Comparison Of Algorithms Research Articles

Construction of a Green and Low-Carbon Travel Order Prediction Model Based on Shared Bicycle Big Data

In the era of big data, traditional analysis methods are insufficient to meet the growing demand for green and low-carbon travel orders in shared bicycle systems. To address this issue, a new order demand forecasting model, named the “convolutional neural network (CNN)”—“long short-term memory (LSTM)” model (CNN-LSTM), is proposed by integrating CNN and LSTM techniques. The research further validates the spatiotemporal prediction performance of this model. The experimental results demonstrate that LSTM exhibits favorable prediction performance in terms of time feature analysis, as evidenced by the overlapping of the true value (TV) and predicted value (PV) curves. Notably, LSTM achieves an impressively low mean squared error (MSE) value of 0.0063, which is significantly lower compared to CNN (0.0082) and XGBoost (0.0074). Upon incorporating date and weather characteristics, the predictive performance improves significantly, achieving an outstanding MSE value of 0.0043. However, when it comes to spatial feature analysis, the LSTM algorithm alone proves inadequate, obtaining a MSE value of 0.0084. Thus, by employing the CNN-LSTM combination model, a lower MSE value of 0.0066 is achieved, outperforming the comparison algorithms. Overall, the CNN-LSTM model exhibits strong predictive capabilities regarding the temporal and spatial requirements of shared bicycles. This model plays a key role in accurately forecasting order demands, facilitating urban transportation planning and management, as well as guiding the planning and location of non-motorized vehicle stops.

Application of Improved Ant Colony Algorithm in Optimizing the Charging Path of Electric Vehicles

In current traffic congestion scenarios, electric vehicles (EVs) have the problem of reduced battery life and continuous decline in endurance. Therefore, this study proposes an optimization method for electric vehicle charging scheduling based onthe ant colony optimization algorithm with adaptive dynamic search (ADS-ACO), and conducts experimental verification on it. The experiment revealed that in the four benchmark functions, the research algorithm has the fastest convergence speed and can achieve convergence in most of them. In the validation of effectiveness, the optimal solution for vehicle time consumption under the ADS-ACO algorithm in the output of the algorithm with a stationary period and a remaining battery energy of 15 kW·h was 2.146 h in the regular road network. In the initial results of 15 kW·h under changes in road conditions from peak to peak periods, the total energy consumption of vehicles under the research algorithm was 4.678 kW·h and 4.656 kW·h under regular and irregular road networks, respectively. The change results were 4.509 kW·h and 4.656 kW·h, respectively. The initial results of 10 kW·h were 4.755 kW·h and 4.873 kW·h, respectively. The change results were 4.461 kW·h and 4.656 kW·h, respectively, which are lower than the comparison algorithm. In stability verification, research algorithms can find the optimal path under any conditions. The algorithm proposed in the study has been demonstrated to be highly effective and stable in electric vehicle charging path planning. It represents a novel solution for electric vehicle charging management and is expected to significantly enhance the range of electric vehicles in practical applications.

Using Deep Learning and Swarm Intelligence to Achieve Personalized English-Speaking Education

This paper presents a pioneering approach to personalized English oral education through the integration of deep learning and swarm intelligence algorithms. Leveraging deep learning techniques, our system offers precise evaluation of various aspects of spoken language, including pronunciation, fluency, and grammatical accuracy. Furthermore, we combine swarm intelligence algorithms to optimize model parameters to achieve optimal performance. We compare the proposed optimization algorithm based on swarm intelligence and its corresponding original algorithm for training comparison to test the effect of the proposed optimizer. Experimental results show that in most cases, the accuracy of the test set using the optimization algorithm based on the swarm intelligence algorithm is better than the corresponding original version, and the training results are more stable. Our experimental results demonstrate the efficacy of the proposed approach in enhancing personalized English oral education, paving the way for transformative advancements in language learning technologies.

Three-dimensional path planning with enhanced gravitational search algorithm for unmanned aerial vehicle

Abstract Path planning for the unmanned aerial vehicle (UAV) is to assist in finding the proper path, serving as a critical role in the intelligence of a UAV. In this paper, a path planning for UAV in three-dimensional environment (3D) based on enhanced gravitational search algorithm (EGSA) is put forward, taking the path length, yaw angle, pitch angle, and flight altitude as considerations of the path. Considering EGSA is easy to fall into local optimum and convergence insufficiency, two factors that are the memory of current optimal and random disturbance with chaotic levy flight are adopted during the update of particle velocity, improving the balance between exploration and exploitation for EGSA through different time-varying characteristics. With the identical cost function, EGSA is compared with seven peer algorithms, such as moth flame optimization algorithm, gravitational search algorithm, and five variants of gravitational search algorithm. The experimental results demonstrate that EGSA is superior to the seven comparison algorithms on CEC 2020 benchmark functions and the path planning method based on EGSA is more valuable than the other seven methods in diverse environments.

Reconstruction from CT truncated data based on dual-domain transformer coupled feature learning

To propose a CT truncated data reconstruction model (DDTrans) based on projection and image dualdomain Transformer coupled feature learning for reducing truncation artifacts and image structure distortion caused by insufficient field of view (FOV) in CT scanning. Transformer was adopted to build projection domain and image domain restoration models, and the long-range dependency modeling capability of the Transformer attention module was used to capture global structural features to restore the projection data information and enhance the reconstructed images. We constructed a differentiable Radon back-projection operator layer between the projection domain and image domain networks to enable end-to-end training of DDTrans. Projection consistency loss was introduced to constrain the image forwardprojection results to further improve the accuracy of image reconstruction. The experimental results with Mayo simulation data showed that for both partial truncation and interior scanning data, the proposed DDTrans method showed better performance than the comparison algorithms in removing truncation artifacts at the edges and restoring the external information of the FOV. The DDTrans method can effectively remove CT truncation artifacts to ensure accurate reconstruction of the data within the FOV and achieve approximate reconstruction of data outside the FOV.

Teaching–Learning-Based Optimization Algorithm with Stochastic Crossover Self-Learning and Blended Learning Model and Its Application

This paper presents a novel variant of the teaching–learning-based optimization algorithm, termed BLTLBO, which draws inspiration from the blended learning model, specifically designed to tackle high-dimensional multimodal complex optimization problems. Firstly, the perturbation conditions in the “teaching” and “learning” stages of the original TLBO algorithm are interpreted geometrically, based on which the search capability of the TLBO is enhanced by adjusting the range of values of random numbers. Second, a strategic restructuring has been ingeniously implemented, dividing the algorithm into three distinct phases: pre-course self-study, classroom blended learning, and post-course consolidation; this structural reorganization and the random crossover strategy in the self-learning phase effectively enhance the global optimization capability of TLBO. To evaluate its performance, the BLTLBO algorithm was tested alongside seven distinguished variants of the TLBO algorithm on thirteen multimodal functions from the CEC2014 suite. Furthermore, two excellent high-dimensional optimization algorithms were added to the comparison algorithm and tested in high-dimensional mode on five scalable multimodal functions from the CEC2008 suite. The empirical results illustrate the BLTLBO algorithm’s superior efficacy in handling high-dimensional multimodal challenges. Finally, a high-dimensional portfolio optimization problem was successfully addressed using the BLTLBO algorithm, thereby validating the practicality and effectiveness of the proposed method.

An enhanced sparrow search swarm optimizer via multi-strategies for high-dimensional optimization problems

With the development of science and technology, high-dimensional global optimization problems have become increasingly prevalent for scientific research and engineering, such as gene recognition, vehicle routing, job scheduling, and network topology. These problems are typically characterized by enormous and complex search spaces and numerous local minima, making it challenging to find the global optimal solution with limited computing resources. This paper introduces an enhanced sparrow search swarm optimizer (ESSSO) based on a bio-mimetic method. The ESSSO employs an adaptive sinusoidal walk strategy based on the von Mises distribution, a learning strategy utilizing roulette wheel selection, a two-stage evolution strategy, and a selection mutation strategy to address these issues. The proposed sinusoidal walk strategy, grounded in the von Mises distribution, supports a balanced evolutionary search. This mechanism disperses the individuals in a swarm in various directions based on a circular normal distribution. It then leads the search and adaptively adjusts their step sizes according to the size of the search domain during each generation of evolution. The learning strategy, based on roulette wheel selection, enhances the diversity of the population and improves the global search capability of the algorithm during the initial iterations. The two-stage evolution strategy involves a sine-learning mechanism based on the von Mises distribution and an adaptive mutation mechanism. The former is designed to boost the convergence speed of ESSSO, while the latter prevents ESSSO from getting trapped in a local optimum. Additionally, the selection mutation strategy further enhances convergence speed while maintaining population diversity. These strategies promote exploration in the early stages of evolution and exploitation in the later stages, enabling a well-balanced search for optimal solutions. We conducted comprehensive experiments two standard benchmark sets (i.e., CEC2010 and CEC2013), antenna array optimization, feature selection, and four engineering design problems. The results indicate that ESSSO outperforms ten comparison algorithms, especially in scenarios with smaller population sizes. This confirms its effectiveness in high-dimensional global optimization tasks and demonstrates that it can achieve better results with less computational resource consumption.

Artificial Neural Network Control Applied to a Photovoltaic-Battery Microgrid System

This paper deals with artificial neural network (ANN) applied to control a standalone microgrid in French Guiana. ANN is an artificial intelligence technique used to control non-linear and complex systems. ANN associated with the Levenberg–Marquardt (LM) algorithm has many advantages, such as rapid decision-making and improved system transients. Therefore, this technique should be adapted for the control of photovoltaic (PV) systems in the tropical climate of French Guiana with high variation in irradiance. The microgrid is composed of a PV source and a storage battery to supply an isolated building which is modeled by a DC load. The PV source is controlled by an ANN-based MPPT (Maximum Power Point Tracking) controller. To validate our ANN-MPPT, we compared it with one of the very popular MPPT algorithms, which is the P&O-MPPT algorithm. The comparison results show that our ANN-MPPT works well because it can find the maximum power point quickly. In the case of battery control, we tested two feed-forward backpropagation neural network (FFBNN) configurations called method1 and method2 associated with the Levenberg–Marquardt (LM) algorithm. We varied the number of hidden layers in each of these two FFBNN configurations to obtain the optimal number of hidden layers for each configuration which optimizes battery control. Method1 is chosen because it is better than method2, in a sense that it respects the maximum amplitude of the battery current for our application and improves the transient regimes of this current. This best configuration (method1) is then tested with two other learning algorithms for comparison: Bayesian regularization (BR) and scaled conjugate gradient (SCG) methods. The system performance with LM algorithm is better than SCG and BR algorithms. LM algorithm improves the performance of the system in transient regimes while the results obtained with the SGG and BR algorithms are similar. Then, we focused on the advantage of using ANN control compared to the conventional proportional integral control (PI control). The comparison results showed that ANN control associated with the LM algorithm (ANN-LM) made it possible to reduce battery current peaks by 26% in transient regimes compared to conventional PI control. Finally, we present and discuss the results of our simulation obtained with the MATLAB Simulink software.

RPC-EAU: Radar Plot Classification Algorithm Based on Evidence Adaptive Updating

Accurately classifying targets and clutter plots is crucial in radar data processing. It is beneficial for filtering out a large amount of clutters and improving the track initiation speed and tracking accuracy of real targets. However, in practical applications, this problem becomes difficult due to complex electromagnetic environments such as cloud and rain clutter, sea clutter, and strong ground clutter. This has led to poor performance of some commonly used radar plot classification algorithms. In order to solve this problem and further improve classification accuracy, the radar plot classification algorithm based on evidence adaptive updating (RPC-EAU) is proposed in this paper. Firstly, the multi-dimensional recognition features of radar plots used for classification are established. Secondly, the construction and combination of mass functions based on feature sample distribution are designed. Then, a confidence network classifier containing an uncertain class was designed, and an iterative update strategy for it was provided. Finally, several experiments based on synthetic and real radar plots were presented. The results show that RPC-EAU can effectively improve the radar plot classification performance, achieving a classification accuracy of about 0.96 and a clutter removal rate of 0.95. Compared with some traditional radar pattern recognition algorithms, it can improve by 1 to 10 percentage points. The target loss rate of RPC-EAU is also the lowest, only about 0.02, which is about one third to one half of the comparison algorithms. In addition, RPC-EAU avoids clustering all radar points in each update, greatly saving the computational time. The proposed algorithm has the characteristics of high classification accuracy, low target loss rate, and less computational time. Therefore, it is suitable for radar data processing with high timeliness requirements and multiple radar plots.

Self-adaptive hybrid mutation slime mould algorithm: Case studies on UAV path planning, engineering problems, photovoltaic models and infinite impulse response

There are many classic highly complex optimization problems in the world, therefore, it is still necessary to find an applicable and effective algorithm to solve these problems. In this paper, self-adaptive hybrid cross mutation slime mold algorithm is proposed, which is AHCSMA, to solve these problems efficiently. Specifically, there are three innovations in this paper: (i) new self-adaptive Cauchy mutation operator is developed to improve the mutation ability of the population; (ii) the crossover rate balance mechanism is proposed to make up for the neglected relationship between individuals and crossover rates. Then the differential vector information between the dominant individual and other individuals in the population is highly utilized to increase the evolution speed of the algorithm; (iii) self-adaptive restart hybrid opposition learning is designed to alleviate the situation where the algorithm falls into local optimality. To verify the competitive of AHCSMA, UAV path planning problems, engineering problems, nonlinear parameter extraction of photovoltaic model problems and parameter identification problems of highly nonlinear infinite impulse response are used to test the ability of the AHCSMA, accumulation more than 50 algorithms are used as comparison algorithms, and results report that AHCSMA is extremely competitive and performs better when optimizing these real-life problems.

An indicator-based evolutionary algorithm with adaptive archive update cycle for multi-objective multi-robot task allocation

The multi-robot task allocation problem has garnered significant attention in research and development. This paper addresses the multi-robot task allocation problem by introducing a unified model that seamlessly transforms into four popular mathematical models through simple parameter adjustments. We propose an efficient indicator-based multi-objective evolutionary algorithm with a hybrid encoding scheme for task execution order and robot starting point information. The algorithm employs the hypervolume indicator for environmental selection to enhance convergence and the modified crowding distance for archive updates to promote diversity. Additionally, an adaptive archive update mechanism is designed for time efficiency. In experiments comparing our proposed algorithm with 8 state-of-the-art algorithms on 18 randomly generated instances of various sizes, along with 4 real-world problems from the TSPLIB benchmark, our algorithm consistently outperformed the comparison algorithms in five key indicators. These results underscore the effectiveness of our approach in addressing real-world multi-robot task allocation problems.

Construction of a painting image classification model based on AI stroke feature extraction

Abstract A large number of digital painting image resources cannot be directly converted into electronic form due to their differences in painting techniques and poor preservation of paintings. Moreover, the difficulty of extracting classification features can also lead to the consumption of human time and misclassification problems. The aim of this research is to address the challenges of converting various digital painting image resources into electronic form and the difficulties of accurately extracting classification features. The goal is to improve the usefulness and accuracy of painting image classification. Converting various digital painting image resources directly into electronic format and accurately extracting classification features are challenging due to differences in painting techniques and painting preservation, as well as the complexity of accurately extracting classification features. Overcoming these adjustments and improving the classification of painting features with the help of artificial intelligence (AI) techniques is crucial. The existing classification methods have good applications in different fields. But their research on painting classification is relatively limited. In order to better manage the painting system, advanced intelligent algorithms need to be introduced for corresponding work, such as feature recognition, image classification, etc. Through these studies, unlabeled classification of massive painting images can be carried out, while guiding future research directions. This study proposes an image classification model based on AI stroke features, which utilizes edge detection and grayscale image feature extraction to extract stroke features; and the convolutional neural network (CNN) and support vector machine are introduced into image classification, and an improved LeNet-5 CNN is proposed to achieve comprehensive assurance of image feature extraction. Considering the diversity of painting image features, the study combines color features with stroke features, and uses weighted K-means clustering algorithm to extract sample features. The experiment illustrates that the K-CNN hybrid model proposed in the study achieved an accuracy of 94.37% in extracting image information, which is higher than 78.24, 85.69, and 86.78% of C4.5, K-Nearest Neighbor (KNN), and Bi directional Long short-term Memory (BiLSTM) algorithms. In terms of image classification information recognition, the algorithms with better performance from good to poor are: the mixed model > BiLSTM > KNN > C4.5 model, with corresponding accuracy values of 0.938, 0.897, 0.872, and 0.851, respectively. And the number of fluctuation nodes in the mixed model is relatively small. And the sample search time is significantly shorter than other comparison algorithms, with a maximum recognition accuracy of 92.64% for the style, content, color, texture, and direction features of the image, which can effectively recognize the contrast and discrimination of the image. This method effectively provides a new technical means and research direction for digitizing image information.

Graph semantic similarity-based automatic assessment for programming exercises

This paper proposes an algorithm for the automatic assessment of programming exercises. The algorithm assigns assessment scores based on the program dependency graph structure and the program semantic similarity, but does not actually need to run the student’s program. By calculating the node similarity between the student’s program and the teacher’s reference programs in terms of structure and program semantics, a similarity matrix is generated and the optimal similarity node path of this matrix is identified. The proposed algorithm achieves improved computational efficiency, with a time complexity of O(n2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(n^2)$$\\end{document} for a graph with n nodes. The experimental results show that the assessment algorithm proposed in this paper is more reliable and accurate than several comparison algorithms, and can be used for scoring programming exercises in C/C++, Java, Python, and other languages.

Joint subchannel power allocation for downlink NOMA systems based on quantum carnivorous plant algorithm

Currently, most existing research on non-orthogonal multiple access (NOMA) systems converts power allocation into two independent procedures, i.e., inter-subchannel power allocation and intra-subchannel power allocation. However, improper inter-subchannel power allocation will adversely affect the power allocation process of intra-subchannel. If the power allocations of inter-subchannel and intra-subchannel are optimized simultaneously, it usually needs high computational complexity, and is hard to obtain an optimal solution. To tackle this issue, this paper studies the joint subchannel power allocation for NOMA systems and proposes a new intelligent algorithm called quantum carnivorous plant algorithm (QCPA) for simultaneously optimizing inter-subchannel and intra-subchannel power allocations. Analysis of the convergence of QCPA verified its superior performance on the test functions. By utilizing the optimal solution obtained by QCPA as the power allocation scheme, energy efficiency and sum transmission rate in NOMA systems are significantly increased compared to existing traditional power allocation methods. The results above demonstrate that QCPA effectively addresses test functions and the power allocation problem for NOMA. QCPA possesses favorable convergence in comparison to other comparison algorithms and methods.

Optimization of university management based on reptile search algorithm combined with short-duration memory neural network

Due to the lack of accuracy and difficulty to meet the actual requirements of the poor students' financial assistance in the management of smart colleges and universities. Therefore, a precise funding model for poor students is constructed on the basis of improved reptile search algorithm and short-term memory neural network. The performance of the algorithm is evaluated by test function, rank sum test and combinatorial model validation. In test function 5, the algorithm is 2.90E+01±6.04E-03, which is lower than the comparison algorithm, and begins to converge after about 10 iterations, and the convergence speed is significantly higher than that of the comparison algorithm. In the rank sum test, the experimental results of the comparison algorithm on most test functions are less than 5 %. In the combined model verification, the fitness result of the maximum convergence times was 0.2203 %, and the classification accuracy reached 98.7 %, which was better than the comparison model. The precise funding model of poor students proposed in this study has important application value in the management of smart colleges and universities, which can effectively improve the accuracy of poor students' funding and meet the actual needs. At the same time, the high accuracy and fast convergence of the model provide a new idea and method for smart university management.

Knowledge-shareable adaptive deep dynamic programming for hierarchical generation control of distributed high-percentage renewable energy systems

The increased proportion of distributed renewable energy sources connected to systems leads to frequency regulation difficulty, such as uncoordinated algorithms, inconsistent optimization and control objectives, and long training time. This work proposes a knowledge-shareable adaptive deep dynamic programming (KSADDP) to improve the active control accuracy and generation economy of the proposed hierarchical generation control framework, which contains two-layer control structures. In the first layer, droop control is employed to optimize the outputs of controllable generators, follow the frequency changes, reduce frequency deviation, and improve the operation economy of battery energy storage systems. In the second layer, a KSADDP is proposed to mitigate local optimum and accelerate the hybrid cooperative structure optimization by sharing the parameters of neural networks. These two layers synergistically optimize control performance and reduce generation costs. The simulation results of a three-high-percentage renewable energy system show that: with two layers of cooperation and sharing training information, the KSADDP outperforms the comparison algorithms in seven evaluation indices and reduces the generation cost by 4.85%–7.41 % compared to the comparison algorithms. The proposed KSADDP cooperates the time scales between multiple layers, cooperates the objectives between multiple layers, increases the parameter-sharing process, and reduces training time.

Multi-strategy enhanced snake optimizer for quantitative structure-activity relationship modeling

Quantitative structure-activity relationship modeling techniques are widely employed in diverse areas of chemistry, including environmental risk assessment of compounds and virtual screening of drugs. The modeling process entails optimizing the hyper parameters of the model and selecting appropriate molecular descriptors. It is a typical optimization problem with high-dimensional, nonlinear, continuous and discrete variables coexisting. To address this challenge, this paper proposes an enhanced snake optimizer with multiple strategies. First, new food emergence and temperature change mechanisms are introduced to balance the exploration and exploitation. Second, a death and regeneration mechanism is employed to enhance the algorithm's ability to escape from local optima. Third, new formulas for food searching, fighting, mating and eating are designed to simplify the complexity of the algorithm and improve its search efficiency and accuracy. Fourth, the performance of the proposed algorithm is evaluated using the CEC2017 benchmark functions, eight engineering cases with continuous variables, and six feature selection cases with discrete variables. Experimental results demonstrate that the algorithm significantly outperforms comparison algorithms. Finally, the algorithm was applied to quantitative structure-activity relationship modeling for environmental toxicity prediction. Compared with other algorithms, the algorithm can better configure hyper-parameters and select fewer and more effective features for environmental toxicity prediction model. It will be an effective tool to improve the performance of quantitative structure-activity relationship models.

Modeling and optimization algorithm for energy-efficient distributed assembly hybrid flowshop scheduling problem considering worker resources

Considering increasingly serious environmental issues, sustainable development and green manufacturing have received much attention. Meanwhile, with the development of economic globalization and requirement of customization production, distributed hybrid flowshop scheduling problem (DHFSP) and assembly shop problem (ASP) have widely existed in realistic manufacturing systems. In addition to machine resources, worker resources are a key element affecting production efficiency. However, previous studies have not considered the integration mode of DHFSP, ASP, and worker resources in green manufacturing systems. Therefore, this paper focuses on an energy-efficient distributed assembly hybrid flowshop scheduling problem considering worker resources (EDAHFSPW) for the first time. To solve this problem, a mixed-integer linear programming (MILP) model and a multi-objective memetic algorithm (MOMA) are proposed with minimization the total tardiness (TTD) and total energy consumption (TEC) objectives. In MOMA, a speed-related decoding method is developed to improve the quality of solutions. To generate excellent initial solutions, an initialization strategy is proposed based on problem characteristics. A local search strategy is presented to improve the exploitation capability. An energy-saving strategy is designed to further optimize TEC. Additionally, to validate the proposed MILP model, we implement CPLEX to solve it on 12 small-sized instances. To verify the effectiveness of the proposed MOMA, extensive experiments are conducted to compare with other 5 comparison algorithms on 90 large-sized instances. Experimental results illustrate that MOMA is superior to its competitors.

Fractional-Order Equivalent-Circuit Model Identification of Commercial Lithium-Ion Batteries

The precise identification of electrical model parameters of Li-Ion batteries is essential for efficient usage and better prediction of the battery performance. In this work, the model identification performance of two metaheuristic optimization algorithms is compared. The algorithms in comparison are the Marine Predator Algorithm (MPA) and the Partial Reinforcement Optimizer (PRO) to find the optimal model parameter values. Three fractional-order (FO) electrical equivalent circuit models (ECMs) of Li-Ion batteries with different levels of complexity are used to fit the electrochemical impedance spectroscopy (EIS) data operating under different states of charge (SoC) and different operating temperatures. It is found that there is a tradeoff between ECM complexity, identification accuracy, and precision.

Application of UAV 3D Point Cloud Data in Highway Slope Disaster Investigation

The safety and stability of highway slopes have always been critical concerns in highway management and maintenance. However, mountain road slopes, characterized by their small scale, large quantity, and complex geological conditions, pose challenges for effective deformation detection, putting significant pressure on highway management and maintenance. To address the difficulty in identifying hidden hazards of highway slopes in mountainous areas, this study proposes the use of unmanned aerial vehicle (UAV) closed-range photogrammetry technology for slope inspection. The M3C2 (Multiscale Model-to-Model Cloud Comparison) algorithm is employed to accurately calculate differences in multi-phase three-dimensional point cloud data, enabling the detection of overall slope deformation with centimeter-level precision. Field verification conducted on a highway slope in Qingtian County, Zhejiang Province, demonstrated the applicability of UAV 3D point cloud data in investigating highway slope hazards, thereby enhancing inspection efficiency and quality and providing technical support for highway management and maintenance.