To see the other types of publications on this topic, follow the link: CBF- Content-based filtering.
Journal articles on the topic 'CBF- Content-based filtering'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'CBF- Content-based filtering.'
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
PUTRA, KURNIA RAMADHAN, and MOHAMMAD ADITIYA RACHMAN. "Perbandingan Metode Content-based, Collaborative dan Hybrid Filtering pada Sistem Rekomendasi Lagu." MIND Journal 9, no. 2 (2024): 179–93. https://doi.org/10.26760/mindjournal.v9i2.179-193.
Full textAbstract:
AbstrakSistem rekomendasi dapat dimanfaatkan untuk membantu pengguna menemukan item atau informasi sesuai preferensi mereka, termasuk lagu. Metode seperti Collaborative Filtering (CF), Content-Based Filtering (CBF), dan Hybrid Filtering digunakan untuk meningkatkan kualitas rekomendasi berdasarkan interaksi pengguna dan karakteristik konten. Penelitian ini membandingkan efektivitas ketiga metode tersebut dalam rekomendasi lagu menggunakan dataset dengan 68.330 entri data. Metode CF dan CBF diterapkan secara terpisah, lalu dikombinasikan dalam pendekatan hybrid untuk mengevaluasi peningkatan hasil. CF mencapai presisi 49.9%, CBF 39.5%, sedangkan hybrid CF-CBF mencatat presisi tertinggi sebesar 50.7%. Sebaliknya, hybrid CBF-CF menghasilkan presisi terendah, yaitu 38.4%. Kesimpulannya, pendekatan hybrid CF-CBF lebih unggul dalam merekomendasikan lagu sesuai preferensi pengguna dibandingkan metode lainnya.Kata kunci: sistem rekomendasi, rekomendasi lagu, content-based filtering, collaborative filtering, hybrid filtering AbstractRecommender systems can be utilized to assist users in discovering items or information that align with their preferences, including music. Methods such as Collaborative Filtering (CF), Content-Based Filtering (CBF), and Hybrid Filtering enhance recommendation quality based on user interactions and content characteristics. This study compares the effectiveness of these three methods in music recommendation using a dataset containing 68,330 entries. CF and CBF were implemented separately and combined in a hybrid approach to evaluate performance improvements. CF achieved a precision of 49.9% and CBF 39.5%, while the hybrid CF-CBF approach recorded the highest precision at 50.7%. In contrast, the hybrid CBF-CF approach yielded the lowest precision, at 38.4%. In conclusion, the hybrid CF-CBF approach outperforms other methods in delivering music recommendations tailored to user preferences.Keywords: recommendation system, song recommendation, content-based filtering, collaborative filtering, hybrid filtering
2
Faurina, Ruvita, and Evlin Sitanggang. "Implementasi Metode Content-Based Filtering dan Collaborative Filtering pada Sistem Rekomendasi Wisata di Bali." Techno.Com 22, no. 4 (2023): 870–81. http://dx.doi.org/10.33633/tc.v22i4.8556.
Full textAbstract:
Sektor pariwisata memiliki peran penting dalam perekonomian Bali. Pada bulan April 2023, kunjungan wisatawan ke Bali mencapai 411.510, meningkat 11,01% dari bulan Maret 2023 (sumber: Badan Pusat Statistik Bali). Untuk memperkenalkan destinasi wisata yang ada, Bali perlu menggunakan teknologi yang sedang berkembang seperti sistem rekomendasi. Dalam hal ini, digunakan metode Content-based filtering (CBF) dan Collaborative Filtering (CF). CBF memberikan rekomendasi berdasarkan preferensi pengguna terhadap kategori destinasi wisata, sementara CF menggunakan data histori rating dari pengguna lain untuk merekomendasikan destinasi yang disukai. Dataset terdiri dari 75 data detail destinasi wisata dan 3000 histori rating dari 100 pengguna. Pengujian dilakukan dengan membagi dataset menjadi 80% data training (2400 data) dan 20% data validasi (600 data), menggunakan 15 epoch dan batch size yang sesuai. Hasil terbaik menunjukkan performa loss sebesar 0.0589 dan RMSE sebesar 0.2427.
3
Liu, Duen-Ren, Chuen-He Liou, Chi-Chieh Peng, and Huai-Chun Chi. "Hybrid content filtering and reputation-based popularity for recommending blog articles." Online Information Review 38, no. 6 (2014): 788–805. http://dx.doi.org/10.1108/oir-12-2013-0273.
Full textAbstract:
Purpose – Social bookmarking is a system which allows users to share, organise, search and manage bookmarks of web resources. However, with the rapid growth in the production of online documents, people are facing the problem of information overload. Social bookmarking web sites offer a solution to this by providing push counts, which are counts of users’ recommendations of articles, and thus indicate the popularity and interest thereof. In this way, users can use the push counts to find popular and interesting articles. A measure of popularity-based solely on push counts, however, cannot be considered a true reflection of popularity. The paper aims to discuss these issues. Design/methodology/approach – In this paper, the authors propose to derive the degree of popularity of an article by considering the reputation of the users who push the article. Moreover, the authors propose a novel personalised blog article recommendation approach which combines reputation-based group popularity with content-based filtering (CBF), for the recommendation of popular blog articles which satisfy users’ personal preferences. Findings – The experimental results show that the proposed approach outperforms conventional CBF, item-based and user-based collaborative filtering approaches. The proposed approach considering reputation-based group popularity scores on neighbouring articles indeed can improve the recommendation quality of traditional CBF method. Originality/value – The recommendation approach modifies CBF method by considering the target user's group preferences, to overcome the limitation of CBF which arises from the recommending only items similar to those the user has previously liked. Users with similar article preferences (profiles) may form a group of users with similar interests. A group's preferences may also reflect an individual's preferences. The reputation-based group preferences of the target user's group can be used to complement the target user's preferences.
4
Juhi, Dhameliya, and Desai Nikita. "Job Recommendation System using Content and Collaborative Filtering Based Techniques." International Journal of Soft Computing and Engineering (IJSCE) 9, no. 3 (2019): 8–13. https://doi.org/10.35940/ijsce.C3266.099319.
Full textAbstract:
Internet based recruiting platforms decrease advertisement cost, but they suffer from information overload problem. The job recommendation systems (JRS) have achieved success in e-recruitment process but still they are not able to capture the complexity of matching between candidates’ desires and organizations’ requirements. Thus, we propose a hybrid JRS which combines recommendations of content-based filtering (CBF) and collaborative filtering (CF) to overcome their individual major shortcomings namely overspecialization and over-fitting. In proposed system, CBF model makes recommendations based on candidates’ skills identified from past jobs in which they have applied and CF model makes recommendations based on jobs in which similar users have applied and also those jobs in which that user has applied frequently together in very similar contexts using Word2Vec’s skip-gram model. We used k-Nearest Neighbors technique and Pearson Correlation Coefficient. The recall of our proposed model is found to be 63.97% on a data set which had nearly 1900+ jobs and 23,000 job applicants.
5
Habibi, Roni, and Darfial Guslan. "RISIKO MAGANG MAHASISWA DENGAN PENDEKATAN ALGORITMA CONTENT-BASED FILTERING DAN SUPPORT VECTOR MACHINE." Competitive 20, no. 1 (2025): 12–23. https://doi.org/10.36618/competitive.v20i1.4195.
Full textAbstract:
Penelitian ini menggunakan pendekatan kuantitatif untuk mengkaji penggunaan algoritma Content-Based Filtering (CBF) dan Support Vector Machine (SVM) dalam manajemen risiko magang mahasiswa. Metode penelitian yang digunakan adalah Crisp-DM (Cross-Industry Standard Process for Data Mining) yang membantu peneliti mengorganisasikan dan menganalisis data dengan langkah-langkah yang terstruktur. Dalam penelitian ini, peneliti mengumpulkan data dengan menggunakan kuesioner yang dirancang khusus yang bertujuan untuk memperoleh informasi mengenai risiko-risiko yang mungkin terjadi selama mahasiswa magang di perusahaan, faktor-faktor yang mempengaruhi keberhasilannya, dan bagaimana algoritma CBF dan SVM dapat digunakan untuk menganalisis risiko. Dengan menggunakan pendekatan kuantitatif dan Crisp-DM, penelitian ini bertujuan untuk memberikan informasi yang objektif dan terukur tentang penggunaan algoritma CBF dan SVM dalam manajemen risiko magang mahasiswa. Diharapkan penelitian ini dapat memberikan pemahaman yang lebih baik tentang bagaimana algoritma CBF dan SVM dapat membantu mengelola risiko dalam magang mahasiswa. Hasil penelitian ini juga diharapkan dapat memberikan saran praktis kepada organisasi yang lebih baik.
6
Aranzamendez, Samantha Gwyn, Joshua Caleb Bolito, Aron Christoper Rafe, Jamillah Guialil, Dan Michael Cortez, and Raymund Dioses. "An Enhanced Content-based Filtering Using Maximal Marginal Relevance." International Journal of Computing Sciences Research 8 (January 1, 2024): 3070–87. https://doi.org/10.25147/ijcsr.2017.001.1.204.
Full textAbstract:
Purpose–The studyaims toenhance Content-based Filtering by diversifying its recommended items to combatoverspecialization. It traditionallyrecommends items that are directly related to the user profile, preventingusers from discovering newer sets ofitems. Method–Maximal Marginal Relevance isintegrated into the algorithm –are-ranking algorithm,developed by Carbonell and Goldsteinthat enhancesthe diversity of items retrieved by information retrieval systems–to enhance Content-based Filtering and address the underlying overspecialization problem. Results–By integrating Maximal Marginal Relevance, themodified algorithmaddressed overspecialization.Out of all the tested values of lambda (λ) for MMR, theenhanced Content-based Filtering (CBF-MMR)with λ = 0.7showed the most prominence, having a good balance between relevance and diversity of recommendations. Onaverage,itimprovedupon the original algorithm by 48.51% in Precision, 6.40%in Recall, 28.12%inF-Score,and 275.45% in Diversity. Conclusion–Resultsshow that integratingMaximal Marginal Relevance to Content-based Filtering (CBF-MMR) improves the diversity of recommendations. Due to the re-ranking process added by the Maximal Marginal Relevance, the average Precision, Recall, and F-Score also improved. Recommendations–The authors of this studysuggest further workon Content-based Filtering withfasterre-ranking algorithms, application ofthe enhanced algorithm to other larger datasets such as GroupLens’ MovieLens 10M dataset, application of the enhanced algorithm to a different domain,andenhancement of the Maximal Marginal Relevance algorithm to be applied in Content-based Filtering. Research Implications–The successful integration of Maximal Marginal Relevance (MMR) in a Content-based Filtering algorithm opens new possibilities for enhancing the diversity and relevance of recommendations of various types of recommender systems. Practical Implications–Beyond the movie recommender system this study was applied to, thisstudyhas profoundpractical implications on other domains that utilize recommender systems including but not limited to the domains of entertainment, e-commerce, and information retrieval platforms. Keywords–recommendersystem, content-based filtering, maximal marginal relevance, overspecialization
7
Vasyl, Lytvyn, Vysotska Victoria, Shatskykh Viktor, et al. "DESIGN OF A RECOMMENDATION SYSTEM BASED ON COLLABORATIVE FILTERING AND MACHINE LEARNING CONSIDERING PERSONAL NEEDS OF THE USER." Eastern-European Journal of Enterprise Technologies 4, no. 2 (100) (2019): 6–28. https://doi.org/10.15587/1729-4061.2019.175507.
Full textAbstract:
The paper reports a study into recommendation algorithms and determination of their advantages and disadvantages. The method for developing recommendations based on collaborative filtering such as Content-Based Filtering (CBF), Collaborative Filtering (CF), and hybrid methods of Machine Learning (ML) has been improved. The paper describes the design principles and functional requirements to a recommendation system in the form of a Web application for choosing the content required by user using movies as an example. The research has focused on solving issues related to cold start and scalability within the method of collaborative filtering. To effectively address these tasks, we have used hybrid training methods. A hybrid recommendation system (HRS) has been practically implemented for providing relevant content recommendations using movies as an example, taking into consideration the user's personal preferences based on the constructed hybrid method. We have improved an algorithm for developing content recommendations based on the collaborative filtering and Machine Learning for the combined filtration of similarity indicators among users or goods. The hybrid algorithm receives initial information in a different form, normalizes it, and generates relevant recommendations based on a combination of CF and CBF methods. Machine Learning is capable of defining those factors that influence the selection of relevant films, which improves development of recommendations specific to the user. To solve these tasks, a new improved method has been proposed, underlying which, in contrast to existing systems of recommendations, are the hybrid methods and Machine Learning. Machine Learning data for the designed HRS were borrowed from MovieLens. We have analyzed methods for developing recommendations to the user; existing recommendation systems have been reviewed. Our experimental results demonstrate that the operational indicators for the proposed HRS, based on the technology of CF+CBF+ML, outperform those for two individual models, CF and CBF, and such their combinations as CF CBF, CF+ML, and CBF+ML. We recommend using HRS to collect data on people's preferences in selecting goods and to providing relevant recommendations.
8
Hermanto, Nandang, Irma Darmayanti, Dimas Saputra, and Aden Hidayatuloh. "Development of Mobile Application by Applying Content-Based Filtering." sinkron 9, no. 1 (2025): 232–38. https://doi.org/10.33395/sinkron.v9i1.14320.
Full textAbstract:
The rapid advancements in information technology have transformed modern lifestyles, driving changes in consumer behavior and expectations, especially in the retail industry. This study focuses on developing a mobile application for Ampu Mart, a newly established retail business in Indonesia, to optimize product recommendation systems using the Content-Based Filtering (CBF) approach. The research integrates CBF with string matching and cosine similarity algorithms to provide personalized product recommendations based on customer preferences, enhancing user satisfaction and supporting more efficient purchasing decisions. The methodology involves several stages, including problem identification through observation and interviews, data collection on product attributes and customer preferences, system design, prototype development, implementation, and testing. The application leverages advanced algorithms to analyze product characteristics, ensuring relevant recommendations by matching user preferences with product attributes. User Acceptance Testing (UAT) conducted with 30 participants—customers, administrators, and management—evaluated the application's functionality, usability, accuracy, and performance. Results indicate that the mobile application improves the shopping experience and boosts sales by offering accurate, user-centered recommendations. The findings highlight the strategic importance of integrating intelligent technology into e-commerce platforms to enhance competitiveness in the retail market. Future work recommends incorporating Collaborative Filtering techniques to further enrich the recommendation system by analyzing collective customer behavior.
9
Aditya Nugraha, Anak Agung, and Ngurah Agus Sanjaya ER. "Penyusunan Sistem Rekomendasi Produk Diecast Mobil Dengan Metode Content-Based Filtering (CBF)." Jurnal Nasional Teknologi Informasi dan Aplikasnya 1, no. 3 (2023): 973. https://doi.org/10.24843/jnatia.2023.v01.i03.p25.
Full textAbstract:
The growing popularity of diecast car collections has created a demand for efficient recommendation systems to assist collectors in discovering new products. This study focuses on the development of a content-based filtering (CBF) recommendation system for diecast car products. The system employs the TF-IDF (Term Frequency-Inverse Document Frequency) and cosine similarity techniques to calculate the relevance between products and user preferences. By analyzing the textual features of diecast car products, such as brand, model, and specifications, the CBF system generates personalized recommendations based on similarity scores. The evaluation of the system's performance demonstrates its effectiveness in providing accurate and relevant recommendations, which enhance the user experience and facilitate the exploration of the diecast car market.
10
Manikandan, J. "Movie Recommendation System Mistreatment Current Trends and Sentiment Analysis from Micro Blogging Knowledge." International Journal for Research in Applied Science and Engineering Technology 9, no. 11 (2021): 393–98. http://dx.doi.org/10.22214/ijraset.2021.38651.
Full textAbstract:
Abstract: Recommendation systems (RSs) have garnered immense interest for applications in e-commerce and digital media. Traditional approaches in RSs include such as collaborative filtering (CF) and content-based filtering (CBF) through these approaches that have certain limitations, such as the necessity of prior user history and habits for performing the task of recommendation. To minimize the effect of such limitation, this article proposes a hybrid RS for the movies that leverage the best of concepts used from CF and CBF along with sentiment analysis of tweets from microblogging sites. The purpose to use movie tweets is to understand the current trends, public sentiment, and user response of the movie. Experiments conducted on the public database have yielded promising results. Keywords: Collaborative filtering, Content based filtering, Recommendation System, Sentiment Analysis, Twitter
11
Ilyas, Muhammad Nur, and Erwin Budi Setiawan. "Weight-Based Hybrid Filtering in a Movie Recommendation System Based on Twitter with LSTM Classification." JURNAL MEDIA INFORMATIKA BUDIDARMA 7, no. 4 (2023): 1838. http://dx.doi.org/10.30865/mib.v7i4.6668.
Full textAbstract:
With the era of digitalization, movie-watching has gained immense popularity, with platforms like Disney+ offering easy access to a variety of films. After watching, users frequently share their opinions on social media platforms such as Twitter, because of it is freedom of expression. With numerous movies available, users frequently encounter challenges in deciding what to watch. To address this, a recommendation system is proposed to streamline the decision-making process for users. Collaborative Filtering (CF), Content-Based Filtering (CBF), and Hybrid Filtering are common techniques used in recommendation systems. However, CF and CBF techniques face issues like cold start, sparse data, and overspecialization. To overcome these, this research constructs a Hybrid Filtering recommendation system, with a weight-based of CF-CBF coupled with Long Short-Term Memory (LSTM) classification. The classification uses various optimizers, including Adam, SGD, Nadam, RMSprop, and Adamax. Dataset is sourced from Kaggle website, which includes movie-related tweets linked to the Disney+ platform. The results indicate that Weight-Based Hybrid Filtering utilizing Adamax optimizer in LSTM classification yields superior performance metrics, by having 78% Precision, 79% Recall, 79% Accuracy, and 77% F1-Score value.
12
Muhammad Akmal Ahmad Nawawi and Tajul Rosli Razak. "Encouraging Recycling in Bangi Selatan Through a Content-Based Filtering Web Application." Journal of Computing Research and Innovation 10, no. 1 (2025): 218–26. https://doi.org/10.24191/jcrinn.v10i1.510.
Full textAbstract:
This study addresses the challenges faced by residents of Bangi Selatan in adopting 3R (Reduce, Reuse, Recycle) practices, primarily due to a lack of interest in conservation efforts and insufficient awareness of recycling’s importance. To address these challenges, we presented a web application that enhances recycling adoption by delivering personalized content recommendations. The key contributions of this study include the development of a novel recommendation system based on content-based filtering (CBF) with improved accuracy through a modified Term Frequency-Inverse Document Frequency (TF-IDF) formula. We compare various recommendation techniques, including collaborative and hybrid filtering, and demonstrate how CBF effectively improves user engagement with recycling content. Our methodology involves advanced text vectorization and cosine similarity for precise content matching. User acceptance testing confirms the system’s effectiveness in increasing user engagement with relevant recycling information. This study highlights the potential of personalized recommendation systems in promoting environmental conservation and provides a foundation for future enhancements in recycling initiatives.
13
Abdullah, Athallah, and Erwin Budi Setiawan. "Performance of Deep Feed-Forward Neural Network Algorithm Based on Content-Based Filtering Approach." INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi 8, no. 2 (2024): 278–94. http://dx.doi.org/10.29407/intensif.v9i1.22999.
Full textAbstract:
Background: Selecting a restaurant in a diverse city like Bandung can be challenging. This study leverages Twitter data and local restaurant information to develop an advanced recommendation system to improve decision-making. Objective: The system integrates content-based filtering (CBF) with deep feedforward neural network (DFF) classification to enhance the accuracy and relevance of restaurant recommendations. Methods: Data was sourced from Twitter and PergiKuliner, with restaurant-related tweets converted into rating values. The CBF combined Bag of Words (BoW) and cosine similarity, followed by DFF classification. SMOTE was applied during training to address data imbalance. Results: The initial evaluation of CBF showed a Mean Absolute Error (MAE) of 0.0614 and a Root Mean Square Error (RMSE) of 0.0934. The optimal DFF configuration in the first phase used two layers with 32/16 nodes, a dropout rate of 0.3, and a 20% test size. This setup achieved an accuracy of 81.08%, precision of 82.89%, recall of 76.93%, and f1-scores of 79.23%. In the second phase, the RMSprop optimizer improved accuracy to 81.30%, and tuning the learning rate to 0.0596 further increased accuracy to 89%, marking a 9.77% improvement. Conclusion: The research successfully developed a robust recommendation system, significantly improving restaurant recommendation accuracy in Bandung. The 9.77% accuracy increase highlights the importance of hyperparameter tuning. SMOTE also proved crucial in balancing the dataset, contributing to a well-rounded learning model. Future studies could explore additional contextual factors and experiment with recurrent or convolutional neural networks to enhance performance further.
14
Maulana, Fikri, and Erwin Budi Setiawan. "Performance of Deep Feed-Forward Neural Network Algorithm Based on Content-Based Filtering Approach." INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi 8, no. 2 (2024): 278–94. http://dx.doi.org/10.29407/intensif.v8i2.22904.
Full textAbstract:
Background: Selecting a restaurant in a diverse city like Bandung can be challenging. This study leverages Twitter data and local restaurant information to develop an advanced recommendation system to improve decision-making. Objective: The system integrates content-based filtering (CBF) with deep feedforward neural network (DFF) classification to enhance the accuracy and relevance of restaurant recommendations. Methods: Data was sourced from Twitter and PergiKuliner, with restaurant-related tweets converted into rating values. The CBF combined Bag of Words (BoW) and cosine similarity, followed by DFF classification. SMOTE was applied during training to address data imbalance. Results: The initial evaluation of CBF showed a Mean Absolute Error (MAE) of 0.0614 and a Root Mean Square Error (RMSE) of 0.0934. The optimal DFF configuration in the first phase used two layers with 32/16 nodes, a dropout rate of 0.3, and a 20% test size. This setup achieved an accuracy of 81.08%, precision of 82.89%, recall of 76.93%, and f1-scores of 79.23%. In the second phase, the RMSprop optimizer improved accuracy to 81.30%, and tuning the learning rate to 0.0596 further increased accuracy to 89%, marking a 9.77% improvement. Conclusion: The research successfully developed a robust recommendation system, significantly improving restaurant recommendation accuracy in Bandung. The 9.77% accuracy increase highlights the importance of hyperparameter tuning. SMOTE also proved crucial in balancing the dataset, contributing to a well-rounded learning model. Future studies could explore additional contextual factors and experiment with recurrent or convolutional neural networks to enhance performance further.
15
E, Praveenkumar, Chandru R, Saran K, and Karthik K. "Blockchain Based Placement Management System And Job Recommendation Using Content-Based Filtering." International Research Journal of Computer Science 11, no. 04 (2024): 154–63. http://dx.doi.org/10.26562/irjcs.2024.v1104.04.
Full textAbstract:
The integration of blockchain technology with placement management systems and job recommendation mechanisms presents a robust solution for enhancing the efficiency, transparency, and security of the recruitment process. This paper proposes a Blockchain-based Placement Management System (BPMS) coupled with Content-Based Filtering (CBF) techniques to streamline the job matching process for both job seekers and recruiters. The BPMS leverages the decentralized nature of blockchain to ensure immutable records of job listings, candidate profiles, and transactional data, thereby reducing the risk of fraudulent activities and ensuring data integrity. Smart contracts are utilized to automate various aspects of the recruitment process, such as job application submissions, candidate evaluations, and offer acceptance, facilitating trustless interactions between parties.In parallel, the CBF approach is employed to provide personalized job recommendations to candidates based on the analysis of their skills, qualifications, and preferences. By analyzing the content of job descriptions and candidate profiles, the system generates tailored recommendations that match the expertise and interests of the candidates, improving the likelihood of successful placements.The proposed system offers several advantages over traditional placement management systems, including increased transparency, reduced operational costs, minimized bias in job recommendations, and enhanced security of sensitive data. Through the synergy of blockchain technology and content-based filtering techniques, the BPMS aims to revolutionize the recruitment industry by fostering trust, efficiency, and fairness in the job market.
16
Dwi Aryanto, Agus, Ardhin Primadewi, and Nugroho Agung Prabowo. "Rekomendasi Wisata Kabupaten Magelang menggunakan Metode Content-Based Filtering dan Location-Based Service." JURNAL FASILKOM 15, no. 1 (2025): 172–78. https://doi.org/10.37859/jf.v15i1.8156.
Full textAbstract:
Kabupaten Magelang dikenal memiliki beragam destinasi wisata, mulai dari keindahan alam, situs sejarah, hingga objek wisata budaya. Jumlah kunjungan wisatawan ke wilayah ini terus meningkat setiap tahunnya, baik dari wisatawan domestik maupun mancanegara. Namun demikian, banyaknya pilihan destinasi seringkali menimbulkan kebingungan bagi wisatawan dalam menentukan tujuan yang sesuai dengan preferensi mereka. Untuk mengatasi permasalahan ini, dikembangkan sebuah sistem rekomendasi wisata dengan menggabungkan metode Content-Based Filtering (CBF) menggunakan cosine similarity dan Location-Based Service (LBS) dengan rumus haversine. Data yang digunakan mencakup 173 destinasi wisata di Kabupaten Magelang, termasuk nama, jenis wisata, fasilitas yang tersedia, serta koordinat geografis. Proses perhitungan diawali dengan one-hot encoding terhadap preferensi pengguna dan atribut wisata, dilanjutkan dengan perhitungan kemiripan berdasarkan jenis dan fasilitas wisata. Nilai kemiripan tersebut kemudian dikombinasikan dengan jarak geografis (menggunakan rumus haversine) untuk menghasilkan skor total. Hasil rekomendasi berupa 10 destinasi wisata dengan skor tertinggi yang dipilih dalam skenario 1. Destinasi dengan skor tertinggi adalah Talang Londo (skor: 0,9586), diikuti oleh Rumah Kamera, Omah Mbudur, Punthuk Mongkrong, dan Limanjawi Art House. Temuan ini menunjukkan bahwa kombinasi metode CBF dan LBS efektif dalam menghasilkan rekomendasi wisata yang relevan dan sesuai preferensi bagi wisatawan di Kabupaten Magelang.
17
Rupali, Hande1 Ajinkya Gutti* Kevin Shah2 Jeet Gandhi3 Vrushal Kamtikar4. "MOVIEMENDER- A MOVIE RECOMMENDER SYSTEM." INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY 5, no. 11 (2016): 469–73. https://doi.org/10.5281/zenodo.167478.
Full textAbstract:
In today’s digital world where there is an endless variety of content to be consumed like books, videos, articles, movies, etc., finding the content of one’s liking has become an irksome task. On the other hand digital content providers want to engage as many users on their service as possible for the maximum time. This is where recommender system comes into picture where the content providers recommend users the content according to the users’ liking. In this paper we have proposed a movie recommender system MovieMender. The objective of MovieMender is to provide accurate movie recommendations to users. Usually the basic recommender systems consider one of the following factors for generating recommendations; the preference of user (i.e content based filtering) or the preference of similar users (i.e collaborative filtering). To build a stable and accurate recommender system a hybrid of content based filtering as well as collaborative filtering will be used.
18
Firdaos, Helfi Apriliyandi, Alun Sujjada, and Somantri Somantri. "Melangkah ke Masa Depan Literasi Digital: Rancang Bangun Sistem Genusian Course Academy dengan Pendekatan Hybrid Collaborative Filtering dan Content-Based Filtering." Briliant: Jurnal Riset dan Konseptual 10, no. 2 (2025): 432–41. https://doi.org/10.28926/briliant.v10i2.1957.
Full textAbstract:
Sistem rekomendasi merupakan komponen penting dalam meningkatkan pengalaman pengguna dengan memberikan saran kursus yang relevan dan personal sesuai dengan preferensi dan kebutuhan individu. Pendekatan Hybrid Collaborative Filtering menggabungkan metode Collaborative Filtering (CF) yang menganalisis pola interaksi pengguna dengan metode Content-Based Filtering (CBF) yang mengevaluasi kesamaan fitur konten kursus. Implementasi sistem hybrid ini diharapkan dapat mengatasi keterbatasan masing-masing metode, seperti masalah cold start pada CF dan keterbatasan variasi rekomendasi pada CBF. Penelitian ini bertujuan untuk merancang sistem rekomendasi di lingkungan akademis yang dikenal sebagai “Genusian Course Academyâ€. Melalui pendekatan hybrid ini, diharapkan dapat mengatasi kelemahan masing-masing pendekatan dan menghasilkan sistem rekomendasi yang lebih akurat dan personal. Implementasi sistem ini diharapkan dapat meningkatkan pengalaman belajar online dan membantu pengguna dalam menemukan pelatihan yang sesuai dengan kebutuhan pengguna
19
Rahayu, Febriya Sri, En Tay, Rr Isni Anisah Puspowati, and Miranti Andhita S. "Improving Shopping Experience: Goods Economic Information System Using Content-Based Filtering Algorithm." Informatics Management, Engineering and Information System Journal 2, no. 2 (2025): 69–78. https://doi.org/10.56447/imeisj.v2i2.356.
Full textAbstract:
The owner's income drop in a sports equipment firm stems from insufficient consumer interest in the physical store of a particular sports equipment company, attributed to unattractive product displays and a difficult-to-access location. This study presents a product recommendation system based on searches for items analogous to the desired sports, which can significantly enhance the owner's revenue and streamline the purchasing experience for consumers without necessitating a visit to a physical store. The study utilizes a descriptive methodology for data acquisition, encompassing observation, interviews, and literature reviews. The employed system development methodology is Rapid Application Development (RAD), while the approach utilized is Content-Based Filtering (CBF). Implementing the CBF approach in the product recommendation information system can facilitate consumers' selection of necessary things without visiting a physical store, consequently enhancing the owner's revenue at the specific sports equipment company. This research indicates that improving the shopping experience via technology can reconcile online and physical retail, resulting in increased consumer happiness and loyalty and sustainable company growth for the owner.
20
Febrianti, Saskia, Rahmad Hidayat, and Mulyadi Mulyadi. "Model Rekomendasi Produk Perawatan Kulit Wajah Menggunakan Metode Content Based Filtering (CBF)." Journal of Applied Electrical Engineering 8, no. 2 (2024): 111–16. https://doi.org/10.30871/jaee.v8i2.8672.
Full textAbstract:
Kulit wajah berfungsi melindungi dari polusi lingkungan, termasuk sinar ultraviolet, yang dapat menyebabkan keriput, penuaan, jerawat, dan pembesaran pori-pori. Selain itu, pola makan tidak seimbang, kurang istirahat, dan paparan radikal bebas juga memperburuk kondisi kulit. Perawatan kulit wajah sangat penting karena berhubungan dengan identitas dan kesehatan. Tipe kulit wajah terbagi menjadi lima kategori: normal, kering, berminyak, kombinasi, dan sensitif, yang diklasifikasi berdasarkan kadar air dan minyak pada kulit. Model rekomendasi produk perawatan kulit diperlukan untuk membantu konsumen menemukan produk yang sesuai dengan masalah kulitnya. Hal ini menjadi semakin penting mengingat banyaknya pilihan produk perawatan wajah di pasaran saat ini. Penelitian ini mengembangkan model rekomendasi menggunakan metode filter berbasis konten (CBF), yang mempertimbangkan karakteristik produk, seperti komposisi bahan. Berdasarkan hasil eksperimen, model mampu memberikan rekomendasi yang sesuai dengan preferensi pengguna. Hasil eksperimen model menunjukkan performa yang baik dimana tingkat akurasi yang diperoleh sebesar 88,89%.
21
Hanun Dhiya Reswara, Rasyida, Evanita Evanita, and Arief Susanto. "IMPLEMENTASI CONTENT-BASED FILTERING PADA SISTEM REKOMENDASI BUKU PERPUSTAKAAN." JATI (Jurnal Mahasiswa Teknik Informatika) 9, no. 2 (2025): 3243–50. https://doi.org/10.36040/jati.v9i2.13312.
Full textAbstract:
Perpustakaan memiliki peran penting sebagai sumber literasi. Jumlah koleksi buku yang banyak sering kali membuat anggota kesulitan menemukan buku yang sesuai dengan minat atau kebutuhan anggota. Penelitian ini bertujuan untuk mengimplementasikan metode Content-Based Filtering (CBF) dalam sistem rekomendasi buku Perpustakaan Universitas Muria Kudus. Metode ini bekerja dengan menganalisis konten atribut buku untuk memberikan rekomendasi yang relevan berdasarkan kesamaan antar buku. Proses implementasi melibatkan algoritma TF-IDF (Term Frequency-Inverse Document Frequency) untuk mengukur relevansi antar konten buku dan Cosine Similarity untuk menghitung tingkat kesamaan antar buku berdasarkan fitur buku. Sistem ini dibangun menggunakan bahasa Python dengan framework Flask. Sistem ini memiliki dua fitur utama: rekomendasi berbasis pencarian dan rekomendasi berbasis riwayat peminjaman, di mana buku yang pernah dipinjam tidak akan direkomendasikan kembali. Evaluasi dilakukan menggunakan metrik Precision@10. Sampel evaluasi diambil dari 10 pengguna perpustakaan dengan riwayat peminjaman berbeda, dan sistem menghasilkan rata-rata Precision@10 sebesar 0.91, yang mengindikasikan bahwa 91% rekomendasi yang diberikan relevan dengan preferensi pengguna.
22
Faadhilah, Adhyasta Naufal, and Erwin Budi Setiawan. "Content-Based Filtering in Recommendation Systems Culinary Tourism Based on Twitter (X) Using Bidirectional Gated Recurrent Unit (Bi-GRU)." Jurnal Ilmiah Teknik Elektro Komputer dan Informatika 10, no. 2 (2024): 406–18. https://doi.org/10.26555/jiteki.v10i2.29010.
Full textAbstract:
To address the challenge of information overload in the rapidly expanding culinary sector, a recommendation system using Content-Based Filtering (CBF) and the Bidirectional Gated Recurrent Unit (Bi-GRU) algorithm was developed. This system can help users to suggest culinary options based on user profiles and preferences. Twitter (X) is frequently used to gather culinary reviews in Bandung, forming the foundation for developing recommendation systems. This research contributes to integrating CBF and Bi-GRU to enhance the relevance of culinary recommendations. The system uses Term Frequency-Inverse Document Frequency (TF-IDF) for feature extraction and Cosine Similarity for item matching. Research adapting CBF and Bi-GRU methods specifically for culinary recommendations, especially in Bandung, remains limited. This study focuses on evaluating the performance of a culinary recommendation system. Data collected from Twitter (X) and PergiKuliner includes 2,645 reviews from 44 Twitter (X) accounts and on 200 culinary places. The culinary recommendation model, using CBF with TF-IDF and Cosine Similarity, achieved a Mean Absolute Error (MAE) of 0.254 and Root Mean Square Error (RMSE) of 0.425, indicating high accuracy in rating predictions compared to previous studies. From the experiments conducted, the third experiment using Bi-GRU, SMOTE, and the Nadam algorithm showed the best improvement with a learning rate of 0.014563484775012459, achieving an accuracy of 86.8%, precision of 86.3%, recall of 85.2%, and an F1-Score of 85.5%, with a 16.2% increase in accuracy from the baseline. Thus, this system effectively helps users with culinary recommendations in Bandung, providing good performance based on user preferences.
23
Charan S N. "Job Recommendation System: Content-Based and Collaborative Filtering for Predictive Job Recommendation Systems." Journal of Information Systems Engineering and Management 10, no. 2 (2025): 453–59. https://doi.org/10.52783/jisem.v10i2.2302.
Full textAbstract:
The Smart work Recommendation System (SWR) was created to meet the difficulties presented by the complex work market of today, which is being impacted by design and the recession. To provide highly customized job recommendations, the SJR uses a hybrid technique that combines the advantages of collaborative filtering (CF) and content-based filtering (CBF). CBF evaluates user talents using Natural Language Processing (NLP) and compares them to pertinent job descriptions. Concurrently, CF finds appropriate job suggestions by analyzing the application history and interests of comparable individuals.By adding features for pay prediction and behavioral profile, the SJR goes above and beyond conventional methods. To ensure a strong fit that goes beyond skills, behavioral profiling examines user behavior and preferences to find team dynamics and company cultures that mesh well. Real-time pay insights are provided via the integrated salary prediction tool, enabling recruiters and job seekers to make well-informed judgments about salary expectations and negotiations.The SJR uses machine learning algorithms to examine patterns and provide pertinent recommendations based on similar user profiles, so addressing the cold start issue that new users face. In order to provide consistently accurate and tailored recommendations for every user, the system is built to continuously learn from and adjust to changing user preferences and employment market trends. The SJR provides a much improved job search experience by integrating behavioral analysis, pay projection, and sophisticated filtering techniques, giving recruiters and job seekers a more accurate, individualized, and effective platform.
24
Fahrizal, Diki, Jaja Kustija, and Muhammad Aqil Haibatul Akbar. "Development Tourism Destination Recommendation Systems using Collaborative and Content-Based Filtering Optimized with Neural Networks." Indonesian Journal of Artificial Intelligence and Data Mining 7, no. 2 (2024): 285. http://dx.doi.org/10.24014/ijaidm.v7i2.28713.
Full textAbstract:
Tourism, a vital sector in the global economy, benefits significantly from advancements in infrastructure, accessibility, and information availability. However, the vast volume of information can overwhelm travelers, underscoring the need for efficient recommendation systems. This research aims to develop an advanced tourist destination recommendation system by integrating Collaborative Filtering (CF) and Content-Based Filtering (CBF) models with Neural Networks. This approach seeks to enhance recommendation accuracy by closely aligning with user preferences and addressing the challenge of limited data. The study utilizes data from 523 tourist destinations across West Java, along with user preference assessments, encompassing stages of data collection, labeling, pre-processing, pre-training, neural network-based training, model evaluation, and the presentation of recommendation outcomes. The optimization of the recommendation models through neural networks has notably improved the precision of tourist destination suggestions, achieving Root Mean Square Error (RMSE) values below 0.37 for both CF and CBF approaches. This research significantly contributes to increasing the search efficiency and accuracy for tourist destination information, offering a strategic solution to the prevalent issue of information overload in the tourism industry.
25
Velamentosa, Desvio, and Eri Zuliarso. "SISTEM REKOMENDASI FILM MENGGUNAKAN METODE CONTENT-BASED FILTERING." JATI (Jurnal Mahasiswa Teknik Informatika) 9, no. 2 (2025): 2918–22. https://doi.org/10.36040/jati.v9i2.13251.
Full textAbstract:
Industri hiburan, khususnya film, telah mengalami transformasi besar dengan berkembangnya teknologi dan internet. Namun, banyaknya pilihan film sering kali membuat pengguna kesulitan menemukan film yang sesuai dengan preferensi mereka. Permasalahan utama dalam pemilihan film adalah kurangnya sistem rekomendasi yang dapat memberikan rekomendasi yang akurat berdasarkan preferensi individu. Pengguna sering kali dihadapkan pada daftar panjang film tanpa panduan yang jelas, sehingga membutuhkan waktu lama untuk menemukan film yang sesuai dengan minat mereka. Penelitian ini bertujuan untuk mengembangkan sistem rekomendasi film menggunakan metode Content-Based Filtering (CBF). Dengan sistem ini, pengguna akan mendapatkan rekomendasi film berdasarkan kesamaan atribut dengan film yang pernah mereka tonton sebelumnya, seperti genre, sinopsis, dan sutradara. Metode yang digunakan dalam penelitian ini mencakup teknik Natural Language Processing (NLP), di antaranya TF-IDF untuk ekstraksi fitur teks dan Cosine Similarity untuk menghitung kesamaan antarfilm. Dataset yang digunakan diperoleh dari The Movie Database (TMDb) yang berisi informasi film dalam berbagai genre. Hasil penelitian menunjukkan bahwa sistem ini memiliki nilai precision sebesar 0,85, recall sebesar 0,78, dan F1-Score sebesar 0,81, yang membuktikan keefektifan metode yang diterapkan. Selain itu, sistem berhasil menampilkan rekomendasi film dengan tingkat kesamaan tertinggi dalam bentuk visualisasi yang memperjelas hubungan antarfilm, sehingga pengguna dapat dengan mudah memahami hasil rekomendasi. Dengan demikian, sistem ini diharapkan dapat membantu pengguna dalam menemukan film yang sesuai dengan preferensi mereka secara lebih efisien dan akurat.
26
M. O., Omisore, and Samuel O. W. "Personalized Recommender System for Digital Libraries." International Journal of Web-Based Learning and Teaching Technologies 9, no. 1 (2014): 18–32. http://dx.doi.org/10.4018/ijwltt.2014010102.
Full textAbstract:
The huge amount of information available online has given rise to personalization and filtering systems. Recommender systems (RS) constitute a specific type of information filtering technique that present items according to user's interests. In this research, a web-based personalized recommender system capable of providing learners with books that suit their reading abilities was developed. Content-based filtering (CBF) was used to analyze learners' reading abilities while books that are found suitable to learners are recommended with fuzzy matching techniques. The yokefellow cold-start problem inherent to CBF is assuaged by cold start engine. An experimental study was carried out on a database of 10000 books from different categories of computing studies. The outcome tracked over a period of eight months shows that the proposed system induces greater user satisfaction and this attests users' desirability of the system.
27
Hulvi, Alfajri, and Kusrini Kusrini. "Optimasi Rekomendasi Sustainable Development Goals (SDGs) di Indonesia menggunakan Content-Based Filtering dan Algoritma Machine Learning." Building of Informatics, Technology and Science (BITS) 6, no. 2 (2024): 1045–58. https://doi.org/10.47065/bits.v6i2.5807.
Full textAbstract:
Abstrak−Lahirnya program tentang Tujuan Pembangunan Berkelanjutan atau Sustainable Development Goals (SDGs) pada tahun 2015 membuat masyarakat di semua negara mulai memandang penting pembangunan berkelanjutan untuk diimplementasikan. Indonesia, sebagai bagian dari komunitas global, juga telah mengadopsi SDGs ini sebagai kerangka kerja dalam upaya mencapai Indonesia Emas 2045. Dengan visi ini, Indonesia bercita-cita menjadi negara maju yang berdaulat, adil, dan makmur tepat pada peringatan 100 tahun kemerdekaannya. Untuk mencapai tujuan secara efektif, penting untuk menerapkan sistem rekomendasi berbasis Artificial Intelligence (AI) yang mempertimbangkan tantangan sosial, ekonomi, dan lingkungan hidup yang dihadapi oleh negara Indonesia di masa mendatang. Content-Based Filtering (CBF) adalah teknik yang populer untuk membangun sistem tersebut. Penelitian ini membahas teknik untuk optimasi CBF menggunakan beberapa algoritma machine learning tradisional yaitu SVM, KNN, DT dan algoritma Deep Learning yaitu MLP. Teknik pengambilan sample dan penyetelan hiperparameter juga diperhatikan dalam penelitian ini. Algoritma Deep Learning MLP menghasilkan akurasi tertinggi yaitu 84%.
28
Artika, Zahwa Dewi, and Erwin Budi Setiawan. "CONTENT-BASED FILTERING CULINARY RECOMMENDATION SYSTEM USING DEEP CONVOLUTIONAL NEURAL NETWORK ON TWITTER (X)." JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 10, no. 2 (2024): 333–41. http://dx.doi.org/10.33480/jitk.v10i2.5640.
Full textAbstract:
Along with the development of technology, social media has become integral to everyday life, especially for sharing content like culinary reviews. Social media platform X (formerly Twitter) is often used for sharing culinary recommendations, but the abundance of information makes it difficult for users to find relevant suggestions. In order to improve rating prediction performance, this study suggests a recommendation system model that is more thoroughly created utilizing Content-Based Filtering (CBF) combined with Deep Convolutional Neural Network (CNN) and optimised with Particle Swarm Optimization (PSO). Data was collected from PergiKuliner and Twitter, totaling 2644 reviews and 200 cuisines. The preprocessing involved text processing, translation, and polarity assessment. Post-labeling, 7438 data were labeled with 0 and 1562 with 1. Label 0 means not recommended while label 1 means recommended. The imbalance is handled by applying the SMOTE method after observing that the fraction of data labeled 0 and 1 is 65.2%. CBF employed TF-IDF feature extraction and FastText word embedding, while Deep CNN handled classification. PSO optimisation was applied to enhance the accuracy of culinary rating predictions. The results showed an initial accuracy of 76.32% with the baseline Deep CNN model, which increased to 86.06% after Nadam optimisation with the best learning rate, and further reached 86.18% after PSO optimisation on dense units. The 9.86% accuracy improvement from the baseline model demonstrates the effectiveness of the combined methods.
29
Shashikala, H.K, Iyer K. Praghnya, K.R Himaja, and Pokharel Rahisha. "Personalized Movie Recommendation System." International Journal of Information Technology, Research and Applications (IJITRA) ISSN: 2583 5343 2, no. 1 (2023): 1–6. https://doi.org/10.5281/zenodo.7779051.
Full textAbstract:
In the digital world of today, where there is an infinite amount of content to consume, including movies, books, videos, articles, and so on, finding content that appeals to one's tastes has become challenging. On the other hand, providers of digital content want to keep as many people using their service for as long as possible. This is where the recommender system comes into play, where content providers suggest content to users based on their preferences. Web applications that offer a variety of services and automatically suggest some services based on user interest increasingly rely on recommendation systems. Different business services each play a significant role in the success of the current marketing field. The personalize recommendation technique is one of the most valuable tools for providing personalized service on websites. When it comes to e-Commerce's online marketing efforts, this strategy is extremely useful. To build the proposal framework, the cooperative sifting is exceptionally helpful advances in the field of recommender frameworks. The accuracy of recommendation engines is the source of many issues in today's web. Therefore, a variety of strategies are utilized to enhance the recommendation system's diversity and accuracy. When generating recommendations, the fundamental recommender systems typically take one of the following into account: The Content-Based Filtering, which is based on the user's preferences, it describes things, and we use keywords other than the user's profile to show what the user likes and dislikes. To put it another way, CBF algorithms suggest products that people have liked in the past or products that are similar to them. It looks at what you've liked in the past and suggests the best match, Or a collaborative filtering system makes recommendations for items based on how similar users and/or items are measured. The CF system only suggests products that are popular with similar types of users. The development of a movie recommendation system with category-based recommendations, more precise results, increased efficiency, and overcoming the cold start are the goals of this system.
30
Ilhamsyah, Ilhamsyah, Syahru Rahmayuda, Dwi Marisa Midyanti, and Shantika Martha. "Pemodelan Sistem Rekomendasi Restoran berdasarkan Preferensi Pengguna dengan Pendekatan Content-Based Filtering." Jurnal Edukasi dan Penelitian Informatika (JEPIN) 10, no. 1 (2024): 154. http://dx.doi.org/10.26418/jp.v10i1.74008.
Full textAbstract:
Setiap individu memiliki preferensi makanan yang unik. Karakteristik rasa yang khas dapat memengaruhi seberapa bersedia seseorang membayar untuk hidangan di restoran tertentu. Keterkaitan antara preferensi makanan seseorang dengan karakteristik harga makanan dapat digunakan sebagai faktor penting dalam menentukan rekomendasi restoran. Penelitian ini memodelkan sebuah sistem rekomendasi restoran berdasarkan prefrensi rasa, harga dan rating makan penggunanya sebagai faktor utama dalam mempengaruhi hasil rekomendasi. Analisis data menggunakan 3 atribut yaitu data ulasan restoran, rating dan harga restoran. Teknik scraping dilakukan untuk pengumpulan dataset, adapun jumlah dataset sebanyak 661 data restoran dari hasil scraping. Pengubahan dataset dilakukan dengan proses Pra-Processing yang kemudian dilanjutkan dengan mempelajari model data dengan pendekatan Content-Based Filtering (CBF). Hasil penelitian menunjukkan bahwa rata-rata akurasi yang diberikan sistem rekomendasi yang dibangun adalah 73.33% dari rekomendasi restoran berdasarkan harga dan ulasan.
31
Efrizoni, Lusiana, Junadhi Junadhi, and Agustin Agustin. "Optimization of Content Recommendation System Based on User Preferences Using Neural Collaborative Filtering." MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 24, no. 2 (2025): 309–20. https://doi.org/10.30812/matrik.v24i2.4775.
Full textAbstract:
Recommender systems play a crucial role in enhancing user experience across various digital platforms by delivering relevant and personalized content. However, many recommender systems still face challenges in providing accurate recommendations, especially in cold-start situations and when user data is limited. This study aims to address these issues by optimizing content recommendation systems using Neural Collaborative Filtering (NCF), a deep learning-based approach capable of capturing non-linear relationships between users and items. We compare the performance of NCF with traditional methods such as Matrix Factorization (MF) and Content-Based Filtering (CBF) using the MovieLens-1M dataset. The research method employed is a quantitative approach that encompasses several stages, including preprocessing, model training, and evaluation using metrics such as Root Mean Squared Error (RMSE) and Precision@K. The results of this research are significant, demonstrating that NCF achieves the lowest RMSE of 0.870, outperforming MF with an RMSE of 0.950 and CBF with an RMSE of 1.020. Additionally, the Precision@K achieved by NCF is 0.73, indicating the model’s superior ability to provide more relevant recommendations compared to baseline methods. Hyperparameter tuning reveals that the optimal combination includes an embedding size of 16, three hidden layers, and a learning rate of 0.005. Despite its excellent performance, NCF still faces challenges in handling cold-start cases and requires significant computational resources. To address these challenges, integrating additional metadata and exploring regularization techniques such as dropout are recommended to enhance generalization. The implications of the findings from this study suggest that NCF can significantly improve prediction accuracy and recommendation relevance, thus having the potential for widespread application across various domains, such as e-commerce, streaming services, and education, to enhance user experience and the efficiency of recommendation systems. Further research is needed to explore innovative solutions to address cold-start challenges and reduce computational demands.
32
Sinaga, Vincentius Loanka, and Antoni Wibowo. "Combining XGBoost and hybrid filtering algorithm in e-commerce recommendation system." International Journal of Advances in Applied Sciences 14, no. 2 (2025): 618. https://doi.org/10.11591/ijaas.v14.i2.pp618-626.
Full textAbstract:
This study proposes a hybrid filtering algorithm (HFA) that combines extreme gradient boosting (XGBoost), content-based filtering (CBF), and collaborative filtering (CF) to improve recommendation accuracy in electronic commerce (e-commerce). XGBoost first leverages demographic data (e.g., age, gender, and location) to address cold start conditions, producing an initial product prediction; CBF refines this prediction by measuring product similarities through term frequency-inverse document frequency (TF-IDF) and cosine similarity, while CF (implemented via singular value decomposition) further incorporates user interaction patterns to enhance recommendations. Experimental results across multiple datasets demonstrate that HFA consistently outperforms standalone XGBoost in key metrics, including precision, F1-score, and hit ratio (HR). HFA’s precision often exceeds 90%, indicating fewer irrelevant recommendations. Although recall levels remain modest, HFA exhibits stronger adaptability under cold start scenarios due to its reliance on demographic features and user-item interactions. These findings highlight the efficacy of combining advanced machine learning with hybrid filtering techniques, offering a more robust and context-aware solution for e-commerce recommendation systems.
33
Juyal, Aayush, Nandini Sharma, Pisati Rithya, and Sandeep Kumar. "An Enhanced Approach to Recommend Data Structures and Algorithms Problems Using Content-based Filtering." International Journal of Intelligent Systems and Applications 15, no. 5 (2023): 28–40. http://dx.doi.org/10.5815/ijisa.2023.05.03.
Full textAbstract:
Data Structures and Algorithms (DSA) is a widely explored domain in the world of computer science. With it being a crucial topic during an interview for a software engineer, it is a topic not to take lightly. There are various platforms available to understand a particular DSA, several programming problems, and its implementation. Hacckerank, LeetCode, GeeksForGeeks (GFG), and Codeforces are popular platforms that offer a vast collection of programming problems to enhance skills. However, with the huge content of DSA available, it is challenging for users to identify which one among all to focus on after going through the required domain. This work aims to use a Content-based filtering (CBF) recommendation engine to suggest users programming-based questions related to different DSAs such as arrays, linked lists, trees, graphs, etc. The recommendations are generated using the concept of Natural Language Processing (NLP). The data set consists of approximately 500 problems. Each problem is represented by the features such as problem statement, related topics, level of difficulty, and platform link. Standard measures like cosine similarity, accuracy, precision, and F1-score are used to determine the proportion of correctly recommended problems. The percentages indicate how well the system performed regarding that evaluation. The result shows that CBF achieves an accuracy of 83 %, a precision of 83 %, a recall of 80%, and an F1-score of 80%. This recommendation system is deployed on a web application that provides a suitable user interface allowing the user to interact with other features. With this, a whole E-learning application is built to aid potential software engineers and computer science students. In the future, two more recommendation systems, Collaborative Filtering (CF) and Hybrid systems, can be implemented to make a comparison and decide which is most suitable for the given problem statement.
34
Arsytania, Ihsani Hawa, Erwin Budi Setiawan, and Isman Kurniawan. "Movie Recommender System Using Cascade Hybrid Filtering with Convolutional Neural Network." Jurnal Ilmiah Teknik Elektro Komputer dan Informatika 10, no. 2 (2024): 188–200. https://doi.org/10.26555/jiteki.v9i4.28146.
Full textAbstract:
The current technological advancements have made it easier to watch movies, especially through online streaming platforms such as Netflix. Social media platforms like Twitter are used to discuss, share information, and recommend movies to other users through tweets. The user tweets from Twitter are utilized as a film review dataset. Film ratings can be used to build a recommendation system, incorporating Collaborative Filtering (CF) and Content-based Filtering (CBF). However, both methods have their limitations. Therefore, a hybrid filtering approach is required to overcome this problem. The filtering approach involves CF and CBF processes to improve the accuracy of film recommendations. No current research employs the Cascade Hybrid Filtering method, particularly within the context of movie recommendation systems. This study addresses this gap by implementing the Cascade Hybrid Filtering method, utilizing the Convolutional Neural Network (CNN) as the evaluative instrument. This research presents a significant contribution by implementing the Cascade Hybrid Filtering method based on CNN. This research uses several scenarios to compare methods to produce the most accurate model. This study's findings demonstrate that the application of Cascade Hybrid Filtering, incorporating CNN and optimized with RMSProp, yields a movie recommendation system with notable performance metrics, including an MAE of 0.8643, RMSE of 0.6325, and the highest accuracy rate recorded at 86.95%. The RMSprop optimizer, facilitating a learning rate of 6.250551925273976e-06, enhances accuracy to 88.40%, showcasing a remarkable improvement of 6.00% from the baseline. These outcomes underscore the significant contribution of the paper in enhancing the precision and effectiveness of movie recommendation systems.
35
Yulfihani, Ilmira, and Muhammad Zakariyah. "Optimization of Tourism Destination Recommendations in Batang Regency Using Content-Based Filtering." Journal of Applied Informatics and Computing 8, no. 2 (2024): 499–508. https://doi.org/10.30871/jaic.v8i2.8618.
Full textAbstract:
In an era where tourism plays a pivotal role in economic development, the need for effective navigation through diverse attractions has never been more critical. This research presents a cutting-edge tourism recommendation system tailored for Batang Regency, leveraging Content-Based Filtering (CBF) to deliver personalized suggestions that enhance the tourist experience. By categorizing tourist attractions into Culinary, Culture, Accommodation, Nature, and Leisure, and employing the Haversine formula for precise geographical calculations, our system prioritizes recommendations based on user preferences and proximity. Recommendation testing yielded an impressive average F1 Score of 0.965, underscoring the system's accuracy and relevance, particularly in straightforward user scenarios. However, the research also identifies challenges in more complex cases, suggesting the need for future enhancements through hybrid models and the integration of user feedback. This innovative approach not only streamlines the decision-making process for tourists but also aims to boost local tourism, making it an invaluable tool for both visitors and the Batang Regency community. Join us in exploring how technology can transform the way we experience travel, ensuring that every journey is tailored to individual desires and needs.
36
Pratiwi, Niken, Dwi Hartanti, and Aprilisa Arum Sari. "Sistem Rekomendasi Pemilihan Laptop Menggunakan Metode Content-Based Filtering Berbasis Spesifikasi Produk." Infotek: Jurnal Informatika dan Teknologi 8, no. 2 (2025): 563–73. https://doi.org/10.29408/jit.v8i2.30618.
Full textAbstract:
The advancement of information technology has led to an increasing demand for computing devices, particularly laptops. The wide variety of options based on specifications, brands, and prices often makes it difficult for consumers to choose the device that best suits their needs. Therefore, this study aims to design a laptop recommendation system using the Content-Based Filtering (CBF) approach to provide relevant suggestions based on user preferences. The developed system applies Term Frequency-Inverse Document Frequency (TF-IDF) and Cosine Similarity methods to measure the similarity between key laptop features such as processor type, RAM capacity, storage, and graphics card. Laptop data was obtained through a web scraping process from trusted e-commerce websites and integrated into a web-based platform. Testing results show that the system can automatically generate personalized and highly relevant recommendations. The main contribution of this study is the development of an efficient content-based laptop recommendation system utilizing a combination of TF-IDF and Cosine Similarity techniques. In addition to facilitating faster decision-making in selecting a laptop, the system also demonstrates the practical application of machine learning-based recommendation technologies in the e-commerce sector. This research further provides a foundation for developing similar recommendation systems in other contexts that require content-based personalization approaches.
37
Nura, Mukhtar, and Zaharaddeen Adamu Hamisu. "AUTHOR-CENTRIC SCIENTIFIC PAPER RECOMMENDER SYSTEM TO IMPROVE CONTENT-BASED FILTERING APPROACH." International Journal of Software Engineering and Computer Systems 10, no. 1 (2024): 40–49. http://dx.doi.org/10.15282/ijsecs.10.1.2024.4.0122.
Full textAbstract:
Scholarly publications on the web are rapidly expanding, making it difficult for scholars to identify relevant study materials. Information overload makes it harder to find important material, especially for new researchers. Scholarly recommender systems solve this issue by employing recommendation techniques to assist researchers in locating appropriate literature based on their interests. Existing systems frequently rely on user profiles and public and non-public metadata, which leads to the persistent problem in scholarly recommendations called cold start. To deal with the challenges of cold start in scholarly-based recommender systems, this research suggests an improved Content-Based Filtering (CBF) approach that takes advantage of publicly available metadata, specifically the author(s) feature. The approach incorporated author(s) features into a scholarly recommender system to serve as a basis and key component for alleviating "A New Paper Cold Start Problem." The proposed approach implements the feature vectors of the metadata using the Count Vectorizer and similarity computation was performed using the Cosine Similarity formula." An experiment using a publicly available dataset shows that the suggested method surpasses the approaches previously proposed by other researchers regarding recommendation accuracy and relevancy, making it a dependable and efficient instrument for scholarly recommendation. The result also shows the effectiveness of the author(s) feature in tackling new papers in scholarly recommendation systems.
38
Husodo, Ario Yudo, Fitri Bimantoro, Nadiyasari Agitha, and Nuraqilla Waidha Bintang Grendis. "IMPROVING SHOPPING EXPERIENCES AT NTB MALL THROUGH PERSONALIZED PRODUCT RECOMMENDATIONS USING CONTENT-BASED FILTERING." Jurnal Teknik Informatika (Jutif) 6, no. 1 (2025): 387–400. https://doi.org/10.52436/1.jutif.2025.6.1.4194.
Full textAbstract:
NTB MALL, an e-commerce platform specializing in unique products from micro, small, and medium enterprises (MSMEs) in West Nusa Tenggara, faces challenges in providing personalized product recommendations due to the diversity of its product categories and consumer preferences. To address this, this study implements a content-based filtering (CBF) approach utilizing Term Frequency-Inverse Document Frequency (TF-IDF) and cosine similarity to enhance recommendation accuracy. The system analyzes product attributes and user interaction history to generate tailored suggestions. Experimental results indicate that cosine similarity outperforms Euclidean distance in recommendation precision, achieving an accuracy of 89% and a Mean Reciprocal Rank (MRR) of 95%. Furthermore, user feedback reveals that 93% of users found the recommendations highly relevant, 89% reported increased engagement, and 96% expressed satisfaction with the personalized shopping experience. This research provides a novel application of AI-driven recommendation systems in regional e-commerce marketplaces, demonstrating their potential to improve user experience and foster stronger connections between consumers and local producers.
39
Sariki, Tulasi Prasad, and G. Bharadwaja Kumar. "AN AGGRANDIZED FRAMEWORK FOR ENRICHING BOOK RECOMMENDATION SYSTEM." Malaysian Journal of Computer Science 35, no. 2 (2022): 111–27. http://dx.doi.org/10.22452/mjcs.vol35no2.2.
Full textAbstract:
In this era of information overload, Recommender Systems have become increasingly important to assist internet users in finding the right choice from umpteen numbers of choices. Especially, in the case of book recommender systems, suggesting an appropriate book by considering user preferences can increase the number of book readers in turn having an aftereffect on the users’ lifestyle by reducing stress, stimulating imagination, improving vocabulary, and making readers smarter. The majority of book recommender systems in the literature have used Collaborative Filtering (CF) and Content-Based Filtering (CBF) methods. Even though CBF methods have shown better performance than CF methods, they are mostly confined to shallow linguistic features. The present work proposed an aggrandized framework having three concurrent modules to improve the recommendation process. NER module extracts the Named Entities from the entire book content which are the key semantic units in providing clues on the possible choices of reading other related books. The Visual feature extraction module analyzes the book front cover to detect objects and text on the cover as well as the description of the cover which can bestow a clue for the genre of that book. The Stylometry module enhances the feature set used in the literature to analyze the author’s literary style for identifying similar authors to the present author of the book. These three modules conjointly improved the overall recommendation accuracy by 18% over the baseline CBF method that indicates the effectiveness of the present framework.
40
Rianat Abimbola Oguntuase. "Optimizing researcher mentorship matching: A particle swarm optimization-based recommendation model." World Journal of Advanced Engineering Technology and Sciences 13, no. 2 (2024): 698–707. https://doi.org/10.30574/wjaets.2024.13.2.0640.
Full textAbstract:
Mentoring is an essential collaborative practice among academic researchers, fostering growth and expertise. It is widely believed that scientific knowledge, practices, and skills are transferred from one generation of scientists to the next through mentorship. The increasing significance of collaboration among academic researchers necessitates innovative, effective tools for optimal mentor-mentee matching, facilitating successful mentorship and knowledge transfer. Despite existing expert-finding recommender systems, matching mentors with mentees remains understudied. This research addresses this gap by developing a novel metaheuristic-based approach to optimize mentor-mentee pairing. Utilizing profile and publication datasets from Academic Family Tree, a Support Vector Machine (SVM) classifier is employed to categorize researchers as experts or young researchers. Term Frequency-Inverse Document Frequency (TF-IDF) extracts research area features, generating researcher vectors. These inputs are then optimized using Particle Swarm Optimization (PSO) algorithm to facilitate mentorship connections. The results demonstrate exceptional performance: the Support Vector Machine (SVM) classifier achieves 99% accuracy, while the optimized recommendation model based on PSO algorithm, which achieves 100% accuracy, outperforms three baseline models, collaborative filtering (CF), content-based filtering (CBF) and Hybrid CF-CBF models. This study's findings can inform research institutions seeking to enhance researcher-mentor connections, fostering collaborative excellence. Future research will explore expanded datasets and algorithmic refinements.
41
Kumar, Akshi, Simran Seth, Shivam Gupta, and Shubham. "Sentiment-Enhanced Content-Based System for Online Recommendations and Rating Prediction." International Journal of Gaming and Computer-Mediated Simulations 12, no. 2 (2020): 1–25. http://dx.doi.org/10.4018/ijgcms.2020040101.
Full textAbstract:
The scarcity of dependable product descriptions and limited emotion unmasking capabilities of user-ratings compromise the accuracy of content-based filtering (CBF) systems. This work puts forward a sentiment-enhanced content-based recommender system (SEC-Rec). The model has four modules, namely key feature extraction module, feature sentiment analysis module, recommendation module, and rating prediction module. Key feature extraction module uses hybrid of RAKE and TextRank to uncover key product features. The authors propose a hybridized model HSVADER (Hybrid SVM and VADER) for feature sentiment evaluation. The recommendation module combines sentiment and similarity for robust product ranking strategy. The practical benefits of SEC-Rec are demonstrated using Amazon Camera dataset, and the results are compared to the state of the art. The rating prediction module uses key feature sentiment score to estimate the overall user-rating resolving the multi-criteria decision-making issue. The RMSE value obtained ascertains the effectiveness of the approach compared to recent models.
42
Khamil, Muhammad Khamil, and Erwin Budi Setiawan. "Content Based Filtering on Culinary Tourism Recommendation System Based on Social Media X Using Bi-LSTM." International Journal on Information and Communication Technology (IJoICT) 10, no. 2 (2024): 170–83. https://doi.org/10.21108/ijoict.v10i2.967.
Full textAbstract:
Advancing technology, especially on social media platforms like X, created a vibrant space for users to share culinary experiences and recommendations through opinions and reviews. X became critical in presenting reviews and recommending places to eat with an excessively high number of active users. Facing the challenge of information overload on X, this research proposed a culinary tourism recommendation system using the Content-Based Filtering (CBF) method with Word to Vector (Word2Vec) and Bidirectional Long Short-Term Memory (Bi-LSTM) for classification. Utilizing culinary tourism data from Tripadvisor and user threads on Twitter, the dataset used included 2,645 tweets and five web crawling results, resulting in a matrix with a total of 200 culinary places and 44 users. Data pre-processing, such as the calculation of sentiment polarity scores using TextBlob and the application of SMOTE technique to balance the data, contributed to the improved accuracy of this research. In addition, optimization of the Bi-GRU model with various optimization methods, such as Adam, and hyperparameter tuning using Learning Rate Finder, resulted in a maximum accuracy of 94.99%, an increase of 29.4% from the baseline. The results of this research contributed significantly to the development of a more accurate and personalized culinary tourism recommendation system.
43
Alshammari, Gharbi, Stelios Kapetanakis, Abdullah Alshammari, Nikolaos Polatidis, and Miltos Petridis. "Improved Movie Recommendations Based on a Hybrid Feature Combination Method." Vietnam Journal of Computer Science 06, no. 03 (2019): 363–76. http://dx.doi.org/10.1142/s2196888819500192.
Full textAbstract:
Recommender systems help users find relevant items efficiently based on their interests and historical interactions with other users. They are beneficial to businesses by promoting the sale of products and to user by reducing the search burden. Recommender systems can be developed by employing different approaches, including collaborative filtering (CF), demographic filtering (DF), content-based filtering (CBF) and knowledge-based filtering (KBF). However, large amounts of data can produce recommendations that are limited in accuracy because of diversity and sparsity issues. In this paper, we propose a novel hybrid method that combines user–user CF with the attributes of DF to indicate the nearest users, and compare four classifiers against each other. This method has been developed through an investigation of ways to reduce the errors in rating predictions based on users’ past interactions, which leads to improved prediction accuracy in all four classification algorithms. We applied a feature combination method that improves the prediction accuracy and to test our approach, we ran an offline evaluation using the 1M MovieLens dataset, well-known evaluation metrics and comparisons between methods with the results validating our proposed method.
44
Timmi, Mohamed. "Educational Video Recommender System." International Journal of Information and Education Technology 14, no. 3 (2024): 362–71. http://dx.doi.org/10.18178/ijiet.2024.14.3.2058.
Full textAbstract:
In recent years, informal education has witnessed a significant upsurge, fueled by technological advancements and the ubiquitous availability of online educational content. Internet users, including students, researchers, and teachers, are increasingly seeking supplementary educational resources across diverse online repositories to augment their knowledge. Within this landscape, recommendation systems emerge as indispensable tools, aiding users in the discovery of pertinent resources aligned with their academic interests. This article proposes a novel recommendation methodology leveraging a hybrid approach, incorporating both Content-Based Filtering (CBF) and Collaborative Filtering (CF) algorithms. By harnessing information from a myriad of data repositories, this system excels in identifying and presenting the most relevant and desirable educational resources, with a particular focus on meeting the needs of students. This holistic approach embraces user profiles, contextual information, and supplementary data, underscoring its potential to revolutionize informal education in the digital age.
45
Daniawan, Benny, and Ivander Darmawan. "Singme Music Entertainment Services Marketing Information System with Content-Based Filtering Method and TAM Testing." Tech-E 7, no. 1 (2023): 1–9. http://dx.doi.org/10.31253/te.v7i1.1500.
Full textAbstract:
With the times, the website used as marketing and sales media, which developed into E-Commerce. In 2019, there was 16,277 businesses used the E-Commerce concept, and also the value of Gross Domestic Product (GDP) was about 5.07%. Furthermore, because of the Coronavirus Disease (COVID) pandemic, the GDP decreased to -2.07% In 2020 and even impacted 10 out of 17 business sectors. Music entertainment business was also impacted by the pandemic, because during the pandemic, the government restricted certain public activities. Therefore, this system named Singme will help singers or music groups to market their services and provide related information for the public. Searching the services in Singme will be assisted by using Content-Based Filtering (CBF) method, it will give the recommendations of the services which have correlations with the keywords. Using Technology Acceptance Model (TAM) to test 122 feedback data about Singme with SmartPLS application v3.2.9. As the results, all hypotheses are acceptable because each t-statistic value > t-table value (1.981), and also each p-value < 0.05. Which PEOU influences PU by 34.3%, PU and POEU influence ATU by 50.7%, PU and ATU influence BITU by 56.1%, and BITU influences ASU by 52.3%.
46
Ihsan, Syahdan Naufal Nur, and Erwin Budi Setiawan. "The HYBRID CONTENT-BASED FILTERING AND CLASSIFICATION RNN WITH PARTICLE SWARM OPTIMIZATION FOR TOURISM RECOMMENDATION SYSTEM." JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 10, no. 2 (2024): 241–51. http://dx.doi.org/10.33480/jitk.v10i2.5674.
Full textAbstract:
Economic recovery in the tourism sector after the COVID-19 pandemic is one of the main focuses of the Indonesian government at the moment, especially in Bandung City. This research aims to develop a personalized tourist spot recommendation system, by addressing the gaps in the existing literature through the integration of Content-Based Filtering (CBF) and Simple Recurrent Neural Network (RNN) methods that aim to improve recommendation accuracy. This study uses a hybrid approach that combines Term Frequency - Inverse Document Frequency (TF-IDF) and word embedding with the Robustly Optimized BERT (RoBERTa) model to identify similarities between tourist destinations based on their content characteristics. Simple RNN is used to analyze user preference patterns over time, which is then further optimized using Particle Swarm Optimization (PSO). As a result, the Simple RNN model that has been optimized with PSO shows an increased accuracy of up to 94.37%, outperforming other optimizations such as Adam and SGD. This research makes a novel contribution by applying advanced machine learning techniques to improve personalization in travel recommendation systems.
47
Patro, Sunkuru Gopal Krishna, Brojo Kishore Mishra, Sanjaya Kumar Panda, Raghvendra Kumar, Hoang Viet Long, and Tran Manh Tuan. "Knowledge-based preference learning model for recommender system using adaptive neuro-fuzzy inference system." Journal of Intelligent & Fuzzy Systems 39, no. 3 (2020): 4651–65. http://dx.doi.org/10.3233/jifs-200595.
Full textAbstract:
A recommender system (RS) delivers personalized suggestions on products based on the interest of a particular user. Content-based filtering (CBF) and collaborative filtering (CF) schemes have been previously used for this task. However, the main challenge in RS is cold start problem (CSP). This originates once a new user joins the system which makes the recommendation task tedious due to the shortage of information (clickstream, dwell time, rating, etc.) regarding the user’s interest. Therefore, CBF and CF are combined together by developing a knowledge-based preference learning (KBPL) system. This system considers the demographic data that includes gender, occupation, and age for the recommendation task. Initially, the dataset is clustered using the self-organizing map (SOM) technique, then the high dimensional data is decomposed by higher-order singular value decomposition (HOSVD) and finally, Adaptive neuro-fuzzy inference system (ANFIS) predicts the output. For the big dataset, SOM is a robust clustering method and the similarities among the users can be easily observed by grid clustering. The HOSVD extracts the required information from the available data set to find the user similarity by decomposing the dataset in lower dimensions. ANFIS uses IF-THEN rules to recommend similar product to the new users. The proposed KBPL system is evaluated with the Black Friday dataset and the obtained error value is compared with the existing CF and CBF techniques. The proposed KBPL system has obtained root mean squared error (RMSE) of 0.71%, mean absolute error (MAE) of 0.54%, and mean absolute percentage error (MAPE) of 37%. Overall, the outcome of the comparative analysis shows minimum error and better performance in terms of precision, recall, and f-measure for the proposed KBPL system compared to the existing techniques and therefore more suitable for accurately recommending the products for the new users.
48
Park, Ji-Hyeok, and Jae-Dong Lee. "A Customized Deep Sleep Recommender System Using Hybrid Deep Learning." Sensors 23, no. 15 (2023): 6670. http://dx.doi.org/10.3390/s23156670.
Full textAbstract:
This paper proposes a recommendation system based on a hybrid learning approach for a personal deep sleep service, called the Customized Deep Sleep Recommender System (CDSRS). Sleep is one of the most important factors for human life in modern society. Optimal sleep contributes to increasing work efficiency and controlling overall well-being. Therefore, a sleep recommendation service is considered a necessary service for modern individuals. Accurate sleep analysis and data are required to provide such a personalized sleep service. However, given the variations in sleep patterns between individuals, there is currently no international standard for sleep. Additionally, service platforms face a cold start problem when dealing with new users. To address these challenges, this study utilizes K-means clustering analysis to define sleep patterns and employs a hybrid learning algorithm to evaluate recommendations by combining user-based and collaborative filtering methods. It also incorporates feedback top-N classification processing for user profile learning and recommendations. The behavior of the study model is as follows. Using personal information received through mobile devices and data, such as snoring, sleep time, movement, and noise collected through AI motion beds, we recommend sleep and receive user evaluations of recommended sleep. This assessment reconstructs the profile and, finally, makes recommendations using top-N classification. The experimental results were evaluated using two absolute error measurement methods: mean squared error (MSE) and mean absolute percentage error (MAPE). The research results regarding the hybrid learning methods show 13.2% fewer errors than collaborative filtering (CF) and 10.2% fewer errors than content-based filtering (CBF) on an MSE basis. According to the MAPE, the methods are 14.7% more accurate than the CF model and 9.2% better than the CBF model. These results demonstrate that CDSRS systems can provide more accurate recommendations and customized sleep services to users than CF, CBF, and combination models. As a result, CDSRS, a hybrid learning method, can better reflect a user’s evaluation than traditional methods and can increase the accuracy of recommendations as the number of users increases.
49
Srikanth, M. V., T. Manaswitha, Priya M. Santhi, Kumar A. Kalyan, and Manikanta B. Rushi. "Enhanced medical image fusion using cross-guided filtering and edge-preserving techniques for improved clinical diagnosis." i-manager’s Journal on Electronics Engineering 15, no. 3 (2025): 29. https://doi.org/10.26634/jele.15.3.21732.
Full textAbstract:
Medical image fusion utilizes diverse diagnostic information found between multiple medical images to produce one improved display for better clinical procedures and diagnostic accuracy. The research develops an effective framework for multimodal medical images fusion by utilizing Cross Bilateral Filtering (CBF) and Edge-Preserving Processing applied to CT, MRI, PET and SPECT data types. The proposed method adopts CBF to maintain edge integrity while it removes noise and reveals fine image details. An enhancement of significant image features occurs through edge-preserving processing by dividing low-pass content from residual elements. A gradient-based integration process combines processed images through a method that strengthens details found in places where gradient magnitudes reach higher levels. The assessments of consolidated images used Normalized Cross-Correlation (NCC) together with Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Entropy as evaluation metrics. Experimental evaluations confirm the proposed technique successfully maintains diagnostic vital information while improving visual clarity, which indicates its reliability for medical practice.
50
Usman, Abdulgafar, Abubakar Roko, Aminu B. Muhammad, and Abba Almu. "Enhancing Personalized Book Recommender System." International Journal of Advanced Networking and Applications 14, no. 03 (2022): 5486–92. http://dx.doi.org/10.35444/ijana.2022.14311.
Full textAbstract:
Recommender systems (Rs) are widely used to provide recommendations for a collection of items or products that may be of interest to user or a group of users. Because of its superior performance, Content-Based Filtering (CBF) is one of the approaches that are commonly utilized in real-world Rs using Time-Frequency and Inverse Document Frequency (TF-IDF) to calculate document similarities. However, it computes document similarity directly in the word-count space. We propose a user-based collaborative filtering (UBCF) method to solve the problem of limited in content analysis which leads to a low prediction rate for large vocabulary. In this study, we present an algorithm that utilises Euclidean distance similarity function, to solve the identified problem. The performance of the proposed scheme was evaluated against the benchmark scheme using different performance metrics. The proposed scheme was implemented and an experimentally tested by using the benchmark datasets (Amazon review datasets). The results revealed that, the proposed scheme achieved better performance than the existing recommender system in terms of Root Mean Square Error (RMSE) which reduces the errors by 29% and also increase the Precision and Recall by 51.4%, and 55.8% respectively in the 1 million datasets.