagged data' without clarifying how the vibration labels were obtained or whether the tagging was performed by multiple annotators.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed and constructive review of our manuscript. The comments highlight important aspects for improving clarity and reproducibility. We address each major comment below and commit to revising the manuscript to incorporate the necessary details.

read point-by-point responses

  1. Referee: [Route index and score calculation (results and methods)] The manuscript never states the exact mathematical definition of the route index or the numerical values of the weighting factors that balance time and vibration. Because the reported preference thresholds (<6% time difference favors lower vibration; >20% favors shortest route) are produced by this index, the central empirical claim cannot be reproduced or tested for robustness without those parameters.

    Authors: We agree that the manuscript does not provide the exact mathematical definition of the route index or the numerical values of the weighting factors. This was an oversight that affects reproducibility. In the revised manuscript, we will explicitly state the formula for the route index (which combines normalized travel time and vibration score) and report the specific weighting factors used to generate the observed thresholds of less than 6% and greater than 20%. revision: yes

  2. Referee: [Validation on second-region routes] No accuracy, confusion matrix, or other performance metric is supplied for the ANN when it is applied to the three routes of the second region, even though the text states that the model is validated on that data. This leaves the generalization claim unsupported by quantitative evidence.

    Authors: We acknowledge that while the manuscript describes validation on three routes from a second region, no quantitative metrics (accuracy, confusion matrix, or similar) were reported for this step. We will add these performance measures in the revised version to provide quantitative support for the generalization claim. revision: yes

  3. Referee: [Training, validation and test datasets] Dataset sizes, number of samples per class, cross-validation procedure, and any error bars or statistical tests accompanying the 97% accuracy figure are omitted. Without these details the reliability of the classifier and the subsequent route recommendations cannot be assessed.

    Authors: We recognize that essential details on dataset composition and evaluation were omitted. The revised manuscript will include the sizes of the training, validation, and test sets, the number of samples per vibration class, the cross-validation procedure, and any error bars or statistical tests associated with the 97% accuracy figure. revision: yes

Circularity Check

0 steps flagged

No significant circularity; empirical ML system with independent validation

full rationale

The paper trains an ANN classifier on tagged vibration data (97% accuracy), validates the model on routes from a second region, and applies it in two test scenarios to compute an index balancing measured time and classified vibration levels. The reported preference thresholds emerge directly from the outcomes of those specific test runs rather than from any self-referential definition, fitted parameter renamed as prediction, or self-citation chain. No equations are presented that reduce the index or thresholds to the inputs by construction, and the derivation chain relies on external sensor data and cross-region validation instead of internal tautology.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The central claim rests on the empirical performance of a standard neural network and on the untested premise that lower vibrations improve medical outcomes; no new physical constants or entities are introduced.

free parameters (1)
  • weighting factors between time and vibration
    The abstract states that current weighting factors cause the system to prefer the shortest route above 20% time difference; these scalars are chosen rather than derived.
axioms (2)
  • domain assumption Vibrations measured by accelerometer in the patient cabin directly affect the performance of sanitary personnel and patient recovery
    Invoked in the opening paragraph to justify the goal of minimizing vibrations.
  • domain assumption Vibration patterns learned in one region transfer to routes in another region
    Used when validating the model on data from a different region.

pith-pipeline@v0.9.0 · 5613 in / 1469 out tokens · 41046 ms · 2026-05-10T08:11:55.415903+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

44 extracted references · 44 canonical work pages

  1. [1]

    VHC de Albuquerque, Deep learning for safe autonomous driving: Current challenges and future directions

    Muhammad, K.; Ullah, A.; Lloret, J.; Del Ser, J. VHC de Albuquerque, Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Trans. Intell. Transp. Syst. 2020, 22, 4316–4336

    work page 2020

  2. [2]

    An empirical investigation of forecasting methods for ambulance calls -a case study

    Al-Azzani, M.A.; Davari, S.; England, T.J. An empirical investigation of forecasting methods for ambulance calls -a case study. Health Syst. 2021, 10, 268–285

    work page 2021

  3. [3]

    Predicting emergency medical service call demand: A modern spatiotemporal machine learning approach

    Martin, R.J.; Mousavi, R.; Saydam, C. Predicting emergency medical service call demand: A modern spatiotemporal machine learning approach. Oper. Res. Health Care. 2021, 28, 100285

    work page 2021

  4. [4]

    Helicopter air ambulance services

    Ruskin, K.J. Helicopter air ambulance services. Curr. Opin. Anaesthesiol. 2019, 32, 252–256

    work page 2019

  5. [5]

    Causes of delay during interfacility transports of injured patients transported by air ambulance

    Nolan, B.; Haas, B.; Tien, H.; Saskin, R.; Nathens, A. Causes of delay during interfacility transports of injured patients transported by air ambulance. Prehosp. Emerg. Care 2020, 24, 625–633

    work page 2020

  6. [6]

    Advanced Air Mobility: Opportunities and Challenges Deploying eVTOLs for Air Ambulance Service

    Goyal, R.; Cohen, A. Advanced Air Mobility: Opportunities and Challenges Deploying eVTOLs for Air Ambulance Service. Appl. Sci. 2022, 12, 1183

    work page 2022

  7. [7]

    Ambulance allocation optimization model for the overcrowding problem in US emergency departments: A case study in Florida

    Acuna, J.A.; Zayas -Castro, J.L.; Charkhgard, H. Ambulance allocation optimization model for the overcrowding problem in US emergency departments: A case study in Florida. Socio-Econ. Plan. Sci. 2020, 71, 100747

    work page 2020

  8. [8]

    Ambulance allocation considering the spatial randomness of demand

    Yang, W.; Su, Q.; Zhou, M.; Qin, X. Ambulance allocation considering the spatial randomness of demand. Comput. Ind. Eng. 2020, 139, 106202

    work page 2020

  9. [9]

    Predicting an Avoidable Conveyance to the Emergency Department for Ambulance Patients on Scene

    Miles, J. Predicting an Avoidable Conveyance to the Emergency Department for Ambulance Patients on Scene. Ph.D. Thesis, University of Sheffield, Sheffield, UK, 2022

    work page 2022

  10. [10]

    Whole-Body Vibration Exposure from Incubators in the Neonatal Care Setting: A Review

    McCallig, M.; Pakrashi, V . Whole-Body Vibration Exposure from Incubators in the Neonatal Care Setting: A Review. J. Environ. Occup. Health 2021, 11, 37–46

    work page 2021

  11. [11]

    Effectivity comparison between mechanical chest compression and manual chest compression in real urban traffic

    Serin, S.; Çağlar, B. Effectivity comparison between mechanical chest compression and manual chest compression in real urban traffic. Fırat Üniversitesi Sağlık Bilim. Tıp Derg. 2020, 34, 193–197

    work page 2020

  12. [12]

    Beom, J.H.; Kim, M.J.; You, J.S.; Lee, H.S.; Kim, J.H.; Park, Y .S.; Shin, D.M.; Chung, H.S. Evaluation of the quality of cardiopulmonary resuscitation according to vehicle driving pattern, using a virtual reality ambulance driving system: A prospective, cross-over, randomised study. BMJ Open 2018, 8, e023784

    work page 2018

  13. [13]

    Acceleration during neonatal transport and its impact on mechanical ventilation

    Lantos, L.; Széll, A.; Chong, D.; Somogyvári, Z.; Belteki, G. Acceleration during neonatal transport and its impact on mechanical ventilation. Arch. Dis. Child. Fetal Neonatal Ed. 2022

    work page 2022

  14. [14]

    The effect on video laryngoscope on intubation process during ambulance transport

    Caglar, B.; Serin, S. The effect on video laryngoscope on intubation process during ambulance transport. J. Coll. Physicians Surg. Pak. JCPSP 2020, 30, 351–354

    work page 2020

  15. [15]

    Modeling of the Heart Rate Variation Caused by Acceleration and Deceleration of an Ambulance

    Kanatani, M.; Ono, T. Modeling of the Heart Rate Variation Caused by Acceleration and Deceleration of an Ambulance. In Proceedings of the 2021 IEEE 60th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) 2021, Tokyo, Japan, 8–10 September 2021; pp. 1420–1425

    work page 2021

  16. [16]

    Effects of spinal immobilization and spinal motion restriction on head-neck kinematics during ambulance transport

    Thézard, F.; McDonald, N.; Kriellaars, D.; Giesbrecht, G.; Weldon, E.; Pryce, R.T. Effects of spinal immobilization and spinal motion restriction on head-neck kinematics during ambulance transport. Prehosp. Emerg. Care 2019, 23, 811–819

    work page 2019

  17. [17]

    A new vibration isolation bed stage with magnetorheological dampers for ambulance vehicles

    Chae, H.D.; Choi, S.B. A new vibration isolation bed stage with magnetorheological dampers for ambulance vehicles. Smart Mater. Struct. 2014, 24, 017001

    work page 2014

  18. [18]

    Evaluating the effects of a simulator -based training on knowledge, attitudes and driving profiles of German ambulance drivers

    Prohn, M.J.; Herbig, B. Evaluating the effects of a simulator -based training on knowledge, attitudes and driving profiles of German ambulance drivers. Accid. Anal. Prev. 2020, 138, 105466

    work page 2020

  19. [19]

    Reducing Response Time of Ambulance Service by Utilizing the Knowledge of Service Location of Ambulance Drivers using Self -Organizing Map

    Jha, R.K.; Chattopadhyay, M.; Gajpal, Y . Reducing Response Time of Ambulance Service by Utilizing the Knowledge of Service Location of Ambulance Drivers using Self -Organizing Map. Int. J. Oper. Quant. Manag. 2021, 27, 219–235

    work page 2021

  20. [20]

    Convolutional neural networks for pavement roughness assessment using calibration- free vehicle dynamics

    Jeong, J.H.; Jo, H.; Ditzler, G. Convolutional neural networks for pavement roughness assessment using calibration- free vehicle dynamics. Comput.-Aided. Civ. Infrastruct. Eng. 2020, 35, 1209–1229

    work page 2020

  21. [21]

    Pavement roughness evaluation method based on the theoretical relationship between acceleration measured by smartphone and IRI

    Zhang, Z.; Zhang, H.; Xu, S.; Lv, W. Pavement roughness evaluation method based on the theoretical relationship between acceleration measured by smartphone and IRI. Int. J. Pavement Eng. 2022, 23, 3082–3098

    work page 2022

  22. [22]

    Development of pavement roughness models using Artificial Neural Network (ANN)

    Alatoom, Y .I.; Al-Suleiman, T.I. Development of pavement roughness models using Artificial Neural Network (ANN). Int. J. Pavement Eng. 2022, 1–16

    work page 2022

  23. [23]

    Pavement roughness index estimation and anomaly detection using smartphones

    Y u, Q.; Fang, Y .; Wix, R. Pavement roughness index estimation and anomaly detection using smartphones. Autom. Constr. 2022, 141, 104409

    work page 2022

  24. [24]

    Road condition monitoring using smart sensing and artificial intelligence: A review

    Ranyal, E.; Sadhu, A.; Jain, K. Road condition monitoring using smart sensing and artificial intelligence: A review. Sensors 2022, 22, 3044

    work page 2022

  25. [25]

    Study on passenger comfort based on human–bus–road coupled vibration

    Wang, G.; Zhang, J.; Kong, X. Study on passenger comfort based on human–bus–road coupled vibration. Appl. Sci. 2020, 10, 3254

    work page 2020

  26. [26]

    International roughness index thresholds based on whole-body vibration in passenger cars

    Múčka, P . International roughness index thresholds based on whole-body vibration in passenger cars. Transp. Res. Rec. 2021, 2675, 305–320

    work page 2021

  27. [27]

    Analysis of movements and degrees of freedom required for a vibration attenuation system on ambulance stretchers

    Marques, L.; Malvezzi, F.; Stavropoulos, K.D. Analysis of movements and degrees of freedom required for a vibration attenuation system on ambulance stretchers. Vibroeng. Procedia 2020, 32, 81–86

    work page 2020

  28. [28]

    Parameter optimization for a vibration attenuation system on ambulance stretchers

    Malvezzi, F.; Maia Matarazzo Orsino, R.; Dimitriou Stavropoulos, K. Parameter optimization for a vibration attenuation system on ambulance stretchers. Vibroeng. Procedia 2021, 37, 36–41

    work page 2021

  29. [29]

    Influence of pavement type and speed on whole body vibration (WBV) levels measured on passenger vehicles

    Duarte, M.L.M.; de Melo, G.C. Influence of pavement type and speed on whole body vibration (WBV) levels measured on passenger vehicles. J. Braz. Soc. Mech. Sci. 2018, 40, 1–12

    work page 2018

  30. [30]

    Development of a GIS -Based Methodology for the Management of Stone Pavements Using Low-Cost Sensors

    Bruno, S.; Vita, L.; Loprencipe, G. Development of a GIS -Based Methodology for the Management of Stone Pavements Using Low-Cost Sensors. Sensors 2022, 22, 6560

    work page 2022

  31. [31]

    Vibration Profiles of a Road Ambulance Using Equivalent Acceleration

    Kehoe, P.; Gibb, K.; Hurley, J.; Chan, A.; Green, J.; Langlois, R.; Greenwood, K.; Aubertin, C.; Ibey, A.; Redpath, S. Vibration Profiles of a Road Ambulance Using Equivalent Acceleration. In Proceedings of the Canadian Society for Mechanical Engineering International Congress 2022, Edmonton, AB, Canada, 5–8 June 2022

    work page 2022

  32. [32]

    Low -Cost System for Automatic Recognition of Driving Pattern in Assessing Interurban Mobility using Geo-Information

    Romero, O.; Miura, A.S.; Parra, L.; Lloret, J. Low -Cost System for Automatic Recognition of Driving Pattern in Assessing Interurban Mobility using Geo-Information. ISPRS Int. J. Geo-Inf. 2022, 11, 597

    work page 2022

  33. [33]

    GY-521 MPU-6050 Datasheet https://invensense.tdk.com/wp-content/uploads/2015/02/MPU-6000-Datasheet1.pdf

    work page 2015

  34. [34]

    PS GY -NEO6MV2 Datashee t https://www.openimpulse.com/blog/wp-content/uploads/wpsc/downloadables/GY- NEO6MV2-GPS-Module-Datasheet.pdf

    work page

  35. [35]

    Raspberry Pi 3 Datasheet https://static.raspberrypi.org/files/product-briefs/Raspberry-Pi-Model-Bplus-Product- Brief.pdf

    work page

  36. [36]

    V ANETs cloud: Architecture, applications, challenges, and issues

    Sharma, S.; Kaul, A. V ANETs cloud: Architecture, applications, challenges, and issues. Arch. Comput. Method 2021, 28, 2081–2102

    work page 2021

  37. [37]

    Modeling of V ANET for future generation transportation system through Edge/Fog/Cloud computing powered by 6G

    Suresh Kumar, K.; Radha Mani, A.S.; Sundaresan, S.; Ananth Kumar, T. Modeling of V ANET for future generation transportation system through Edge/Fog/Cloud computing powered by 6G. Cloud IoT -Based Veh. Ad Hoc Netw. 2021, 105–124

    work page 2021

  38. [38]

    A hybridization of artificial neural network and support vector machine for prevention of road accidents in V ANET

    Dutta, C.; Singhal, D. A hybridization of artificial neural network and support vector machine for prevention of road accidents in V ANET. Int. J. Comput. Sci. Eng. Technol. 2019, 10, 110–116

    work page 2019

  39. [39]

    An overview of traffic congestion detection and classification techniques in V ANET

    Ramli, N.I.; MOHAMED RAWI, M.I. An overview of traffic congestion detection and classification techniques in V ANET. Indones. J. Electr. Eng. Comput. Sci. 2020, 20, 437–444

    work page 2020

  40. [40]

    A hyperspectral image classification method using multifeature vectors and optimized KELM

    Chen, H.; Miao, F.; Chen, Y .; Xiong, Y .; Chen, T. A hyperspectral image classification method using multifeature vectors and optimized KELM. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 2781–2795

    work page 2021

  41. [41]

    Optimal search mapping among sensors in heterogeneous smart homes

    Yu, Y .; Hao, Z.; Li, G.; Liu, Y .; Yang, R.; Liu, H. Optimal search mapping among sensors in heterogeneous smart homes. Math. Biosci. Eng 2023, 2023, 1960–1980

    work page 2023

  42. [42]

    Data-driven simultaneous identification of the 6DOF dynamic model and wave load for a ship in waves

    Ren, Z.; Han, X.; Yu, X.; Skjetne, R.; Leira, B.J.; Sævik, S.; Zhu, M. Data-driven simultaneous identification of the 6DOF dynamic model and wave load for a ship in waves. Mech. Syst. Signal. Process. 2023, 184, 109422

    work page 2023

  43. [43]

    Co-evolutionary competitive swarm optimizer with three- phase for large-scale complex optimization problem

    Huang, C.; Zhou, X.; Ran, X.; Liu, Y .; Deng, W.; Deng, W. Co-evolutionary competitive swarm optimizer with three- phase for large-scale complex optimization problem. Inf. Sci. 2022, 619, 2–18

    work page 2022

  44. [44]

    Intelligent beaconless geographical forwarding for urban vehicular environments

    Ghafoor, K.Z.; Abu Bakar, K.; Lloret, L.; Khokhar, R.H.; Lee, K.C. Intelligent beaconless geographical forwarding for urban vehicular environments. Wirel. Netw. 2013, 19, 345–362

    work page 2013