Article
Computer Science, Artificial Intelligence
Irfan Ullah, Sikandar Alam, Zafar Ali, Mahmood Khan, Fouzia Jabeen, Shah Khusro
Summary: The role of query formulation in retrieving relevant search results is important in Information Retrieval (IR) systems. Researchers have experimented with various approaches such as using topic fields, reducing verbose queries, and query expansion. However, there is a lack of survey or review articles on query formulation in the domain of book search. This paper fills this gap by reviewing research publications from 2007 to 2022, summarizing findings using a well-defined theoretical framework, identifying current trends, and providing a cross-comparison of best-performing methods. It has implications for researchers in IR and book search.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Yasir Hadi Farhan, Shahrul Azman Mohd Noah, Masnizah Mohd, Jaffar Atwan
Summary: This article introduces the Deep Averaging Networks (DANs) architecture for query expansion, which utilizes the average word embedding vectors of the query terms through multiple neural network layers to represent the overall meaning of the query. The potential of DANs for Arabic document retrieval is explored, and it outperforms baseline methods when incorporated into specific expansion strategies.
JOURNAL OF INFORMATION SCIENCE
(2023)
Article
Computer Science, Information Systems
Xiao Wang, Craig Macdonald, Iadh Ounis
Summary: Pseudo-relevance feedback is a classical technique to improve search engine retrieval effectiveness. Past external expansion methods have only been studied for sparse retrieval methods, and the effectiveness for recent dense retrieval methods remains under-investigated. This study examines the application of dense external expansion to improve zero-shot retrieval effectiveness.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Ayman A. Taan, Shafiq Ur Rehman Khan, Ali Raza, Ayaz Muhammad Hanif, Hira Anwar
Summary: This study investigated the performance of different Information Retrieval models in Cross-Language Information Retrieval (CLIR) system, as well as the impact of query length and query expansion models on effective retrieval. The results showed that query length has an influence on retrieval effectiveness, leading to the suggestion of an appropriate query length and the best query expansion and retrieval models for Arabic CLIR system.
Article
Computer Science, Artificial Intelligence
Min Pan, Quanli Pei, Yu Liu, Teng Li, Ellen Anne Huang, Junmei Wang, Jimmy Xiangji Huang
Summary: This study proposes a semantic-based Pseudo-relevance Feedback model (SPRF) that leverages ConceptNet to enhance the selection of query expansion terms for information retrieval. The experimental results demonstrate that SPRF achieves good performance and shows advantages over baseline models and neural network-based methods.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Information Systems
Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis
Summary: Pseudo-relevance feedback mechanisms have proven useful in expanding and reweighting initial queries using information from retrieved documents. Dense retrieval, using neural contextual language models like BERT, has shown promising performance in information retrieval tasks. The use of multiple representations in dense retrieval, such as ColBERT, can be enhanced with pseudo-relevance feedback.
ACM TRANSACTIONS ON THE WEB
(2023)
Article
Computer Science, Information Systems
Tao Qiu, Peiliang Xie, Xiufeng Xia, Chuanyu Zong, Xiaoxu Song
Summary: This paper proposes a technique for processing aggregated Boolean queries using edge computing, which demonstrates high efficiency and performance for document retrieval in search engines. Experimental results show that this technique outperforms traditional centralized methods.
Article
Computer Science, Artificial Intelligence
Sarah Dahir, Abderrahim El Qadi, Hamid Bennis
Summary: Query Expansion aims to address the vocabulary mismatch issue in Information Retrieval Systems by adding new terms to the initial user query. Linked Data can be used as a valuable resource for providing additional expansion features. Selecting the right candidate terms for expansion is a key issue in Query Expansion.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Chemistry, Multidisciplinary
Sergio Silva, Adrian Seara Vieira, Pedro Celard, Eva Lorenzo Iglesias, Lourdes Borrajo
Summary: Information retrieval aims to obtain relevant information for users, with query expansion techniques used to improve retrieval by adding similar meaningful terms. A supervised query expansion technique based on Multinomial Naive Bayes demonstrated improved performance in extracting relevant terms from initial query documents.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Min Pan, Junmei Wang, Jimmy X. Huang, Angela J. Huang, Qi Chen, Jinguang Chen
Summary: In this study, a probabilistic framework based on the classic Rocchio model is proposed to incorporate sentence-level semantics into PRF using Bidirectional Encoder Representations from Transformers (BERT). Experimental results show that the improved models achieve significant improvements over baseline models, providing a promising avenue for integrating sentence-level semantics into PRF.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Qianqian Qi, David J. Hessen, Tejaswini Deoskar, Peter G. M. van der Heijden
Summary: This article compares latent semantic analysis (LSA) and correspondence analysis (CA) for dimensionality reduction in the context of document-term matrices. The study shows that CA outperforms LSA by effectively eliminating margin effects and focusing on relationships among documents and terms. A unified framework is proposed, with CA and LSA as special cases. Empirical comparisons on text categorization and authorship attribution tasks demonstrate the superior performance of CA. Additionally, CA provides further evidence on the authorship of the Dutch national anthem Wilhelmus.
NATURAL LANGUAGE ENGINEERING
(2023)
Article
Computer Science, Information Systems
Dilip Kumar Sharma, Rajendra Pamula, D. S. Chauhan
Summary: This paper presents a method for query enhancement by analyzing the impact of abbreviation resolution, lexical variation, synonyms, n-gram pseudo relevance feedback, and co-occurrence on the baseline query expansion approaches. The experimental results show improvement in the performance of query expansion in terms of mean average precision, F-measure, and precision-recall curve.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hiteshwar Kumar Azad, Akshay Deepak, Chinmay Chakraborty, Kumar Abhishek
Summary: Query expansion is a technique used in information retrieval to address word mismatch between a user's query and the target information. Existing weighting techniques often fail to capture the term-term relationship and term to the whole query relationship accurately, resulting in low retrieval effectiveness. This study proposes a query expansion approach based on tf-idf, k-nearest neighbor (kNN) based cosine similarity, and correlation score to address this issue. The proposed model, called web knowledge based query expansion (WKQE), achieves significant improvement in retrieval performance compared to other related approaches.
PATTERN RECOGNITION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Bilel Elayeb, Oussama Ben Khiroun
Summary: In this paper, we propose a new architecture for a possibilistic mono- and cross-language information retrieval (IR/CLIR) system. The system allows for query disambiguation, expansion, and translation processes, and overcomes the challenges of uncertainty and imprecision in IR/CLIR using possibility theory. By utilizing a co-occurrence graph representation, we quantify the similarity between query terms and their semantically close words or possible meanings. Our possibilistic approaches show significant improvements compared to state-of-the-art IR/CLIR works.
INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING
(2023)
Article
Computer Science, Artificial Intelligence
Dilip Kumar Sharma, Rajendra Pamula, D. S. Chauhan
Summary: This paper provides a comprehensive survey on semantic-based query expansion methods proposed by researchers, discussing the merits and demerits of each technique in detail. It emphasizes the importance of computational intelligence in automatic query expansion for advanced information processing.
EVOLUTIONARY INTELLIGENCE
(2021)
Article
Engineering, Civil
Nafeesa Kalsoom, Iftikhar Ahmad, Roobaea Alroobaea, Muhammad Ahsan Raza, Samina Khalid, Zaheed Ahmed, Ihsan Ali
Summary: Internet of Vehicles (IoV) is a complex system consisting of vehicles, humans, and sensors, which improves communication among vehicles on the roads. Quality of service (QoS) enabled by the cooperative driving system (CDS) based on 5G technology enhances road traffic efficiency. To improve QoS for CDS, a 5G network-based architecture and D2D technology-based resource allocation scheme were proposed, along with a density-based scattered clustering algorithm for vehicular clustering. The proposed scheme shows significant improvement in throughput compared to existing D2D approaches.
JOURNAL OF ADVANCED TRANSPORTATION
(2021)
Article
Computer Science, Information Systems
Sehrish Batool, Farrukh Zeeshan Khan, Syed Qaiser Ali Shah, Muneer Ahmed, Roobaea Alroobaea, Abdullah M. Baqasah, Ihsan Ali, Muhammad Ahsan Raza
Summary: Distributed Denial of Service (DDoS) attack is a lethal attack in traditional network architecture where the attacker overwhelms network resources using botnets. Software-defined networking (SDN) is suggested as a solution to fight DDoS attacks, and an entropy-based statistical approach is proposed to detect and mitigate these attacks.
SECURITY AND COMMUNICATION NETWORKS
(2022)
Article
Computer Science, Information Systems
Talha Ahsan, Farrukh Zeeshan Khan, Zeshan Iqbal, Muneer Ahmed, Roobaea Alroobaea, Abdullah M. Baqasah, Ihsan Ali, Muhammad Ahsan Raza
Summary: Advancement in technology has led to an increasing number of IoT devices, but security remains a challenge. This paper proposes using blockchain-embedded algorithms for authentication and access control of IoT devices, providing a decentralized and secure solution.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2022)
Review
Multidisciplinary Sciences
Binish Raza, Rodina Ahmad, Mohd H. N. M. Nasir, Shukor S. M. Fauzi, Muhammad A. Raza
Summary: Software development relies on team coordination, with social-technical congruence (STC) being a key technique to measure alignment. A systematic literature review (SLR) identified the need for further research on STC, including risk issues, measurement techniques, and development factors.
KUWAIT JOURNAL OF SCIENCE
(2022)
Article
Computer Science, Information Systems
Julius Beneoluchi Odili, A. Noraziah, Asegunloluwa Eunice Babalola
Summary: In recent years, control system engineering has become increasingly important in industrial processes. This paper critically examines the fitness functions used for metaheuristic tuning of PID controllers and introduces a new fitness function with experimental evidence of its effectiveness. The paper suggests further research on the application of this fitness function due to its simplicity and ease of use.
Correction
Engineering, Electrical & Electronic
Muhammad Nadeem, Hasan M. Khan, Saeed Ahmad Buzdar, Javed Ahmed, Mohammed A. Assiri, Muhammad Imran, Mohammad Ehsan Mazhar, Mehrun Nisa, Muhammad Ahsan Raza, Binish Raza, Mohammad Jamshed
JOURNAL OF MATERIALS SCIENCE-MATERIALS IN ELECTRONICS
(2022)
Article
Chemistry, Multidisciplinary
Zaid Bin Faheem, Mubashir Ali, Muhammad Ahsan Raza, Farrukh Arslan, Jehad Ali, Mehedi Masud, Mohammad Shorfuzzaman
Summary: This paper proposes a digital watermarking technique based on the least significant bit, image gradient, and chaotic map. The watermark signal is embedded in the image by modifying the least significant bits according to the image gradient, and it exhibits high robustness against various attacks while maintaining imperceptibility.
APPLIED SCIENCES-BASEL
(2022)
Review
Computer Science, Information Systems
Attique Ur Rehman, Muhammad Sajid Mahmood, Muhammad Ahsan Raza, Fahad Qaswar, Sumayh S. Aljameel, Irfan Ullah Khan, Nida Aslam
Summary: Physical layer security for wireless sensor networks is a critical issue. Challenges include data security in wireless transmission and threats to the physical security of networks. The paper surveys parameters of a security design model and discusses attacks and mitigation techniques at different layers. Additionally, it introduces applications of WSNs in various fields and proposes a solution to enhance WSN security.
Article
Multidisciplinary Sciences
Julius Beneoluchi Odili, A. Noraziah, Basem Alkazemi, M. Zarina
Summary: This paper presents the data description of the African buffalo optimization algorithm (ABO). The algorithm is inspired by the migrant behaviour of African buffalos and aims to provide a user-friendly and reproducible optimization algorithm. The paper describes the manual workings of the algorithm and verifies its effectiveness through practical implementation. This contribution is of significant importance to the research community.
SCIENTIFIC REPORTS
(2022)
Article
Medicine, General & Internal
Talha Mahboob Alam, Kamran Shaukat, Waseem Ahmad Khan, Ibrahim A. Hameed, Latifah Abd Almuqren, Muhammad Ahsan Raza, Memoona Aslam, Suhuai Luo
Summary: This study proposes a deep learning-based skin cancer detection method using data augmentation to address the issue of data imbalance. Experimental results using the Skin Cancer MNIST: HAM10000 dataset show that the proposed method outperforms conventional methods in terms of accuracy, F1-score, and ROC curve.
Article
Chemistry, Multidisciplinary
Khalid Mahmood, Rahmah Mokhtar, Muhammad Ahsan Raza, A. Noraziah, Basem Alkazemi
Summary: Knowledge management in a structured system is a complex task that requires common, standardized methods. This research proposes an enhanced ecological and confined domain ontology construction (EC-DOC) scheme, which includes five important phases such as conceptualization and clustering. The EC-DOC scheme can provide accurate domain concepts and make them available in a preferred local language.
APPLIED SCIENCES-BASEL
(2023)
Review
Computer Science, Information Systems
Fahad Qaswar, M. Rahmah, Muhammad Ahsan Raza, A. Noraziah, Basem Alkazemi, Z. Fauziah, Mohd. Khairul Azmi Hassan, Ahmed Sharaf
Summary: This research conducted a systematic literature review to analyze the use of ontology in the Internet of Things (IoT). The findings show that ontologies are needed in the IoT field to minimize interoperability and integration issues, and there are existing ontologies that can be used for this purpose. Therefore, ontology is beneficial for achieving interoperability, integration, and privacy in the IoT.
Article
Computer Science, Information Systems
V. Praveena, A. Vijayaraj, P. Chinnasamy, Ihsan Ali, Roobaea Alroobaea, Saleh Yahya Alyahyan, Muhammad Ahsan Raza
Summary: Recently, the use of intelligent UAV networks in the Internet of Things technology has received a lot of attention, but network security remains a significant challenge. Traditional intrusion detection systems are not suitable for modern networks with high bandwidth and data traffic. Researchers have tried to improve intrusion detection performance by employing machine learning and deep learning algorithms. This research proposes a deep reinforcement learning technique optimized by the Black Widow Optimization algorithm to enhance intrusion detection in UAV networks, and extensive experimental analysis demonstrates its superiority.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)