Conditional Generative Adversarial Nets(CGAN) is often used to improve conditional image generation ***,there is little research on Representation learning with CGAN for causal *** paper proposes a new method for find...
详细信息
Conditional Generative Adversarial Nets(CGAN) is often used to improve conditional image generation ***,there is little research on Representation learning with CGAN for causal *** paper proposes a new method for finding representation learning functions by adopting the adversarial *** apply the pattern of CGAN and theoretically demonstrate the feasibility of finding a suitable representation function in the context of two distributions being *** theoretical result shows that when two distributions are balanced,the ideal representation function can be found and thus can be used to further research.
Radio maps enrich radio propagation and spectrum occupancy information, which provides fundamental support for the operation and optimization of wireless communication systems. Traditional radio maps are mainly achiev...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Radio maps enrich radio propagation and spectrum occupancy information, which provides fundamental support for the operation and optimization of wireless communication systems. Traditional radio maps are mainly achieved by extensive manual channel measurements, which is time-consuming and inefficient. To reduce the complexity of channel measurements, radio map estimation (RME) through novel artificial intelligence techniques has emerged to attain higher resolution radio maps from sparse measurements or few observations. However, black box problems and strong dependency on training data make learning-based methods less explainable, while model-based methods offer strong theoretical grounding but perform inferior to the learning-based methods. In this paper, we develop a deep unrolled low-rank tensor completion network (DULRTC-RME) for radio map estimation, which integrates theoretical interpretability and learning ability by unrolling the tedious low-rank tensor completion optimization into a deep network. It is the first time that algorithm unrolling technology has been used in the RME field. Experimental results demonstrate that DULRTC-RME outperforms existing RME methods.
Cricket is a popular sport worldwide, played with a bat and balls. This paper used classification and regression to predict the T20 and Test matches results and scores because cricket fans and analysts always want to ...
详细信息
ISBN:
(数字)9798350349719
ISBN:
(纸本)9798350349726
Cricket is a popular sport worldwide, played with a bat and balls. This paper used classification and regression to predict the T20 and Test matches results and scores because cricket fans and analysts always want to predict which team will win the match and how much score a team will make. We have used a supervised machine learning technique to predict the score and result for T20 and Test matches. Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model. For the prediction of winning and losing, we have used Naïve Bayes, Gradient Boosted Trees, Logistic Regression, Deep learning, Decision Tree, Random Forest, and Generalized Linear Model. For Score Prediction, we have used Decision Trees, Random Forests, Gradient Boosted Trees, Generalized Linear Models, and Deep Learning. We've shown the most accurate model after evaluating the accuracy percentages of the several classifiers listed above. Our introduced model has gained an accuracy rate of 96.15% using the Gradient Boosted Trees classifier for Match Score Prediction and 71.72% accuracy by using the Generalized Linear Model for match result prediction. The Rapid Miner tool has been used to perform machine learning techniques to train models. This paper discusses the effectiveness and use of machine learning methods to develop highly accurate models for Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model.
Grouping vehicles into platoons is a promising cooperative driving scenario to enhance the traffic safety and capacity of future vehicular networks. However, fast changing channel conditions in multi-platoon vehicular...
详细信息
With technology for digital photography and high resolution displays rapidly evolving and gaining popularity, there is a growing demand for blind image quality assessment (BIQA) models for high resolution images. Unfo...
详细信息
A hashing index provides rapid search performance by swiftly locating key-value items. Non-volatile memory (NVM) technologies have driven research into hashing indexes for NVM, combining hard disk persistence with DRA...
详细信息
ISBN:
(数字)9783982674100
ISBN:
(纸本)9798331534646
A hashing index provides rapid search performance by swiftly locating key-value items. Non-volatile memory (NVM) technologies have driven research into hashing indexes for NVM, combining hard disk persistence with DRAM-level performance. Nevertheless, current NVM-based hashing indexes must tackle data inconsistency challenges caused by NVM write reordering or partial writes, and mitigate rapid local wear due to frequent updates, considering NVM's limited endurance. The temporary allocation of buckets in NVM-based chained hashing to resolve hash collisions prolongs the critical path for writing, thus hampering write performance. This paper presents WOPHI, a write-optimized persistent hash index scheme for NVM. By utilizing log-free failure-atomic writes, WOPHI minimizes data consistency overhead and addresses hash conflicts with bucket pre-allocation. Experimental results underscore WOPHI's significant performance enhancements, with insertion latency slashed by up to 88.2% and deletion latency boosted by up to 82.6% compared to existing state-of-the-art schemes. Moreover, WOPHI substantially mitigates data consistency overhead, reducing cache line flushes by 59.3%, while maintaining robust write throughput for insert and delete operations.
Parallel task systems with real-time constraints are widely applied in various fields. Response time analysis is a necessary condition for online admission of applications in dynamic systems. This article focuses on t...
详细信息
ISBN:
(数字)9798331507077
ISBN:
(纸本)9798331507084
Parallel task systems with real-time constraints are widely applied in various fields. Response time analysis is a necessary condition for online admission of applications in dynamic systems. This article focuses on the worst-case response time (WCRT) analysis of directed acyclic graph (DAG) tasks on multiprocessors under partitioned scheduling. We propose a new WCRT analysis algorithm, named the radiative-extended structure analysis (RESA) algorithm. We demonstrate that an-alyzing the radiative-extended structure (Res) helps to obtain more accurate analysis results. Compared with state-of-the-art algorithms, RESA achieves tighter upper bounds on self-interference and high-priority interference without increasing time and space complexity. RESA performs better by comparing the average response time observed in simulation experiments.
Stock price forecasting is challenging because stock markets are volatile and nonlinear in nature. With the impact of the Covid-19 outbreak in 2019, stock market forecasting has become more complicated. The goal of th...
Stock price forecasting is challenging because stock markets are volatile and nonlinear in nature. With the impact of the Covid-19 outbreak in 2019, stock market forecasting has become more complicated. The goal of this study is to identify the top brands in the global covid-19 vaccination market and their impact on the stock market. By forecasting the next months stock exchange, traders will be able to select the most suitable company to invest in. In this paper, MSE, RMSE, and MAPE are used as evaluation matrices to compare timeseries and neural network models such as Arima, Prophet, and LSTM. According to the results of a comparative analysis, the LSTM model produced the most accurate predictions on majority stock prices dataset for the selected vaccination brands. Brand stability is achieved by predicting future stock exchange prices using an outperformed LSTM model. As a result, BioNTech has been identified as a high potential stable brand that the buyer can invest to gain enormous returns among the massive number of probabilistic events.
Large-scale trajectory data is critical for a smart city to improve the efficiency of a transportation system. However, the release of original trajectory data violates privacy protection principles if no privacy-pres...
Large-scale trajectory data is critical for a smart city to improve the efficiency of a transportation system. However, the release of original trajectory data violates privacy protection principles if no privacy-preserving approach is adopted, that’s why the public trajectory data for research is so limited. To enable extensive available trajectory data publishing, we propose a Privacy-Preserving and research-utilizable Trajectory Generator (PPTG), which uses a deep generative model to provide utilizable synthetic trajectories. Specifically, PPTG can not only extract the intrinsic and spatial features, but also get rid of possible privacy information from the real trajectories. In experiments, we show that the privacy-preserving trajectory data generated by PPTG can achieve superior performance in terms of privacy protection and data utility against the existing approaches.
In the era of rapid Internet expansion, the data generated has witnessed exponential growth, concealing valuable information within. Consequently, the field of data mining has flourished, finding extensive application...
In the era of rapid Internet expansion, the data generated has witnessed exponential growth, concealing valuable information within. Consequently, the field of data mining has flourished, finding extensive applications across diverse industries. However, its full potential remains untapped in the realm of higher education. In light of the "Big Data Analysis and Mining" course, this paper makes a detailed investigation on the problems existing in practical teaching. To address these problems, we propose an intelligent practical teaching platform based on data mining technology. This platform harnesses data mining and cloud storage techniques, adopting a blended approach that seamlessly integrates online and offline teaching methods. It offers a comprehensive solution for practical teaching, with the primary objective of enhancing the effectiveness of practical teaching and augmenting students’ hands-on capabilities. Finally, we present the outcomes and applications of this platform since its inception over one year ago, showcasing its tangible impact on higher education.
暂无评论