International Journal of Computational Intelligence and Applications

Effectively reducing the dimensionality of big data and retaining its key information has been a research challenge. As an important step in data pre-processing, feature selection plays a critical role in reducing data size and increasing the overall value of the data. Many previous studies have focused on single-label feature selection, however, with the increasing variety of data types, the need for feature selection on multi-label data types has also arisen. Unlike single-labeled data, multi-labeled data with more combinations of classifications place higher demands on the capabilities of feature selection algorithms. In this paper, we propose a filter-based Multi-Objective Equilibrium Optimizer algorithm (MOEO-Smp) to solve the feature selection problem for both single-label and multi-label data. MOEO-Smp rates the optimization results of solutions and features based on four pairs of optimization principles, and builds three equilibrium pools to guide exploration and exploitation based on the total scores of solutions and features and the ranking of objective fitness values, respectively. Seven UCI single-label datasets and two Mulan multi-label datasets and one COVID-19 multi-label dataset are used to test the feature selection capability of MOEO-Smp, and the feature selection results are compared with 10 other state-of-the-art algorithms and evaluated using three and seven different metrics, respectively. Feature selection experiments and comparisons with the results in other literatures show that MOEO-Smp not only has the highest classification accuracy and excellent dimensionality reduction on single-labeled data, but also performs better on multi-label data in terms of Hamming loss, accuracy, dimensionality reduction, and so on.

With the rapid advancement of internet technology, various industries have accumulated vast amounts of data, including on user behavior and personal preferences. Traditional museums can leverage this user data to uncover individual preferences and offer personalized services to their visitors. However, the exponential growth of information has also led to the problem of information overload, making it challenging for users to find relevant information within the vast data landscape. Consequently, the utilization rate of available information decreases. By harnessing the power of cloud computing, big data analytics, and recommendation systems, museums can enhance visitors’ touring experiences by helping them discover collections aligned with their interests and connecting with like-minded individuals. To address this objective, the research focuses on optimizing the initial clustering centers of the fuzzy clustering algorithm and parallelizing the optimized algorithm using MapReduce, resulting in the development of a novel MapReduce-based k-prototype fuzzy c-means (MRKPFCM) algorithm. Subsequently, the MRKPFCM algorithm is combined with the classical collaborative filtering algorithm to create a hybrid and parallelized collaborative filtering recommendation algorithm, incorporating elements such as MRKPFCM, audience, and collection. This hybrid algorithm is further supplemented by a content-based recommendation approach to generate comprehensive and refined recommendation results. Experimental findings demonstrate that the predictive scoring errors, as measured by RMSE and MAE, exhibited a downward trend when the number of nearest neighbors for target users fell within the range of 10–20. For instance, the studied algorithm’s MAE value decreased from 0.7512 to 0.7179, surpassing the corresponding figures for the two comparison algorithms. Moreover, with an increase in the number of nearest neighbors within the same range, all three algorithms experienced improved accuracy in prediction results. In particular, the accuracy rate rose from 17.84% to 18.82%, outperforming the two comparison algorithms. In summary, the enhanced hybrid recommendation algorithm achieved through this study displays superior recommendation accuracy and holds significant practical value.

Soybean leaf disease labeling data are not easy to obtain, and soybean leaf disease model training often needs a lot of data. Due to the limitations of fixed rules such as rotation and clipping, traditional data enhancement cannot generate images with diversity and variability. In view of the above problems, this study proposed a data enhancement method based on generative adversarial network to expand the original soybean leaf disease dataset. This method was based on cyclic confrontation network, and its discriminator uses dense connection strategy to realize feature reuse, so as to reduce the amount of calculation. In the training process, improved transfer learning is used to automatically fine tune the pre-training model. The accuracy of the optimized method in 9 kinds of soybean leaf disease image recognition is 95.84%, which is 0.98% higher than the traditional fine-tuning method. The experimental results show that this method based on generating confrontation network has significant ability in generating soybean leaf disease image, and can expand the existing dataset. In addition, this method also provides an effective data enhancement solution for the expansion of other crop disease image datasets.

Orchid is a type of plant that grows on land. It is highly valued for its beauty and is cherished by many because of its graceful flower shape, delicate fragrance, vibrant colors, and noble symbolism. Although there are various types of orchids, some of them look similar in appearance and color, making it challenging for people to distinguish them quickly and accurately. The existing methods for classifying orchid species face issues with accuracy due to the similarities between different species and the differences within the same species. This affects their practical use. To address these challenges, this paper introduces an efficient method for classifying orchid species using transfer learning. The main achievement of this study is the successful utilization of transfer learning to achieve accurate orchid species classification. This approach reduces the need for large datasets, minimizes overfitting, cuts down on training time and costs, and enhances classification accuracy. Specifically, the proposed approach involves four phases. First, we gathered a collection of 12 orchid image sets, totaling 12,227 images, through a combination of network sources and field photography. Next, we analyzed the distinctive features present in the collected orchid image sets. We identified certain connections between the acquired orchid datasets and other datasets. Finally, we employed transfer learning technology to create an efficient classification function for orchid species based on these relationships. As a result, our proposed method effectively addresses the challenges highlighted. Experimental results demonstrate that our classification algorithm, which utilizes transfer learning, achieves a classification accuracy rate of 96.16% compared to not using the transfer learning method. This substantial improvement in accuracy greatly enhances the efficiency of orchid classification.

Software development effort estimation is regarded as a crucial activity for managing project cost, time, and quality, as well as for the software development life cycle. As a result, proper estimating is crucial to the success of projects and to lower risks. Software effort estimation has drawn much research interest recently and has become a problem for the software industry. When results are inaccurate, an effort may be over- or under-estimated, which can disastrously affect project resources. In the sector, machine learning methods are becoming more and more prominent. Therefore, in this paper, we propose a Modified Jaya algorithm to improve the effectiveness of the estimated model; Modified JOA selects the ideal subset of components from an extensive feature collection. Then, the ensemble machine learning-based Enhanced Extreme gradient boosting algorithm and Ensemble Learning machine approach are employed to estimate the software effort. On the PROMISE SDEE repository, the proposed methodologies are empirically assessed. In this approach, applying machine learning techniques to the effort estimation process increases the likelihood that the time and cost estimates will be accurate. The proposed approach yields a greater performance. The key benefit of this approach is that it lowers the computational cost. This approach can also inspire the development of a tool that could reliably, effectively, and accurately estimate the effort required to complete different software projects.

With the rapid development of deep learning technology, object detection algorithms have made significant breakthroughs in the field of computer vision. However, due to the complexity and computational requirements of deep Convolutional Neural Network (CNN), these models face many challenges in practical applications, especially on resource-constrained edge devices. To address this problem, researchers have proposed many lightweight methods that aim to reduce the model size and computational complexity while maintaining high performance. The popularity of mobile devices and embedded systems has led to an increasing demand for lightweight models. However, existing lightweight methods often lead to accuracy loss, limiting their feasibility in practical applications. Therefore, how to realize the light weight of the model while maintaining high accuracy has become an urgent problem to be solved. To address this challenge, this paper proposes a lightweight YOLOv7 method based on PConv, Squeeze-and-Excitation (SE) attention mechanism and Wise-IoU (WIoU), which we refer to as YOLOv7-PSW. PConv can effectively reduce the number of parameters and computational complexity. The SE can help the model focus on important feature information, thereby improving performance. WIoU is introduced to measure the similarity between the detection box and the Ground Truth, so that the model can effectively reduce the False Positive rate. By applying these advanced techniques to the YOLOv7, we achieve a lightweight model while maintaining a high detection accuracy. Experimental results on PASCAL VOC dataset show that YOLOv7-PSW performs better than the original YOLOv7 on object detection tasks. The number of parameters is reduced by 12.3%, FLOPs is reduced by 18.86%, and the accuracy is improved by about 0.5%. While the detection accuracy is not decreased or even slightly improved, the number of FLOPs and parameters is greatly reduced, which realizes lightweight to a certain extent. The proposed method can provide new ideas and directions for the subsequent research on lightweight object detection, and is expected to promote its application on edge devices. Meanwhile, YOLOv7-PSW can also be applied to other computer vision tasks to improve its performance and efficiency. In summary, the proposed YOLOv7-PSW lightweight method realizes the light weight of the model while maintaining high accuracy. This is of great significance for promoting the application of object detection algorithms on edge devices.

Attention deficit hyperactivity disorder (ADHD) is one of the most common mental disorders. This disease includes a combination of disorders in maintaining attention, hyperactivity, and impulsive behaviors. Diagnosis of ADHD is primarily clinical and based on history and examination. This study aims to provide a method for a more accurate diagnosis of adult ADHD using electroencephalography (EEG) signals. EEG signals recorded from 37 ADHD and 42 healthy adults were used as a control group in the age range of 20–68 years. We designed a convolutional neural network with three convolutional layers, three max-pooling layers, and one fully connected layer and trained it using spectrogram images obtained from EEG signals. The Cz channel was used for the diagnosis ADHD in four different states. To evaluate the performance of the proposed method, metrics such as accuracy, sensitivity, specificity, and precision were calculated. The results showed that using only one Cz channel has a good performance in diagnosing of ADHD. The highest accuracy of classification was related to the classification of two groups in the state when their eyes-open and eyes-closed spectrogram images were subtracted from each other. The results showed that proposed method based on deep learning can be a suitable method for diagnosing ADHD.

In view of the problems of high production cost, scarcity and lack of diversity of 3D face datasets, this paper designs an end-to-end self-supervised learning 3D face reconstruction algorithm with a single 2D face image as input, which only uses 2D face datasets to complete model training. First, the improved ResNet module is introduced to preprocess the input face image. The deep residual neural network has strong feature extraction and characterization ability for the image, which can provide rich high-level semantic feature maps for the subsequent subnetwork. Then, add transformer module completely based on self-attention mechanism to the parameter prediction subnetwork, which can make different parameters of the subnetwork focus on self-related feature map information and avoid interference from invalid feature map information, so as to further improve the parameter prediction accuracy of the subnetwork. Next, training, ablation and comparison experiments were conducted on CelebA, BFM and Photoface datasets, and the combined function of pixel loss function and perceptual loss function was selected as the loss function. The experimental results show that: compared with the historical optimal results of the same network structure, the scale-invariant depth error (SIDE) and mean angle deviation (MAD) are improved by 5.9% and 10.8%, respectively, which strongly proves the effectiveness of the algorithm. Finally, in order to verify the actual effect of the 3D face reconstruction algorithm, examples are selected in this paper for reconstruction. The 3D faces generated by the algorithm all have a good sense of reality, which intuitively and effectively proves the advancement of the algorithm.

Breast cancer is one of the most common types of cancer and it presents itself as being the leading cause of death among women. If its diagnosis occur soon enough, the probability to achieve the cure of the patient can be increased. Recently, it has been more common the use of deep neural network techniques to aid pathologists in their prognosis, but they still do not fully trust them because they lack interpretability. In light of that, this work investigates if previous training of the models as encoders could enhance their accuracy in both classification and interpretability. There were implemented three models to the BreakHis and BreCaHAD dataset: NASNet Mobile, DenseNET201, and MobileNetV2. The experiments have shown that the three models increased the classification performance and two models improved their interpretability using the proposed strategy. DenseNet201 encoder has performed almost 23% better than its vanilla version in classifying a tumor and the NASNet Mobile encoder has improved 28.5% in its tumor interpretation.