Systems and Soft Computing最新文献

To improve the efficiency of intelligent procurement of library literature and intelligence resources, the study conducts the design of literature and intelligence resources procurement model. The procurement model is constructed by using the support vector machine, and the optimal parameters of the support vector machine are obtained by using the genetic algorithm. The experimental results demonstrated that the mean square error of the proposed model was only 0.03, which was 40 % lower compared with the procurement models based on other optimization algorithms. The average accuracy of the proposed model was as high as 95.18 % and the prediction accuracy was 95.78 % compared to other methods. The accuracy was improved by 15.11 %, 24.57 % and 19.67 % respectively compared to other models. The results show that using genetic algorithm to optimize support vector machine can effectively improve the prediction speed and prediction efficiency of the model. The proposed hybrid procurement model based on genetic algorithm and support vector machine can effectively meet the needs of library literature and intelligence resources procurement construction. The model has positive application significance in library literature and intelligence resources procurement.

To solve the problems of the classical color image hybrid noise filtering method, a deep convolutional neural network improved by evolutionary strategy and jump connection is proposed and applied to the filtering noise reduction of color images. First, the color information of the image is described quantitatively by digital means. The common method is to build color space model. According to the characteristics of color and the needs of human vision, mathematical algorithms are used to convert images into machine recognizable data. The distance between pixels is measured according to the difference of pixels in the color image determined above. Then, the probability density function and noise probability density function of Gaussian noise are calculated to determine the hybrid noise feature points of color image. The filtering algorithm structure designed this time is as follows: A color image hybrid noise filter is used to map the noise points in the mapped image to the feature space, and linear regression is performed on the noise point data. Relaxation variables are introduced in the network to improve the denoising ability. The experimental results show that the Peak Signal to Noise Ratio and structural similarity index values of the filtering algorithm designed in this study are higher than the two methods in the literature. The color image hybrid noise filtering model designed in this study has good filtering performance, good image cleanliness, and high filtering efficiency.

With the increasing demand for personalized and customized home products, how to realize the innovative design of furniture and improve the design efficiency has become a research hotspot for related professionals. Aiming at these problems, the study extracts the main color of furniture images by optimizing the K-mean clustering algorithm, uses the simulated annealing algorithm to color-match the furniture, and reconstructs the image by edge detection to design a furniture design method based on image color extraction. The results revealed that in the foreground part, the correct rate of color match based on the design method was 95.7%, and in the background part, the correct rate of color match based on the design method was 94.81 %, which proved its effectiveness. The average feature point extraction time and the average feature point matching time of the design-based algorithm were 5.45 ms and 9.83 ms, respectively, which proved its high computational efficiency. In furniture color edge detection and overall color match, the image obtained based on the design method was significantly clearer, and the overall coherence, saturation and brightness were closer to the input image. In addition to raising the standard of furniture design, the study's design methodology increases design efficiency and offers solid technical support for the area.

As distribution systems continue to expand, they face challenges such as increased system losses and inadequate voltage regulation. To address these issues, shunt capacitors are being deployed in distribution networks. These capacitors offer reactive power compensation, enhance power factor, improve voltage profiles, promote system stability, and significantly reduce losses. However, determining the appropriate capacitor sizes and their optimal placements requires careful consideration of both technical and economic factors. The nonlinear nature of optimal capacitor placement and sizing, leveraging optimization techniques becomes crucial in identifying the best locations and values for capacitors. This paper demonstrates the effective utilization of Particle Swarm Optimization (PSO) and Real Coded Genetic Algorithm (RCGA) optimization techniques for capacitor placement and selection. The optimization techniques are applied to a 33-bus IEEE standard radial distribution system, to reduce the real power loss and to improve the voltage profile considering both constant and variable loads. Both PSO and RCGA algorithms identify suitable locations for the placement of capacitors for reactive power compensation within the distribution system. By optimizing the objective function associated with capacitor placement costs and maximizing annual cost savings, the PSO and RCGA techniques yield promising results. After implementing the optimal capacitor placements at the identified candidate nodes, a significant reduction in losses within the radial distribution system is observed. Moreover, the cost savings achieved through optimal placement and sizing are substantial.

Solar energy is key to achieving a more environmentally responsible future. One way to exploit it is to use semiconductor technology through solar panels to generate clean, sustainable, and controllable energy. However, the use of such solutions must be optimised by methods such as maximum power point tracking (MPPT) to extract the maximum available solar energy. Although MPPT algorithms have been widely used and improved, the use of newer approaches, such as quantum computing, appears to hold the promise of achieving new performance levels, particularly for real-time MPPT implementation. The goal of this work is to develop and test a quantum algorithm for the photovoltaic (PV) energy MPPT problem using quantum particle swarm optimisation. The performance of the classic and quantum MPPT algorithms was evaluated under three main operating conditions: normal, high-temperature, and partial shading conditions. This represents a variety of environmental scenarios that can affect the efficiency of solar power generation. According to the study's results, the classical algorithm recorded 0.15% more power than the quantum algorithm in normal operating conditions, and the quantum algorithm generated 3.33% more power in higher temperature tests and 0.89% more power in the partial shading test. Moreover, the quantum algorithm recorded lower duty cycles for the three tests. While the classical algorithm may have a slight edge in power output under normal operation conditions, the quantum algorithm indicates superior performance in challenging conditions and consistently reveals more promising overall efficiency.

To solve the problems of low matching degree, long tracking time, and low accuracy of multi-target tracking in the process of athlete motion trajectory tracking using deep learning technology, a new athlete motion trajectory tracking model was proposed in this study. The study first optimized the current object detection algorithm in basketball, utilized a hybrid attention mechanism to extract object features, and improved the non-maximum suppression strategy. Then, a hybrid branch network was introduced to improve the residual network and a new athlete identity recognition model was proposed. Finally, a new trajectory tracking model was designed by combining the object detection model and the athlete identity recognition model. The research results indicated that in the object detection experiment, the detection time of the proposed object detection algorithm was always below 0.4 s, and its average accuracy reached up to 0.63. In trajectory tracking testing, the final built tracking model had a multi-target tracking accuracy of up to 0.98, and its tracking overlap rate was as low as 0.02. This study has the following two contributions. Firstly, a new model of athlete trajectory tracking is proposed, which improves the accuracy and efficiency of multi-target tracking by optimizing object detection algorithm and introducing hybrid branch network. Second, the model has excellent performance in both object detection and track tracking, which can not only provide a new solution for athletes' motion trajectory tracking, but also significantly improve the effect of motion tracking.

In our study, we introduce a novel hybrid ensemble model that synergistically combines LSTM, BiLSTM, CNN, GRU, and GloVe embeddings for the classification of gene mutations in cancer. This model was rigorously tested using Kaggle's Personalized Medicine: Redefining Cancer Treatment dataset, demonstrating exceptional performance across all evaluation metrics. Notably, our approach achieved a training accuracy of 80.6 %, precision of 81.6 %, recall of 80.6 %, and an F1 score of 83.1 %, alongside a significantly reduced Mean Squared Error (MSE) of 2.596. These results surpass those of advanced transformer models and their ensembles, showcasing our model's superior capability in handling the complexities of gene mutation classification. The accuracy and efficiency of gene mutation classification are paramount in the era of precision medicine, where tailored treatment plans based on individual genetic profiles can dramatically improve patient outcomes and save lives. Our model's remarkable performance highlights its potential in enhancing the precision of cancer diagnoses and treatments, thereby contributing significantly to the advancement of personalized healthcare.

With the development of computer technology, the teaching methods of table tennis have ushered in a new technological revolution. To solve the problem of traditional teaching methods overly focusing on athlete limbs and athlete force movements, this study uses an improved deep learning algorithm technology detection model to analyze the trajectory of table tennis and provide targeted tactical training for athletes. The results showed that the success rate and accuracy score of the model were 95 % and 96 %, respectively, with a calculation time of only 21.75 ms, indicating high analytical accuracy and computational efficiency. Meanwhile, the winning rate of the training strategy under this method can reach over 65 %, effectively improving the winning rate of athletes. This proves that the proposed technology detection model has good algorithm performance and data analysis ability, and can provide data support for table tennis training and teaching work.

In the design of furniture wood texture images, image restoration is a key issue. This study proposes a Bregmanized operator splitting optimization algorithm based on variable space. This study combines variable spatial morphology to process texture images and effectively extract image features using different operators, thereby achieving image restoration. The results of comparing the proposed algorithm with other image processing algorithms showed that the research algorithm achieved a peak signal-to-noise ratio of 29.86 and a structural similarity index of 0.87 in image denoising, respectively, and had a good denoising effect. In terms of image deblurring, the research algorithm had the lowest root mean square error values on the France and Boat datasets, with values of 8.98 and 8.82, respectively, indicating that the image processed by the algorithm had a high similarity with the real image. In terms of image resolution reconstruction, the peak signal-to-noise ratio and root mean square error values of the research algorithm reached 29.74 and 12.67, respectively, indicating that the reconstructed image had the best fit with the original image and the smallest error. In summary, the proposed algorithm has shown good performance in image processing and can be effectively applied in fields such as image denoising, deblurring, and resolution reconstruction. It provides effective methods and technical support for innovative design of wood texture images in indoor furniture.

In the current field of animation and gaming, the action collection cost for 3D animated character generation is high, and the accuracy of action recognition is poor. Therefore, to reduce the cost of generating 3D animated characters and improve the similarity between animated characters and real humans, a 3D action recognition and animated character generation model based on ResNet and phase function neural network is proposed. The experiment outcomes denote that the raised model begins to converge at 50 iterations, with a minimum loss value of 0.13. The convergence speed and loss value are better than other models. In human pose classification, the raised algorithm has the highest accuracy of 99.46 % and an average accuracy of 99.13 %. The highest classification precision and average precision are 97.79 % and 97.33 %, respectively. In terms of human pose orientation classification, the average accuracy and precision of the raised algorithm are 98.09 % and 97.41 %, respectively, which are also higher than other models. In addition, the mean per joint position error of the proposed algorithm is the highest at 80.1 mm and the lowest at 79.3 mm, respectively. The average recognition time for each image is only 46.8 ms, which is lower than other algorithms. In addition, the average update times of the algorithm and the Unreal Engine are 39.28 ms and 27.52 ms, respectively, and both run at different frame rates. The above results indicate that the proposed 3D human pose recognition and animated character generation model based on ResNet and phase function neural network can not only improve the accuracy of pose recognition, but also improve recognition speed, effectively reducing the cost of 3D animated character generation. The animation character generation method includes data collection and the application after data collection, which shows the various roles that deep learning technology can play in the field of computer graphics animation, and also provides excellent solutions for other computer graphics problems.