Search Results (6,895)

Figure 1
<p>Taxonomy of meta-heuristic algorithms and representative algorithms.</p> Full article ">Figure 2
<p>Melting and sublimation process of SAO algorithm.</p> Full article ">Figure 3
<p>Schematic diagram of the cross term.</p> Full article ">Figure 4
<p>Distribution of tent chaos mapping.</p> Full article ">Figure 5
<p>MISAO flowchart.</p> Full article ">Figure 6
<p>Convergence process of different algorithms.</p> Full article ">Figure 7
<p>Convergence process of different strategies.</p> Full article ">Figure 8
<p>Runtime line chart.</p> Full article ">Figure 9
<p>Friedman cumulative value.</p> Full article ">Figure 10
<p>Terrain environment with mountain peaks.</p> Full article ">Figure 11
<p>Path planning diagram of different algorithms.</p> Full article ">Figure 12
<p>3D and plan view of path planning with different algorithms.</p> Full article ">

Figure 1
<p>FusionOpt-Net framework.</p> Full article ">Figure 2
<p>Reconstruction results for butterfly and bird images using FusionOpt-Net and other methods. Sampling rates <math display="inline"><semantics> <mi>τ</mi> </semantics></math> are 0.04 for the first row and 0.25 for the second row. Please zoom in for better comparison.</p> Full article ">Figure 3
<p>Noise Robustness Comparison. Visual analysis of different image CS methods on cactus and ship images from the BSD100 dataset at sampling rates <math display="inline"><semantics> <mrow> <mi>τ</mi> <mo>∈</mo> <mrow> <mn>0.04</mn> <mo>,</mo> <mn>0.10</mn> <mo>,</mo> <mn>0.25</mn> </mrow> </mrow> </semantics></math>. Gaussian noise with variances <math display="inline"><semantics> <mrow> <mi>σ</mi> <mo>∈</mo> <mrow> <mn>0.001</mn> <mo>,</mo> <mn>0.002</mn> <mo>,</mo> <mn>0.004</mn> </mrow> </mrow> </semantics></math> was introduced. Note the effectiveness in recovering the ship images.</p> Full article ">Figure 4
<p>Comparison of the number of GFLOPs required to run a 256 × 256 pixel image in the model and the number of model parameters for <math display="inline"><semantics> <mrow> <mi>τ</mi> <mo>=</mo> <mn>0.1</mn> </mrow> </semantics></math>.</p> Full article ">Figure 5
<p>Comparison of visualizations with and without momentum at different sampling rates <math display="inline"><semantics> <mrow> <mi>τ</mi> <mo>∈</mo> <mrow> <mn>0.04</mn> <mo>,</mo> <mn>0.25</mn> </mrow> </mrow> </semantics></math>.</p> Full article ">

Figure 1
<p>The structure of the proposed algorithm.</p> Full article ">Figure 2
<p>The total priority interdependent maps.</p> Full article ">

Figure 1
<p>Multi-microgrid island operation diagram.</p> Full article ">Figure 2
<p>Schematic diagram of bi-level optimization decision-making model for islanded microgrid equipped with shared energy storage.</p> Full article ">Figure 3
<p>Improved grey wolf algorithm flow chart.</p> Full article ">Figure 4
<p>ADMM bargaining model flow chart.</p> Full article ">Figure 5
<p>Output curve of each main body of microgrid I.</p> Full article ">Figure 6
<p>Microgrid I load curve after optimization and adjustment.</p> Full article ">Figure 7
<p>Microgrid I electric energy transaction diagram.</p> Full article ">Figure 8
<p>The output curve of each main body of microgrid II.</p> Full article ">Figure 9
<p>Microgrid II load optimization adjustment curve diagram.</p> Full article ">Figure 10
<p>Microgrid II energy trading diagram.</p> Full article ">Figure 11
<p>The output curve of each main body of the Microgrid III.</p> Full article ">Figure 12
<p>Microgrid III load optimization adjustment curve diagram.</p> Full article ">Figure 13
<p>Microgrid III electric energy transaction diagram.</p> Full article ">Figure 14
<p>Microgrid I energy transaction optimization results.</p> Full article ">Figure 15
<p>Microgrid II energy transaction optimization results.</p> Full article ">Figure 16
<p>Microgrid III energy transaction optimization results.</p> Full article ">Figure 17
<p>Charging and discharging power and power state of shared energy storage power station.</p> Full article ">

Figure 1
<p>The exploratory technology used to assess geo-environmental conditions within a working face.</p> Full article ">Figure 2
<p>The schematic diagram of mesh discretization for electromagnetic wave tomography.</p> Full article ">Figure 3
<p>Flow chart of the proposed MPGA-SIRT program.</p> Full article ">Figure 4
<p>Distribution diagram of the model construction.</p> Full article ">Figure 5
<p>Evolution curves of objective function f obtained based on different reconstruction models. (<b>a</b>) Evolution curve of objective function inversion based on the SIRT algorithm. (<b>b</b>) Evolution curve of objective function inversion based on the SGA-SIRT hybrid intelligent optimization algorithm. (<b>c</b>) Evolution curve of objective function inversion based on the MPGA-SIRT hybrid intelligent optimization algorithm.</p> Full article ">Figure 5 Cont.
<p>Evolution curves of objective function f obtained based on different reconstruction models. (<b>a</b>) Evolution curve of objective function inversion based on the SIRT algorithm. (<b>b</b>) Evolution curve of objective function inversion based on the SGA-SIRT hybrid intelligent optimization algorithm. (<b>c</b>) Evolution curve of objective function inversion based on the MPGA-SIRT hybrid intelligent optimization algorithm.</p> Full article ">Figure 6
<p>Tomography inversion results obtained using different reconstruction models. (<b>a</b>) Tomography inversion result obtained via the SIRT algorithm. (<b>b</b>) Tomography inversion result obtained via the SGA-SIRT algorithm. (<b>c</b>) Tomography inversion result obtained via the MPGA-SIRT algorithm.</p> Full article ">Figure 7
<p>Evolution curves of objective function f obtained based on different reconstruction models with repeated tests. (<b>a</b>) Evolution curves of objective function based on SIRT with repeated tests. (<b>b</b>) Evolution curves of objective function based on SGA-SIRT with repeated tests. (<b>c</b>) Evolution curves of objective function based on MPGA-SIRT with repeated tests.</p> Full article ">Figure 7 Cont.
<p>Evolution curves of objective function f obtained based on different reconstruction models with repeated tests. (<b>a</b>) Evolution curves of objective function based on SIRT with repeated tests. (<b>b</b>) Evolution curves of objective function based on SGA-SIRT with repeated tests. (<b>c</b>) Evolution curves of objective function based on MPGA-SIRT with repeated tests.</p> Full article ">Figure 8
<p>Convergence results of objective function <span class="html-italic">f</span> obtained based on different reconstruction models with repeated tests.</p> Full article ">Figure 9
<p>The distribution diagram of the 8208 working face survey area.</p> Full article ">Figure 10
<p>Evolution curves of objective function obtained based on different reconstruction models for 8208 working face. (<b>a</b>) Evolution curve of objective function inversion based on SIRT algorithm. (<b>b</b>) Evolution curve of objective function inversion based on SGA-SIRT hybrid intelligent optimization algorithm. (<b>c</b>) Evolution curve of objective function inversion based on MPGA-SIRT hybrid intelligent optimization algorithm.</p> Full article ">Figure 10 Cont.
<p>Evolution curves of objective function obtained based on different reconstruction models for 8208 working face. (<b>a</b>) Evolution curve of objective function inversion based on SIRT algorithm. (<b>b</b>) Evolution curve of objective function inversion based on SGA-SIRT hybrid intelligent optimization algorithm. (<b>c</b>) Evolution curve of objective function inversion based on MPGA-SIRT hybrid intelligent optimization algorithm.</p> Full article ">Figure 11
<p>Tomography inversion results of the 8208 working face obtained using different reconstruction models. (<b>a</b>) Tomography inversion result obtained using the SIRT algorithm. (<b>b</b>) Tomography inversion result obtained using the SGA-SIRT algorithm. (<b>c</b>) Tomography inversion result obtained using the MPGA-SIRT algorithm.</p> Full article ">Figure 12
<p>Evolution curves of objective function <span class="html-italic">f</span> obtained based on different reconstruction models with repeated tests for 8208 working face. (<b>a</b>) Evolution curves of objective function based on SIRT with repeated tests. (<b>b</b>) Evolution curves of objective function based on SGA-SIRT with repeated tests. (<b>c</b>) Evolution curves of objective function based on MPGA-SIRT with repeated tests.</p> Full article ">Figure 12 Cont.
<p>Evolution curves of objective function <span class="html-italic">f</span> obtained based on different reconstruction models with repeated tests for 8208 working face. (<b>a</b>) Evolution curves of objective function based on SIRT with repeated tests. (<b>b</b>) Evolution curves of objective function based on SGA-SIRT with repeated tests. (<b>c</b>) Evolution curves of objective function based on MPGA-SIRT with repeated tests.</p> Full article ">Figure 13
<p>Convergence results of objective function <span class="html-italic">f</span> obtained based on different reconstruction models with repeated tests for 8208 working face.</p> Full article ">

Figure 1
<p>TIM components.</p> Full article ">Figure 2
<p>Failure tree.</p> Full article ">Figure 3
<p>Topology of a recurrent neural network.</p> Full article ">Figure 4
<p>Topology of a NARX neural network.</p> Full article ">Figure 5
<p>ROC curve.</p> Full article ">Figure 6
<p>Confusion matrix for multiclass classification.</p> Full article ">Figure 7
<p>Process flowchart.</p> Full article ">Figure 8
<p>Test bench.</p> Full article ">Figure 9
<p>Three-phase induction motor.</p> Full article ">Figure 10
<p>Current sensor.</p> Full article ">Figure 11
<p>Signal at the output of the sensor.</p> Full article ">Figure 12
<p>Current conditioning circuit.</p> Full article ">Figure 13
<p>Current conditioning board.</p> Full article ">Figure 14
<p>Sinusoidal waveform with offset value.</p> Full article ">Figure 15
<p>Vibration accelerometer sensor.</p> Full article ">Figure 16
<p>Temperature sensor.</p> Full article ">Figure 17
<p>NI USB 6008.</p> Full article ">Figure 18
<p>LabVIEW block diagram.</p> Full article ">Figure 19
<p>NARX neural network.</p> Full article ">Figure 20
<p>Sensors installed in the motor.</p> Full article ">Figure 21
<p>Vibration signal in the time domain.</p> Full article ">Figure 22
<p>Current signal in the time domain.</p> Full article ">Figure 23
<p>Vibration signal in the frequency domain.</p> Full article ">Figure 24
<p>Current signal in the frequency domain.</p> Full article ">Figure 25
<p>Signal of motor temperature under good operating conditions.</p> Full article ">Figure 26
<p>Installation of mass for unbalancing.</p> Full article ">Figure 27
<p>Vibration signal in the time domain.</p> Full article ">Figure 28
<p>Vibration signal in the frequency domain.</p> Full article ">Figure 29
<p>Current signal in the time domain.</p> Full article ">Figure 30
<p>Current signal in the frequency domain.</p> Full article ">Figure 31
<p>Temperature signal for the unbalanced motor.</p> Full article ">Figure 32
<p>Failure occurrence frequencies for bearings 6203–2z.</p> Full article ">Figure 33
<p>Failure occurrence frequencies for bearings 6204–2z.</p> Full article ">Figure 34
<p>Bearings with defects 6203–2z/6204–2z.</p> Full article ">Figure 35
<p>Vibration signal in the time domain.</p> Full article ">Figure 36
<p>Vibration signal in the frequency domain.</p> Full article ">Figure 37
<p>Current signal in the time domain.</p> Full article ">Figure 38
<p>Current signal in the frequency domain.</p> Full article ">Figure 39
<p>Temperature signal of motor bearing with defect.</p> Full article ">Figure 40
<p>Bank of resistors for current unbalance.</p> Full article ">Figure 41
<p>Vibration signal in the time domain.</p> Full article ">Figure 42
<p>Vibration signal in the frequency domain.</p> Full article ">Figure 43
<p>Current signal in the time domain—Phase 1.</p> Full article ">Figure 44
<p>Current signal in the frequency domain—Phase 1.</p> Full article ">Figure 45
<p>Current signal in the time domain—Phase 2.</p> Full article ">Figure 46
<p>Current signal in the frequency domain—Phase 2.</p> Full article ">Figure 47
<p>Current signal in the time domain—Phase 3.</p> Full article ">Figure 48
<p>Current signal in the frequency domain—Phase 3.</p> Full article ">Figure 49
<p>Temperature signal for phase unbalanced motor.</p> Full article ">Figure 50
<p>Standard training ROC curve.</p> Full article ">Figure 51
<p>Standard training confusion matrix.</p> Full article ">Figure 52
<p>Failures classified in standard training.</p> Full article ">Figure 53
<p>ROC curve of the motor without defect test set.</p> Full article ">Figure 54
<p>Confusion matrix of the ‘Motor without defect’ test set.</p> Full article ">Figure 55
<p>Number of failures classified in the ‘Motor without defect’ test set.</p> Full article ">Figure 56
<p>ROC curve of the defect unbalanced test set.</p> Full article ">Figure 57
<p>Confusion matrix of the ‘Defect unbalance’ test set.</p> Full article ">Figure 58
<p>Number of failures classified in the ‘Defect unbalance’ test set.</p> Full article ">Figure 59
<p>ROC curve of the faulty bearings test set.</p> Full article ">Figure 60
<p>Confusion matrix for defective bearings.</p> Full article ">Figure 61
<p>Classified failures for defective bearings.</p> Full article ">Figure 62
<p>ROC curve for defective stator.</p> Full article ">Figure 63
<p>Confusion matrix for the defective stator.</p> Full article ">Figure 64
<p>Faults classified for defective stator.</p> Full article ">

Figure 1
<p>Conceptual framework of smart building integration into a smart city [<a href="#B5-sustainability-16-08032" class="html-bibr">5</a>].</p> Full article ">Figure 2
<p>Integration of LLMs within AI subfields (adopted from [<a href="#B103-sustainability-16-08032" class="html-bibr">103</a>]).</p> Full article ">Figure 3
<p>Open AI ChatGPT-3 model application.</p> Full article ">Figure 4
<p>Google Bard model application.</p> Full article ">Figure 5
<p>Round 1 agreement levels for the smart building service factors.</p> Full article ">Figure 6
<p>Round 2 agreement level for the smart building services factors.</p> Full article ">Figure 7
<p>Smart city infrastructure domain analysis responses from Rounds 1 and 2.</p> Full article ">Figure 8
<p>The overview of case studies’ integration scores.</p> Full article ">

Figure 1
<p>Difference between semi-analytical and numerical results: <math display="inline"><semantics> <mrow> <msub> <mi>ϵ</mi> <mi>w</mi> </msub> <mo>=</mo> <mrow> <mo>|</mo> <msub> <mi>w</mi> <mrow> <mi>n</mi> <mi>u</mi> <mi>m</mi> <mi>e</mi> <mi>r</mi> <mi>i</mi> <mi>c</mi> <mi>a</mi> <mi>l</mi> </mrow> </msub> <mo>−</mo> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>|</mo> </mrow> </mrow> </semantics></math> for the initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.45</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.5</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>; <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>1</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD27-processes-12-01977" class="html-disp-formula">27</a>) and (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>).</p> Full article ">Figure 2
<p>The function <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>1</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD27-processes-12-01977" class="html-disp-formula">27</a>), (<a href="#FD28-processes-12-01977" class="html-disp-formula">28</a>) and (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.45</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.5</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dotted black line) and numerical results (solid green line), respectively.</p> Full article ">Figure 3
<p>The functions <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <msub> <mover accent="true"> <mi>x</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>y</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>z</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>∈</mo> <msub> <mi mathvariant="script">CFS</mi> <mn>1</mn> </msub> </mrow> </semantics></math> using Equation (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.45</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.5</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dashing black line) and numerical results (solid color line: green line for <math display="inline"><semantics> <mrow> <mi>x</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, red line for <math display="inline"><semantics> <mrow> <mi>y</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, blue line for <math display="inline"><semantics> <mrow> <mi>z</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>), respectively.</p> Full article ">Figure 4
<p>Difference between semi-analytical and numerical results: <math display="inline"><semantics> <mrow> <msub> <mi>ϵ</mi> <mi>w</mi> </msub> <mo>=</mo> <mrow> <mo>|</mo> <msub> <mi>w</mi> <mrow> <mi>n</mi> <mi>u</mi> <mi>m</mi> <mi>e</mi> <mi>r</mi> <mi>i</mi> <mi>c</mi> <mi>a</mi> <mi>l</mi> </mrow> </msub> <mo>−</mo> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>|</mo> </mrow> </mrow> </semantics></math> for the initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.65</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>; <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>2</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD38-processes-12-01977" class="html-disp-formula">38</a>) and (<a href="#FD55-processes-12-01977" class="html-disp-formula">A4</a>).</p> Full article ">Figure 5
<p>The function <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>2</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD38-processes-12-01977" class="html-disp-formula">38</a>), (<a href="#FD39-processes-12-01977" class="html-disp-formula">39</a>) and (<a href="#FD55-processes-12-01977" class="html-disp-formula">A4</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.65</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dotted black line) and numerical results (solid green line), respectively.</p> Full article ">Figure 6
<p>The functions <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <msub> <mover accent="true"> <mi>x</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>y</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>z</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>∈</mo> <msub> <mi mathvariant="script">CFS</mi> <mn>2</mn> </msub> </mrow> </semantics></math> using Equation (<a href="#FD55-processes-12-01977" class="html-disp-formula">A4</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.65</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mn>0.75</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dashing black line) and numerical results (solid color line: green line for <math display="inline"><semantics> <mrow> <mi>x</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, red line for <math display="inline"><semantics> <mrow> <mi>y</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, blue line for <math display="inline"><semantics> <mrow> <mi>z</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>), respectively.</p> Full article ">Figure 7
<p>Difference between semi-analytical and numerical results: <math display="inline"><semantics> <mrow> <msub> <mi>ϵ</mi> <mi>w</mi> </msub> <mo>=</mo> <mrow> <mo>|</mo> <msub> <mi>w</mi> <mrow> <mi>n</mi> <mi>u</mi> <mi>m</mi> <mi>e</mi> <mi>r</mi> <mi>i</mi> <mi>c</mi> <mi>a</mi> <mi>l</mi> </mrow> </msub> <mo>−</mo> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>|</mo> </mrow> </mrow> </semantics></math> for the initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.450</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.25</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>16</mn> </mrow> </semantics></math>; <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD47-processes-12-01977" class="html-disp-formula">47</a>) and (<a href="#FD56-processes-12-01977" class="html-disp-formula">A5</a>).</p> Full article ">Figure 8
<p>The function <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD47-processes-12-01977" class="html-disp-formula">47</a>), (<a href="#FD48-processes-12-01977" class="html-disp-formula">48</a>) and (<a href="#FD56-processes-12-01977" class="html-disp-formula">A5</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.450</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.25</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dotted black line) and numerical results (solid green line), respectively.</p> Full article ">Figure 9
<p>The functions <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <msub> <mover accent="true"> <mi>x</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>y</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>z</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>∈</mo> <msub> <mi mathvariant="script">CFS</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equation (<a href="#FD56-processes-12-01977" class="html-disp-formula">A5</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.55</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.25</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mo>−</mo> <mn>0.450</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.25</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>16</mn> </mrow> </semantics></math>: OPIM solution (dashing black line) and numerical results (solid color line: green line for <math display="inline"><semantics> <mrow> <mi>x</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, red line for <math display="inline"><semantics> <mrow> <mi>y</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, blue line for <math display="inline"><semantics> <mrow> <mi>z</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>), respectively.</p> Full article ">Figure 10
<p>Difference between semi-analytical and numerical results: <math display="inline"><semantics> <mrow> <msub> <mi>ϵ</mi> <mi>w</mi> </msub> <mo>=</mo> <mrow> <mo>|</mo> <msub> <mi>w</mi> <mrow> <mi>n</mi> <mi>u</mi> <mi>m</mi> <mi>e</mi> <mi>r</mi> <mi>i</mi> <mi>c</mi> <mi>a</mi> <mi>l</mi> </mrow> </msub> <mo>−</mo> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>|</mo> </mrow> </mrow> </semantics></math> for the initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.95</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.750</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.45</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>16</mn> </mrow> </semantics></math>; <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD47-processes-12-01977" class="html-disp-formula">47</a>) and (<a href="#FD57-processes-12-01977" class="html-disp-formula">A6</a>).</p> Full article ">Figure 11
<p>The function <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>w</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>∈</mo> <msub> <mi mathvariant="script">SA</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD47-processes-12-01977" class="html-disp-formula">47</a>), (<a href="#FD48-processes-12-01977" class="html-disp-formula">48</a>) and (<a href="#FD57-processes-12-01977" class="html-disp-formula">A6</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.95</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.750</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.45</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>23</mn> </mrow> </semantics></math>: OPIM solution (dotted black line) and numerical results (solid green line), respectively.</p> Full article ">Figure 12
<p>The functions <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <msub> <mover accent="true"> <mi>x</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>y</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>,</mo> <msub> <mover accent="true"> <mi>z</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>∈</mo> <msub> <mi mathvariant="script">CFS</mi> <mn>3</mn> </msub> </mrow> </semantics></math> using Equations (<a href="#FD9-processes-12-01977" class="html-disp-formula">9</a>) and (<a href="#FD57-processes-12-01977" class="html-disp-formula">A6</a>) for initial data: <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.85</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.95</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mn>0</mn> </msub> <mo>=</mo> <mn>0.35</mn> </mrow> </semantics></math>, physical parameters: <math display="inline"><semantics> <mrow> <mi>k</mi> <mo>=</mo> <mn>0.750</mn> </mrow> </semantics></math>, <math display="inline"><semantics> <mrow> <mi>l</mi> <mo>=</mo> <mo>−</mo> <mn>0.45</mn> </mrow> </semantics></math> and index <math display="inline"><semantics> <mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mn>16</mn> </mrow> </semantics></math>: OPIM solution (dashing black line) and numerical results (solid color line: green line for <math display="inline"><semantics> <mrow> <mi>x</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, red line for <math display="inline"><semantics> <mrow> <mi>y</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>, blue line for <math display="inline"><semantics> <mrow> <mi>z</mi> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </semantics></math>), respectively.</p> Full article ">Figure 13
<p>Approximate analytical solution <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>x</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> of the Equation (<a href="#FD1-processes-12-01977" class="html-disp-formula">1</a>) using Equation (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>), the iterative solution <math display="inline"><semantics> <mrow> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>t</mi> <mi>e</mi> <mi>r</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> using Equation (<a href="#FD51-processes-12-01977" class="html-disp-formula">51</a>) and the corresponding numerical ones: OPIM solution (dashing black line), iterative solution (dotted red line) and numerical results (solid green line), respectively.</p> Full article ">Figure 14
<p>Approximate analytical solution <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>y</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> of Equation (<a href="#FD1-processes-12-01977" class="html-disp-formula">1</a>) using Equation (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>), the iterative solution <math display="inline"><semantics> <mrow> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>t</mi> <mi>e</mi> <mi>r</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> using Equation (<a href="#FD51-processes-12-01977" class="html-disp-formula">51</a>) and the corresponding numerical ones: OPIM solution (dashing black line), iterative solution (dotted red line) and numerical results (solid magenta line), respectively.</p> Full article ">Figure 15
<p>Approximate analytical solution <math display="inline"><semantics> <mrow> <msub> <mover accent="true"> <mi>z</mi> <mo stretchy="false">¯</mo> </mover> <mrow> <mi>O</mi> <mi>P</mi> <mi>I</mi> <mi>M</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> of Equation (<a href="#FD1-processes-12-01977" class="html-disp-formula">1</a>) using Equation (<a href="#FD54-processes-12-01977" class="html-disp-formula">A3</a>), the iterative solution <math display="inline"><semantics> <mrow> <msub> <mi>z</mi> <mrow> <mi>i</mi> <mi>t</mi> <mi>e</mi> <mi>r</mi> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> using Equation (<a href="#FD51-processes-12-01977" class="html-disp-formula">51</a>) and the corresponding numerical ones: OPIM solution (dashing black line), iterative solution (dotted red line) and numerical results (solid blue line), respectively.</p> Full article ">

Figure 1
<p>Delivery sketch map.</p> Full article ">Figure 2
<p>Time satisfaction graph.</p> Full article ">Figure 3
<p>Satisfaction rate of material delivery volume.</p> Full article ">Figure 4
<p>Flowchart of DBSCAN algorithm.</p> Full article ">Figure 5
<p>Flowchart of ABC algorithm.</p> Full article ">Figure 6
<p>Encoding diagram.</p> Full article ">Figure 7
<p>Diagram for neighborhood search technique.</p> Full article ">Figure 8
<p>Decoding diagram.</p> Full article ">Figure 9
<p>Basic probability graph.</p> Full article ">Figure 10
<p>Adaptive probability graph.</p> Full article ">Figure 11
<p>Customer clustering results for UAV delivery.</p> Full article ">Figure 12
<p>Vehicle delivery path solved by genetic algorithm.</p> Full article ">Figure 13
<p>Vehicle delivery path solved by artificial bee colony algorithm.</p> Full article ">Figure 14
<p>Comparison between genetic algorithm and artificial bee colony algorithm for optimizing vehicle path iteration.</p> Full article ">Figure 15
<p>Path optimization of three different classes of UAV delivery customers using genetic algorithm.</p> Full article ">Figure 16
<p>Path optimization of three different classes of UAV delivery to customers using artificial bee colony algorithm.</p> Full article ">Figure 17
<p>Comparison of iterative solutions between artificial bee colony algorithm and genetic algorithm for all classes of UAV customers.</p> Full article ">Figure 18
<p>Flowchart of improved bee colony algorithm.</p> Full article ">Figure 19
<p>Improved bee colony algorithm for path optimization.</p> Full article ">Figure 20
<p>Comparison of iterative optimization curves for solving vehicle paths.</p> Full article ">Figure 21
<p>Solving path optimization for three different classes of UAV delivery customers using the improved bee colony algorithm.</p> Full article ">Figure 22
<p>Comparison chart of iterative optimization curves between improved bee colony algorithm and artificial bee colony algorithm for solving all classes of UAV customers.</p> Full article ">

Figure 1
<p>Taxonomy of video quality analysis methodologies.</p> Full article ">Figure 2
<p>Conceptual overview of the main contributions of this paper.</p> Full article ">Figure 3
<p>Software architecture of the proposed drone simulator system.</p> Full article ">Figure 4
<p>Snapshots of the simulator environment, showing the elements of the standardised test environment.</p> Full article ">Figure 5
<p>Interface of the QGroundControl application.</p> Full article ">Figure 6
<p>Video quality scores obtained by seven operators.</p> Full article ">Figure 7
<p>Main interface of the performance analysis tool, featuring on the right side a number of performance metrics and on the left side a top-down view of the standardised simulation environment, showing the locations of the different enemies (blue dots), the enemy camp (red square), and the drone trajectory (blue line).</p> Full article ">Figure 8
<p>Expert analysis panel of the performance analysis tool. The user can select any of the 60 recorded time-signals on the right to better understand the composition of the performance score. Here, the graph shows the <span class="html-italic">X</span>-axis component of the drone velocity, as measured by its on-board GPS system.</p> Full article ">Figure 9
<p>Expert analysis panel of the performance analysis tool. The user can select any of the 60 recorded time-signals on the right to better understand the composition of the performance score. Here, the graph shows the <span class="html-italic">Z</span>-axis component of the drone vibrations.</p> Full article ">Figure 10
<p>Degradation of performance due to increasing wind speed. Each line represents the performance score of an individual pilot across various wind speeds. The figure shows that good pilots manage to keep a consistent performance level, whereas bad pilots see their performance reduced.</p> Full article ">Figure 11
<p>Degradation of performance due to auditive disturbances level. The figure shows that military pilots (blue line) handle auditive disturbances very well, whereas civilian pilots tend to have their performance reduced when subjected to auditive disturbances.</p> Full article ">Figure 12
<p>Degradation of performance due to a priori stress level. No clear correlation between the a priori stress level and the pilot flight performance could be established [<a href="#B92-drones-08-00482" class="html-bibr">92</a>].</p> Full article ">Figure 13
<p>Degradation of performance due to pilot experience. The figure shows that training drastically improves performance (red line), but the training should be specific to the type of drone, as training on fixed wing drones (blue line) will not help much for increasing the performance on quadrotors.</p> Full article ">Figure 14
<p>Convergence of the accuracy and loss of the ADAM pilot skill classifier [<a href="#B57-drones-08-00482" class="html-bibr">57</a>].</p> Full article ">Figure 15
<p>Co-pilot classifier performance [<a href="#B57-drones-08-00482" class="html-bibr">57</a>].</p> Full article ">Figure 16
<p>Drone trajectory generation validation. (<b>a</b>) Evolution of the <math display="inline"><semantics> <msub> <mi>ϕ</mi> <mi>p</mi> </msub> </semantics></math> criterion. (<b>b</b>) Evolution of the <math display="inline"><semantics> <msub> <mi>ϕ</mi> <mi>d</mi> </msub> </semantics></math> criterion. (<b>c</b>) Evolution of the <math display="inline"><semantics> <msub> <mi>ϕ</mi> <mi>t</mi> </msub> </semantics></math> criterion. (<b>d</b>) Scan completeness evolution. (<b>e</b>) Drone trajectory.</p> Full article ">Figure 17
<p>Graphical user interface of the drone mission preparation tool. (<b>a</b>) Interface of the drone mission preparation tool, enabling the operator to select the available drones and pilots and the type of mission. The system then calculates the optimal drone and pilot for the given mission and presents this information to the user. (<b>b</b>) Details of the calculation of the optimal resource allocation. The optimizer uses stored capability profiles for drones and pilots for different missions and experience levels of the different pilots with all the drones to propose an optimal allocation.</p> Full article ">

Figure 1
<p>Circular interpolation based on relative coordinate system.</p> Full article ">Figure 2
<p>Trapezoidal speed planning.</p> Full article ">Figure 3
<p>S-shaped speed planning.</p> Full article ">Figure 4
<p>RTPPSO algorithm flow chart.</p> Full article ">Figure 5
<p>Machine arm motion illustration.</p> Full article ">Figure 6
<p>Comparison of trapezoidal curve and S-curve.</p> Full article ">Figure 7
<p>Velocity curve of the first iteration.</p> Full article ">Figure 8
<p>Velocity curve of global optimal solution.</p> Full article ">Figure 9
<p>Fitness learning curve.</p> Full article ">

Figure 1
<p>Plants implementing ILC strategies with state estimators.</p> Full article ">Figure 2
<p>The velocity states of motors with no processing when noise variances are 0.05.</p> Full article ">Figure 3
<p>The velocity states of motors with the time-domain compensation when noise variances are 0.05.</p> Full article ">Figure 4
<p>The velocity states of motors with the proposed estimator when noise variances are 0.05.</p> Full article ">Figure 5
<p>The inputs emitted by controllers and corresponding outputs with no processing when noise variances are 0.05.</p> Full article ">Figure 6
<p>The inputs emitted by controllers and corresponding outputs with the time-domain compensation when noise variances are 0.05.</p> Full article ">Figure 7
<p>The inputs emitted by controllers and corresponding outputs with the proposed estimator when noise variances are 0.05.</p> Full article ">Figure 8
<p>The velocity states of motors with no processing when noise variances are 0.15.</p> Full article ">Figure 9
<p>The velocity states of motors with the time-domain compensation when noise variances are 0.15.</p> Full article ">Figure 10
<p>The velocity states of motors with the proposed estimator when noise variances are 0.15.</p> Full article ">Figure 11
<p>The inputs emitted by controllers and corresponding outputs with no processing when noise variances are 0.15.</p> Full article ">Figure 12
<p>The inputs emitted by controllers and corresponding outputs with the time-domain compensation when noise variances are 0.15.</p> Full article ">Figure 13
<p>The inputs emitted by controllers and corresponding outputs with the proposed estimator when noise variances are 0.15.</p> Full article ">Figure 14
<p>The convergence of mean absolute errors of velocity states of motors when noise variances are 0.15.</p> Full article ">Figure 15
<p>The convergence of mean absolute errors of inputs emitted by controllers when noise variances are 0.15.</p> Full article ">Figure 16
<p>The convergence of mean absolute errors of system output when noise variances are 0.15.</p> Full article ">

Figure 1
<p>The logic diagram showing the novelty and advantages of the proposed method.</p> Full article ">Figure 2
<p>The relationship between the four coordinate systems.</p> Full article ">Figure 3
<p>Position shift phenomenon due to distortion.</p> Full article ">Figure 4
<p>Relationship of coordinate transformation in camera calibration.</p> Full article ">Figure 5
<p>Schematic diagram of convex lens imaging of light.</p> Full article ">Figure 6
<p>The reverse learning strategy for the convex lens imaging technique.</p> Full article ">Figure 7
<p>Flowchart of the optimized camera calibration method using the CLI-WPP.</p> Full article ">Figure 8
<p>Calibration plate image acquisition.</p> Full article ">Figure 9
<p>The 3D model diagram of the external parameters of the camera.</p> Full article ">Figure 10
<p>Binocular camera reprojection error graph. The horizontal coordinates of the figure indicate the 30 images used for left and right target timing, and the vertical coordinates indicate the value of the reprojection error.</p> Full article ">Figure 11
<p>The reprojection error distribution of SA.</p> Full article ">Figure 12
<p>The reprojection error distribution of Zhang’s calibration method.</p> Full article ">Figure 13
<p>The reprojection error distribution of PSO.</p> Full article ">Figure 14
<p>The reprojection error distribution of the SSA.</p> Full article ">Figure 15
<p>The reprojection error distribution of WPP.</p> Full article ">Figure 16
<p>The reprojection error distribution of the CLI-WPP.</p> Full article ">Figure 17
<p>The objective value optimization process.</p> Full article ">Figure 18
<p>Average calibration results under different levels of noise intensity.</p> Full article ">