Találati lista | Tudóstér

001-es BibID:	BIBFORM092439
035-os BibID:	(WoS)000631194900001 (Scopus)85102656412
Első szerző:	Aldabbas, Ashraf Khaled Abd Elkareem (informatikus)
Cím:	Deep Learning-Based Approach for Detecting Trajectory Modifications of Cassini-Huygens Spacecraft / Ashraf Aldabbas, Zoltan Gal, Khawaja Moyeezullah Ghori, Muhammad Imran, Muhammad Shoaib
Dátum:	2021
ISSN:	2169-3536
Megjegyzések:	There were necessary trajectory modifications of Cassini spacecraft during its last 14 years movement cycle of the interplanetary research project. In the scale 1.3 hour of signal propagation time and 1.4-billion-kilometer size of Earth-Cassini channel, complex event detection in the orbit modifications requires special investigation and analysis of the collected big data. The technologies for space exploration warrant a high standard of nuanced and detailed research. The Cassini mission has accumulated quite huge volumes of science records. This generated a curiosity derives mainly from a need to use machine learning to analyze deep space missions. For energy saving considerations, the communication between the Earth and Cassini was executed in non-periodic mode. This paper provides a sophisticated in-depth learning approach for detecting Cassini spacecraft trajectory modifications in post-processing mode. The proposed model utilizes the ability of Long Short Term Memory (LSTM) neural networks for drawing out useful data and learning the time series inner data pattern, along with the forcefulness of LSTM layers for distinguishing dependencies among the long-short term. Our research study exploited the statistical rates, Matthews correlation coefficient, and F1 score to evaluate our models. We carried out multiple tests and evaluated the provided approach against several advanced models. The preparatory analysis showed that exploiting the LSTM layer provides a notable boost in rising the detection process performance. The proposed model achieved a number of 232 trajectory modification detections with 99.98% accuracy among the last 13.35 years of the Cassini spacecraft life.
Tárgyszavak:	Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk Cassini-Huygens interplanetary project complex event sensory data big data neural network pattern processing knowledge representation
Megjelenés:	IEEE Access. - 9 (2021), p. 39111-39125. -
További szerzők:	Gál Zoltán (1966-) (informatikus) Ghori, Khawaja Moyeezullah (1982-) (informatikus) Imran, Muhammad (1981-) (informatikus) Shoaib Muhammad (1971-) (mérnök, informatikus)
Pályázati támogatás:	FIKP-20428-3/2018/FEKUTSTRAT FIKP
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM118903
035-os BibID:	(WoS)001152827800001 (Scopus)85186081541
Első szerző:	Csernoch Mária (informatika tanár)
Cím:	Human-centered digital sustainability : handling enumerated lists in digital texts / Csernoch, Mária; Nagy, Tímea; Nagy, Keve; Csernoch, Júlia; Hannusch, Carolin
Dátum:	2024
ISSN:	2169-3536
Megjegyzések:	In advance to the present study, the authors introduced a method which makes it possible to calculate the entropy of natural language digital texts, focusing on word-processed texts, presentations, and webpages. This entropy reveals that the more underdeveloped documents are, the more demanding their content-related modification becomes. It was also found that the time and data required to complete a modification task in an erroneous document is several times more than in its correct counterpart. This finding leads to the end-user paradox: the less trained end-users are, the more errors they make, and the modification of their documents requires more resources. To resolve these discrepancies, the present study defines the sustainability rate of natural language digital texts which calculates the losses - the waste of human resources, time, workspace, computers, energy, frustration, working in bees, losing data - generated by negligent text management. Furthermore, we present examples of how manual and enumerated lists behave to modifications in a 213-page long document and conclude from our investigations that while the waste of human and machine resources occurs repeatedly in erroneous documents, the sustainability rate remains low. To prove the necessity of correction, we cleared the sample document, which took approximately 67 hours of two experts of our research group (2x67 hours). With this method, we found that the correction of errors can be extremely demanding, but uses resources only once, and further modifications in the now correct document need only the content-required amount of time, activities, entropy, and resources, in accordance with the expectations of the person intended to update the document. To correct documents, we present the Error Recognition Model, which is proved effective and efficient in digital education. All our findings indicate that both education and industry should adapt the presented approach (1) to develop students' and end-users' computational thinking skills, (2) to manage and take advantage of errors, (3) to recognize connections between the structure of the text and the complex word processing tools, (4) to pay attention to digital sustainability - beyond hardware and software development and recycling - with a focus on the human factor. Recently, the Error Recognition Model is a reactive problem-solving approach, whose effectiveness is justified. However, the near future is to run parallel the reactive and proactive uses of this approach, while if we look far into the future, the proactive use to digital born natural language texts should dominate.
Tárgyszavak:	Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk
Megjelenés:	IEEE Access. - 12 (2024), p. 30544-30561. -
További szerzők:	Nagy Tímea Katalin (1995-) (informatika-matematika tanár) Nagy Keve (1974-) (mérnökinformatikus) Csernoch Júlia (1989-) (jogász) Hannusch, Carolin (1984-) (matematikus)
Pályázati támogatás:	NKFI - KDP-2021 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM082861
035-os BibID:	(WoS)000524745100014 (Scopus)85077292469
Első szerző:	Ghori, Khawaja Moyeezullah (informatikus)
Cím:	Performance Analysis of Different Types of Machine Learning Classifiers for Non-Technical Loss Detection / Khawaja Moyeezullah Ghori, Rabeeh Ayaz Abbasi, Muhammad Awais, Muhammad Imran, Ata Ullah, Laszlo Szathmary
Dátum:	2020
ISSN:	2169-3536
Megjegyzések:	With the ever-growing demand of electric power, it is quite challenging to detect and prevent Non-Technical Loss (NTL) in power industries. NTL is committed by meter bypassing, hooking from the main lines, reversing and tampering the meters. Manual on-site checking and reporting of NTL remains an unattractive strategy due to the required manpower and associated cost. The use of machine learning classifiers has been an attractive option for NTL detection. It enhances data-oriented analysis and high hit ratio along with less cost and manpower requirements. However, there is still a need to explore the results across multiple types of classifiers on a real-world dataset. This paper considers a real dataset from a power supply company in Pakistan to identify NTL. We have evaluated 15 existing machine learning classifiers across 9 types which also include the recently developed CatBoost, LGBoost and XGBoost classifiers. Our work is validated using extensive simulations. Results elucidate that ensemble methods and Artificial Neural Network (ANN) outperform the other types of classifiers for NTL detection in our real dataset. Moreover, we have also derived a procedure to identify the top-14 features out of a total of 71 features, which are contributing 77% in predicting NTL. We conclude that including more features beyond this threshold does not improve performance and thus limiting to the selected feature set reduces the computation time required by the classifiers. Last but not least, the paper also analyzes the results of the classifiers with respect to their types, which has opened a new area of research in NTL detection.
Tárgyszavak:	Természettudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk
Megjelenés:	IEEE Access. - 8 (2020), p. 16033-16048. -
További szerzők:	Abbasi, Rabeeh Ayaz Awais, Muhammad Imran, Muhammad (1981-) (informatikus) Ullah, Ata Szathmáry László (1977-) (programtervező-informatikus)
Pályázati támogatás:	EFOP-3.6.3-VEKOP-16-2017-00002 EFOP
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat Szerző által megadott URL DOI
Borító:
Saját polcon: