-
A Framework for Mobile Based Research Paper Recommendation in a Conference
Issue:
Volume 8, Issue 5, October 2022
Pages:
131-148
Received:
14 June 2022
Accepted:
19 July 2022
Published:
29 September 2022
DOI:
10.11648/j.ijdsa.20220805.11
Downloads:
Views:
Abstract: Finding conferences with papers relevant to their interests can be difficult for research conference attendees because everyone has different preferences. To address this issue, this research proposes a framework and a prototype of a personalized recommendation system for research conference items. When making recommendations, the prototype considers the user's research area and college. The prototype employs three algorithms to recommend conference papers based on what users have previously read: a collaborative filtering algorithm (k-Nearest Neighbor), a content-based filtering algorithm, and a hybrid of the two. The design science research paradigm was used to write the research. This research covers the conceptual framework design and prototype implementation in programming languages that the researcher is capable of implementing, as well as a brief state of the art of the recommending systems literature. The prototype's usability was assessed using the information retrieval concept. To assess the quality of recommendations, system performance and a user-centered evaluation were performed. The usability evaluation results showed that users were generally pleased with the prototype's usability. Users who tested the prototype were generally pleased with the quality of the recommendations. The performance of a prototype system is 86 percent, and user acceptance is 86.5 percent. Finally, future works in the area are clearly stated.
Abstract: Finding conferences with papers relevant to their interests can be difficult for research conference attendees because everyone has different preferences. To address this issue, this research proposes a framework and a prototype of a personalized recommendation system for research conference items. When making recommendations, the prototype conside...
Show More
-
Predicting Music Popularity with the Hybrid Approach: K-Means + LGBM
Issue:
Volume 8, Issue 5, October 2022
Pages:
149-156
Received:
26 September 2022
Accepted:
10 October 2022
Published:
17 October 2022
DOI:
10.11648/j.ijdsa.20220805.15
Downloads:
Views:
Abstract: The global revenue from streaming, CD, and digital music sales have exceeded pre-COVID-19 levels since the COVID-19 outbreak. Although other stocks have fallen, stocks relating to the music industry have risen. HYBE entertainment even yielded integrated platform services. Furthermore, there are many people who make music without an agency and post it on platforms such as Soundcloud. Whether the popular music last week can be predicted to be popular this week using the methods we outlined in this paper. We obtained the dataset from Spotify, the main subscription service. The paper has two objectives: predicting popularity and revealing the relationship between K-means and LGBM since there is a paper claiming that the K-means algorithm is efficient in the Spotify dataset. The experiment yielded that the K-means algorithm is not efficient in our dataset by showing less Silhouette score. However, when combining K-means with LGBM, this approach achieved higher performance compared to using LGBM solely. Even if the experiment’s result is positive, which could assist in determining whether a composer’s songs will be lucrative, we do acknowledge some drawbacks in our methods. For instance, we did not account for the numerous variables introduced by utilizing phony streams to enhance their placement inside the real-time chart. Additionally, we did not include any of the time’s top tunes. Christmas theme music, for instance. Throughout the future, we will conduct additional research into this topic to overcome those drawbacks.
Abstract: The global revenue from streaming, CD, and digital music sales have exceeded pre-COVID-19 levels since the COVID-19 outbreak. Although other stocks have fallen, stocks relating to the music industry have risen. HYBE entertainment even yielded integrated platform services. Furthermore, there are many people who make music without an agency and post ...
Show More
-
Characterization of Meteorological Drought in the Alibori Watershed (North Benin, West Africa)
Alain Ibikunle Ague,
Cyr Gervais Etene,
Ibouraima Yabi
Issue:
Volume 8, Issue 5, October 2022
Pages:
157-162
Received:
10 September 2022
Accepted:
8 October 2022
Published:
28 October 2022
DOI:
10.11648/j.ijdsa.20220805.16
Downloads:
Views:
Abstract: Benin has experienced a significant variation in rainfall with prolonged drought since 1970. In view of the consequences of this extreme phenomenon on vital sectors, such as agriculture, updating the results previously obtained is obviously essential to guarantee optimal management of water resources. The present study aims to characterize the drought in the Alibori watershed in northern Benin. The climatic data used are those made available by the National Aeronautics and Space Administration (NASA) through its POWER “Prediction of Worldwide Energy Resources”; they cover the period from 1981 to 2018. Four approaches were used to assess drought in the basin: the Standardized Precipitation Index, the Climatic Moisture Index, the segmentation of Hubert and Spearman's correlation. The analysis of the precipitation data shows decreasing trends in the lower part of the basin and increasing trends in the middle and upper part. Over the period from 1981 to 2018, we note that the frequency of moderate and severe droughts varies respectively between 31.8% to 39.47% and 15.79% to 18.42%. Extreme drought was observed in 2000 west of the middle part of the Alibori watershed around the point of Latitude 11.0645 and Longitude 2.2944. The data used clearly highlights drought situations in the Alibori watershed.
Abstract: Benin has experienced a significant variation in rainfall with prolonged drought since 1970. In view of the consequences of this extreme phenomenon on vital sectors, such as agriculture, updating the results previously obtained is obviously essential to guarantee optimal management of water resources. The present study aims to characterize the drou...
Show More
-
User and Entity Behavior Analytics Method Based on Adaptive Mixed-Attribute-Data Density Peaks Clustering
Issue:
Volume 8, Issue 5, October 2022
Pages:
163-168
Received:
6 October 2022
Accepted:
25 October 2022
Published:
29 October 2022
DOI:
10.11648/j.ijdsa.20220805.17
Downloads:
Views:
Abstract: In the era of digital economy, new technologies emerge in an endless stream, and the network environment becomes increasingly complex. Traditional security products, technologies and solutions cannot meet the needs. In order to deal with the increasingly severe network security challenges, User and Entity Behavior Analytics (UEBA) technology provides a new solution. The application of new technologies such as statistical analysis, machine learning and deep learning also increases the adaptability and effectiveness of UEBA technology. User and entity behavior analysis technology based on machine learning has also become one of the research hotspots in current academia. In this paper, An User and Entity Behavior Analytics Method based on Adaptive Mixed-Attribute-Data Density Peaks Clustering is proposed. Firstly, the relevant access behavior data records of user entities are extracted from the access logs of the servers that need to be monitored. Since these records contain mixed attributes, adaptive mixed-attribute-data density peak clustering (AMDPC) can be used for clustering. Then, by constructing the user behavior baseline in each cluster, suspicious users and behaviors are analyzed. Combined with log backtracking and expert manual verification, the threat behavior is finally determined. This method has been applied in a company's network security situation awareness platform, and has achieved good practical results.
Abstract: In the era of digital economy, new technologies emerge in an endless stream, and the network environment becomes increasingly complex. Traditional security products, technologies and solutions cannot meet the needs. In order to deal with the increasingly severe network security challenges, User and Entity Behavior Analytics (UEBA) technology provid...
Show More
