发布求助
文献互助 智能选刊 最新文献

Infocommunications Journal最新文献

筛选
英文 中文
Improve Performance of Fine-tuning Language Models with Prompting 使用提示提高微调语言模型的性能
IF 1.1
Infocommunications Journal Pub Date : 2023-01-01 DOI: 10.36244/icj.2023.5.10
Noémi Ligeti-Nagy, Zijian Győző Yang
{"title":"Improve Performance of Fine-tuning Language Models with Prompting","authors":"Noémi Ligeti-Nagy, Zijian Győző Yang","doi":"10.36244/icj.2023.5.10","DOIUrl":"https://doi.org/10.36244/icj.2023.5.10","url":null,"abstract":"This paper explores the effectiveness of prompt programming in the fine-tuning process of a Hungarian language model. The study builds on the prior success of prompt engineering in natural language processing tasks and employs the prompting method to enhance the fine-tuning performance of a huBERT model on several benchmark datasets of HuLU. The experimentation involves testing 45 prompt combinations for the HuCoPA dataset and 15 prompt variations for the HuRTE and HuWNLI datasets. The findings reveal that the addition of an instructional text consistently produces the best results across all winning cases, and that the [CLS] token produces the best results in the separator token experiments. The most significant enhancement was observed in the HuWNLI dataset, with an increase in accuracy from 65% to 85%. These results demon- strate that the addition of instruct text is crucial and sufficient in enabling the language model to effectively interpret and solve the Winograd Schemata problem. These results showcase the potential of prompt programming in enhancing the performance of language models in fine-tuning tasks, and highlight the importance of incorporating task-specific instructions to improve model interpretability and accuracy.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76860755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Learning-Based Refactoring with Formally Verified Training Data 基于深度学习的重构与正式验证训练数据
IF 1.1
Infocommunications Journal Pub Date : 2023-01-01 DOI: 10.36244/icj.2023.5.1
Balázs Szalontai, Péter Bereczky, Dániel Horpácsi
{"title":"Deep Learning-Based Refactoring with Formally Verified Training Data","authors":"Balázs Szalontai, Péter Bereczky, Dániel Horpácsi","doi":"10.36244/icj.2023.5.1","DOIUrl":"https://doi.org/10.36244/icj.2023.5.1","url":null,"abstract":"Refactoring source code has always been an active area of research. Since the uprising of various deep learning methods, there have been several attempts to perform source code transformation with the use of neural networks. More specifically, Encoder-Decoder architectures have been used to transform code similarly to a Neural Machine Translation task. In this paper, we present a deep learning-based method to refactor source code, which we have prototyped for Erlang. Our method has two major components: a localizer and a refactoring component. That is, we first localize the snippet to be refactored using a recurrent network, then we generate an alternative with a Sequence-to- Sequence architecture. Our method could be used as an extension for already existing AST-based approaches for refactoring since it is capable of transforming syntactically incomplete code. We train our models on automatically generated data sets, based on formally verified refactoring definitions and by using attribute grammar-based sampling.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77931825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Application of Neural Network Tools in Process Mining 神经网络工具在过程挖掘中的应用
IF 1.1
Infocommunications Journal Pub Date : 2023-01-01 DOI: 10.36244/icj.2023.5.3
László Kovács, Erika Baksáné Varga, Péter Mileff
{"title":"Application of Neural Network Tools in Process Mining","authors":"László Kovács, Erika Baksáné Varga, Péter Mileff","doi":"10.36244/icj.2023.5.3","DOIUrl":"https://doi.org/10.36244/icj.2023.5.3","url":null,"abstract":"Dominant current technologies in process mining use schema induction approaches based on graph and au- tomaton methods. The paper investigates the application of neural network approaches in schema induction focusing on three alternative architectures: MLP, CNN and LSTM networks. The proposed neural network models can be used to discover XOR, loop and parallel execution templates. In the case of loop detection, the performed test analyses show the dominance of CNN approach where the string is represented with a two- dimensional similarity matrix. The usability of the proposed approach is demonstrated with test examples.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89295033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Primer on Software Defined Radios 软件定义无线电入门
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.3.3
D. Popescu, R. Vida
{"title":"A Primer on Software Defined Radios","authors":"D. Popescu, R. Vida","doi":"10.36244/icj.2022.3.3","DOIUrl":"https://doi.org/10.36244/icj.2022.3.3","url":null,"abstract":"The commercial success of cellular phone systems during the late 1980s and early 1990 years heralded the wireless revolution that became apparent at the turn of the 21st century and has led the modern society to a highly interconnected world where ubiquitous connectivity and mobility are enabled by powerful wireless terminals. Software defined radio (SDR) technology has played a major role in accelerating the pace at which wireless capabilities have advanced, in particular over the past 15 years, and SDRs are now at the core of modern wireless communication systems. In this paper we give an overview of SDRs that includes a discussion of drivers and technologies that have contributed to their continuous advancement, and presents the theory needed to understand the architecture and operation of current SDRs. We also review the choices for SDR platforms and the programming options that are currently available for SDR research, development, and teaching, and present case studies illustrating SDR use. Our hope is that the paper will be useful as a reference to wireless researchers and developers working in the industry or in academic settings on further advancing and refining the capabilities of wireless systems.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72665991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Exact Outage Analysis for Non-regenerative Secure Cooperation Against Double-tap Eavesdropping 针对双重窃听的非再生安全合作的精确中断分析
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.4.6
Kotha Venugopalachary, Deepak Mishra, R. Saini
{"title":"Exact Outage Analysis for Non-regenerative Secure Cooperation Against Double-tap Eavesdropping","authors":"Kotha Venugopalachary, Deepak Mishra, R. Saini","doi":"10.36244/icj.2022.4.6","DOIUrl":"https://doi.org/10.36244/icj.2022.4.6","url":null,"abstract":"This paper presents the secrecy performance analysis of an amplify-and-forward relay-assisted cooperative communication system in the presence of a passive external eavesdropper. In contrast to existing works that assume high signal-to-noise ratio (SNR) approximations, we have investigated exact and secrecy outage probabilities. Furthermore, we consider a more challenging scenario where the source may not be reachable to the intended user directly. But the eavesdropper can tap both the source link and the relay link. First of all, the outage probability is analyzed at the intended user as well as the eavesdropper. Next, defining the secrecy rate for the amplify-and-forward (AF) relaying system, the expression of the secrecy outage probability (SOP) and the secrecy intercept probability (SIP) have been derived, respectively. Noticing the complexity involved in the integration of SOP and SIP expressions, the closed-form expressions have been derived for asymptotic cases. Finally, the exact and asymptotic analysis has been verified by performing Monte-Carlo simulations. It is observed that the relay position should be closer to the source compared to the eavesdropper to achieve improved SOP.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80159100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
LoRa Positioning in Verification of Location Data’s Credibility LoRa定位在位置数据可信度验证中的应用
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.4.8
Anna Strzoda, Rafał Marjasz, K. Grochla
{"title":"LoRa Positioning in Verification of Location Data’s Credibility","authors":"Anna Strzoda, Rafał Marjasz, K. Grochla","doi":"10.36244/icj.2022.4.8","DOIUrl":"https://doi.org/10.36244/icj.2022.4.8","url":null,"abstract":"The LoRa is a novel radio communication technology providing low power and a high range of data transmission. The LoRa transmission may be used for a low-cost localization to estimate the network nodes’ location. Some recent research showed that the location could be found with reasonable accuracy, with median error as low as tens of meters. Still, such results are achieved in a controlled environment with low interferences. We first evaluate the LoRa localization using an extensive data set of a telemetric network of a few thousand devices. We show that although the direct positioning based on trilateration provides limited accuracy, the measurement of LoRa transmission may be successfully used to evaluate the credibility of location information. The information about which gateways received the data and the RSSI measurements allow us to verify if the potential coordinates of a location are accurate. We propose a metric for location verification and estimate its credibility on a sample of measurements from the LoRa telemetry network.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87538153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Novel Time Series Representation Approach for Dimensionality Reduction 一种新的降维时间序列表示方法
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.2.5
Mohammad Bawaneh, V. Simon
{"title":"A Novel Time Series Representation Approach for Dimensionality Reduction","authors":"Mohammad Bawaneh, V. Simon","doi":"10.36244/icj.2022.2.5","DOIUrl":"https://doi.org/10.36244/icj.2022.2.5","url":null,"abstract":"With the growth of streaming data from many domains such as transportation, finance, weather, etc, there has been a surge in interest in time series data mining. With this growth and massive amounts of time series data, time series representation has become essential for reducing dimensionality to overcome the available memory constraints. Moreover, time series data mining processes include similarity search and learning of historical data tasks. These tasks require high computation time, which can be reduced by reducing the data dimensionality. This paper proposes a novel time series representation called Adaptive Simulated Annealing Representation (ASAR). ASAR considers the time series representation as an optimization problem with the objective of preserving the time series shape and reducing the dimensionality. ASAR looks for the instances in the raw time series that can represent the local trends and neglect the rest. The Simulated Annealing optimization algorithm is adapted in this paper to fulfill the objective mentioned above. We compare ASAR to three well-known representation approaches from the literature. The experimental results have shown that ASAR achieved the highest reduction in the dimensions. Moreover, it has been shown that using the ASAR representation, the data mining process is accelerated the most. The ASAR has also been tested in terms of preserving the shape and the information of the time series by performing One Nearest Neighbor (1-NN) classification and K-means clustering, which assures its ability to preserve them by outperforming the competing approaches in the K-means task and achieving close accuracy in the 1-NN classification task.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88509688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Analytical Review and Study on Various Vertical Handover Management Technologies in 5G Heterogeneous Network 5G异构网络中各种垂直切换管理技术的分析综述与研究
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.2.3
K. Kiran, D. Rao
{"title":"Analytical Review and Study on Various Vertical Handover Management Technologies in 5G Heterogeneous Network","authors":"K. Kiran, D. Rao","doi":"10.36244/icj.2022.2.3","DOIUrl":"https://doi.org/10.36244/icj.2022.2.3","url":null,"abstract":"In recent mobile networks, due to the huge number of subscribers, the traffic may occur rapidly; therefore, it is complex to guarantee the accurate operation of the network. On the other hand, the Fifth generation (5G) network plays a vital role in the handover mechanism. Handover management is a prominent issue in 5G heterogeneous networks. Therefore, the Handover approach relocates the connection between the user equipment and the consequent terminal from one network to another. Furthermore, the handover approaches manage each active connection for the user equipment. This survey offers an extensive analysis of 50 research papers based on existing handover approaches in the 5G heterogeneous network. Finally, existing methods considering conventional vertical handover management strategies are elaborated to improve devising effective vertical handover management strategies. Moreover, the possible future research directions in attaining efficient vertical handover management in a 5G heterogeneous network are elaborated.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79933360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Towards Implementing a Software Tester for Benchmarking MAP-T Devices 实现对MAP-T设备进行基准测试的软件测试
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.3.6
Ahmed Al-hamadani, G. Lencse
{"title":"Towards Implementing a Software Tester for Benchmarking MAP-T Devices","authors":"Ahmed Al-hamadani, G. Lencse","doi":"10.36244/icj.2022.3.6","DOIUrl":"https://doi.org/10.36244/icj.2022.3.6","url":null,"abstract":"Several IPv6 transition technologies have been designed and developed over the past few years to accelerate the full adoption of the IPv6 address pool. To make things more organized, the Benchmarking Working Group of IETF has standardized a comprehensive benchmarking methodology for these technologies in its RFC 8219. The Mapping of Address and Port using Translation (MAP-T) is one of the most important transition technologies that belong to the double translation category in RFC 8219. This paper aims at presenting our progress towards implementing the world’s first RFC 8219 compliant Tester for the MAP-T devices, more specifically, the MAP-T Customer Edge (CE) and the MAP-T Border Relay (BR). As part of the work of this paper, we presented a typical design for the Tester, followed by a discussion about the operational requirements, the scope of measurements, and some design considerations. Then, we installed a testbed for one of the MAP-T implementations, called Jool, and showed the results of the testbed. And finally, we ended up with a brief description of the MAP-T test program and its configuration parameters in case of testing the BR device.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85273532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Saving Bit-flips through Smart Overwrites in NVRAM 在NVRAM中通过智能覆盖保存位翻转
IF 1.1
Infocommunications Journal Pub Date : 2022-01-01 DOI: 10.36244/icj.2022.4.5
A. Kulandai, Thomas Schwarz
{"title":"Saving Bit-flips through Smart Overwrites in NVRAM","authors":"A. Kulandai, Thomas Schwarz","doi":"10.36244/icj.2022.4.5","DOIUrl":"https://doi.org/10.36244/icj.2022.4.5","url":null,"abstract":"New generations of non-volatile random access memories will combine the best features of memory (access times, byte addressability) with the best features of storage (non-volatility, low costs per byte). Some, like PCM, have a limited endurance. All will only consume energy when accessed, but writes will use much more energy than reads. These characteristics put a cost on flipping bits in memory. Bit-flip aware data structures lower the number of bits flipped by not resetting fields to zero to indicate a deleted record but by using bit-maps. If given a choice of where to over-write data, they will select the location which results in a lower number of bit-flips. We calculate the expected bit-flip savings of this strategy and derive a rule to determine the number of the possible candidate locations.","PeriodicalId":42504,"journal":{"name":"Infocommunications Journal","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89934344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信