Article
Computer Science, Artificial Intelligence
Kalpathy Jayanth Krishnan, Kishalay Mitra
Summary: This study proposes a modified Self Organizing Map algorithm for clustering time series data. By modifying the original steps of the algorithm and using specific initialization methods and similarity measures, this algorithm outperforms other popular clustering algorithms in terms of clustering performance and computation time.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Chaoyu Gong, Zhi-gang Su, Pei-hong Wang, Yang You
Summary: The study introduces a distributed evidential clustering algorithm that can analyze time series data on a large scale without losing information, improving the accuracy and interpretability of clustering results.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
C. Johnpaul, Munaga V. N. K. Prasad, S. Nickolas, G. R. Gangadharan
Summary: The article introduces a method using fuzzylets for unsupervised clustering of time series elements, and compares it with other traditional methods through experiments. The experimental results show that the classification algorithm based on fuzzylets has higher accuracy than other methods, indicating the importance of this novel time series primitive in time series feature learning.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xiyang Yang, Fusheng Yu, Witold Pedrycz, Zhiwei Li
Summary: This paper proposes a trend-oriented time series granulation method to transform a long numerical time series into a relatively short granular time series. The transformed granular time series captures the main characteristics of the original time series and saves calculation in time series clustering. The distance measures for unequal-size LFIGs and LFIG time series are defined, and the k-medoids method is employed to cluster datasets from UCR time-series database.
APPLIED SOFT COMPUTING
(2023)
Article
Environmental Sciences
Rolf Simoes, Gilberto Camara, Gilberto Queiroz, Felipe Souza, Pedro R. Andrade, Lorena Santos, Alexandre Carvalho, Karine Ferreira
Summary: This paper introduces an open-source R package sits for satellite image time series analysis using machine learning, which adopts a time-first, space-later approach and supports the complete cycle of data analysis for land classification. The software provides a simple but powerful set of functions and works in different cloud computing environments. It includes methods for quality assessment of training data and provides validation and accuracy measurement methods.
Article
Computer Science, Artificial Intelligence
Leonardo Ramos Emmendorfer, Anne Magaly de Paula Canuto
Summary: A novel linkage criterion for Hierarchical agglomerative clustering (HAC) is proposed and evaluated in this paper, named GAL. Empirical analysis shows that the results obtained by the proposed criterion surpass all existing reference methods in terms of performance.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Xingcheng Ran, Yue Xi, Yonggang Lu, Xiangwen Wang, Zhenyu Lu
Summary: Data clustering is a widely used technique in various fields to divide objects into different clusters based on similarity measures. Hierarchical clustering methods generate consistent partitions of data at different levels, allowing analysis of complex data structures. This article comprehensively reviews various hierarchical clustering methods, including recent developments, and examines the role of similarity measures in the clustering process.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Nana Liu, Zeshui Xu, Xiao-Jun Zeng, Peijia Ren
Summary: This paper introduces a new method for clustering LOR information using the AHC algorithm, by extending existing distance measure methods and simplifying aggregation methods. A numerical case study is presented to illustrate the algorithm's usage, and discussions are made on the features of the algorithm.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Theory & Methods
Rong Jiang, Xue Chen, Yimin Yu, Ying Zhang, Weiping Ding
Summary: The rapid development of healthcare big data has brought convenience to medical research and health management, but the issue of privacy protection must be considered. This paper proposes an access control model, RQ-UCON, based on risk quantification and usage control. The model adds a risk quantification module to achieve privacy protection of medical data. Through experiments, it is shown that the proposed model has control over excessive access behavior of doctors and limitations on the privacy leakage of healthcare big data.
JOURNAL OF BIG DATA
(2023)
Article
Genetics & Heredity
Jef van den Eynde, Bhargava Chinni, Hilary Vernon, W. Reid Thompson, Brittany Hornby, Shelby Kutty, Cedric Manlhiot
Summary: This study showed that continuous physiological measurements from wearable devices can be used to predict functional status and response to treatment in patients with Barth syndrome.
ORPHANET JOURNAL OF RARE DISEASES
(2023)
Article
Computer Science, Artificial Intelligence
Guoliang He, Wenjun Jiang, Rong Peng, Ming Yin, Min Han
Summary: In this study, a variable-weighted K-medoids clustering algorithm is proposed to address the issues of correlations and redundancies between variables in MTS data. In addition, a new approach is introduced to handle the initialization sensitivity problem, along with an ensemble clustering framework based on density peaks to further enhance the clustering performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Igor Manojlovic, Goran Svenda, Aleksandar Erdeljan, Milan Gavric, Darko Capko
Summary: The paper proposes a Hierarchical Multiresolution Time Series Representation model for reducing data model size and supporting streaming time series data mining. By utilizing a buffer-based approach and considering fluctuations and continuity of modeled processes, the proposed model achieves high processing speed while preserving fundamental characteristics of time series at reduced dimensionality. The usefulness of the proposed solution was proven in a case study, showing improved processing speed and information loss reduction in real UK smart meter data.
Article
Computer Science, Information Systems
Md Monjur Ul Hasan, Reza Shahidi, Dennis K. Peters, Lesley James, Ray Gosine
Summary: Various approaches for data clustering, such as partitioning, hierarchical, and machine learning methods, have been discussed in the literature. However, most of these approaches require prior knowledge about the clusters and may not be robust enough for higher-dimensional data. In this study, a new clustering algorithm called Piecemeal Clustering is proposed, which successfully clusters data without prior knowledge of the number of clusters and works well with both low- and high-dimensional data. Experimental results on two real-world datasets show that the proposed algorithm outperforms seven other state-of-the-art algorithms.
Article
Engineering, Civil
Ali Javed, Scott D. Hamshaw, Byung Suk Lee, Donna M. Rizzo
Summary: This study combines a multivariate event time series clustering approach with traditional 2-D hysteresis analysis to analyze river discharge and suspended sediment data during hydrological storm events, successfully identifying four common types of hydrological water quality events.
JOURNAL OF HYDROLOGY
(2021)
Article
Environmental Sciences
Fabio Bovenga, Guido Pasquariello, Alberto Refice
Summary: This study introduces a method for automatically identifying relevant changes in MTInSAR displacement time series, and proposes a procedure for automatically recognizing the minimum number of parameters needed for reliable modeling of a given time series. Through the use of polynomial models, it is possible to effectively approximate the piecewise linear trends used to model warning signals preceding the failure of structures. Finally, the proposed procedure is demonstrated on displacement time series derived from processing Sentinel-1 data.
Article
Computer Science, Artificial Intelligence
S. Pradeepa, K. R. Manjula, S. Vimal, Mohammad S. Khan, Naveen Chilamkurti, Ashish Kr Luhach
Summary: The study proposes a method to detect the risk of stroke by finding relevant symptoms and preventive measures from social media content, providing a viable approach for stroke risk detection.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Pandit Byomakesha Dash, Bighnaraj Naik, Janmenjoy Nayak, S. Vimal
Summary: This paper presents an effective deep learning-based technique for detection of robotic manipulator's failure execution. By employing a certain control strategy, the proposed method is able to accurately detect failures at each different position and instance of robotic manipulators. Experimental results demonstrate that the method achieves a high detection rate and robustness in failure detection.
Article
Computer Science, Artificial Intelligence
Javeria Naz, Muhammad Sharif, Mudassar Raza, Jamal Hussain Shah, Mussarat Yasmin, Seifedine Kadry, S. Vimal
Summary: This paper introduces a hybrid approach based on texture and deep learning features for computer-aided diagnosis of stomach diseases. The method extracts texture features and deep convolutional neural network features, which are then serially fused to obtain a strong feature vector, thereby improving diagnostic accuracy.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Information Systems
Pandit Byomakesha Dash, Bighnaraj Naik, Janmenjoy Nayak, S. Vimal
Summary: The study uses the Extrs-trees classifier machine learning model and voting classifiers ensemble learning approach to analyze the relationship between farmers' socio-economic factors and agricultural productivity. Data is collected through structured interviews and questionnaires, and the proposed methods are found to be efficient in identifying socio-economic factors and predicting agricultural productivity.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Zi-Ching Lan, Guan-Yu Huang, Yun-Pei Li, Seungmin Rho, S. Vimal, Bo-Wei Chen
Summary: This study presents a data augmentation technique, called SMOGANs, for solving insufficient/imbalanced data problems during crowdsensing by the Internet of Medical Things or wireless sensor networks. The proposed technique uses synthetic minority oversampling generative adversarial networks to automatically expand insufficient samples in quantities and avoid biased modeling. Experimental results showed that the proposed SMOGANs outperformed the baselines in terms of accuracy.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Suyel Namasudra, Pratima Sharma, Ruben Gonzalez Crespo, Vimal Shanmuganathan
Summary: This article proposes a privacy-preserving technique using blockchain technology for IoT-based healthcare systems to generate and maintain healthcare documents. The proposed scheme ensures security by specifying rules with a smart contract and is more efficient than existing schemes.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Computer Science, Artificial Intelligence
Ghazaala Yasmin, Asit Kumar Das, Janmenjoy Nayak, S. Vimal, Soumi Dutta
Summary: Speech is a delicate medium for identifying the gender of speakers. Deep learning has provided a good research area to explore gender discrimination deficiencies in traditional machine learning techniques. The combination of automatically generated features and human-generated features can enhance gender recognition performance, especially when considering transgender individuals.
Article
Computer Science, Artificial Intelligence
Yongzhao Xu, Paulo C. S. Barbosa, Joel S. da Cunha Neto, Lijuan Zhang, Vimal Shanmuganathan, Victor Hugo C. de Albuquerque, Subbulakshmi Pasupathi
Summary: This study proposes the use of a low-cost functional prosthesis prototype combined with artificial intelligence technology to control the prosthesis in real time, aiding in the rehabilitation of amputees. Through the analysis of signals from volunteers, the optimal topology for the artificial neural network was identified and the effectiveness of the system was validated. A cost analysis of the project showed that the developed prototype is both feasible and affordable based on Brazilian cost of living standards.
Retraction
Computer Science, Hardware & Architecture
S. Vimal, Y. Harold Robinson, M. Kaliappan, K. Vijayalakshmi, Sanghyun Seo
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Telecommunications
P. Bhuvaneshwari, A. Nagaraja Rao, Y. Harold Robinson
Summary: Deep neural networks have achieved impressive results in various natural language processing tasks, attracting researchers to apply them in recommender systems. However, most recommendation algorithms only utilize implicit data. To improve performance, we propose a new architecture that utilizes explicit user-item rating matrix and outer product function to learn high-order correlations.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Priyanka Chugh, Meenu Gupta, S. Indu, Gopal Chaudhary, Manju Khari, Vimal Shanmuganathan
Summary: The advancements in Wireless Sensor Networks (WSNs) technology have led to the development of smaller, cheaper, and more powerful sensor nodes. Energy conservation and prolonging network lifetime have become critical issues, and a novel energy-efficient routing protocol based on advanced fixed path and mobile base station (PEGASIS) is proposed in this research. The proposed method focuses on the base station's mobility and uses a multiple-chain model to reduce energy consumption and prolong network lifetime. Experimental results show the efficiency of the proposed method in achieving the objectives. The method is also compared with three current routing protocols.
MICROPROCESSORS AND MICROSYSTEMS
(2023)
Article
Computer Science, Software Engineering
Vimal Shanmuganathan, Victor Hugo C. de Albuquerque, Paulo C. S. Barbosa, Marcello Carvalho dos Reis, Gaurav Dhiman, Mohd Asif Shah
Summary: To address the issue of the simple neural network's inability to capture the contextual semantics and extract meaningful information from text, a sentiment analysis model FAGB iAGRU, which combines attention mechanism and gated recurrent unit (GRU), is designed. The model preprocesses the text, performs word vectorization using GloVe to reduce the vector space dimension, merges the attention mechanism with the update gate of the gating unit to extract meaningful information from the text features, and uses a softmax classifier to classify the text. Experimental results on public datasets demonstrate that the algorithm can effectively improve sentiment analysis performance.
Article
Computer Science, Hardware & Architecture
Rajesh Kumar Garg, Surender Kumar Soni, S. Vimal, Gaurav Dhiman
Summary: In Wireless Sensor Networks, an analytical model is used to divide the whole network into groups of correlated regions, selecting a small number of transmitting nodes to save battery power.
MICROPROCESSORS AND MICROSYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Jerart Julus Lawrence, Vimal Shanmuganathan, Rajesh Manoharan, Sitharthan Ramachandran, Moustafa H. Aly, Prasun Chakrabarti
Summary: This paper presents the performance of an OFDM system using intensity modulation in a WDM-ROF-PON. By introducing the advanced equalizer DNN-NLE, the system achieves better bit error rate and optical signal to noise ratio.
OPTICAL AND QUANTUM ELECTRONICS
(2023)
Article
Nanoscience & Nanotechnology
Neha Singh, Deepali Virmani, Gaurav Dhiman, S. Vimal
Summary: Wireless sensor network (WSN) is widely used in various fields, but the increasing amount of data makes accurate analysis unfeasible. To overcome this challenge, machine learning is applied in WSN. This paper proposes a multi to binary class size based imbalance handling technique (MBSCIH) to solve the class imbalance problem in multi-class classification. Experimental results show that the proposed method improves efficiency and enhances intrusion detection in WSN.
INTERNATIONAL JOURNAL OF NANOTECHNOLOGY
(2023)