Article
Computer Science, Information Systems
Cun Ji, Mingsen Du, Yanxuan Wei, Yupeng Hu, Shijun Liu, Li Pan, Xiangwei Zheng
Summary: Time series classification is widely used in various domains, including EEG/ECG classification, device anomaly detection, and speaker authentication. Despite the existence of many methods, selecting intuitive temporal features for accurate classification remains a challenge. Therefore, this paper proposes a new method called TSC-RTF, which utilizes random temporal features, and shows that it can compete with state-of-the-art methods.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Cun Ji, Mingsen Du, Yupeng Hu, Shijun Liu, Li Pan, Xiangwei Zheng
Summary: With the increasing application of Internet of Things technology, time series classification has become a research hotspot in the field of data mining. This paper proposes a new method for time series classification based on temporal features (TSC-TF), which generates temporal feature candidates through time series segmentation and selects important features with the help of a random forest. The experimental results on various datasets demonstrate the superiority of the proposed method.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Jianhua Zhao, Haiye Liang, Shulan Li, Zhiji Yang, Zhen Wang
Summary: Matrix-based or bilinear discriminant analysis (BLDA) methods have gained attention in the past two decades. This study breaks the limitations of previous comparisons and investigates the performance of vector-based regularized LDA (RLDA) and matrix-based regularized BLDA (RBLDA) on multivariate time series (MTS) data. The results show that RLDA is not always superior to BLDA on general matrix data, and RBLDA outperforms RLDA on MTS data.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Cun Ji, Yupeng Hu, Shijun Liu, Li Pan, Bo Li, Xiangwei Zheng
Summary: This study combines a fully convolutional network with shapelet features to address the low efficiency and inadequate accuracy of shapelet feature extraction in time series classification. Experimental results demonstrate that the proposed method achieves high accuracy and more effectively extracts shapelet features.
INFORMATION SCIENCES
(2022)
Article
Medicine, General & Internal
Alexander A. Koronovskii, Inna A. Blokhina, Alexander Dmitrenko, Matvey A. Tuzhilkin, Tatyana Moiseikina, Inna Elizarova, Oxana Semyachkina-Glushkovskaya, Alexey N. Pavlov
Summary: In this paper, we discuss how the coarse-graining procedure can be used in combination with other time series analysis methods. Signal processing results for data sets with and without coarse-graining are compared using extended detrended fluctuation analysis. The procedure is shown to increase the distinctions between local scaling exponents quantifying synchronous and asynchronous chaotic oscillations by up to 48% using simulated data and up to 41% in experimental data of electrocorticograms (ECoG) of mice.
Article
Engineering, Electrical & Electronic
Yuechi Jiang, Frank H. F. Leung
Summary: PLDA has shown good performance in face recognition and speaker recognition. We propose scalable formulations for more efficient computation and better performance. By using scalable formulations, the PLDA model can outperform other classifiers and be applied to feature transformation techniques.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Computer Science, Information Systems
Jianhua Zhao, Feng Sun, Haiye Liang, Xuan Ma, Xingxu Li, Jun He
Summary: This paper proposes a new method for MTS classification based on bidirectional linear discriminant analysis (BLDA), which can utilize label information to reduce redundancy in both time and variable modes simultaneously. The performance of the proposed method is demonstrated through experiments on real MTS datasets.
Article
Computer Science, Information Systems
Mingsen Du, Yanxuan Wei, Xiangwei Zheng, Cun Ji
Summary: Multivariate time series classification is widely used in various real-life applications and has attracted significant research interest. However, existing methods only focus on local or global features and overlook the spatial dependency features among multiple variables. In this study, we propose a multi-feature based network (MF-Net) that captures both local and global features through the attention-based mechanism and integrates them to capture spatial dependency features. Experimental results on UEA datasets demonstrate that our method performs competitively with state-of-the-art methods.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Ruiping Yang, Xianyu Zha, Kun Liu, Shaohua Xu
Summary: A novel CNN model is proposed for local prior feature embedding and imbalanced dataset modeling. The model utilizes dynamic clustering and sliding window to select typical local features for signal classification. It can extract both global and local signal features, improving classification accuracy and generalization.
Article
Engineering, Electrical & Electronic
Timo De Waele, Adnan Shahid, Daniel Peralta, Anniek Eerdekens, Margot Deruyck, Frank A. M. Tuyttens, Eli De Poorter
Summary: To track the activities and performance of horses, inertial measurement units (IMUs) combined with machine learning algorithms are commonly used. A data-efficient algorithm is proposed that only requires 3 minutes of labeled calibration data. This algorithm achieved a 95% accuracy on datasets captured with leg-mounted IMUs and neck-mounted IMU. However, when the algorithm was calibrated on multiple horses and evaluated on unfamiliar horses, there was a 15% drop in classification accuracy.
IEEE SENSORS JOURNAL
(2023)
Article
Environmental Sciences
Bingshi Liu, Xiancai Zou, Shuang Yi, Nico Sneeuw, Jiancheng Li, Jianqiang Cai
Summary: This study proposes a statistical model driven by precipitation and temperature data to reconstruct mass anomalies of high mountain glaciers. The method shows good performance in predicting and reconstructing mass anomalies, and provides valuable information for the sustainable management and protection of water resources.
REMOTE SENSING OF ENVIRONMENT
(2022)
Article
Computer Science, Artificial Intelligence
Bing Bai, Guiling Li, Senzhang Wang, Zongda Wu, Wenhe Yan
Summary: The study introduces a novel ensemble method called TBOPE, which is based on multi-feature dictionary representation and ensemble learning. By extracting multiple dimensions of features and constructing multiple classifiers, the method aims to improve the classification performance of time series data.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Weibo Shu, Yaqiang Yao, Shengfei Lyu, Jinlong Li, Huanhuan Chen
Summary: In the research area of time series classification, a novel algorithm called short isometric shapelet transform (SIST) is introduced in this paper to reduce time complexity by fixing the length of shapelet and training a single linear classifier. The theoretical evidence and empirical experiments demonstrate the superior performance of the proposed algorithm in terms of near-lossless accuracy while reducing time complexity.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Hongping Yan, Liukun He, Xiangmei Song, Wang Yao, Chang Li, Qiang Zhou
Summary: This paper presents an efficient real-time identification scheme for Tor traffic, which extracts more accurate features using the time window method and bidirectional statistical characteristics, enabling effective detection and classification of Tor flow.
Article
Agronomy
Meng Zhou, Hengbiao Zheng, Can He, Peng Liu, G. Mustafa Awan, Xue Wang, Tao Cheng, Yan Zhu, Weixing Cao, Xia Yao
Summary: This study proposes a classification method based on UAV imagery for crop phenology detection. The results show that the combination of spectral and texture features can improve classification accuracy, providing technical guidance for real-time detection of crop phenology.
FIELD CROPS RESEARCH
(2023)
Article
Biology
Hanjie Chen, Saptarshi Das, John M. Morgan, Koushik Maharatna
Summary: This paper proposes a novel method for predicting and classifying ventricular arrhythmias. The method has been validated using data from two open databases and showed promising results in terms of prediction time and accuracy. This method has the potential to advance technologies such as implantable cardioverter defibrillators and help prevent sudden cardiac death.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Automation & Control Systems
Deepak Kumar Panda, Saptarshi Das, Stuart Townley
Summary: This article investigates load frequency control in smart grids, focusing on utilizing energy storage elements and addressing cyber-physical system challenges such as packet drops and random time delays. A filtered PID controller is tuned using the PSO algorithm, and the performance is tested with synthetic and real profiles. The study quantifies the impacts of stochastic profiles on the stability and performance of the LFC loops under communication constraints.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Multidisciplinary Sciences
Eric P. M. Grist, Trevelyan J. McKinley, Saptarshi Das, Tom Tregenza, Aileen Jeffries, Nicholas Tregenza
Summary: This article presents a simple and transparent non-parametric trend evaluation method called "Paired Year Ratio Assessment (PYRA)" for evaluating population trends in acoustic monitoring data for cetacean conservation. The study compares the performance of PYRA with traditional generalized additive models (GAMS) and nonparametric randomization tests, concluding that PYRA is a powerful tool for identifying population trends.
Article
Chemistry, Physical
Moutushi Dutta Choudhury, Saptarshi Das, Arun G. Banpurkar, Amruta Kulkarni
Summary: This study investigates the wetting characteristics of Polydimethylsiloxane (PDMS) polymer on different surfaces. Statistical models are developed to predict the temporal evolution of drying droplets with varying surface properties. The best statistical model is identified to capture the dynamics of drying droplets on hydrophobic surfaces with random roughness.
COLLOIDS AND SURFACES A-PHYSICOCHEMICAL AND ENGINEERING ASPECTS
(2022)
Article
Computer Science, Artificial Intelligence
Deepak Kumar Panda, Saptarshi Das, Stuart Townley
Summary: This paper applies machine learning methods to obtain the locational information of energy consumers based on their historical energy consumption patterns. The author tackles the issue of unbalanced classification problem for the dataset and uses Monte Carlo based under-sampling and genetic programming optimizer to optimize and compare the classification algorithms. The classification performance metrics are evaluated and the energy policy implications for urban and rural consumers are discussed.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Physics, Multidisciplinary
Kaushik Halder, Deepak Kumar Panda, Saptarshi Das, Sourav Das, Amitava Gupta
Summary: This paper proposes a novel observer based networked PI controller for control systems considering bounded disturbance and measurement noise. The Lyapunov stability condition is derived using an asynchronous dynamical system approach to improve the quality-of-service and quality-of-control. The algorithm is validated on energy conversion systems and the experimental results demonstrate the effectiveness of the proposed method.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Mathematics, Interdisciplinary Applications
Saptarshi Das, Kaushik Halder
Summary: This paper proposes a new concept for designing PID controllers using dominant pole placement method and a derivative filter. By mapping the design onto the discrete time domain with a suitable sampling time, the continuous time delays can be converted into discrete time poles. The continuous-time plant and the filtered PID controller are discretized using the pole-zero matching method. Global optimization method is used to discover the stabilizable region and meet the pole placement conditions. Simulation results on test-bench plants demonstrate the validity and effectiveness of the proposed control design method.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Energy & Fuels
Khawaja Haider Ali, Mohammad Abusara, Asif Ali Tahir, Saptarshi Das
Summary: Real-time energy management in grid-connected microgrids is challenging due to intermittent renewable energy sources, load variations, and variable grid tariffs. This paper proposes a novel dual-layer Q-learning strategy, where the first layer produces directive commands offline using forecasted data, and the second layer refines these commands every 15 minutes by considering real-time changes in the RES and load demand.
Article
Energy & Fuels
Marvin B. Sigalo, Saptarshi Das, Ajit C. Pillai, Mohammad Abusara
Summary: The use of combined heat and power (CHP) systems has increased recently due to their high efficiency and low emissions. However, using CHP systems in off-grid applications can introduce challenges such as the need for load-following operation and the potential for lower efficiency and emissions during low loads. This paper proposes a real-time Energy Management System (EMS) using a combination of LSTM neural networks, MILP, and RH control strategy to optimize the dispatch of CHP and battery energy storage system (BESS). Simulation results show that the proposed method can prevent power export to the grid and reduce operational cost compared to offline methods.
Article
Multidisciplinary Sciences
Nivedita Bhadra, Shre Kumar Chatterjee, Saptarshi Das
Summary: In this paper, a statistical analysis pipeline is proposed to deal with a multiclass environmental stimuli classification problem using imbalanced plant electrophysiological data. Fifteen statistical features extracted from the plant electrical signals are used to classify three different environmental chemical stimuli and the performance of eight different classification algorithms is compared. The findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly imbalanced datasets and advance existing studies on environmental pollution level monitoring using plant electrophysiological data.
Article
Chemistry, Analytical
Lamia Alyami, Deepak Kumar Panda, Saptarshi Das
Summary: A new method has been proposed to estimate the measurement noise covariance in COVID-19 pandemic data, using Bayesian model selection and the Extended Kalman filter. This method helps evaluate the accuracy of complex compartmental epidemiological models.
Article
Computer Science, Theory & Methods
Andrea Vitaletti, Maurizio Pizzonia, Marco Zecchini, Diego Pennino, Salvatore Esposito De Falco, Francesco Pacileo, Alessandro Bellini, Antonio Bonifacio, Domenico Sardanelli, Pietro Vito, Simone Naldini
Summary: Facility management involves outsourcing non-core business activities to specialized companies. Maintenance is a crucial aspect of facility management, often handled by Global Maintenance Services (GMS). This paper presents a blockchain solution for supporting an on-chain GMS, including a reference architecture, a use case, and a proof-of-concept in a hospital setting. The legal and managerial implications of this approach are also discussed.
INTERNATIONAL JOURNAL OF PARALLEL EMERGENT AND DISTRIBUTED SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Lorenzo Ariemma, Niccolo De Carlo, Diego Pennino, Maurizio Pizzonia, Andrea Vitaletti, Marco Zecchini
Summary: In the fragmented market of Italian craft beer, it is difficult for beerlovers to assess the quality of beer and for breweries and pubs to inform customers about their offerings. This paper proposes a blockchain-based supply chain tracking system tailored for this sector. The authors collaborated with a market player to analyze specific problems and provide a solution that may be applied to other fragmented industries. The cost estimation for implementation is found to be affordable. Additionally, the adoption of the blockchain infrastructure to support a discount coupon system is discussed, along with considerations for privacy regulation.
INTERNATIONAL JOURNAL OF PARALLEL EMERGENT AND DISTRIBUTED SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ezenwa Udoha, Saptarshi Das, Mohammad Abusara
Summary: This paper presents a novel structure and control scheme for interconnecting multiple standalone microgrids to a common AC bus. The proposed controller maximizes renewable power utilization and minimizes auxiliary power usage, providing better load support.
Review
Telecommunications
Diego Pennino, Maurizio Pizzonia, Andrea Vitaletti, Marco Zecchini
Summary: This review paper evaluates the potential of blockchain technology in supporting economic transactions in IoT projects and applications. It discusses the impact of blockchain on transaction throughput, latency, costs, limits on ecosystem growth, and explores additional financial tools that blockchain can bring to the IoT ecosystem. The paper also highlights the lack of utilization of blockchain's potential in current IoT projects and suggests open problems and research directions for easier and more effective blockchain adoption.
JOURNAL OF SENSOR AND ACTUATOR NETWORKS
(2022)