This article delves into the intricate relationship between big data, cloud computing, and artificial intelligence, shedding light on their fundamental attributes and interdependence. It explores the seamless amalgama...This article delves into the intricate relationship between big data, cloud computing, and artificial intelligence, shedding light on their fundamental attributes and interdependence. It explores the seamless amalgamation of AI methodologies within cloud computing and big data analytics, encompassing the development of a cloud computing framework built on the robust foundation of the Hadoop platform, enriched by AI learning algorithms. Additionally, it examines the creation of a predictive model empowered by tailored artificial intelligence techniques. Rigorous simulations are conducted to extract valuable insights, facilitating method evaluation and performance assessment, all within the dynamic Hadoop environment, thereby reaffirming the precision of the proposed approach. The results and analysis section reveals compelling findings derived from comprehensive simulations within the Hadoop environment. These outcomes demonstrate the efficacy of the Sport AI Model (SAIM) framework in enhancing the accuracy of sports-related outcome predictions. Through meticulous mathematical analyses and performance assessments, integrating AI with big data emerges as a powerful tool for optimizing decision-making in sports. The discussion section extends the implications of these results, highlighting the potential for SAIM to revolutionize sports forecasting, strategic planning, and performance optimization for players and coaches. The combination of big data, cloud computing, and AI offers a promising avenue for future advancements in sports analytics. This research underscores the synergy between these technologies and paves the way for innovative approaches to sports-related decision-making and performance enhancement.展开更多
The prevalent multi-copy routing algorithms in mobile opportunistic networks(MONs)easily cause network congestion.This paper introduces a disjoint-path(DP)routing algorithm,where each node can only transmit packets on...The prevalent multi-copy routing algorithms in mobile opportunistic networks(MONs)easily cause network congestion.This paper introduces a disjoint-path(DP)routing algorithm,where each node can only transmit packets once except the source node,to effectively control the number of packet copies in the network.The discrete continuous time Markov chain(CTMC)was utilized to analyze the state transition between nodes,and the copy numbers of packets with the DP routing algorithm were calculated.Simulation results indicate that DP has a great improvement in terms of packet delivery ratio,average delivery delay,average network overhead,energy and average hop count.展开更多
The spread of rumors and diseases threatens the development of society,it is of great practical significance to locate propagation source quickly and accurately when rumors or epidemic outbreaks occur.However,the topo...The spread of rumors and diseases threatens the development of society,it is of great practical significance to locate propagation source quickly and accurately when rumors or epidemic outbreaks occur.However,the topological structure of online social network changes with time,which makes it very difficult to locate the propagation source.There are few studies focus on propagation source identification in dynamic networks.However,it is usually necessary to know the propagation model in advance.In this paper the label propagation algorithm is proposed to locate propagation source in temporal network.Then the propagation source was identified by hierarchical processing of dynamic networks and label propagation backwards without any underlying information dissemination model.Different propagation models were applied for comparative experiments on static and dynamic networks.Experimental results verify the effectiveness of the algorithm on temporal networks.展开更多
文摘This article delves into the intricate relationship between big data, cloud computing, and artificial intelligence, shedding light on their fundamental attributes and interdependence. It explores the seamless amalgamation of AI methodologies within cloud computing and big data analytics, encompassing the development of a cloud computing framework built on the robust foundation of the Hadoop platform, enriched by AI learning algorithms. Additionally, it examines the creation of a predictive model empowered by tailored artificial intelligence techniques. Rigorous simulations are conducted to extract valuable insights, facilitating method evaluation and performance assessment, all within the dynamic Hadoop environment, thereby reaffirming the precision of the proposed approach. The results and analysis section reveals compelling findings derived from comprehensive simulations within the Hadoop environment. These outcomes demonstrate the efficacy of the Sport AI Model (SAIM) framework in enhancing the accuracy of sports-related outcome predictions. Through meticulous mathematical analyses and performance assessments, integrating AI with big data emerges as a powerful tool for optimizing decision-making in sports. The discussion section extends the implications of these results, highlighting the potential for SAIM to revolutionize sports forecasting, strategic planning, and performance optimization for players and coaches. The combination of big data, cloud computing, and AI offers a promising avenue for future advancements in sports analytics. This research underscores the synergy between these technologies and paves the way for innovative approaches to sports-related decision-making and performance enhancement.
基金the National Natural Science Foundation of China under Grants U1804164,61902112 and U1404602in part by the Science and Technology Foundation of Henan Educational Committee under Grants 19A510015,20A520019,20A520020.
文摘The prevalent multi-copy routing algorithms in mobile opportunistic networks(MONs)easily cause network congestion.This paper introduces a disjoint-path(DP)routing algorithm,where each node can only transmit packets once except the source node,to effectively control the number of packet copies in the network.The discrete continuous time Markov chain(CTMC)was utilized to analyze the state transition between nodes,and the copy numbers of packets with the DP routing algorithm were calculated.Simulation results indicate that DP has a great improvement in terms of packet delivery ratio,average delivery delay,average network overhead,energy and average hop count.
文摘The spread of rumors and diseases threatens the development of society,it is of great practical significance to locate propagation source quickly and accurately when rumors or epidemic outbreaks occur.However,the topological structure of online social network changes with time,which makes it very difficult to locate the propagation source.There are few studies focus on propagation source identification in dynamic networks.However,it is usually necessary to know the propagation model in advance.In this paper the label propagation algorithm is proposed to locate propagation source in temporal network.Then the propagation source was identified by hierarchical processing of dynamic networks and label propagation backwards without any underlying information dissemination model.Different propagation models were applied for comparative experiments on static and dynamic networks.Experimental results verify the effectiveness of the algorithm on temporal networks.
