Article
Computer Science, Software Engineering
Gias Uddin, Yann-Gael Guehenuc, Foutse Khomh, Chanchal K. Roy
Summary: Sentiment analysis in software engineering has the potential to support diverse development activities, but current tools may not be fully satisfactory in terms of accuracy. The combination of stand-alone sentiment detectors for fault detection has shown better performance, but there is no such approach for sentiment detection in software artifacts. This study explores the feasibility of developing an ensemble engine by combining the polarity labels of stand-alone sentiment detectors in the field of software engineering. The results show that the existing tools can complement each other, but a majority voting-based ensemble does not improve the accuracy. The developed tool, Sentisead, combining polarity labels and bag of words, outperforms the individual tools. The use of advanced language-based pre-trained transformer models further improves the infrastructure of Sentisead.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2022)
Article
Automation & Control Systems
Jieyu An, Wan Mohd Nazmee Wan Zainon
Summary: Multimodal sentiment analysis is an important research area, especially in social media where emotions are expressed through text and images. This paper proposes a novel model called ICCI, which integrates color cues to improve sentiment analysis accuracy. The model extracts semantic and color features, and utilizes a cross-attention mechanism for feature interaction. Experimental results on benchmark datasets demonstrate the effectiveness of ICCI, outperforming existing methods with higher accuracy.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Environmental
Yuantian Sun, Guichen Li, Junfei Zhang, Jiandong Huang
Summary: The study proposed an ensemble classifier RF-FA model for rockburst prediction, which effectively optimized the hyperparameters of RF using FA. By selecting key parameters as input variables and rockburst intensity as output, the model demonstrated high performance in independent test sets and new engineering projects, showing better accuracy compared to existing models.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
Article
Computer Science, Artificial Intelligence
Xin Ye, Hongxia Dai, Lu-an Dong, Xinyue Wang
Summary: The study proposes a novel multi-view ensemble learning method to better integrate information from different features for improved microblog sentiment classification. Through two stages of processing, local fusion and global fusion, basic classifiers are combined into multiple classifier groups for classification, with experimental results showing that this method outperforms other methods in identifying the polarities of microblog posts.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Abhilash Pathak, Sudhanshu Kumar, Partha Pratim Roy, Byung-Gyu Kim
Summary: Sentiment Analysis is evolving with Aspect-Based models like ABSA which identify and analyze different aspects within a sentence. The use of pre-trained models such as BERT has led to state-of-the-art results in this field. In this study, ensemble models based on multilingual-BERT were proposed to achieve new, top-notch results for Hindi language datasets across different domains.
Article
Chemistry, Analytical
Subhajit Chatterjee, Yung-Cheol Byun
Summary: This study aims to improve the efficiency of emotion classification using EEG data by using a stacking-ensemble-based classification model. The suggested technique achieves a higher classification accuracy of 99.55% and outperforms the base classifiers. It shows promising performance in emotion categorization and has significant implications in the medical field.
Article
Computer Science, Information Systems
Zongxi Li, Xinhong Chen, Haoran Xie, Qing Li, Xiaohui Tao, Gary Cheng
Summary: This study explores emotion construction by incorporating fine-grained emotions and domain knowledge, proposing a novel method EmoChannel to capture intensity variation of specific emotions and utilizing a self-attention module to extract dependency relationships among emotions, enhancing emotion classification performance. The proposed method demonstrates competitive performance against state-of-the-art baselines on multi-class and sentiment analysis datasets.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Neha Punetha, Goonjan Jain
Summary: Sentiment Analysis is a method to identify and quantify people's feelings, opinions, or attitudes. It is essential for organizations to track customers' opinions and improve satisfaction. Machine learning methods are commonly used but have limitations in terms of dataset size and complexity. This study proposes a novel unsupervised sentiment classification model that combines context, rating, and emotion scores to achieve rational and consistent results. The experiments on restaurant review datasets demonstrate state-of-the-art performance and the significance of the results.
APPLIED INTELLIGENCE
(2023)
Article
Environmental Sciences
Hamid Jafarzadeh, Masoud Mahdianpari, Eric Gill, Fariba Mohammadimanesh, Saeid Homayouni
Summary: The study investigates the capability of different ensemble learning algorithms for satellite image classification, with XGBoost showing superior performance in multispectral, hyperspectral, and Polarimetric Synthetic Aperture Radar (PolSAR) data classification.
Article
Psychology, Multidisciplinary
Baitao Liu
Summary: This study focuses on the method of emotion analysis in the application of psychoanalysis based on sentiment recognition. The improved C-BiL model is applied to the sentiment recognition module, and it effectively realizes the function of sentiment recognition. The experimental results show that the C-BiL model designed in this study achieves relatively high accuracy in different datasets.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Information Systems
Xiaoyu Guo, Jing Ma, Arkaitz Zubiaga
Summary: This article proposes a novel model, called cluster-based deep ensemble learning (CDEL), for emotion classification in memes. The model combines the advantages of deep learning and clustering algorithms to enhance the effectiveness of emotion classification. The performance of CDEL is evaluated on a benchmark dataset and has achieved state-of-the-art results, outperforming various baseline models.
JOURNAL OF INFORMATION SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Amgad M. Mohammed, Enrique Onieva, Michal Wozniak, Gonzalo Martinez-Munoz
Summary: This article discusses the strategy of classifier ensemble pruning, involving optimizing predefined performance criteria to identify subensembles. The study analyzes a set of heuristic metrics to guide the pruning process, with results indicating that ordered aggregation is an effective strategy for improving predictive performance and reducing computational complexities.
PATTERN RECOGNITION
(2022)
Article
Geosciences, Multidisciplinary
Khanh Pham, Dongku Kim, Sangyeong Park, Hangseok Choi
Summary: This study utilized ensemble learning to develop a classification model for accurately estimating slope stability and demonstrated the superiority of ensemble classifiers over single-learning models. The performance of ensemble classifiers varied slightly depending on the learning techniques employed, with extreme gradient boosting framework showing the best performance.
Article
Computer Science, Information Systems
Chen Duan, Zhengwei Huang, Yiting Tan, Jintao Min, Ribesh Khanal
Summary: Understanding users' exact feelings and enhancing enterprise customer relationship management depend heavily on emotion and sentiment analysis in intelligent customer service conversations. However, the research that is currently available analyzes either emotion or sentiment. This paper proposes a multi-task ensemble model that can perform multiple tasks of emotion and sentiment analysis simultaneously. The proposed model outperforms the single-task framework and performs well in emotion and sentiment analysis tasks in intelligent service conversation.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Zhang, Yanan Liu, Zhaoyu Xiong, Zhichao Wu, Dan Xu
Summary: This paper proposes a Transformer-based visual semantic correlation network for visual sentiment analysis. By using an extended attention network and an object query tool, it comprehensively considers the correlation among visual components and filters out redundant and noisy visual proposals. Experiments show that this method outperforms other methods on multiple datasets.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Seyed Mostafa Pourhashemi, Mohammad Mosleh, Yousof Erfani
Summary: The paper proposes an audio watermark extraction method that combines discrete wavelet transform with ensemble-intelligent extraction approach to address weaknesses of conventional and simple intelligent methods, improving system performance with successful experimental results.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Seyed-Sajad Ahmadpour, Mohammad Mosleh, Mohammad-Ali Asadi
Summary: This paper presents an effective design of a 2-to-4 decoder in the QCA technology, utilizing a small number of gates for design and exhibiting good performance.
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Mohammad-Ali Asadi, Mohammad Mosleh, Majid Haghparast
Summary: Reversible ternary logic is a promising field for the future of quantum computing, and this paper introduces a novel design for reversible ternary coded decimal (TCD) adder/subtractor, utilizing a comprehensive reversible ternary full-adder and other key components to achieve efficiency.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Mojtaba Noorallahzadeh, Mohammad Mosleh
Summary: The paper emphasizes the importance of reversible computations in reducing energy consumption, presenting new reversible block design and reversible D flip-flop circuit design. Evaluation results demonstrate that these reversible circuits outperform existing designs in terms of quantum cost.
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS
(2021)
Article
Engineering, Electrical & Electronic
Mojtaba Noorallahzadeh, Mohammad Mosleh, Seyed-Sajad Ahmadpour
Summary: Reversible circuits have been a focus of research recently, with applications in low-power digital circuits, quantum computers, and DNA-based calculations. The paper introduces a new 5 x 5 reversible block, the NB, and uses it to design a novel reversible T flip-flop. The proposed designs outperform previous ones in terms of gate count, input/output parameters, quantum cost, and delay.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Hardware & Architecture
Seyed-Sajad Ahmadpour, Mohammad Mosleh, Saeed Rasouli Heikalabad
Summary: This manuscript presents a novel 2:1 QCA MUX based on quantum-dot cellular automata with low cell count and high speed, successfully demonstrating 4:1 and 8:1 multiplexers. Utilizing the 2:1 QCA MUX, a new and efficient QCA RAM memory cell was proposed, showcasing significant performance advantages.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Quantum Science & Technology
Mohammad-Ali Asadi, Mohammad Mosleh, Majid Haghparast
Summary: This study proposed a new approach to design ternary reversible multipliers that efficiently reduce the number of operations and chip occupied area, overcome energy loss, and achieve high flexibility and speed. By ignoring the most significant digit in the partial products, the computational load was successfully reduced. Furthermore, the efficiency of partial product summation was improved by designing a new reversible ternary full-adder.
QUANTUM INFORMATION PROCESSING
(2021)
Article
Computer Science, Hardware & Architecture
Ehsan Jokar, Mohammad Mosleh, Mohammad Kheyrandish
Summary: This paper presents a novel community detection algorithm called GWBM, which aims to optimize a newly introduced fitness function balanced modularity. Experimental results show that the algorithm performs accurately and is comparable with state-of-the-art methods on synthetic and known real-world networks.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Information Systems
Ehsan Jokar, Mohammad Mosleh, Mohammad Kheyrandish
Summary: In this paper, the authors propose a hybrid community detection method called LPASA, which combines label propagation and simulated annealing algorithm to accurately uncover communities in complex networks. Experimental results on synthetic and real-world networks demonstrate the accuracy and superiority of LPASA.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Sanaz Norouzi Larki, Mohammad Mosleh, Mohammad Kheyrandish
Summary: Researchers have proposed a universal audio steganalysis approach based on the frequency domain to detect quantum steganography, utilizing quantum machine learning and the Deutsch-Jozsa algorithm to increase computational speed and accuracy by combining different classifiers.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Physics, Multidisciplinary
Mohammad Talebi, Mohammad Mosleh, Majid Haghparast, Mohsen Chekin
Summary: In this article, a new design of parity-preserving-reversible (PPR) floating-point divider is suggested to meet the growing need for low energy consumption and high-speed circuits in fast transmission systems. The proposed circuits are optimized and compared with previous works, demonstrating their superiority in various criteria.
EUROPEAN PHYSICAL JOURNAL PLUS
(2022)
Article
Engineering, Electrical & Electronic
Mojtaba Noorallahzadeh, Mohammad Mosleh, Seyed-Sajad Ahmadpour, Jayanta Pal, Bibhash Sen
Summary: Reversible logic is increasingly used in designing low power consumption digital circuits, with the parity preserving property contributing to fault detection. Vedic mathematics is popular for efficient problem-solving, and this work proposes novel 2-bit and 4-bit PP reversible Vedic multipliers with improved performance compared to previous works in terms of QC, GO, CI, and GC.
INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS
(2023)
Article
Physics, Multidisciplinary
Hadi Rasmi, Mohammad Mosleh, Nima Jafari Navimipour, Mohammad Kheyrandish
Summary: This paper focuses on the output stability and defects in circuits implemented in ASDB nanotechnology. Two novel and stable computing circuits are proposed, and an efficient ASDB full-adder is designed based on these circuits. Two and four-bit ripple carry adders are developed using the proposed full-adder. Simulation results show that the proposed designs outperform previous designs in terms of occupied area, energy, and occurrence. The proposed gates also exhibit high stability against possible defects.
Article
Engineering, Electrical & Electronic
Fatemeh Akbarian, Mohammad Mosleh
Summary: In constructing integrated circuits, the essential factors are occupied area, power consumption, and delay. Quantum-dot cellular automata (QCA) technology, with its small occupied area, low power consumption, and high speed, is considered superior to complementary metal-oxide-semiconductor (CMOS) technology for nanoscale circuit construction. However, fault tolerance becomes crucial in QCA due to the sensitivity of quantum dots to errors and faults. This paper introduces fault-tolerant structures and designs, along with a new and efficient fault-tolerant 3-input majority voter (FT MV3) gate in QCA technology. The introduced gate is able to tolerate single-cell and double-cell omission defects and is verified using physical proofs.
NANO COMMUNICATION NETWORKS
(2023)
Article
Quantum Science & Technology
Masoumeh Velayatipour, Mohammad Mosleh, Mohsen Yoosefi Nejad, Mohammad Kheyrandish
Summary: This paper proposes a novel quantum reversible realization of echo hiding-based audio watermarking in the quantum representation of digital signal, which demonstrates high robustness against quantum signal processing attacks.
QUANTUM INFORMATION PROCESSING
(2022)