Vol. 18, No. 3, pp. 293-301, Jun. 2022
Keywords: DOA Estimation, Eigenvector, High-Precision, MUSIC, Parallelism
Show / Hide AbstractDirection of arrival (DOA) estimation of space signals is a basic problem in array signal processing. DOA estimation based on the multiple signal classification (MUSIC) algorithm can theoretically overcome the Rayleigh limit and achieve super resolution. However, owing to its inadequate real-time performance and accuracy in practical engineering applications, its applications are limited. To address this problem, in this study, a DOA estimation algorithm with high parallelism and precision based on an analysis of the characteristics of complex matrix eigenvalue decomposition and the coordinate rotation digital computer (CORDIC) algorithm is proposed. For parallel and single precision, floating-point numbers are used to construct an orthogonal identity matrix. Thus, the efficiency and accuracy of the algorithm are guaranteed. Furthermore, the accuracy and computation of the fixed-point algorithm, double-precision floating-point algorithm, and proposed algorithm are compared. Without increasing complexity, the proposed algorithm can achieve remarkably higher accuracy and efficiency than the fixed-point algorithm and double-precision floating-point calculations, respectively.
Explainable Machine Learning Based a Packed Red Blood Cell Transfusion Prediction and Evaluation for Major Internal Medical ConditionSeongbin Lee, Seunghee Lee, Duhyeuk Chang, Mi-Hwa Song, Jong-Yeup Kim, Suehyun Lee
Vol. 18, No. 3, pp. 302-310, Jun. 2022
Keywords: Explainable AI, Feature Importance Analysis, LightGBM, Partial Dependence Plot, prediction, Transfusion
Show / Hide AbstractEfficient use of limited blood products is becoming very important in terms of socioeconomic status and patient recovery. To predict the appropriateness of patient-specific transfusions for the intensive care unit (ICU) patients who require real-time monitoring, we evaluated a model to predict the possibility of transfusion dynamically by using the Medical Information Mart for Intensive Care III (MIMIC-III), an ICU admission record at Harvard Medical School. In this study, we developed an explainable machine learning to predict the possibility of red blood cell transfusion for major medical diseases in the ICU. Target disease groups that received packed red blood cell transfusions at high frequency were selected and 16,222 patients were finally extracted. The prediction model achieved an area under the ROC curve of 0.9070 and an F1-score of 0.8166 (LightGBM). To explain the performance of the machine learning model, feature importance analysis and a partial dependence plot were used. The results of our study can be used as basic data for recommendations related to the adequacy of blood transfusions and are expected to ultimately contribute to the recovery of patients and prevention of excessive consumption of blood products.
Yuxiang Shan, Cheng Wang, Qin Ren, Xiuhui Wang
Vol. 18, No. 3, pp. 311-318, Jun. 2022
Keywords: Artificial intelligence, Image recognition, residual network
Show / Hide AbstractTobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.
A Novel Approach to Enhance Dual-Energy X-Ray Images Using Region of Interest and Discrete Wavelet TransformBurhan Ullah, Aurangzeb Khan, Muhammad Fahad, Mahmood Alam, Allah Noor, Umar Saleem, Muhammad Kamran
Vol. 18, No. 3, pp. 319-331, Jun. 2022
Keywords: Background Noise, Discrete wavelet transform, Dual Energy X-Ray Pictures, Image fusion
Show / Hide AbstractThe capability to examine an X-ray image is so far a challenging task. In this work, we suggest a practical and novel algorithm based on image fusion to inspect the issues such as background noise, blurriness, or sharpness, which curbs the quality of dual-energy X-ray images. The current technology exercised for the examination of bags and baggage is “X-ray”; however, the results of the incumbent technology used show blurred and low contrast level images. This paper aims to improve the quality of X-ray images for a clearer vision of illegitimate or volatile substances. A dataset of 40 images was taken for the experiment, but for clarity, the results of only 13 images have been shown. The results were evaluated using MSE and PSNR metrics, where the average PSNR value of the proposed system compared to single X-ray images was increased by 19.3%, and the MSE value decreased by 17.3%. The results show that the proposed framework will help discern threats and the entire scanning process.
Xinxin Zhou, Guangwei Zhu
Vol. 18, No. 3, pp. 332-343, Jun. 2022
Keywords: Asynchronous Learning, Gravitational Search Algorithm, Levy Flight, Sinusoidal Map
Show / Hide AbstractTo address the problems of the gravitational search algorithm (GSA) in which the population is prone to converge prematurely and fall into the local solution when solving the single-objective optimization problem, a sine map jumping gravity search algorithm based on asynchronous learning is proposed. First, a learning mechanism is introduced into the GSA. The agents keep learning from the excellent agents of the population while they are evolving, thus maintaining the memory and sharing of evolution information, addressing the algorithm’s shortcoming in evolution that particle information depends on the current position information only, improving the diversity of the population, and avoiding premature convergence. Second, the sine function is used to map the change of the particle velocity into the position probability to improve the convergence accuracy. Third, the Levy flight strategy is introduced to prevent particles from falling into the local optimization. Finally, the proposed algorithm and other intelligent algorithms are simulated on 18 benchmark functions. The simulation results show that the proposed algorithm achieved improved the better performance.
Tae-Seok Lee, Hyun-Young Lee, Seung-Shik Kang
Vol. 18, No. 3, pp. 344-358, Jun. 2022
Keywords: BERT, Deep Learning, Generative Summarization, Selective OOV Copy Model, Unknown Words
Show / Hide AbstractText summarization is the task of producing a shorter version of a long document while accurately preserving the main contents of the original text. Abstractive summarization generates novel words and phrases using a language generation method through text transformation and prior-embedded word information. However, newly coined words or out-of-vocabulary words decrease the performance of automatic summarization because they are not pre-trained in the machine learning process. In this study, we demonstrated an improvement in summarization quality through the contextualized embedding of BERT with out-of-vocabulary masking. In addition, explicitly providing precise pointing and an optional copy instruction along with BERT embedding, we achieved an increased accuracy than the baseline model. The recall-based word-generation metric ROUGE- 1 score was 55.11 and the word-order-based ROUGE-L score was 39.65.
Chaoqun Li, Zhigang Chen, Tongrui Yu, Xinxia Song
Vol. 18, No. 3, pp. 359-373, Jun. 2022
Keywords: Bibliometrics, Citation Analysis, Contact tracking, Development Trend
Show / Hide AbstractThe new crown pneumonia (COVID-19) has become a global epidemic. The disease has spread to most countries and poses a challenge to the healthcare system. Contact tracing technology is an effective way for public health to deal with diseases. Many experts have studied traditional contact tracing and developed digital contact tracking. In order to better understand the field of contact tracking, it is necessary to analyze the development of contact tracking in the field of computer science by bibliometrics. The purpose of this research is to use literature statistics and topic analysis to characterize the research literature of contact tracking in the field of computer science, to gain an in-depth understanding of the literature development status of contact tracking and the trend of hot topics over the past decade. In order to achieve the aforementioned goals, we conducted a bibliometric study in this paper. The study uses data collected from the Scopus database. Which contains more than 10,000 articles, including more than 2,000 in the field of computer science. For popular trends, we use VOSviewer for visual analysis. The number of contact tracking documents published annually in the computer field is increasing. At present, there are 200 to 300 papers published in the field of computer science each year, and the number of uncited papers is relatively small. Through the visual analysis of the paper, we found that the hot topic of contact tracking has changed from the past “mathematical model,” “biological model,” and “algorithm” to the current “digital contact tracking,” “privacy,” and “mobile application” and other topics. Contact tracking is currently a hot research topic. By selecting the most cited papers, we can display high-quality literature in contact tracking and characterize the development trend of the entire field through topic analysis. This is useful for students and researchers new to field of contact tracking ai well as for presenting our results to other subjects. Especially when comprehensive research cannot be conducted due to time constraints or lack of precise research questions, our research analysis can provide value for it.
Huijun Jin, Won Gi Choi, Jonghwan Choi, Hanseung Sung, Sanghyun Park
Vol. 18, No. 3, pp. 374-388, Jun. 2022
Keywords: database, genetic algorithm, Log-Structured Merge-Tree, Optimization, Random Forest, Space Amplification, Write Amplification
Show / Hide AbstractDatabase systems usually have many parameters that must be configured by database administrators and users. RocksDB achieves fast data writing performance using a log-structured merged tree. This database has many parameters associated with write and space amplifications. Write amplification degrades the database performance, and space amplification leads to an increased storage space owing to the storage of unwanted data. Previously, it was proven that significant performance improvements can be achieved by tuning the database parameters. However, tuning the multiple parameters of a database is a laborious task owing to the large number of potential configuration combinations. To address this problem, we selected the important parameters that affect the performance of RocksDB using random forest. We then analyzed the effects of the selected parameters on write and space amplifications using analysis of variance. We used a genetic algorithm to obtain optimized values of the major parameters. The experimental results indicate an insignificant reduction (-5.64%) in the execution time when using these optimized values; however, write amplification, space amplification, and data processing rates improved considerably by 20.65%, 54.50%, and 89.68%, respectively, as compared to the performance when using the default settings.
Vol. 18, No. 3, pp. 389-401, Jun. 2022
Keywords: Allocation of Communication Resources, genetic algorithm, internet of vehicles, Knapsack Problem, MEC
Show / Hide AbstractThe business of Internet of Vehicles (IoV) is growing rapidly, and the large amount of data exchange has caused problems of large mobile network communication delay and large energy loss. A strategy for resource allocation of IoV communication based on mobile edge computing (MEC) is thus proposed. First, a model of the cloud-side collaborative cache and resource allocation system for the IoV is designed. Vehicles can offload tasks to MEC servers or neighboring vehicles for communication. Then, the communication model and the calculation model of IoV system are comprehensively analyzed. The optimization objective of minimizing delay and energy consumption is constructed. Finally, the on-board computing task is coded, and the optimization problem is transformed into a knapsack problem. The optimal resource allocation strategy is obtained through genetic algorithm. The simulation results based on the MATLAB platform show that: The proposed strategy offloads tasks to the MEC server or neighboring vehicles, making full use of system resources. In different situations, the energy consumption does not exceed 300 J and 180 J, with an average delay of 210 ms, effectively reducing system overhead and improving response speed.
Jaehyeok Han, Sangjin Lee
Vol. 18, No. 3, pp. 402-410, Jun. 2022
Keywords: Digital Forensics, Filesystem, Multimedia, OS, Reversal, Smartphone, timestamp
Show / Hide AbstractDigital data can be manipulated easily, so information related to the timestamp is important in establishing the reliability of the data. The time values for a certain file can be extracted following the analysis of the filesystem metadata or file internals, and the information can be utilized to organize a timeline for a digital investigation. Suppose the reversal of a timestamp is found on a mobile device during this process. In this case, a more detailed analysis is required due to the possibility of anti-forensic activity, but little previous research has investigated the handling and possible manipulation of timestamps on mobile devices. Therefore, in this study, we determine how time values for multimedia files are handled according to the operating system or filesystem on mobile devices. We also discuss five types of timestamps—file created (C), last modified (M), last accessed (A), digitalized (Di), and filename (FN) of multimedia files, and experimented with their operational features across multiple devices such as smartphones and cameras.
Ze-dong Dun, Jian-yu Chen, Mei-xia Qu, Bin Jiang
Vol. 18, No. 3, pp. 411-427, Jun. 2022
Keywords: Character recognition, feature extraction, FPN, RefineMask, Seal Character Segmentation
Show / Hide AbstractDigging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.
Development of a Real-Time Automatic Passenger Counting System using Head Detection Based onDeep LearningHyunduk Kim, Myoung-Kyu Sohn, Sang-Heon Lee
Vol. 18, No. 3, pp. 428-442, Jun. 2022
Keywords: Automatic Passenger Counting, Deep Learning, Embedded System, Head Detection
Show / Hide AbstractA reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.
Hongqi Xi, Huijuan Sun
Vol. 18, No. 3, pp. 443-456, Jun. 2022
Keywords: DDQN Model, internet of vehicles, Markov Decision Model, Mobile Edge Computing, system model
Show / Hide AbstractAn efficient and reasonable resource allocation strategy can greatly improve the service quality of Internet of Vehicles (IoV). However, most of the current allocation methods have overestimation problem, and it is difficult to provide high-performance IoV network services. To solve this problem, this paper proposes a network resource allocation strategy based on deep learning network model DDQN. Firstly, the method implements the refined modeling of IoV model, including communication model, user layer computing model, edge layer offloading model, mobile model, etc., similar to the actual complex IoV application scenario. Then, the DDQN network model is used to calculate and solve the mathematical model of resource allocation. By decoupling the selection of target Q value action and the calculation of target Q value, the phenomenon of overestimation is avoided. It can provide higher-quality network services and ensure superior computing and processing performance in actual complex scenarios. Finally, simulation results show that the proposed method can maintain the network delay within 65 ms and show excellent network performance in high concurrency and complex scenes with task data volume of 500 kbits.