Article
Computer Science, Information Systems
Anastasios Dounis, Andreas-Nestor Avramopoulos, Maria Kallergi
Summary: This paper discusses the development of Computer Aided Diagnosis (CADx) Systems for the classification of abnormalities in mammography. The uncertainties in the shape and geometry of the breast parenchyma can lead to inaccurate diagnoses. Fuzzy processing, using fuzzy sets, can handle imperfect data arising from vagueness and ambiguity. Fuzzy contrast enhancement improves edge detection and classification features.
Article
Computer Science, Artificial Intelligence
Mohammad Beheshti Roui, Mariam Zomorodi, Masoomeh Sarvelayati, Moloud Abdar, Hamid Noori, Pawel Plawiak, Ryszard Tadeusiewicz, Xujuan Zhou, Abbas Khosravi, Saeid Nahavandi, U. Rajendra Acharya
Summary: This paper introduces a novel approach for generating classification rules based on evolutionary computation, with custom crossover and mutation operators for GPU execution, and leveraging parallelism to enhance fitness function performance. Experimental results demonstrate high accuracy and speedup for HCV, Poker, and COVID-19 datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
S. Sharmila, S. Vijayarani
Summary: Association rule mining is a well-known data mining scheme used to discover commonly co-occurred itemsets, with frequent item recognition and association rule generation being key steps. Various algorithms have been developed by researchers to generate association rules, with fuzzy logic incorporated for uncovering recurrent itemsets and interesting fuzzy association rules. Dimensionality reduction techniques are proposed to effectively identify significant transactions and items from databases, while the efficiency of the proposed algorithm is compared with other optimization techniques for frequent item identification and rule generation.
Article
Mathematics
Melih Coban, Suleyman Sungur Tezcan
Summary: In this study, the hybrid Taguchi vortex search algorithm was used as a new training algorithm for feed-forward neural networks. The performance of the algorithm was analyzed by comparing it with other algorithms, and the results showed that it performed well in solving classification problems.
Article
Computer Science, Artificial Intelligence
Xiaohe Zhang, Degang Chen, Jusheng Mi
Summary: This article introduces a fuzzy decision rule-based online classification algorithm called OFRCA, which combines online learning theory and Formal Concept Analysis (FCA) in a fuzzy formal decision context. The algorithm obtains weight vectors for attributes and incremental fuzzy decision rules through a fusion process. The weight vector is updated based on a loss function, and the final attribute-weighted classifier is formed by fusing all the rules. Numerical experiments show that OFRCA achieves the highest advanced classification performance.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Computer Science, Information Systems
Seyedehfaezeh Hosseininoorbin, Siamak Layeghy, Brano Kusy, Raja Jurdak, Marius Portmann
Summary: This paper examines the performance of Google's Edge TPU on feed-forward neural networks. It considers the Edge TPU as a hardware platform and explores different architectures of deep neural network classifiers, which have traditionally been challenging to run on resource-constrained edge devices. By utilizing a spectrogram data representation, the study examines the trade-off between classification performance and energy consumption for inference. The energy efficiency of the Edge TPU is compared to that of the widely-used embedded CPU ARM Cortex-A53. The results provide insights into the impact of neural network architecture on the performance of the Edge TPU and offer guidance for selecting the optimal operating point based on classification accuracy and energy consumption. Additionally, the evaluations highlight the performance crossover between the Edge TPU and Cortex-A53, depending on the neural network specifications. The analysis also provides a decision chart to assist in platform selection based on model parameters and context.
INTERNET OF THINGS
(2023)
Article
Computer Science, Hardware & Architecture
Dev Narayan Yadav, Phrangboklang Lyngton Thangkhiew, Kamalika Datta, Sandip Chakraborty, Rolf Drechsler, Indranil Sengupta
Summary: This paper introduces a training algorithm based on resistive memory systems that achieves accuracy similar to existing algorithms, but with faster training speed, by using additional memristors and a threshold gate.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Automation & Control Systems
Sunita M. Dol, Pradip M. Jawandhiya
Summary: Educational data mining (EDM) applies data mining techniques in the field of education to classify, analyze, and predict students' academic performance, dropout rate, and instructors' performance. This review article analyzes 142 research articles from 2010 to 2020 and discusses the current developments in EDM in 2021 and 2022. It presents the use of classification techniques, clustering algorithms, association rule algorithms, regression techniques, and ensemble techniques in EDM. The article also compares different classification techniques and identifies research gaps for future improvement in the teaching-learning process.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Hamid Rezatofighi, Tianyu Zhu, Roman Kaskman, Farbod T. Motlagh, Javen Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixe, Ian Reid
Summary: This paper addresses the task of set prediction using deep feed-forward neural networks. It presents a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. The validity of the proposed approach is demonstrated on various vision problems.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Biology
Ela Kaplan, Sengul Dogan, Turker Tuncer, Mehmet Baygin, Erman Altunisik
Summary: In this study, a new automatic AD detection model called LPQNet was proposed, demonstrating high classification accuracy on three different image datasets and showing superiority over other detection models. Additionally, LPQNet can be used to develop a new generation intelligent AD detection application for MRI and CT devices.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Automation & Control Systems
Trinh T T Tran, Tu N Nguyen, Thuan T Nguyen, Giang L Nguyen, Chau N Truong
Summary: This paper proposes the NPSFF algorithm in fuzzy association rule mining, which combines the Node-list data structure and Pre-order Size Code structure to accelerate tree building and find frequent fuzzy item sets. By applying the AP clustering technique for data preprocessing and converting quantitative values to fuzzy values, the efficiency of the NPSFF algorithm is improved.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yan Shen, Luyi Jing, Tian Gao, Zizhao Song, Ji Ma
Summary: This paper investigates efficient classification learning of accumulated big data in nonstationary environments. The ensemble mechanism of the LearnNSE algorithm is adjusted, and a novel mechanism called FLearnNSE is designed to reuse learned classification knowledge. Experimental results show that the FLearnNSE-Pruned-Age algorithm performs well in terms of classification accuracy and efficiency.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Priyanka Singh, Samir Kumar Borgohain, Achintya Kumar Sarkar, Jayendra Kumar, Lakhan Dev Sharma
Summary: In this study, deep features are extracted from the portable executable header (PEH) information through hidden layers of a feed-forward deep neural network (FFDNN). The deep features of hidden layers improve the generalization performance for malware detection. The proposed model achieves a classification accuracy of 99.15% using the FFDNN-ML classifier with the GeLU activation function and internal discriminative deep features.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Kunal Biswas, Palaiahnakote Shivakumara, Umapada Pal, Tapabrata Chakraborti, Tong Lu, Mohamad Nizam Bin Ayub
Summary: The usage of social media has been increasing exponentially in recent years for various applications such as content sharing and entertainment. This paper proposes a new method for classifying social images based on personality traits, using fuzzy and genetic algorithms. The proposed approach extracts profile pictures and descriptions to construct vocabularies and utilizes fuzzy logic and genetic algorithms for classification. The effectiveness of the approach is demonstrated on different datasets, showing improved classification rate compared to existing methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Muniba Ashfaq, Nasru Minallah, Atiq ur Rehman, Samir Brahim Belhaouari
Summary: In image registration, the genetic algorithm is utilized to find the optimal solution by evaluating the fitness function with a similarity measure index. The proposed multistage forward path regenerative genetic algorithm (MFRGA) improves rigid image registration accuracy by reducing the search space at each stage.
Proceedings Paper
Multidisciplinary Sciences
Samaneh Nadali, Masrah Azrifah Azmi Murad, Nurfadhlina Mohamad Sharef
ADVANCED SCIENCE LETTERS
(2018)
Proceedings Paper
Multidisciplinary Sciences
Sofian Hazrina, Nurfadhlina Mohd Sharef, Hamidah Ibrahim, Masrah Azrifah Azmi Murad, Shahrul Azman Mohd Noah
ADVANCED SCIENCE LETTERS
(2018)
Proceedings Paper
Multidisciplinary Sciences
Harnani Mat Zin, Norwati Mustapha, Masrah Azrifah Azmi Murad, Nurfadhlina Mohd Sharef
ADVANCED SCIENCE LETTERS
(2018)
Article
Engineering, Multidisciplinary
Rizwan Iqbal, Masrah Azrifah Azmi Murad, Layth Sliman, Clay Palmeira da Silva
Article
Computer Science, Information Systems
Md Saifullah Razali, Alfian Abdul Halin, Yang-Wai Chow, Noris Mohd Norowi, Shyamala Doraisamy
Summary: This work discusses the task of automatically detecting satire instances in short articles. It explores the extraction of optimal features using a deep learning architecture and contextual features. It demonstrates that combining feature sets can improve performance, with Logistic Regression identified as the best algorithm. The results outperform existing works in the same domain, highlighting the importance of considering the contextual meaning behind satire.
Article
Computer Science, Interdisciplinary Applications
Ismail Bile Hassan, Masrah Azrifah Azmi Murad, Ibrahim El-Shekeil, Jigang Liu
Summary: This study validates and extends the latest unified theory of acceptance and use of technology (UTAUT2) with the privacy calculus model. The results show that factors like habit, expectancy, social influence, and value have a direct influence on behavioral intentions to use, while behavioral intentions, facilitating conditions, habits, risks, and privacy concerns are direct predictors of use behavior.
Article
Computer Science, Information Systems
Md Saifullah Razali, Alfian Abdul Halin, Lei Ye, Shyamala Doraisamy, Noris Mohd Norowi
Summary: The study focuses on detecting sarcasm in tweets by combining deep learning features with contextual handcrafted features. Logistic Regression is identified as the best classification algorithm for this task, based on positive results in terms of Accuracy, Precision, Recall, and F1-measure.
Proceedings Paper
Computer Science, Information Systems
Azreen Azman, Mostafa Alksher, Shyamala Doraisamy, Razali Yaakob, Eissa Alshari
COMPUTATIONAL SCIENCE AND TECHNOLOGY (ICCST 2019)
(2020)
Article
Multidisciplinary Sciences
Rizwan Iqbal, Masrah Azrifah Azmi Murad, Adnan Ashraf
PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY
(2020)
Article
Computer Science, Theory & Methods
Muhammad Ehsan Rana, Wan Nurhayati Wan Ab Rahman, Masrah Azrifah Azmi Murad, Rodziah Binti Atan
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Muath Alali, Nurfadhlina Mohd Sharef, Masrah Azrifah Azmi Murad, Hazlina Hamdan, Nor Azura Husin
Proceedings Paper
Computer Science, Information Systems
Ana Salwa Shafie, Nurfadhlina Mohd Sharef, Masrah Azrifah Azmi Murad, Azreen Azman
2018 FOURTH INTERNATIONAL CONFERENCE ON INFORMATION RETRIEVAL AND KNOWLEDGE MANAGEMENT (CAMP)
(2018)
Proceedings Paper
Computer Science, Information Systems
Rizwan Iqbal, Masrah Azrifah Azmi Murad, Aida Mustapha, Abdul Attayyab Khan, Syed Rizwan Ali, Clay Palmeira da Silva
2018 FOURTH INTERNATIONAL CONFERENCE ON INFORMATION RETRIEVAL AND KNOWLEDGE MANAGEMENT (CAMP)
(2018)
Proceedings Paper
Computer Science, Information Systems
Roko Abubakar, Shyamala Doraisamy, Bello Nakone
2018 FOURTH INTERNATIONAL CONFERENCE ON INFORMATION RETRIEVAL AND KNOWLEDGE MANAGEMENT (CAMP)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Muath Alali, Nurfadhlina Mohd Sharef, Hazlina Hamdan, Masrah Azrifah Azmi Murad, Nor Azura Husin
RECENT ADVANCES ON SOFT COMPUTING AND DATA MINING (SCDM 2018)
(2018)