To see the other types of publications on this topic, follow the link: Predictive prefetch.
Journal articles on the topic 'Predictive prefetch'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 25 journal articles for your research on the topic 'Predictive prefetch.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
T., R. Gopalakrishnan Nair, and Jayarekha P. "Strategic Prefetching of VoD Programs Based on ART2 driven Request Clustering." International Journal of Information Sciences and Techniques (IJIST) 1, no. 2 (2011): 13–21. https://doi.org/10.5281/zenodo.8280938.
Full textAbstract:
In this paper we present a novel neural architecture to classify various types of VoD request arrival pattern using an unsupervised clustering Adaptive Resonance Theory 2 (ART2). The knowledge extracted from the ART2 clusters is used to prefetch the multimedia objects into the proxy server’s cache, from the disk and prepare the system to serve the clients more efficiently before the user’s arrival of the request. This approach adapts to changes in user request patterns over a period by storing the previous information. Each cluster is represented as prototype vector by generalizing the most frequently used video blocks that are accessed by all the cluster members. The simulation results of the proposed clustering and prefetching algorithm shows a significant increase in the performance of streaming server. The proposed algorithm helps the server’s agent to learn user preferences and discover the information about the corresponding videos. These videos can be prefetched to the cache and identify those videos for the users who demand it.
2
Alves, Ricardo, Stefanos Kaxiras, and David Black-Schaffer. "Early Address Prediction." ACM Transactions on Architecture and Code Optimization 18, no. 3 (2021): 1–22. http://dx.doi.org/10.1145/3458883.
Full textAbstract:
Achieving low load-to-use latency with low energy and storage overheads is critical for performance. Existing techniques either prefetch into the pipeline (via address prediction and validation) or provide data reuse in the pipeline (via register sharing or L0 caches). These techniques provide a range of tradeoffs between latency, reuse, and overhead. In this work, we present a pipeline prefetching technique that achieves state-of-the-art performance and data reuse without additional data storage, data movement, or validation overheads by adding address tags to the register file. Our addition of register file tags allows us to forward (reuse) load data from the register file with no additional data movement, keep the data alive in the register file beyond the instruction’s lifetime to increase temporal reuse, and coalesce prefetch requests to achieve spatial reuse. Further, we show that we can use the existing memory order violation detection hardware to validate prefetches and data forwards without additional overhead. Our design achieves the performance of existing pipeline prefetching while also forwarding 32% of the loads from the register file (compared to 15% in state-of-the-art register sharing), delivering a 16% reduction in L1 dynamic energy (1.6% total processor energy), with an area overhead of less than 0.5%.
3
Jain, Puneet, Justin Manweiler, Arup Acharya, and Romit Roy Choudhury. "Scalable Social Analytics for Live Viral Event Prediction." Proceedings of the International AAAI Conference on Web and Social Media 8, no. 1 (2014): 226–35. http://dx.doi.org/10.1609/icwsm.v8i1.14504.
Full textAbstract:
Large-scale, predictive social analytics have proven effective. Over the last decade, research and industrial efforts have understood the potential value of inferences based on online behavior analysis, sentiment mining, influence analysis, epidemic spread, etc. The majority of these efforts, however, are not yet designed with realtime responsiveness as a first-order requirement. Typical systems perform a post-mortem analysis on volumes of historical data and validate their “predictions” against already-occurred events.We observe that in many applications, real-time predictions are critical and delays of hours (and even minutes) can reduce their utility. As examples: political campaigns could react very quickly to a scandal spreading on Facebook; content distribution networks (CDNs) could prefetch videos that are predicted to soon go viral; online advertisement campaigns can be corrected to enhance consumer reception. This paper proposes CrowdCast, a cloud-based framework to enable real-time analysis and prediction from streaming social data. As an instantiation of this framework, we tune CrowdCast to observe Twitter tweets, and predict which YouTube videos are most likely to “go viral” in the near future. To this end, CrowdCast first applies online machine learning to map natural language tweets to a specific YouTube video. Then, tweets that indeed refer to videos are weighted by the perceived “influence” of the sender. Finally, the video’s spread is predicted through a sociological model, derived from the emerging structure of the graph over which the video-related tweets are (still) spreading. Combining metrics of influence and live structure, CrowdCast outputs sets of candidate videos, identified as likely to become viral in the next few hours. We monitor Twitter for more than 30 days, and find that CrowdCast’s real-time predictions demonstrate encouraging correlation with actual YouTube viewership in the near future.
4
Panda, Biswabandan, and Shankar Balachandran. "Expert Prefetch Prediction: An Expert Predicting the Usefulness of Hardware Prefetchers." IEEE Computer Architecture Letters 15, no. 1 (2016): 13–16. http://dx.doi.org/10.1109/lca.2015.2428703.
Full text
5
Shyamala, K., and S. Kalaivani. "Application of Monte Carlo Search for Performance Improvement of Web Page Prediction." International Journal of Engineering & Technology 7, no. 3.4 (2018): 133. http://dx.doi.org/10.14419/ijet.v7i3.4.16761.
Full textAbstract:
Prediction in web mining is one of the most complex tasks which will reduce web user latency. The main objective of this research work is to reduce web user latency by predicting and prefetching the users future request page. Web user activities were analyzed and monitored from the web server log file. The present work consists of two phases. In the first phase a directed graph is constructed for web user navigation with the reduction of repeated path. In the second phase, Monte Carlo search is applied on the constructed graph to predict the future request and prefetch the page. This work is successfully implemented and the prediction technique gives a better accuracy. This implementation paves a new way to prefetch the predicted pages at user end to reduce the user latency. Proposed Monte Carlo Prediction (MCP) Algorithm is compared with the existing algorithm Hidden Markov model. Proposed algorithm achieved better accuracy than the Hidden Markov Model. Accuracy is measured for the predicted web pages and achieved the optimal results.
6
Jung, Sungmin, Hyeonmyeong Lee, and Heeseung Jo. "CluMP: Clustered Markov Chain for Storage I/O Prefetch." Electronics 12, no. 15 (2023): 3293. http://dx.doi.org/10.3390/electronics12153293.
Full textAbstract:
Due to advancements in CPU and storage technologies, the processing speed of tasks has been increasing. However, there has been a relative slowdown in the data transfer speeds between disks and memory. Consequently, the issue of I/O processing speed has become a significant concern in I/O-intensive tasks. This research paper proposes CluMP, which predicts the next block to be requested within a process using a clustered Markov chain. Compared to the simple read-ahead approach commonly used in Linux systems, CluMP can predict prefetching more accurately and requires less memory for the prediction process. CluMP demonstrated a maximum memory hit ratio improvement of 191.41% in the KVM workload compared to read-ahead, as well as a maximum improvement of 130.81% in the Linux kernel build workload. Additionally, CluMP provides the advantage of adaptability to user objectives and utilized workloads by incorporating several parameters, thereby allowing for optimal performance across various workload patterns.
7
Shang, Jing, Zhihui Wu, Zhiwen Xiao, Yifei Zhang, and Jibin Wang. "BERT4Cache: a bidirectional encoder representations for data prefetching in cache." PeerJ Computer Science 10 (August 29, 2024): e2258. http://dx.doi.org/10.7717/peerj-cs.2258.
Full textAbstract:
Cache plays a crucial role in improving system response time, alleviating server pressure, and achieving load balancing in various aspects of modern information systems. The data prefetch and cache replacement algorithms are significant factors influencing caching performance. Due to the inability to learn user interests and preferences accurately, existing rule-based and data mining caching algorithms fail to capture the unique features of the user access behavior sequence, resulting in low cache hit rates. In this article, we introduce BERT4Cache, an end-to-end bidirectional Transformer model with attention for data prefetch in cache. BERT4Cache enhances cache hit rates and ultimately improves cache performance by predicting the user’s imminent future requested objects and prefetching them into the cache. In our thorough experiments, we show that BERT4Cache achieves superior results in hit rates and other metrics compared to generic reactive and advanced proactive caching strategies.
8
Yu, Genghua, and Jia Wu. "Content caching based on mobility prediction and joint user Prefetch in Mobile edge networks." Peer-to-Peer Networking and Applications 13, no. 5 (2020): 1839–52. http://dx.doi.org/10.1007/s12083-020-00954-x.
Full text
9
Hörbeck, E. A., L. Jonsson, E. Pålsson, and M. Landén. "More bipolar than bipolar disorder – a polygenic risk score analysis of postpartum psychosis." European Psychiatry 66, S1 (2023): S508—S509. http://dx.doi.org/10.1192/j.eurpsy.2023.1079.
Full textAbstract:
IntroductionPostpartum psychosis is a rare psychiatric emergency, occurring days to weeks after 1-2 per 1000 deliveries. Its low prevalence makes it difficult to recruit enough participants to investigate the underlying pathophysiology. It is epidemiologically linked to bipolar disorder, which one study also found it to resemble in genetic susceptibility for psychiatric disorders (Di Florio et al. Lancet Psych 2021; 8: 1045–52).ObjectivesIn this study we aim to investigate polygenic liability for psychiatric disorders in two new Swedish postpartum psychosis cohorts.MethodsCases with postpartum psychosis, defined as a psychiatric hospitalization within 6 weeks after delivery, and/or receiving a diagnosis of F53.1 (ICD 10) or 294.40 (ICD 8.), parous women with severe mental illness without postpartum psychosis, and healthy parous controls were identified in two Swedish genetic studies: the Swedish bipolar collection (SWEBIC) and Predictors for ECT (PREFECT). Polygenic risk scores (PRS) were calculated from summary statistics from genome wide studies on bipolar disorder (Mullins et al. Nat Genet 2021; 53 817-829), schizophrenia (Trubetskoy et al. Nature 2022; 604 502-508) and major depression (Wray et al. Nat Genet. 2018; 50 668-681). The p-value thresholds best predicting their respective phenotype were used in logistic regression analyses with the first six principal components and genotyping platform as confounders.ResultsWe identified 176 patients with postpartum psychosis and genetic information (N(SWEBIC)=126, N(PREFECT)=50). Compared with healthy parous women, patients with postpartum psychosis had significantly higher PRS for bipolar disorder (SWEBIC: odds ratio [OR] 2.6 (95% confidence interval [CI] 1.9-3.5), PREFECT: OR 2.4 (95% CI 1.8-3.2), Figure 1.) and schizophrenia (SWEBIC: OR 1.6 (95% CI 1.2-2.2), PREFECT: OR 1.8 (95%; CI 1.3-2.5)). Patients with postpartum psychosis had significantly higher PRS for bipolar disorder (SWEBIC: OR 1.4 (95% CI 1.2-1.8), PREFECT: OR 1.5 (95% CI 1.1-2)) compared with parous women with severe mental illness without postpartum psychosis. We found no associations with major depression PRS in either cohort.Image:ConclusionsWe replicated previous findings of significantly higher PRS for bipolar disorder and schizophrenia in postpartum psychosis compared with healthy controls. In contrast to previous research, we find postpartum psychosis cases to have higher PRS for bipolar disorder than bipolar disorder cases. Our findings highlight the genetic influence in postpartum psychosis and support previous genetic and epidemiological evidence that postpartum psychosis lies on the bipolar spectrum.Disclosure of InterestNone Declared
10
Choi, Seyun, Sukjun Hong, Hoijun Kim, Seunghyun Lee, and Soonchul Kwon. "Prefetching Method for Low-Latency Web AR in the WMN Edge Server." Applied Sciences 13, no. 1 (2022): 133. http://dx.doi.org/10.3390/app13010133.
Full textAbstract:
Recently, low-latency services for large-capacity data have been studied given the development of edge servers and wireless mesh networks. The 3D data provided for augmented reality (AR) services have a larger capacity than general 2D data. In the conventional WebAR method, a variety of data such as HTML, JavaScript, and service data are downloaded when they are first connected. The method employed to fetch all AR data when the client connects for the first time causes initial latency. In this study, we proposed a prefetching method for low-latency AR services. Markov model-based prediction via the partial matching (PPM) algorithm was applied for the proposed method. Prefetched AR data were predicted during AR services. An experiment was conducted at the Nowon Career Center for Youth and Future in Seoul, Republic of Korea from 1 June 2022 to 31 August 2022, and a total of 350 access data points were collected over three months; the prefetching method reduced the average total latency of the client by 81.5% compared to the conventional method.
11
Setia, Sonia, Jyoti, and Neelam Duhan. "Neural Network Based Prefetching Control Mechanism." International Journal of Engineering and Advanced Technology 9, no. 2 (2019): 1361–66. http://dx.doi.org/10.35940/ijeat.a5089.129219.
Full textAbstract:
An important issue incurred by users that limits the use of internet is the long web access delays. Most efficient way to solve this problem is to use “Prefetching”. This paper is an attempt to dynamically monitor the network bandwidth for which a neural network-based model has been worked upon. Prefetching is an effective and efficient technique for reducing users perceived latency. It is a technique that predicts & fetches the web pages in advance corresponding to the clients’ request, that will be accessed in future. Generally, this prediction is based on the historical information that the sever maintains for each web page it serves in a chronological order. This is a speculative technique where if predictions are incorrect then prefetching adds extra traffic to the network, which is seriously negating the network performance. Therefore, there is critical need of a mechanism that could analyze the network bandwidth of the system before prefetching is done. Based on network conditions, this model not only guides if the prefetching should be done or not but also tells number of pages which are to be prefetched in advance so that network bandwidth can be effectively utilized. Proposed control mechanism has been validated using NS-2 simulator and thus various adverse effects of prefetching in terms of response time and bandwidth utilization have been reduced.
12
Ma, Youwei, Jianping Li, Shaoqing Zhang, and Haoran Zhao. "A multi-model study of atmosphere predictability in coupled ocean–atmosphere systems." Climate Dynamics 56, no. 11-12 (2021): 3489–509. http://dx.doi.org/10.1007/s00382-021-05651-w.
Full textAbstract:
AbstractOf great importance for guiding numerical weather and climate predictions, understanding predictability of the atmosphere in the ocean − atmosphere coupled system is the first and critical step to understand predictability of the Earth system. However, previous predictability studies based on prefect model assumption usually depend on a certain model. Here we apply the predictability study with the Nonlinear Local Lyapunov Exponent and Attractor Radius to the products of multiple re-analyses and forecast models in several operational centers to realize general predictability of the atmosphere in the Earth system. We first investigated the predictability characteristics of the atmosphere in NCEP, ECMWF and UKMO coupled systems and some of their uncoupled counterparts and other uncoupled systems. Although the ECMWF Integrated Forecast System shows higher skills in geopotential height over the tropics, there is no certain model providing the most precise forecast for all variables on all levels and the multi-model ensemble not always outperforms a single model. Improved low-frequency signals from the air − sea and stratosphere − troposphere interactions that extend predictability of the atmosphere in coupled system suggests the significance of air − sea coupling and stratosphere simulation in practical forecast development, although uncertainties exist in the model representation for physical processes in air − sea interactions and upper troposphere. These inspire further exploration on predictability of ocean and stratosphere as well as sea − ice and land processes to advance our understanding of interactions of Earth system components, thus enhancing weather − climate prediction skills.
13
Sharma, Satyendra, and Srikanta Routroy. "Modeling information risk in supply chain using Bayesian networks." Journal of Enterprise Information Management 29, no. 2 (2016): 238–54. http://dx.doi.org/10.1108/jeim-03-2014-0031.
Full textAbstract:
Purpose – Information sharing enhances the supply chain profitability significantly, but it may result in adverse impacts also (e.g. leakages of secret information to competitors, sharing of wrong information that result into losses). So, it is important to understand the various risk factors that lead to distortion in information sharing and results in negative consequences. Information risk identification and assessment in supply chain would help in choosing right mitigation strategies. The purpose of this paper is to identify various information risks that could impact a supply chain, and develop a conceptual framework to quantify them. Design/methodology/approach – Bayesian belief network (BBN) modeling will be used to provide a framework for information risk analysis in a supply chain. Bayesian methodology provides the reasoning in causal relationship among various risk factors and incorporates both objective and subjective data. Findings – This paper presents a causal relationship among various information risks in a supply chain. Three important risk factors, namely, information security, information leakages and reluctance toward information sharing showed influence on a company’s revenue. Practical implications – Capability of Bayesian networks while modeling in uncertain conditions, provides a prefect platform for analyzing the risk factors. BBN provides a more robust method for studying the impact or predicting various risk factors. Originality/value – The major contribution of this paper is to develop a quantitative model for information risks in supply chain. This model can be updated when a new data arrives.
14
Fu, Chen, Heming Sun, Zhiqiang Zhang, and Jinjia Zhou. "A Highly Pipelined and Highly Parallel VLSI Architecture of CABAC Encoder for UHDTV Applications." Sensors 23, no. 9 (2023): 4293. http://dx.doi.org/10.3390/s23094293.
Full textAbstract:
Recently, specifically designed video codecs have been preferred due to the expansion of video data in Internet of Things (IoT) devices. Context Adaptive Binary Arithmetic Coding (CABAC) is the entropy coding module widely used in recent video coding standards such as HEVC/H.265 and VVC/H.266. CABAC is a well known throughput bottleneck due to its strong data dependencies. Because the required context model of the current bin often depends on the results of the previous bin, the context model cannot be prefetched early enough and then results in pipeline stalls. To solve this problem, we propose a prediction-based context model prefetching strategy, effectively eliminating the clock consumption of the contextual model for accessing data in memory. Moreover, we offer multi-result context model update (MCMU) to reduce the critical path delay of context model updates in multi-bin/clock architecture. Furthermore, we apply pre-range update and pre-renormalize techniques to reduce the multiplex BAE’s route delay due to the incomplete reliance on the encoding process. Moreover, to further speed up the processing, we propose to process four regular and several bypass bins in parallel with a variable bypass bin incorporation (VBBI) technique. Finally, a quad-loop cache is developed to improve the compatibility of data interactions between the entropy encoder and other video encoder modules. As a result, the pipeline architecture based on the context model prefetching strategy can remove up to 45.66% of the coding time due to stalls of the regular bin, and the parallel architecture can also save 29.25% of the coding time due to model update on average under the condition that the Quantization Parameter (QP) is equal to 22. At the same time, the throughput of our proposed parallel architecture can reach 2191 Mbin/s, which is sufficient to meet the requirements of 8 K Ultra High Definition Television (UHDTV). Additionally, the hardware efficiency (Mbins/s per k gates) of the proposed architecture is higher than that of existing advanced pipeline and parallel architectures.
15
G.Bharathikannan and G.Gayathri. "Distributed File System To Data Prefetching For Cloud." July 30, 2023. https://doi.org/10.5281/zenodo.8197211.
Full textAbstract:
The history of disk I/O access events, and then send the prefetched data to the relevant user machines proactively. To put this technique to work, the data about client nodes is piggybacked onto the real client This paper presents an initiative information prefetching scheme on the room servers in distributed file systems for cloud computing. In this prefetching technique, the client machines are not substantially involved in the process of information prefetching, but the storage servers can directly prefetch the data after analyzing I/O requests, and then forwarded to the relevant room server. Next, two prediction algorithms have been proposed to forecast past block access operations for directing what data should be fetched on storage servers in advance. Finally, the prefaced data can be pushed to the relevant client machine from the storage server. Through a series of evaluation research with a collection of application benchmarks, we have demonstrated that our presented initiative prefetching technique can advantage distributed file systems for cloud environments to achieve better I/O performance. In particular, configuration-limited client machines in the cloud are not culpable for predicting I/O access operations, which can definitely contribute to preferable scheme performance on them
16
Zhang, Pengmiao, Rajgopal Kannan, Anant V. Nori, and Viktor K. Prasanna. "Accelerating Graph Analytics Using Attention-Based Data Prefetcher." SN Computer Science 5, no. 5 (2024). http://dx.doi.org/10.1007/s42979-024-02989-w.
Full textAbstract:
AbstractGraph analytics shows promise for solving challenging problems on relational data. However, memory constraints arise from the large size of graphs and the high complexity of algorithms. Data prefetching is a crucial technique to hide memory access latency by predicting and fetching data into the memory cache beforehand. Traditional prefetchers struggle with fixed rules in adapting to complex memory access patterns in graph analytics. Machine learning (ML) algorithms, particularly long short-term memory (LSTM) models, excel in memory access prediction. However, they encounter challenges such as difficulty in learning interleaved access patterns and high storage costs when predicting in large memory address space. In addition, there remains a gap between designing a high-performance ML-based memory access predictor and developing an effective ML-based prefetcher for an existing memory system. In this work, we propose a novel Attention-based prefetching framework to accelerate graph analytics applications. To achieve high-performance memory access prediction, we propose A2P, a novel Attention-based memory Access Predictor for graph analytics. We use the multi-head self-attention mechanism to extract features from memory traces. We design a novel bitmap labeling method to collect future deltas within a spatial range, making interleaved patterns easier to learn. We introduce a novel super page concept, allowing the model to surpass physical page constraints. To integrate A2P into a memory system, we design a three-module prefetching framework composed of an existing memory hierarchy, a prefetch controller, and the predictor A2P. In addition, we propose a hybrid design to combine A2P and existing hardware prefetchers for higher prefetching performance. We evaluate A2P and the prefetching framework using the widely used GAP benchmark. Prediction experiments show that for the top three predictions, A2P outperforms the widely used state-of-the-art LSTM-based model by 23.1% w.r.t. Precision, 21.2% w.r.t. Recall, and 10.4% w.r.t. Coverage. Prefetching experiments show that A2P provides 18.4% IPC Improvement on average, outperforming state-of-the-art prefetchers BO by 17.2%, ISB by 15.0%, and Delta-LSTM by 10.9%. The hybrid prefetcher combining A2P and ISB achieves 21.7% IPC Improvement, outperforming the hybrid of BO and ISB by 16.3%.
17
Xu, Tao, and Youchao Sun. "Prefetch and Push Method of Flight Information Based on Migration Workflow." Journal of Aerospace Information Systems, October 24, 2023, 1–13. http://dx.doi.org/10.2514/1.i011197.
Full textAbstract:
As the architecture of aircraft cockpit panels becomes more complicated and more flight data are placed onto the panels, trainee pilots require more time during flight training to learn and comprehend flight information. This problem lengthens flight training time and raises costs. This paper proposes a mechanism for prefetching and pushing flight information to facilitate flight training for trainee pilots. This paper addresses the challenges of a high quantity of data and the chaotic time-series relationship between distinct data in flight sequence data by building a migration workflow model in the aircraft cockpit environment and getting flight data with shorter time intervals. Then the flight data are input into the Multilayer Perceptron Long Short-Term Memory (MLP-LSTM) prediction algorithm, which generates the prompt operation information and prediction information by analyzing the current flight data and predicting flight data of next stage. A case study of the takeoff stage is given. The experimental results of the prediction algorithm are given, which prove that the time-series flight data refined by the migration workflow model and MLP-LSTM algorithm have a better prediction effect compared with the LSTM algorithm.
18
Sofien, Chtourou, Chtourou Mohamed, and Hammami Omar. "Performance Evaluation of Neural Network Prediction for Data Prefetching in Embedded Applications." International Journal of Information, Control and Computer Sciences 1.0, no. 12 (2007). https://doi.org/10.5281/zenodo.1331439.
Full textAbstract:
Embedded systems need to respect stringent real time constraints. Various hardware components included in such systems such as cache memories exhibit variability and therefore affect execution time. Indeed, a cache memory access from an embedded microprocessor might result in a cache hit where the data is available or a cache miss and the data need to be fetched with an additional delay from an external memory. It is therefore highly desirable to predict future memory accesses during execution in order to appropriately prefetch data without incurring delays. In this paper, we evaluate the potential of several artificial neural networks for the prediction of instruction memory addresses. Neural network have the potential to tackle the nonlinear behavior observed in memory accesses during program execution and their demonstrated numerous hardware implementation emphasize this choice over traditional forecasting techniques for their inclusion in embedded systems. However, embedded applications execute millions of instructions and therefore millions of addresses to be predicted. This very challenging problem of neural network based prediction of large time series is approached in this paper by evaluating various neural network architectures based on the recurrent neural network paradigm with pre-processing based on the Self Organizing Map (SOM) classification technique.
19
Gellert, Arpad. "Web Usage Mining by Neural Hybrid Prediction with Markov Chain Components." Journal of Web Engineering, July 19, 2021. http://dx.doi.org/10.13052/jwe1540-9589.2053.
Full textAbstract:
This paper presents and evaluates a two-level web usage prediction technique, consisting of a neural network in the first level and contextual component predictors in the second level. We used Markov chains of different orders as contextual predictors to anticipate the next web access based on specific web access history. The role of the neural network is to decide, based on previous behaviour, whose predictor’s output to use. The predicted web resources are then prefetched into the cache of the browser. In this way, we considerably increase the hit rate of the web browser, which shortens the load times. We have determined the optimal configuration of the proposed hybrid predictor on a real dataset and compared it with other existing web prefetching techniques in terms of prediction accuracy. The best configuration of the proposed neural hybrid method provides an average web access prediction accuracy of 86.95%.
20
P., Sengottuvelan, and Gopalakrishnan T. "Efficient Web Usage Mining Based on K-Medoids Clustering Technique." November 2, 2015. https://doi.org/10.5281/zenodo.1110664.
Full textAbstract:
Web Usage Mining is the application of data mining techniques to find usage patterns from web log data, so as to grasp required patterns and serve the requirements of Web-based applications. User's expertise on the internet may be improved by minimizing user's web access latency. This may be done by predicting the future search page earlier and the same may be prefetched and cached. Therefore, to enhance the standard of web services, it is needed topic to research the user web navigation behavior. Analysis of user's web navigation behavior is achieved through modeling web navigation history. We propose this technique which cluster's the user sessions, based on the K-medoids technique.
21
Shu, Xiaokui, Nikolay Laptev, and Danfeng Yao. "DECT: Distributed Evolving Context Tree for Understanding User Behavior Pattern Evolution." Proceedings of the AAAI Conference on Artificial Intelligence 30, no. 1 (2016). http://dx.doi.org/10.1609/aaai.v30i1.9835.
Full textAbstract:
Internet user behavior models characterize user browsing dynamics or the transitions among web pages. The models help Internet companies improve their services by accurately targeting customers and providing them the information they want. For instance, specific web pages can be customized and prefetched for individuals based on sequences of web pages they have visited. Existing user behavior models abstracted as time-homogeneous Markov models cannot efficiently model user behavior variation through time. This demo presents DECT, a scalable time-variant variable-order Markov model. DECT digests terabytes of user session data and yields user behavior patterns through time. We realize DECT using Apache Spark and deploy it on top of Yahoo! infrastructure. We demonstrate the benefits of DECT with anomaly detection and ad click rate prediction applications. DECT enables the detection of higher-order path anomalies and provides deep insights into ad click rates with respect to user visiting paths.
22
An, Hongli, Kaijie Xing, and Yao Chen. "Adaptive sampling physics-informed neural network method for high-order rogue waves and parameters discovery of the (2 + 1)-dimensional CHKP equation." Chaos: An Interdisciplinary Journal of Nonlinear Science 34, no. 4 (2024). http://dx.doi.org/10.1063/5.0193513.
Full textAbstract:
Rogue waves are important physical phenomena, which have wide applications in nonlinear optics, hydrodynamics, Bose–Einstein condensates, and oceanic and atmospheric dynamics. We find that when using the original PINNs to study rogue waves of high dimensional PDEs, the prediction performance will become very poor, especially for high-order rogue waves due to that the randomness of selection of sample points makes insufficient use of the physical information describing the local sharp regions of rogue waves. In this paper, we propose an adaptive sampling physics-informed neural network method (ASPINN), which renders the points in local sharp regions to be selected sufficiently by a new adaptive search algorithm to lead to a prefect prediction performance. To valid the performance of our method, the (2+1)-dimensional CHKP equation is taken as an illustrative example. Experimental results reveal that the original PINNs can hardly be able to predict dynamical behaviors of the high-order rogue waves for the CHKP equation, but the ASPINN method can not only predict dynamical behaviors of these high-order rogue waves, but also greatly improve the prediction efficiency and accuracy to four orders of magnitude. Then, the data-driven inverse problem for the CHKP equation with different levels of corrupted noise is studied to show that the ASPINN method has good robustness. Moreover, some main factors affecting the neural network performance are discussed in detail, including the size of training data, the number of layers of the neural network, and the number of neurons per layer.
23
Han, Xu, Hui Li, Sha-Sha Dong, et al. "Application of triple evaluation method in predicting the efficacy of neoadjuvant therapy for breast cancer." World Journal of Surgical Oncology 21, no. 1 (2023). http://dx.doi.org/10.1186/s12957-023-02998-8.
Full textAbstract:
Abstract Objective To analyze the factors related to the efficacy of neoadjuvant therapy for breast cancer and find appropriate evaluation methods for evaluating the efficacy of neoadjuvant therapy Methods A total of 143 patients with breast cancer treated by neoadjuvant chemotherapy at Baotou Cancer Hospital were retrospectively analyzed. The chemotherapy regimen was mainly paclitaxel combined with carboplatin for 1 week, docetaxel combined with carboplatin for 3 weeks, and was replaced with epirubicin combined with cyclophosphamide after evaluation of disease progression. All HER2-positive patients were treated with simultaneous targeted therapy, including trastuzumab single-target therapy and trastuzumab combined with pertuzumab double-target therapy. Combined with physical examination, color Doppler ultrasound, and magnetic resonance imaging (MRI), a systematic evaluation system was initially established—the “triple evaluation method.” A baseline evaluation was conducted before treatment. The efficacy was evaluated by physical examination and color Doppler every cycle, and the efficacy was evaluated by physical examination, color Doppler, and MRI every two cycles. Results The increase in ultrasonic blood flow after treatment could affect the efficacy of monitoring. The presence of two preoperative time–signal intensity curves is a therapeutically effective protective factor for inflow. The triple evaluation determined by physical examination, color Doppler ultrasound, and MRI in determining clinical efficacy is consistent with the effectiveness of the pathological gold standard. Conclusion The therapeutic effect of neoadjuvant therapy can be better evaluated by combining clinical physical examination, color ultrasound, and nuclear magnetic resonance evaluation. The three methods complement each other to avoid the insufficient evaluation of a single method, which is convenient for most prefecty-level hospitals. Additionally, this method is simple, feasible, and suitable for promotion.
24
"Neural Network Based Prefetching Control Mechanism." International Journal of Engineering and Advanced Technology 9, no. 2 (2019): 1361–66. http://dx.doi.org/10.35940/ijeat.b2621.129219.
Full textAbstract:
An important issue incurred by users that limits the use of internet is the long web access delays. Most efficient way to solve this problem is to use “Prefetching”. This paper is an attempt to dynamically monitor the network bandwidth for which a neural network-based model has been worked upon. Prefetching is an effective and efficient technique for reducing users perceived latency. It is a technique that predicts & fetches the web pages in advance corresponding to the clients’ request, that will be accessed in future. Generally, this prediction is based on the historical information that the sever maintains for each web page it serves in a chronological order. This is a speculative technique where if predictions are incorrect then prefetching adds extra traffic to the network, which is seriously negating the network performance. Therefore, there is critical need of a mechanism that could analyze the network bandwidth of the system before prefetching is done. Based on network conditions, this model not only guides if the prefetching should be done or not but also tells number of pages which are to be prefetched in advance so that network bandwidth can be effectively utilized. Proposed control mechanism has been validated using NS-2 simulator and thus various adverse effects of prefetching in terms of response time and bandwidth utilization have been reduced.
25
Steen, H., M. Montenbruck, B. Gersak, et al. "Intramyocardial fast-SENC is less impacted by compensatory mechanisms while monitoring cardiotoxic effects of chemotherapy than echocardiography and conventional CMR: the PREFECT study." European Heart Journal 41, Supplement_2 (2020). http://dx.doi.org/10.1093/ehjci/ehaa946.1222.
Full textAbstract:
Abstract Background Cancer treatments (CT) have been shown to occasionally elicit a toxic reaction on the heart. Echocardiography (ECHO) and cardiac magnetic resonance imaging (CMR) have been used to monitor cardiotoxicity through left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS). Fast-SENC (fSENC) CMR testing directly measures intramyocardial contraction to quantify subtle changes in function capable of detecting cardiotoxicity missed by conventional imaging modalities. The PREFECT study compares fast-SENC vs ECHO in terms of sensitivity of predicting and detecting subclinical (sCTX) or clinical cardiotoxicity (cCTX) irrespective of loading conditions or changes in cardiac output. Methods A single center, prospective clinical trial of patients receiving anthracycline-based CT had fSENC acquired during CMR exams with a 1.5T scanner. Intramyocardial LV & RV strain was quantified with MyoStrain software. Three short axis scans (basal, midventricular, & apical) were used to calculate peak strain in 16 LV & 6 RV longitudinal segments while three long axis scans (2-, 3-, & 4-chamber) were used to calculate 21 LV & 5 RV circumferential segments. Results 63 patients had 323 scans; 41% experienced sCTX and 15% cCTX. Figure 1 shows a Box and Whisker's plot for the % of fSENC ≤−17 by cardiotoxicity status. Both fSENC and CMR LVEF detected sCTX and cCTX based on ANOVA analysis (p<0.001) although fSENC had better delineation of both sCTX and cCTX. However, ECHO LVEF and GLS did not detect sCTX or cCTX (p=NS). CMR stroke volume index decreased while blood pressure and heart rate increased for both sCTX and cCTX (p<0.001). Meanwhile, mass index and end-systolic volume index increased for cCTX (p<0.001). Conclusion Segmental fSENC detected early CT-induced sCTX regardless of loading conditions. ECHO did not detect sCTX potentially due to compensatory mechanisms or acoustic window limitations in breast cancer and lymphoma patients that had less effect on CMR. Figure 1 Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Myocardial solution (MSI)