Electronics

Research

14 pages, 2927 KiB

Open AccessArticle

Embedding Enhancement Method for LightGCN in Recommendation Information Systems

by Sangmin Lee, Junho Ahn and Namgi Kim

Electronics 2024, 13(12), 2282; https://doi.org/10.3390/electronics13122282 - 11 Jun 2024

Viewed by 803

In the modern digital age, users are exposed to a vast amount of content and information, and the importance of recommendation systems is increasing accordingly. Traditional recommendation systems mainly use matrix factorization and collaborative filtering methods, but problems with scalability due to an [...] Read more.

In the modern digital age, users are exposed to a vast amount of content and information, and the importance of recommendation systems is increasing accordingly. Traditional recommendation systems mainly use matrix factorization and collaborative filtering methods, but problems with scalability due to an increase in the amount of data and slow learning and inference speeds occur due to an increase in the amount of computation. To overcome these problems, this study focused on optimizing LightGCN, the basic structure of the graph-convolution-network-based recommendation system. To improve this, techniques and structures were proposed. We propose an embedding enhancement method to strengthen the robustness of embedding and a non-combination structure to overcome LightGCN’s weight sum structure through this method. To verify the proposed method, we have demonstrated its effectiveness through experiments using the SELFRec library on various datasets, such as Yelp2018, MovieLens-1M, FilmTrust, and Douban-book. Mainly, significant performance improvements were observed in key indicators, such as Precision, Recall, NDCG, and Hit Ratio in Yelp2018 and Douban-book datasets. These results suggest that the proposed methods effectively improved the recommendation performance and learning efficiency of the LightGCN model, and the improvement of LightGCN, which is most widely used as a backbone network, makes an important contribution to the entire field of GCN-based recommendation systems. Therefore, in this study, we improved the learning method of the existing LightGCN and changed the weight sum structure to surpass the existing accuracy. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

19 pages, 6925 KiB

Open AccessArticle

Improving Object Detection Accuracy with Self-Training Based on Bi-Directional Pseudo Label Recovery

by Shoaib Sajid, Zafar Aziz, Odilbek Urmonov and HyungWon Kim

Electronics 2024, 13(12), 2230; https://doi.org/10.3390/electronics13122230 - 7 Jun 2024

Viewed by 421

Abstract

Semi-supervised training methods need reliable pseudo labels for unlabeled data. The current state-of-the-art methods based on pseudo labeling utilize only high-confidence predictions, whereas poor confidence predictions are discarded. This paper presents a novel approach to generate high-quality pseudo labels for unlabeled data. It [...] Read more.

Semi-supervised training methods need reliable pseudo labels for unlabeled data. The current state-of-the-art methods based on pseudo labeling utilize only high-confidence predictions, whereas poor confidence predictions are discarded. This paper presents a novel approach to generate high-quality pseudo labels for unlabeled data. It utilizes predictions with high- and low-confidence levels to generate refined labels and then validates the accuracy of those predictions through bi-directional object tracking. The bi-directional object tracker leverages both past and future information to recover missing labels and increase the accuracy of the generated pseudo labels. This method can also substantially reduce the effort and time needed in label creation compared to the conventional manual labeling. The proposed method utilizes a buffer to accumulate detection labels (bounding boxes) predicted by the object detector. These labels are refined for accuracy though forward and backward tracking, ultimately constructing the final set of pseudo labels. The method is integrated in the YOLOv5 object detector and tested on the BDD100K dataset. Through the experiments, we demonstrate the effectiveness of the proposed scheme in automating the process of pseudo label generation with notably higher accuracy than the recent state-of-the-art pseudo label generation schemes. The results show that the proposed method outperforms previous methods in terms of mean average precision (mAP), label generation accuracy, and speed. Using the bi-directional recovery method, an increase in mAP@50 for the BDD100K dataset by 0.52% is achieved, and for the Waymo dataset, it provides an improvement of mAP@50 by 8.7% to 9.9% compared to 8.1% of the existing method when pre-training with 10% of the dataset. An improvement by 2.1% to 2.9% is achieved as compared to 1.7% of the existing method when pre-training with 20% of the dataset. Overall, the improved method leads to a significant enhancement in detection accuracy, achieving higher mAP scores across various datasets, thus demonstrating its robustness and effectiveness in diverse conditions. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

19 pages, 16050 KiB

Open AccessArticle

A Comparative Analysis of Computational Intelligence Methods for Autonomous Navigation of Smart Ships

by Agnieszka Lazarowska

Electronics 2024, 13(7), 1370; https://doi.org/10.3390/electronics13071370 - 4 Apr 2024

Viewed by 741

Abstract

This paper presents the author’s approaches based on computational intelligence methods for application in the Autonomous Navigation System (ANS) of a smart ship. The considered task is collision avoidance, which is one of the vital functions of the ANS. The proposed methods, applying [...] Read more.

This paper presents the author’s approaches based on computational intelligence methods for application in the Autonomous Navigation System (ANS) of a smart ship. The considered task is collision avoidance, which is one of the vital functions of the ANS. The proposed methods, applying the Ant Colony Optimization and the Firefly Algorithm, were compared with other artificial intelligence approaches introduced in the recent literature, e.g., evolutionary algorithms and machine learning. The advantages and disadvantages of different algorithms are formulated. Results of simulation experiments carried out with the use of the developed algorithms are presented and discussed. Future trends and challenges of presented smart technologies are also stated. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

19 pages, 17320 KiB

Open AccessArticle

Three-Dimensional Double Random-Phase Encryption for Simultaneous Two-Primary Data

by Jae-Young Jang and Myungjin Cho

Electronics 2024, 13(5), 823; https://doi.org/10.3390/electronics13050823 - 20 Feb 2024

Viewed by 635

Abstract

In this paper, we propose a three-dimensional (3D) optical encryption technique for simultaneous two-primary data using double random-phase encryption (DRPE). In conventional DRPE, the primary data can be encrypted through two different random phase masks optically. Thus, its speed is the same as [...] Read more.

In this paper, we propose a three-dimensional (3D) optical encryption technique for simultaneous two-primary data using double random-phase encryption (DRPE). In conventional DRPE, the primary data can be encrypted through two different random phase masks optically. Thus, its speed is the same as the speed of light. However, in this method, each primary dataset can be decrypted by the individual key data. For simultaneous two primary dataset such as stereo images or multi-view images, a new encryption technique is required. Therefore, in this paper, we encrypt the simultaneous two different primary datasets by DRPE. In our method, the first and second primary data are regarded as the amplitude and phase with single key data for encryption. To verify the feasibility of our method, we implement the simulation and measure the performance metrics such as thw peak signal to noise ratio (PSNR) and the peak sidelobe ratio (PSR). As a result, PSNR values of two-dimensional decryption results for the first (“LENA” text) and second (lena image) primary data by our proposed method with the correct and incorrect key data are 311.0139, 41.9609, 12.0166, and 7.4626, respectively, since the first primary data are lossless, and the second primary data are lossy. For 3D reconstruction, PSR values of the first and second primary data are 914.2644 and 774.1400, respectively. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

21 pages, 13794 KiB

Open AccessArticle

Computational Intelligence Supporting the Safe Control of Autonomous Multi-Objects

by Józef Lisowski

Electronics 2024, 13(4), 780; https://doi.org/10.3390/electronics13040780 - 16 Feb 2024

Viewed by 560

Abstract

The essence of this work, which is an extension of the author’s previous research, is an analysis of computational intelligence algorithms that the support safe control of an autonomous object moving in a large group of other autonomous objects. Linear and dynamic programming [...] Read more.

The essence of this work, which is an extension of the author’s previous research, is an analysis of computational intelligence algorithms that the support safe control of an autonomous object moving in a large group of other autonomous objects. Linear and dynamic programming methods with neural constraints on the process state, as well as positional and matrix game methods, were used to synthesize computational algorithms for the safe trajectory of one’s own object. The aim of the comparative analysis of intelligent computational methods for the safe trajectory of an object was to show, through their use, the possibility of taking into account the risk of collision resulting from both the degree of cooperation of objects while observing traffic laws and the impact of the environment in the form of visibility and the complexity of the situation. Simulation tests of the algorithms were carried out on the example of a real navigation situation of several dozen objects passing each other at sea. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

23 pages, 729 KiB

Open AccessArticle

Semi-Supervised Feature Selection of Educational Data Mining for Student Performance Analysis

by Shanshan Yu, Yiran Cai, Baicheng Pan and Man-Fai Leung

Electronics 2024, 13(3), 659; https://doi.org/10.3390/electronics13030659 - 5 Feb 2024

Viewed by 1076

Abstract

In recent years, the informatization of the educational system has caused a substantial increase in educational data. Educational data mining can assist in identifying the factors influencing students’ performance. However, two challenges have arisen in the field of educational data mining: (1) How [...] Read more.

In recent years, the informatization of the educational system has caused a substantial increase in educational data. Educational data mining can assist in identifying the factors influencing students’ performance. However, two challenges have arisen in the field of educational data mining: (1) How to handle the abundance of unlabeled data? (2) How to identify the most crucial characteristics that impact student performance? In this paper, a semi-supervised feature selection framework is proposed to analyze the factors influencing student performance. The proposed method is semi-supervised, enabling the processing of a considerable amount of unlabeled data with only a few labeled instances. Additionally, by solving a feature selection matrix, the weights of each feature can be determined, to rank their importance. Furthermore, various commonly used classifiers are employed to assess the performance of the proposed feature selection method. Extensive experiments demonstrate the superiority of the proposed semi-supervised feature selection approach. The experiments indicate that behavioral characteristics are significant for student performance, and the proposed method outperforms the state-of-the-art feature selection methods by approximately 3.9% when extracting the most important feature. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

14 pages, 1578 KiB

Open AccessArticle

Separable ConvNet Spatiotemporal Mixer for Action Recognition

by Hsu-Yung Cheng, Chih-Chang Yu and Chenyu Li

Electronics 2024, 13(3), 496; https://doi.org/10.3390/electronics13030496 - 24 Jan 2024

Viewed by 646

Abstract

Video action recognition is vital in the research area of computer vision. In this paper, we develop a novel model, named Separable ConvNet Spatiotemporal Mixer (SCSM). Our goal is to develop an efficient and lightweight action recognition backbone that can be applied to [...] Read more.

Video action recognition is vital in the research area of computer vision. In this paper, we develop a novel model, named Separable ConvNet Spatiotemporal Mixer (SCSM). Our goal is to develop an efficient and lightweight action recognition backbone that can be applied to multi-task models to increase the accuracy and processing speed. The SCSM model uses a new hierarchical spatial compression, employing the spatiotemporal fusion method, consisting of a spatial domain and a temporal domain. The SCSM model maintains the independence of each frame in the spatial domain for feature extraction and fuses the spatiotemporal features in the temporal domain. The architecture can be adapted to different frame rate requirements due to its high scalability. It is suitable to serve as a backbone for multi-task video feature extraction or industrial applications with its low prediction and training costs. According to the experimental results, SCSM has a low number of parameters and low computational complexity, making it highly scalable with strong transfer learning capabilities. The model achieves video action recognition accuracy comparable to state-of-the-art models with a smaller parameter size and fewer computational requirements. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

18 pages, 1465 KiB

Open AccessArticle

Recognizing Complex Activities by Combining Sequences of Basic Motions

by Chenghong Lu, Wu-Chun Hsu and Lei Jing

Electronics 2024, 13(2), 372; https://doi.org/10.3390/electronics13020372 - 16 Jan 2024

Viewed by 677

Abstract

For daily motion recognition, each researcher builds their own method to recognize their own specific target actions. However, for other types of target motions, they cannot use their method to recognize other kinds of motions because the features of their target motions that [...] Read more.

For daily motion recognition, each researcher builds their own method to recognize their own specific target actions. However, for other types of target motions, they cannot use their method to recognize other kinds of motions because the features of their target motions that they extracted cannot be extracted from other kinds of motions. Therefore, we wanted to develop a general method that can be used in most kinds of motions. From our observations, we found that a meaningful motion is combined with some basic motions. Therefore, we could recognize basic motions and then combine them to recognize a target motion. First, we simply defined the basic motions according to the sensor’s basic sensing directions. Second, we used k-nearest neighbors (KNN) and dynamic time warping (DTW) to recognize different categories of basic motions. Then, we gave each basic motion a specific number to represent it, and finally, used continuous dynamic programming (CDP) to recognize a target motion by the sequence of basic motions we collected. In our experiment on our basic motions, the accuracy of all of the basic motions is higher than 80%, so the recognition of basic motions is reliable. Then, we performed an experiment for recognizing the target motions. The results of recognizing the target motions were not good, the average accuracy being only 65.9%, and we still have to improve our system. However, we also compared our system with recognizing motions by using another general recognition method, KNN. And the average accuracy of using KNN to recognize motions was 53.4%. As this result shows, our method still obtains better results in recognizing different kinds of motions than using KNN. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

16 pages, 3067 KiB

Open AccessArticle

Sleep Analysis by Evaluating the Cyclic Alternating Pattern A Phases

by Arturo Alves, Fábio Mendonça, Sheikh Shanawaz Mostafa and Fernando Morgado-Dias

Electronics 2024, 13(2), 333; https://doi.org/10.3390/electronics13020333 - 12 Jan 2024

Viewed by 749

Abstract

Sleep is a complex process divided into different stages, and a decrease in sleep quality can lead to adverse health-related effects. Therefore, diagnosing and treating sleep-related conditions is crucial. The Cyclic Alternating Pattern (CAP) is an indicator of sleep instability and can assist [...] Read more.

Sleep is a complex process divided into different stages, and a decrease in sleep quality can lead to adverse health-related effects. Therefore, diagnosing and treating sleep-related conditions is crucial. The Cyclic Alternating Pattern (CAP) is an indicator of sleep instability and can assist in assessing sleep-related disorders such as sleep apnea. However, manually detecting CAP-related events is time-consuming and challenging. Therefore, automatic detection is needed. Despite their usually higher performance, the utilization of deep learning solutions may result in models that lack interpretability. Addressing this issue can be achieved through the implementation of feature-based analysis. Nevertheless, it becomes necessary to identify which features can better highlight the patterns associated with CAP. Such is the purpose of this work, where 98 features were computed from the patient’s electroencephalographic signals and used to train a neural network to identify the CAP activation phases. Feature selection and model tuning with a genetic algorithm were also employed to improve the classification results. The proposed method’s performance was found to be among the best state-of-the-art works that use more complex models. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Future Trends and Challenges of Ubiquitous Computing and Smart Systems

Share This Special Issue

Special Issue Editor

Special Issue Information

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI