Article
Spectroscopy
Hao Jin, Gui -Mei Dong, Hai-Yun Wu, Yan-Rong Yang, Ming-Yue Huang, Meng -Yuan Wang, Ren-Jie Yang
Summary: A qualitative analysis method for melamine-adulterated milk based on two-trace two-dimensional auto-correlation spectra was proposed. Infrared spectroscopy was used to measure the spectral data of pure milk and melamine-adulterated milk. The intensity of auto-correlation peaks at specific wave numbers was selected as independent variables for modeling. The method achieved 100% accuracy for individual brands and 99.05% accuracy for all four brands combined.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Article
Chemistry, Multidisciplinary
Mojtaba Farrokh, Farzaneh Ghasemi, Mohammad Noori, Tianyu Wang, Vasilis Sarhosis
Summary: This study proposes a novel approach combining extreme learning machine (ELM) and least-squares support vector machine (LS-SVM) for simulating hysteresis with different features. The approach accurately identifies hysteretic systems and provides more accurate results with lower computational cost compared to previous experimental studies.
APPLIED SCIENCES-BASEL
(2022)
Article
Mathematics, Interdisciplinary Applications
Tasmi Tamanna, Md Anisur Rahman, Samia Sultana, Mohammad Hasibul Haque, Mohammad Zavid Parvez
Summary: This paper aims to predict epileptic seizures in advance with high prediction accuracy from EEG signals using time-frequency feature extraction and classification techniques. The average prediction accuracy of the proposed method was observed to be 96.38%, and the method could predict a seizure 26.1 min before the actual occurrence. The findings suggest the potential future application of this method in seizure prediction.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Automation & Control Systems
Mohammadreza Nasiri Boroujeni, Yaser Samimi, Emad Roghanian
Summary: The paper discusses four methods for monitoring nonlinear fuzzy profiles, including data-driven fuzzy rule-based and extended least square support vector machine approaches, as well as modified fuzzy regression models and fuzzy least square methods based on linearizing transformation. A comparison of the methods in detecting process shifts and their performance in out-of-control conditions was conducted to evaluate their effectiveness.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
M. A. Ganaie, Anuradha Kumari, A. K. Malik, M. Tanveer
Summary: This paper discusses the application of support vector machines (SVMs) in diagnosing neurological disorders and the challenges of dealing with noise and outliers in EEG signal classification. The authors propose an improved intuitionistic fuzzy twin support vector machine (IIFTWSVM) to address these challenges and evaluate its performance compared to baseline models.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Ali Alqahtani, Nayef Alqahtani, Abdulaziz A. Alsulami, Stephen Ojo, Prashant Kumar Shukla, Shraddha V. Pandit, Piyush Kumar Pareek, Hany S. Khalifa
Summary: The field of electroencephalography (EEG) has greatly contributed to our understanding of the brain and neurological diseases. The electroencephalogram can detect epileptic seizures, strokes, and even death. This research suggests using binary classification to automate epilepsy diagnosis, through preprocessing EEG signals and utilizing a genetic algorithm for feature extraction. The EEG data are then classified as seizure-free or related to epileptic seizures using a support vector classifier.
Article
Automation & Control Systems
Xinjiang Lu, Yunxu Bai
Summary: This article proposes a novel probabilistic LS-SVM method to enhance the modeling reliability of data contaminated by non-Gaussian noise. The effectiveness of the proposed method is demonstrated using both artificial and real cases.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Clinical Neurology
Jonas Munch Nielsen, Ivan C. Zibrandtsen, Paolo Masulli, Torben Lykke Sorensen, Tobias S. Andersen, Troels Wesenberg Kjaer
Summary: This study explores the potential of wearable multi-modal monitoring in epilepsy and identifies effective seizure detection strategies. Automatic seizure detection using multi-modal monitoring shows improved sensitivity and reduced false alarm rates. Visual analysis of multi-modal time series data generates insights for future research on seizure detection.
CLINICAL NEUROPHYSIOLOGY
(2022)
Article
Engineering, Civil
Jia Wang, Xu Wang, Soon Thiam Khu
Summary: This study proposes a hybrid decomposition-based multi-model and multi-parameter ensemble streamflow forecast method, which combines signal decomposition and artificial intelligence models to improve the accuracy and efficiency of streamflow prediction. The results demonstrate that this method effectively reduces forecast uncertainty and expands ensemble size, making it suitable for nonlinear and non-stationary hydrological series forecasting.
JOURNAL OF HYDROLOGY
(2023)
Article
Spectroscopy
Zou Jin-ping, Zhang Shuai, Dong Wen-tao, Zhang Hai-liang
Summary: This paper discusses the importance of freshness in fish products and the significance of the TVB-N indicator for meat freshness, as well as the method of using hyperspectral imaging technology and stoichiometry for detecting TVB-N content.
SPECTROSCOPY AND SPECTRAL ANALYSIS
(2021)
Article
Automation & Control Systems
Qian Shi, Hui Zhang
Summary: In this article, an output-feedback path following controller for autonomous ground vehicles (AGVs) is designed using a learning-based least squares support vector machine (LS-SVM) model to reduce computation loads. The control performance is deteriorated by considering the signal transmission delay. The LS-SVM model is trained for the vehicle path following system, and an output-feedback controller subject to stochastic communication delay is designed to meet the stability condition. H-infinity controller is designed to attenuate the disturbance of LS-SVM model, and the grey wolf optimizer is employed to solve the controller design problem with H-infinity performance. The proposed control strategy is verified to be effective through experimental results based on a hardware-in-loop platform.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Instruments & Instrumentation
Jun Hu, Yin Li, Rui Chen, Yong He, Yande Liu
Summary: Regulating the use of food additives is important for human health. This paper presents an enhanced detection method for benzoic acid additives using terahertz technology. The experiment demonstrates improved accuracy and sensitivity with the optimized compensation method.
INFRARED PHYSICS & TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Solveig Vieluf, Tanuj Hasija, Maurice Kuschel, Claus Reinsberger, Tobias Loddenkemper
Summary: This study aims to identify biomarkers for evaluating seizure-related differences and proposes a biomarker that can classify pre-ictal and inter-ictal data from epilepsy patients. By analyzing the data of 42 pediatric epilepsy patients, it is found that DCCA analysis based on changes in heart rate and electrodermal activity can predict seizure occurrence.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Chao Li, Ziyu Song, Yi Wang, Yancheng Zhang
Summary: This study proposes a method for counting lily buds based on machine vision. Through color space transformation, threshold segmentation, SVM classification, and ellipse fitting, accurate counting and fitting of lily buds are achieved. Experimental results show that the proposed algorithm performs better than other algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
Kamil Krasuski, Adam Ciecko, Mieczyslaw Bakula, Grzegorz Grunwald, Damian Wierzbicki
Summary: This paper presents a new aircraft positioning solution based on the differential RTK-OTF technique, improving the accuracy of aircraft positioning through a new mathematical model and the use of a stochastic process. The developed method shows significant improvement in the accuracy of determining the aircraft position compared to the classical RTK-OTF solution.
Article
Engineering, Electrical & Electronic
Pan Gao, Shengzhou Luo, Manoranjan Paul
Summary: This paper proposes a quantization parameter selection scheme based on rate-distortion model for bit rate constrained point cloud compression. A unified model is proposed to evaluate the distortion by considering the correlation between geometry and color variables. The relationships between overall distortion, bit rate, and quantization parameters are derived, and a solution is obtained using an iterative numerical method. Experimental results show that the proposed algorithm achieves optimal decoded point cloud quality at various target bit rates and outperforms the video-rate-distortion model based scheme.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Cybernetics
Ben W. Morrison, Joshua N. Kelson, Natalie M. Morrison, J. Michael Innes, Gregory Zelic, Yeslam Al-Saggaf, Manoranjan Paul
Summary: This study investigated the relationship between participants' adherence to an algorithmic aid, the degree of control they had at decision points, and their attitudes toward new technologies and algorithms. It also examined the influence of control on participants' subjective reports of task demands. Results showed that participants with more control over the final forecast tended to deviate more and reported lower frustration levels. Additionally, participants with positive implicit attitudes toward algorithms deviated less from the algorithm's forecasts, regardless of the degree of control they had. These findings emphasize the importance of user control and preexisting attitudes in the acceptance and frustration of using algorithmic aids.
INTERACTING WITH COMPUTERS
(2023)
Article
Chemistry, Analytical
Sadia Sabrin Nodi, Manoranjan Paul, Nathan Robinson, Liang Wang, Sabih Ur Rehman
Summary: Soil colour is crucial in agriculture for monitoring soil health and determining properties. Munsell soil colour charts are commonly used, but subjective and error-prone. This study captured soil colours from the Munsell Soil Colour Book using smartphones and compared them with readings from a sensor. Discrepancies were observed. Different colour models were investigated, and a relationship between Nix Pro and smartphone images was introduced to accurately determine Munsell soil colour.
Article
Multidisciplinary Sciences
Md Ershadul Haque, Manoranjan Paul, Anwaar Ulhaq, Tanmoy Debnath
Summary: Quantum image computing has gained attention for its ability to store and process image data faster than classical computers. This study proposes a block-wise DCT-EFRQI approach to efficiently represent and compress grayscale images inside a quantum computer. The experimental results show that the proposed approach provides better representation and compression compared to other existing methods.
SCIENTIFIC REPORTS
(2023)
Review
Imaging Science & Photographic Technology
Sourabhi Debnath, Manoranjan Paul, Tanmoy Debnath
Summary: LiDAR sensors are increasingly used in agriculture due to their non-destructive data capturing mode. They emit pulsed light waves that bounce off objects and calculate the distances traveled by measuring return time. LiDAR data is applied in various agricultural applications, such as measuring landscaping and crop characteristics, estimating biomass, and detecting soil properties. This review focuses on LiDAR-based system applications and data in agriculture, providing comparisons and future research directions.
JOURNAL OF IMAGING
(2023)
Article
Environmental Sciences
Dristi Datta, Manoranjan Paul, Manzur Murshed, Shyh Wei Teng, Leigh Schmidtke
Summary: Estimating soil properties is important for studying their correlation with plant health and food production. Conventional methods are laborious and expensive, but remote sensing technologies offer a cost-effective solution for large-scale prediction. This research explores machine and deep learning techniques to predict soil nutrient properties and compares different spectral bands to provide guidance for optimal prediction methods.
Article
Computer Science, Information Systems
Ershadul Haque, Sami Ul Hoque, Manoranjan Paul, Mahidur R. Sarker, Abdullah Al Suman, Tanvir Ul Huque
Summary: This paper uses LSTM to predict the recovery cases of the novel coronavirus, analyzing data from 258 regions worldwide and extracting key features for time series analysis. This research is of great importance for studying the prediction of virus propagation.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
Michael J. Horry, Subrata Chakraborty, Biswajeet Pradhan, Manoranjan Paul, Jing Zhu, Hui Wen Loh, Prabal Datta Barua, U. Rajendra Acharya
Summary: Screening programs for early lung cancer diagnosis are uncommon due to difficulties in reaching at-risk patients in rural areas. This study presents a pre-processing pipeline that enhances the accuracy and generalization of deep learning models for lung nodule detection by debiasing chest X-ray images. The proposed pipeline combines pruning, histogram equalization, lung field segmentation, and rib/bone suppression techniques. The resulting deep learning models achieve a generalization accuracy of 89% on an independent lung nodule dataset, paving the way for a low-cost and accessible clinical system for lung cancer screening.
Article
Telecommunications
Helen K. K. Joy, Manjunath R. R. Kounte, Arunkumar Chandrasekhar, Manoranjan Paul
Summary: In recent years, advancements in video coding technologies have been highly volatile. With the rise of internet and video acquisition devices like mobile phones and cameras, the need for video compression has become crucial. Features like resolution variance, framerate, and display underscore the importance of compression. Deep learning has provided a new perspective in video compression, particularly in terms of efficiency, quality, and adaptivity. This paper focuses on the impact of deep learning on video compression, reviewing developments in intelligent and self-trained steps for compression and proposing ideas for enhancement in various stages.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Samia Sultana, Boshir Ahmed, Manoranjan Paul, Muhammad Rafiqul Islam, Shamim Ahmad
Summary: Lane marking detection is crucial for advanced driving assistance systems and traffic surveillance systems. However, it is highly challenging to detect lane markings under low visibility, obscured, or invisible conditions due to real-life challenging environment and adverse weather. This paper proposes a simple, real-time, and robust lane detection and tracking method that addresses these challenging conditions.
Article
Computer Science, Artificial Intelligence
Ashek Ahmmed, Manoranjan Paul, Mark Pickering
Summary: This research introduces a video coding algorithm that utilizes the commonality of global and local motion models to improve coding efficiency. By using DCO motion modeling and rectangular region partitioning, the proposed step-by-step motion modeling approach achieves better motion compensation and reduced computational complexity. Experimental results show that the approach can save up to 9% to 2.37% bit rate compared to existing video coding standards.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Fariha Afsana, Manoranjan Paul, Manzur Murshed, David Taubman
Summary: This paper improves the idea of 2D cuboid coding by adopting a three-dimensional cuboid partitioning scheme to exploit both local and global redundancy in a video sequence, leading to improved SHVC compression for 360-degree videos.
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
S. M. Ataul Karim Rajin, Manzur Murshed, Manoranjan Paul, Shyh Wei Teng, Jiangang Ma
Summary: This paper explores a new video coding approach by modeling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. Experimental results show that the proposed approach can achieve better coding performance for high motion video sequences.
2022 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ashek Ahmmed, Manoranjan Paul, Manzur Murshed, Mark Pickering
Summary: The paper proposes a method to capture commonality information in dynamic mesh attribute maps using the cuboidal partitioning algorithm, which achieves up to 3.66% bit rate savings in compressing dynamic mesh sequences.
2022 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)
(2022)
Proceedings Paper
Acoustics
Haoyue Tian, Pan Gao, Ran Wei, Manoranjan Paul
Summary: This paper proposes a deep reference picture generator to create a picture that is more relevant to the current encoding frame, thereby improving video compression efficiency. Experimental results demonstrate that this method achieves an average of 9.7% bit saving compared to VVC.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)