CN116863106A - Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm - Google Patents
Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm Download PDFInfo
- Publication number
- CN116863106A CN116863106A CN202310712636.8A CN202310712636A CN116863106A CN 116863106 A CN116863106 A CN 116863106A CN 202310712636 A CN202310712636 A CN 202310712636A CN 116863106 A CN116863106 A CN 116863106A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- prey
- gastrointestinal tract
- jackal
- jin chai
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 49
- 210000001035 gastrointestinal tract Anatomy 0.000 title claims abstract description 43
- 239000002775 capsule Substances 0.000 title claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 28
- 241000282421 Canidae Species 0.000 claims abstract description 38
- 230000000739 chaotic effect Effects 0.000 claims abstract description 26
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000003384 imaging method Methods 0.000 claims abstract description 6
- 239000002131 composite material Substances 0.000 claims abstract description 5
- 230000002068 genetic effect Effects 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 7
- 208000027697 autoimmune lymphoproliferative syndrome due to CTLA4 haploinsuffiency Diseases 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 3
- 239000010931 gold Substances 0.000 claims description 3
- 229910052737 gold Inorganic materials 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 230000004936 stimulating effect Effects 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 abstract description 6
- 238000000605 extraction Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 238000004088 simulation Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 244000025352 Artocarpus heterophyllus Species 0.000 description 5
- 235000008725 Artocarpus heterophyllus Nutrition 0.000 description 5
- 230000035772 mutation Effects 0.000 description 4
- 241000282461 Canis lupus Species 0.000 description 3
- 238000013142 basic testing Methods 0.000 description 3
- 235000003642 hunger Nutrition 0.000 description 3
- 210000003097 mucus Anatomy 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 241001529936 Murinae Species 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 210000001156 gastric mucosa Anatomy 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 230000003313 weakening effect Effects 0.000 description 2
- 241000958587 Canis aureus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/003—Navigation within 3D models or images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computer Graphics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Hardware Design (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a capsule robot gastrointestinal tract path planning method based on a self-adaptive variation Jin Chai algorithm, which comprises the steps of performing image preprocessing and SIFT feature point extraction based on complex and changeable surface environments of the gastrointestinal tract, and precisely matching image feature points by adopting a quick nearest neighbor search algorithm based on local feature topological constraint; the projection error of an image imaging plane is weakened by adopting an LM algorithm, the actual condition in the gastrointestinal tract is three-dimensionally reconstructed by utilizing a Poisson surface reconstruction method, the gastrointestinal tract live condition after reconstruction is obtained, and an adaptive variation Jin Chai algorithm is introduced; and a Henon chaotic mapping theory, a nonlinear composite adaptive convergence factor random decision strategy and a genetic algorithm variation strategy are respectively introduced, so that the convergence accuracy and the convergence speed of the jackal algorithm are improved, the algorithm is prevented from being trapped into local optimum, the optimized path planning of the capsule robot is realized, the complex environment of the gastrointestinal tract is dealt with, and the guarantee is provided for the high-precision control and the gastrointestinal tract inspection of the capsule robot.
Description
Technical Field
The invention relates to a gastrointestinal tract path planning method, in particular to a capsule robot gastrointestinal tract path planning method based on a self-adaptive variation Jin Chai algorithm, and belongs to the technical field of path optimization of novel medical instruments.
Background
In recent years, with a high rate of life pace and increasing working pressure, the gastrointestinal tract of most people is in sub-health. With the continuous development and perfection of national policies, novel medical instruments such as capsule robots and the like are continuously developed, are widely applied to gastrointestinal tract examination, and effectively reduce pain and uncomfortable feeling in the whole examination process.
However, the working environment of the capsule robot is extremely complex, and the rugged and changeable working environment formed by the factors of mucus, folds and the like on the surface of the gastrointestinal tract brings great difficulty to the active control and the full-range inspection of the capsule robot. Therefore, for the complex environment of the gastrointestinal tract, it is highly necessary to find an optimal path for the capsule robot to meet the requirements.
In recent years, intelligent optimization algorithms have been widely used for path planning problems. Among them, nitish Chopra and Muhammad Mohsin Ansari proposed a Cochinal optimization algorithm (Golden jackal optimization, GJO) in 2022, by which Jin Chai hunting behavior is simulated, and the algorithm is novel, fast and efficient. However, the algorithm itself tends to be locally optimal, and there are some problems in terms of convergence accuracy, convergence speed, and the like.
Disclosure of Invention
The invention aims to solve at least one technical problem, and provides a capsule robot gastrointestinal tract planning method based on an adaptive variation Jin Chai algorithm.
The invention realizes the above purpose through the following technical scheme: a capsule robot gastrointestinal tract path planning method based on an adaptive variation Jin Chai algorithm comprises the following steps:
firstly, because the stomach working environment where the capsule robot is located is complex and changeable, the image shot by the capsule robot shooting module has complex noise interference, such as the influence of factors of salt and pepper noise, uneven illumination, gastric mucosa mucus and the like, the acquired image is preprocessed, including bilateral filtering, image enhancement and the like;
step two, establishing a scale space of the image, and extracting feature points of the image by adopting a SIFT algorithm;
searching the feature points, and performing fine matching on the image feature points by adopting a rapid nearest neighbor searching algorithm based on local feature topological constraint;
step four, along with the continuous accumulation of image matching points and accumulated projection errors in the reconstruction process, adopting an LM algorithm to weaken the projection errors of an image imaging plane;
fifthly, carrying out three-dimensional reconstruction on the actual condition inside the gastrointestinal tract by using a poisson surface reconstruction method to obtain a reconstructed gastrointestinal tract live condition;
step six, introducing an adaptive variation Jin Chai algorithm;
and step seven, planning the running path of the capsule robot in advance according to the obtained gastrointestinal tract information.
As still further aspects of the invention: in the step six, the basic algorithm process of the Jin Chai algorithm is as follows:
the hunting process of the whole population mainly comprises three basic stages:
(1) Searching for and approximating the prey;
(2) Surrounding the prey and stimulating the prey until they stop moving;
(3) Attack prey;
J 0 ＝J min +rand×(J max -J min ) (1)
wherein: j (J) 0 Is the location of the initial Jin Chai population; rand is [0,1]Random numbers within a range; j (J) max And J min The upper and lower boundaries of the solution problem are respectively;
in the GJO algorithm, the prey matrix is expressed as:
wherein: prey is Prey matrix; j (J) i,j A j-th dimensional location for an i-th prey; n is the size of the jackal population; d is the solving dimension of the problem.
As still further aspects of the invention: in the self-adaptive variation optimization process of the Jin Chai algorithm, a target fitness function is adopted to calculate the fitness value of each jackal in the process of hunting, and the fitness value matrix is expressed as follows:
wherein: f (F) PP A fitness value matrix for the prey; f (…) is an fitness function or an objective function; wherein, the fitness value is optimal as male jackal, and the fitness value is suboptimal as female jackal.
Jin Chai is a population which searches for prey by means of self perception, and meanwhile, the escape energy of the prey can directly influence the population behavior of the jackal; e is the escape energy of the prey and can be calculated by the following formula:
E＝E 0 ×E 1 (4)
wherein E is 0 =2×rand-1 represents the initial state of prey energy, E 1 Indicating the decline of hunting energy;
wherein: t is the maximum iteration number; c 1 Is a constant and takes a value of 1.5; t is the current iteration number; throughout the iteration process E 1 Linearly decreasing from 1.5 to 0;
rl mentioned in the above formula is a random number vector based on levy distribution, expressed as:
rl＝0.05×levy(j) (6)
where levy () represents the Lev flight function, the calculation method is as follows:
wherein: mu and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
when the obtained |E| is more than or equal to 1, jin Chai population enters a search exploration stage, the male jackal wolves are responsible for leading hunting work, the female jackal wolves are responsible for following the male jackal wolves, and the population behaviors are as follows:
J 1 (t)＝J M (t)-E×|J M (t)-rl×Prey(t)| (9)
J 2 (t)＝J FM (t)-E×|J FM (t)-rl×Prey(t)| (10)
wherein: t is the current iteration number; prey (t) is the position of the Prey for the t-th iteration;J M (t),J FM (t) positions of male Jin Chai and female jackal, respectively, of the t-th iteration; j (J) 1 (t)，J 2 (t) positions of male Jin Chai and female jackfruit, respectively, after the t-th iteration update; the updated gold jackal positions after the t+1st iteration are thus obtained as follows:
when the obtained |E| < 1, the Jin Chai population enters a surrounding attack stage, and Jin Chai carries out surrounding predation on the hunting objects searched in the previous stage; the behavioral model of male and female Jin Chai at this stage is as follows:
J 1 (t)＝J M (t)-E×|rl×J M (t)-Prey(t)| (12)
J 2 (t)＝J FM (t)-E×|rl×J FM (t)-Prey(t)| (13)
the positions of male and female jackal after the t iteration are updated by the method, and the position update of jackal is still completed according to the formula (11).
As still further aspects of the invention: based on Jin Chai optimization algorithm, introducing a Henon chaotic mapping theory for an initialization stage of Jin Chai population;
the Henon chaotic mapping theory is a nonlinear theory, is generated in a two-dimensional space, is typical discrete chaotic mapping, and has the following dynamics formula:
wherein x is 0 ,y 0 The four parameters a and b determine the state of the Henon chaotic map, the state is more complex than the one-dimensional chaotic map, and when a=1.3 and b=0.4 are taken, the strong randomness of the generated chaotic sequence is ensured when the function enters the chaotic state, so that the chaotic initialization population is obtained.
As still further aspects of the invention: based on Jin Chai optimization algorithm, introducing a nonlinear composite adaptive convergence factor random decision strategy for a searching stage and a predation stage of Jin Chai population;
firstly, presetting gama=0.9, and introducing a starting threshold yz=rand, wherein a selection formula for obtaining a convergence factor is as follows:
and brings the convergence factor into a search stage and a predation stage, and changes a position update formula of the search stage into:
J 1 (t)＝ω×J M (t)-E×|J M (t)-rl×Prey(t)| (16)
J 2 (t)＝ω×J FM (t)-E×|J FM (t)-rl×Prey(t)| (17)
the location update formula for the predation phase is as follows:
J 1 (t)＝ω×J M (t)-E×|rl×J M (t)-Prey(t)| (18)
J 2 (t)＝ω×J FM (t)-E×|rl×J FM (t)-Prey(t)| (19)
the convergence factor is introduced, so that the convergence speed of the jackal algorithm can be greatly increased, the optimizing precision is improved to a great extent, and the requirements of the algorithm on global searching capability and local searching capability in different stages are supplemented.
As still further aspects of the invention: on the basis of Jin Chai optimization algorithm, a genetic algorithm variation strategy is introduced for the output stage of Jin Chai population.
The variation probability pm=0.2 is predetermined.
The method can effectively increase the diversity of solutions, thereby improving the possibility of jumping out of local extremum and leading the overall optimizing effect of the improved algorithm to be better.
The beneficial effects of the invention are as follows: based on complex and changeable surface environment of gastrointestinal tract, firstly, image preprocessing and SIFT feature point extraction are carried out, and a quick nearest neighbor search algorithm based on local feature topological constraint is adopted to carry out fine matching on the image feature points. And (3) weakening the projection error of the image imaging plane by adopting an LM algorithm, and finally, carrying out three-dimensional reconstruction on the actual condition inside the gastrointestinal tract by utilizing a Poisson surface reconstruction method to obtain the gastrointestinal tract live condition after reconstruction. An adaptive variation Jin Chai algorithm is introduced for the gastrointestinal tract live condition obtained by three-dimensional reconstruction. Based on the original algorithm, the method introduces a Henon chaotic mapping theory, a nonlinear composite adaptive convergence factor random choice strategy and a genetic algorithm variation strategy. Through the improvement, the diversity of the population is increased, the global searching capability and the local searching capability of the algorithm are balanced, the convergence accuracy and the convergence speed of the Jin Chai algorithm are effectively improved, and the algorithm is prevented from being trapped into local optimum. The path planning optimized for the capsule robot is realized through the improved Jin Chai algorithm, and the guarantee is provided for the high-precision control and gastrointestinal tract inspection of the capsule robot.
Drawings
Fig. 1 is a schematic flow chart of the present invention.
Fig. 2 is an algorithm flow chart of the adaptive mutation Jin Chai algorithm in the present invention.
FIG. 3 is a graph showing the convergence of the first test function under the adaptive mutation Jin Chai algorithm and other intelligent optimization algorithms according to an embodiment of the present invention.
FIG. 4 is a graph showing the convergence of a second test function under the adaptive mutation Jin Chai algorithm and other intelligent optimization algorithms according to an embodiment of the present invention.
FIG. 5 is a graph showing the convergence of a third test function under the adaptive mutation Jin Chai algorithm and other intelligent optimization algorithms according to an embodiment of the present invention.
FIG. 6 is a diagram of a general simulation environment in accordance with an embodiment of the present invention;
FIG. 7 is a diagram of simulation results of a common simulation environment map in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1 to 7, a capsule robot gastrointestinal tract planning method based on an adaptive variation Jin Chai algorithm comprises the following steps:
firstly, because the stomach working environment where the capsule robot is located is complex and changeable, the image shot by the capsule robot shooting module has complex noise interference, such as the influence of factors of salt and pepper noise, uneven illumination, gastric mucosa mucus and the like, the acquired image is preprocessed, including bilateral filtering, image enhancement and the like;
step two, establishing a scale space of the image, and extracting feature points of the image by adopting a SIFT algorithm;
searching the feature points, and performing fine matching on the image feature points by adopting a rapid nearest neighbor searching algorithm based on local feature topological constraint;
step four, along with the continuous accumulation of image matching points and accumulated projection errors in the reconstruction process, adopting an LM algorithm to weaken the projection errors of an image imaging plane;
fifthly, carrying out three-dimensional reconstruction on the actual condition inside the gastrointestinal tract by using a poisson surface reconstruction method to obtain a reconstructed gastrointestinal tract live condition;
step six, introducing an adaptive variation Jin Chai algorithm;
and step seven, planning the running path of the capsule robot in advance according to the obtained gastrointestinal tract information.
Example two
In addition to all the technical features in the first embodiment, the present embodiment further includes:
in the step six, the basic algorithm process of the Jin Chai algorithm is as follows:
the hunting process of the whole population mainly comprises three basic stages:
(1) Searching for and approximating the prey;
(2) Surrounding the prey and stimulating the prey until they stop moving;
(3) Attack prey;
J 0 ＝J min +rand×(J max -J min ) (1)
wherein: j (J) 0 Is the location of the initial Jin Chai population; rand is [0,1]Random numbers within a range; j (J) max And J min The upper and lower boundaries of the solution problem are respectively;
in the GJO algorithm, the prey matrix is expressed as:
wherein: prey is Prey matrix; j (J) i,j A j-th dimensional location for an i-th prey; n is the size of the jackal population; d is the solving dimension of the problem.
In the self-adaptive variation optimization process of the Jin Chai algorithm, a target fitness function is adopted to calculate the fitness value of each jackal in the process of hunting, and the fitness value matrix is expressed as follows:
wherein: f (F) PP A fitness value matrix for the prey; f (…) is an fitness function or an objective function; wherein, the fitness value is optimal as male jackal, and the fitness value is suboptimal as female jackal.
Jin Chai is a population which searches for prey by means of self perception, and meanwhile, the escape energy of the prey can directly influence the population behavior of the jackal; e is the escape energy of the prey and can be calculated by the following formula:
E＝E 0 ×E 1 (4)
wherein E is 0 ＝2×rand-1 represents the initial state of prey energy, E 1 Indicating the decline of hunting energy;
wherein: t is the maximum iteration number; c 1 Is a constant and takes a value of 1.5; t is the current iteration number; throughout the iteration process E 1 Linearly decreasing from 1.5 to 0;
rl mentioned in the above formula is a random number vector based on levy distribution, expressed as:
rl＝0.05×levy(j) (6)
where levy () represents the Lev flight function, the calculation method is as follows:
wherein: mu and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
when the obtained E is more than or equal to 1, jin Chai population enters a search exploration stage, the male jackfruit is responsible for leading hunting work, the female jackfruit is responsible for following the male jackfruit, and the population behavior is as follows:
J 1 (t)＝J M (t)-E×|J M (t)-rl×Prey(t)| (9)
J 2 (t)＝J FM (t)-E×|J FM (t)-rl×Prey(t)| (10)
wherein: t is the current iteration number; prey (t) is the position of the Prey for the t-th iteration; j (J) M (t),J FM (t) positions of male Jin Chai and female jackal, respectively, of the t-th iteration; j (J) 1 (t)，J 2 (t) positions of male Jin Chai and female jackfruit, respectively, after the t-th iteration update; thereby obtaining the t+1st iterationThe updated jackal positions after generation are as follows:
when the obtained |E| < 1, the Jin Chai population enters a surrounding attack stage, and Jin Chai carries out surrounding predation on the hunting objects searched in the previous stage; the behavioral model of male and female Jin Chai at this stage is as follows:
J 1 (t)＝J M (t)-E×|rl×J M (t)-Prey(t)| (12)
J 2 (t)＝J FM (t)-E×|rl×J FM (t)-Prey(t)| (13)
the positions of male and female jackal after the t iteration are updated by the method, and the position update of jackal is still completed according to the formula (11).
Example III
In addition to all the technical features in the first embodiment, the present embodiment further includes:
based on Jin Chai optimization algorithm, introducing a Henon chaotic mapping theory for an initialization stage of Jin Chai population;
the Henon chaotic mapping theory is a nonlinear theory, is generated in a two-dimensional space, is typical discrete chaotic mapping, and has the following dynamics formula:
wherein x is 0 ,y 0 The four parameters a and b determine the state of the Henon chaotic map, the state is more complex than the one-dimensional chaotic map, and when a=1.3 and b=0.4 are taken, the strong randomness of the generated chaotic sequence is ensured when the function enters the chaotic state, so that the chaotic initialization population is obtained.
Based on Jin Chai optimization algorithm, introducing a nonlinear composite adaptive convergence factor random decision strategy for a searching stage and a predation stage of Jin Chai population;
firstly, presetting gama=0.9, and introducing a starting threshold yz=rand, wherein a selection formula for obtaining a convergence factor is as follows:
and brings the convergence factor into a search stage and a predation stage, and changes a position update formula of the search stage into:
J 1 (t)＝ω×J M (t)-E×|J M (t)-rl×Prey(t)| (16)
J 2 (t)＝ω×J FM (t)-E×|J FM (t)-rl×Prey(t)| (17)
the location update formula for the predation phase is as follows:
J 1 (t)＝ω×J M (t)-E×|rl×J M (t)-Prey(t)| (18)
J 2 (t)＝ω×J FM (t)-E×|rl×J FM (t)-Prey(t)| (19)
the convergence factor is introduced, so that the convergence speed of the jackal algorithm can be greatly increased, the optimizing precision is improved to a great extent, and the requirements of the algorithm on global searching capability and local searching capability in different stages are supplemented.
On the basis of Jin Chai optimization algorithm, a genetic algorithm variation strategy is introduced for the output stage of Jin Chai population.
The variation probability pm=0.2 is predetermined.
The method can effectively increase the diversity of solutions, thereby improving the possibility of jumping out of local extremum and leading the overall optimizing effect of the improved algorithm to be better.
Example IV
Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm adopts basic test functionTo verify the performance of the improved algorithm, the theoretical optimum of the function being 0. The performance of the improved Jin Chai optimization algorithm was verified by comparing the improved Jin Chai algorithm with the base Jin Chai algorithm, the gray wolf optimization algorithm, the northern hawk optimization algorithm, the hunger game search algorithm, the murine intelligent optimization algorithm, and the harris hawk optimization algorithm. To ensure fairness of the test, the population number of each algorithm is set to 30, and the maximum iteration number is set to 500.
As shown in fig. 3, it can be seen that the adaptive variation Jin Chai algorithm has a great advantage over other algorithms in terms of convergence speed and convergence accuracy.
Example five
Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm adopts basic test functionTo verify the performance of the improved algorithm, the theoretical optimum of the function being 0. The performance of the improved Jin Chai optimization algorithm was verified by comparing the improved Jin Chai algorithm with the base Jin Chai algorithm, the gray wolf optimization algorithm, the northern hawk optimization algorithm, the hunger game search algorithm, the murine intelligent optimization algorithm, and the harris hawk optimization algorithm. To ensure fairness of the test, the population number of each algorithm is set to 30, and the maximum iteration number is set to 500.
As shown in fig. 4, it can be seen that the adaptive variation Jin Chai algorithm has a great advantage over other algorithms in terms of convergence speed and convergence accuracy.
Example six
Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm adopts basic test functionTo verify the performance of the improved algorithm, the theoretical optimum of the function being 1. The improved Jin Chai algorithm, the basic Jin Chai algorithm, the gray wolf optimization algorithm, the northern hawk optimization algorithm, the hunger game search algorithm and the intelligent optimization algorithm for the rat groupThe improved Jin Chai optimization algorithm performance was verified by comparison with the harris eagle optimization algorithm. To ensure fairness of the test, the population number of each algorithm is set to 30, and the maximum iteration number is set to 500.
As shown in fig. 5, it can be seen that the adaptive variation Jin Chai algorithm has a great advantage over other algorithms in terms of convergence speed and convergence accuracy.
Example seven
In order to verify the dominant machine applicability of the provided algorithm again, the invention compares and analyzes the adaptive variation Jin Chai algorithm with the basic gold algorithm under a 30 x 30 simulation environment map, as shown in fig. 6, which is the 30 x 30 simulation environment map. The simulation result after the algorithm is operated is shown in fig. 7, and according to the graph, the adaptive variation Jin Chai algorithm can obtain the optimal path length more quickly, so as to complete path planning.
Working principle: based on complex and changeable surface environment of gastrointestinal tract, image preprocessing and SIFT feature point extraction are carried out, and a quick nearest neighbor search algorithm based on local feature topological constraint is adopted to carry out fine matching on the image feature points. And (3) weakening the projection error of the image imaging plane by adopting an LM algorithm, and finally, carrying out three-dimensional reconstruction on the actual condition inside the gastrointestinal tract by utilizing a Poisson surface reconstruction method to obtain the gastrointestinal tract live condition after reconstruction.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (6)
1. The capsule robot gastrointestinal tract path planning method based on the adaptive variation Jin Chai algorithm is characterized by comprising the following steps of:
step one, preprocessing an acquired image;
step two, establishing a scale space of the image, and extracting feature points of the image by adopting a SIFT algorithm;
searching the feature points, and performing fine matching on the image feature points by adopting a rapid nearest neighbor searching algorithm based on local feature topological constraint;
step four, along with the continuous accumulation of image matching points and accumulated projection errors in the reconstruction process, adopting an LM algorithm to weaken the projection errors of an image imaging plane;
fifthly, carrying out three-dimensional reconstruction on the actual condition inside the gastrointestinal tract by using a poisson surface reconstruction method to obtain a reconstructed gastrointestinal tract live condition;
step six, introducing an adaptive variation Jin Chai algorithm;
and step seven, planning the running path of the capsule robot in advance according to the obtained gastrointestinal tract information.
2. The capsule robotic gastrointestinal tract planning method of claim 1, wherein: in the sixth step, the basic algorithm process of the Jin Chai algorithm is as follows:
the hunting process of the whole population mainly comprises three basic stages:
(1) Searching for and approximating the prey;
(2) Surrounding the prey and stimulating the prey until they stop moving;
(3) Attack prey;
J 0 ＝J min +rand×(J max -J min ) (1)
wherein: j (J) 0 Is the location of the initial Jin Chai population; rand is [0,1]Random numbers within a range; j (J) max And J min The upper and lower boundaries of the solution problem are respectively;
in the GJO algorithm, the prey matrix is expressed as:
wherein: prey is Prey matrix; j (J) i,j A j-th dimensional location for an i-th prey; n is the size of the jackal population; d is the solving dimension of the problem.
3. The capsule robotic gastrointestinal tract planning method of claim 2, wherein: in the self-adaptive variation optimization process of the Jin Chai algorithm, a target fitness function is adopted to calculate the fitness value of each jackal in the process of hunting, and the fitness value matrix is expressed as follows:
wherein: f (F) PP A fitness value matrix for the prey; f (…) is an fitness function or an objective function;
wherein, the fitness value is optimal and is used as male jackal, and the fitness value is suboptimal and is used as female jackal;
jin Chai is a population which searches for prey by means of self perception, and meanwhile, the escape energy of the prey can directly influence the population behavior of the jackal;
e is the escape energy of the prey, calculated using the following formula:
E＝E 0 ×E 1 (4)
wherein E is 0 =2×rand-1 indicates huntingInitial state of object energy, E 1 Indicating the decline of hunting energy;
wherein: t is the maximum iteration number; c 1 Is a constant and takes a value of 1.5; t is the current iteration number; throughout the iteration process E 1 Linearly decreasing from 1.5 to 0;
rl mentioned in the above formula is a random number vector based on levy distribution, expressed as:
rl＝0.05×levy(j) (6)
where levy () represents the Lev flight function, the calculation method is as follows:
wherein: mu and v are random numbers in the range of (0, 1); beta is a default constant, and the value is 1.5;
when the obtained |E| is more than or equal to 1, jin Chai population enters a search exploration stage, the male jackal wolves are responsible for leading hunting work, the female jackal wolves are responsible for following the male jackal wolves, and the population behaviors are as follows:
J 1 (t)＝J M (t)-E×|J M (t)-rl×Prey(t)| (9)
J 2 (t)＝J FM (t)-E×|J FM (t)-rl×Prey(t)| (10)
wherein: t is the current iteration number; prey (t) is the position of the Prey for the t-th iteration;
J M (t),J FM (t) positions of male Jin Chai and female jackal, respectively, of the t-th iteration;
J 1 (t)，J 2 (t)positions of male Jin Chai and female jackal after the t-th iteration update respectively;
the updated gold jackal positions after the t+1st iteration are thus obtained as follows:
when the obtained |E| < 1, the Jin Chai population enters a surrounding attack stage, and Jin Chai carries out surrounding predation on the hunting objects searched in the previous stage;
the behavioral model of male and female Jin Chai at this stage is as follows:
J 1 (t)＝J M (t)-E×|rl×J M (t)-Prey(t)| (12)
J 2 (t)＝J FM (t)-E×|rl×J FM (t)-Prey(t)| (13)
the positions of male and female jackal after the t iteration are updated by the method, and the position update of jackal is still completed according to the formula (11).
4. A capsule robotic gastrointestinal tract planning method according to claim 3, wherein: based on Jin Chai optimization algorithm, introducing a Henon chaotic mapping theory for an initialization stage of Jin Chai population;
the Henon chaotic mapping theory is a nonlinear theory, is generated in a two-dimensional space, is typical discrete chaotic mapping, and has the following dynamics formula:
wherein x is 0 ,y 0 The four parameters a and b determine the state of the Henon chaotic map, the state is more complex than the one-dimensional chaotic map, and when a=1.3 and b=0.4 are taken, the strong randomness of the generated chaotic sequence is ensured when the function enters the chaotic state, so that the chaotic initialization population is obtained.
5. A capsule robotic gastrointestinal tract planning method according to claim 3, wherein: based on Jin Chai optimization algorithm, introducing a nonlinear composite adaptive convergence factor random decision strategy for a searching stage and a predation stage of Jin Chai population;
firstly, presetting gama=0.9, and introducing a starting threshold yz=rand, wherein a selection formula for obtaining a convergence factor is as follows:
and brings the convergence factor into a search stage and a predation stage, and changes a position update formula of the search stage into:
J 1 (t)＝ω×J M (t)-E×|J M (t)-rl×Prey| (16)
J 2 (t)＝ω×J FM (t)-E×|J FM (t)-rl×Prey| (17)
the location update formula for the predation phase is as follows:
J 1 (t)＝ω×J M (t)-E×|rl×J M (t)-Prey(t)| (18)
J 2 (t)＝ω×J FM (t)-E×|rl×J FM (t)-Prey(t)| (19)
the convergence factor is introduced, so that the convergence speed of the jackal algorithm can be greatly increased, the optimizing precision is improved to a great extent, and the requirements of the algorithm on global searching capability and local searching capability in different stages are supplemented.
6. A capsule robotic gastrointestinal tract planning method according to claim 3, wherein: on the basis of Jin Chai optimization algorithm, a genetic algorithm variation strategy is introduced for the output stage of Jin Chai population.
The variation probability pm=0.2 is given in advance,
the method increases the diversity of solutions, thereby improving the possibility of jumping out of local extremum and leading the overall optimizing effect of the improved algorithm to be better.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310680041 | 2023-06-08 | ||
| CN2023106800419 | 2023-06-08 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116863106A true CN116863106A (en) | 2023-10-10 |
Family
ID=88233109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310712636.8A Pending CN116863106A (en) | 2023-06-08 | 2023-06-15 | Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116863106A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117434829A (en) * | 2023-12-21 | 2024-01-23 | 济南大学 | Aircraft main engine wheel fan PID control method based on improved Jin Chai algorithm |
-
2023
- 2023-06-15 CN CN202310712636.8A patent/CN116863106A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117434829A (en) * | 2023-12-21 | 2024-01-23 | 济南大学 | Aircraft main engine wheel fan PID control method based on improved Jin Chai algorithm |
| CN117434829B (en) * | 2023-12-21 | 2024-04-16 | 济南大学 | Aircraft main engine wheel fan PID control method based on improved Jin Chai algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111415379B (en) | Three-dimensional point cloud data registration method based on cuckoo optimization | |
| Wang et al. | An edge-weighted centroidal Voronoi tessellation model for image segmentation | |
| CN112469050B (en) | WSN three-dimensional coverage enhancement method based on improved wolf optimizer | |
| CN116863106A (en) | Capsule robot gastrointestinal tract path planning method based on adaptive variation Jin Chai algorithm | |
| CN110837891B (en) | Self-organizing mapping method and system based on SIMD (Single instruction multiple data) architecture | |
| CN114611801A (en) | Traveler problem solving method based on improved whale optimization algorithm | |
| CN108399105B (en) | Software and hardware partitioning method based on improved brainstorming algorithm | |
| CN115730743A (en) | Battlefield combat trend prediction method based on deep neural network | |
| CN114662638A (en) | Mobile robot path planning method based on improved artificial bee colony algorithm | |
| CN114841611A (en) | Method for solving job shop scheduling based on improved ocean predator algorithm | |
| CN117471919A (en) | Robot path planning method based on improved pelican optimization algorithm | |
| CN106650916B (en) | A kind of mesh segmentation method based on ant group optimization | |
| CN113222808A (en) | Face mask removing method based on generative confrontation network | |
| CN115222006A (en) | Numerical function optimization method based on improved particle swarm optimization algorithm | |
| CN116071331A (en) | Workpiece surface defect detection method based on improved SSD algorithm | |
| CN111080517B (en) | Three-dimensional point cloud splicing method based on improved butterfly optimization algorithm | |
| CN115034262A (en) | Bearing fault diagnosis method based on fusion of convolutional neural network and optimization SVM | |
| CN114998520A (en) | Three-dimensional interactive hand reconstruction method and system based on implicit expression | |
| CN110288606B (en) | Three-dimensional grid model segmentation method of extreme learning machine based on ant lion optimization | |
| CN114417947A (en) | Parallel industrial Internet of things big data clustering method based on meta-heuristic algorithm | |
| Wang et al. | Image retrieval based on fireworks algorithm optimizing convolutional neural network | |
| CN117608318B (en) | Unmanned aerial vehicle formation obstacle avoidance control method and system based on bird-like phototaxis | |
| CN111709494B (en) | Novel hybrid-optimized image stereo matching method | |
| CN117034480B (en) | Parameterized dimension reduction-based multi-type surface integrated optimization method and platform for air compressor | |
| CN113780390B (en) | Unsupervised dense matching method and system based on reconstruction mapping consistency |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |