Article
Chemistry, Physical
Shenglong Wang, Weili Deng, Tao Yang, Guo Tian, Da Xiong, Xiao Xiao, Hongrui Zhang, Yue Sun, Yong Ao, Junfeng Huang, Jun Chen, Weiqing Yang
Summary: Monitoring physiological signals of the human body is crucial for sports healthcare and injury prevention. This article presents the development of a high-performance piezoresistive sensor using a conductive elastomer with micro-structured PDMS/CNT composite. The sensor demonstrates a broad detection range, fast response/recovery time, ultrahigh sensitivity, and excellent durability, making it potentially valuable for personal sports healthcare and telemedicine monitoring.
Article
Remote Sensing
W. Ross Winans, Qi Chen, Yi Qiang, Erik C. Franklin
Summary: Marine debris is a global crisis, and machine learning techniques show potential in automatically detecting and classifying certain types of debris from aerial surveys. However, there are challenges to overcome in terms of manual interpretation of imagery.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Computer Science, Information Systems
Sungtae Moon, Jihun Jeon, Doyoon Kim, Yongwoo Kim
Summary: Recent developments in drone technology have led to the widespread use of unmanned aerial vehicles (UAVs). In particular, UAVs are often used in reconnaissance to detect objects such as missing persons in large areas. However, traditional systems use only one UAV to search for missing persons in a large area. This paper proposes a reconnaissance drone system using multiple UAVs, which performs real-time object detection on each UAV and stitches the images together using a ground control system (GCS). The lightweight YOLOv5 model and the image stitching method effectively enable real-time monitoring and detection of objects over large areas.
Article
Environmental Sciences
Liping Hou, Ke Lu, Xue Yang, Yuqiu Li, Jian Xue
Summary: This paper proposes a unified Gaussian representation called G-Rep for constructing Gaussian distributions for OBB, QBB, and PointSet, achieving a unified solution to various representations and problems. The proposed method utilizes Gaussian metrics to optimize the regression loss and align label assignment, resulting in excellent performance for arbitrary-oriented object detection.
Article
Environmental Sciences
Yongjun Liu, Guisheng Liao, Haichuan Li, Shengqi Zhu, Yachao Li, Yingzeng Yin
Summary: This paper investigates target detection of passive MIMO radar with multiple illuminators of opportunity and receivers. A generalized likelihood ratio test is proposed for the radar, which is applicable for cases with unknown covariance matrix of colored noise. Numerical examples verify the effectiveness of the proposed method.
Article
Geochemistry & Geophysics
Nan Su, Zhibo Huang, Yiming Yan, Chunhui Zhao, Shuyuan Zhou
Summary: Ship detection is a major problem in satellite image analysis, especially for fast detection of ships in large-area remote-sensing images. This letter proposes an arbitrary-oriented detector based on YOLO, which can quickly locate ship positions. By reducing parameters, adding deformable convolution, and integrating rotation detection capability without angle regression, the proposed method achieves excellent accuracy and speed.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Shaoxiu Wei, Boxiang Zhang, Wei Yi
Summary: This paper introduces TPHD and TCPHD filters that can adaptively learn the history of unknown target detection probability through minimizing Kullback-Leibler divergence, and proposes L-scan approximations with lower computational burden.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Gong Cheng, Xiang Yuan, Xiwen Yao, Kebing Yan, Qinghua Zeng, Xingxing Xie, Junwei Han
Summary: This paper provides a thorough review of small object detection and introduces two large-scale Small Object Detection datasets (SODA). The proposed datasets are expected to facilitate the development of small object detection and spawn more breakthroughs in this field.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Ronghao Fu, Chengcheng Chen, Shuang Yan, Ali Asghar Heidari, Xianchang Wang, Jose Escorcia-Gutierrez, Romany F. Mansour, Huiling Chene
Summary: Significant achievements have been made in generic object detection thanks to advanced deep learning techniques. However, detecting tiny objects remains challenging due to low resolution, insufficient geometric cues, and high noise levels. In this study, we propose two novel components, Gaussian probabilistic distribution-based fuzzy similarity metric (GPM) and adaptive dynamic anchor mining strategy (ADAS), to address these issues and achieve superior performance in tiny object detection tasks.
Article
Computer Science, Information Systems
Hang Xu, Xinyuan Liu, Yike Ma, Zunjie Zhu, Shuai Wang, Chenggang Yan, Feng Dai
Summary: In this study, we propose a circular Gaussian distribution (CGD)-based method for predicting the rotation angle of objects. We convert the labeled angle into a discrete circular Gaussian distribution and let the model predict the distribution parameters. Additionally, we design a rotated object detector based on CenterNet to improve overall efficiency. Experimental results show that our method achieves superior performances, outperforming state-of-the-art competitors on various public datasets.
Article
Chemistry, Multidisciplinary
Jingting Wang, Mingying Lu, Yongxing Chen, Guolin Hao, Bin Liu, Pinghua Tang, Lian Yu, Lei Wen, Haining Ji
Summary: In this study, a machine learning Gaussian regression model was constructed to explore the growth mechanism of MoS2 materials prepared by chemical vapor deposition (CVD). The model revealed that carrier gas flow rate, molybdenum sulfur ratio, and reaction temperature had a crucial impact on the CVD growth of MoS2 materials. The optimal model was then used to predict the size of molybdenum disulfide synthesis under various experimental conditions, providing an effective solution for the preparation of large-size MoS2 materials.
Article
Computer Science, Artificial Intelligence
Lijun Gou, Shengkai Wu, Jinrong Yang, Hangcheng Yu, Xiaoping Li
Summary: This paper presents an anchor-based detection method that uses Gaussian Guided IoU for target assignment and proposes corresponding balanced learning methods to address the issues of insufficient supervision for slender objects and inaccurate feature alignment.
IET COMPUTER VISION
(2022)
Article
Nanoscience & Nanotechnology
Hongchuan Zhong, Rongda Fu, Shiqi Chen, Zaiwei Zhou, Yue Zhang, Xiangyu Yin, Bingwei He
Summary: A new flexible sensor preparation strategy was proposed in this study, based on MWCNT/PDMS composite materials, with advantages of low resistance, high sensitivity, and fast response. Combining the sensor array with deep learning, the technology can be used for accurately recognizing human sitting inclination.
Article
Computer Science, Artificial Intelligence
Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai, Wen Yang, Michael Ying Yang, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, Liangpei Zhang
Summary: This paper presents a large-scale DOTA dataset for object detection in aerial images, along with comprehensive baselines and a code library. The dataset and evaluations provided can facilitate the design of robust algorithms and reproducible research in the field of object detection in aerial images.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Robotics
Jae Hyung Jung, Chan Gook Park
Summary: In this letter, a novel method for merging Gaussian mixtures on matrix Lie groups is proposed and applied to simultaneous localization and mapping problem. By predetermining a weighted mean and merging components at the associated tangent space, the original density can be captured more accurately. Experimental results also show that rotational error of symmetric objects follows a heavy-tailed behavior and can be modeled using Gaussian mixture noise.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Gowtham Polumati, Vivek Adepu, Chandra Sekhar Reddy Kolli, Jeevan Reji, Parikshit Sahatiya
Summary: This study investigates the band alignment of solution processed MoSe2 with MXene using Ultraviolet Photoelectron Spectroscopy and applies it to broadband photodetection. The research shows that MXene functions as an excellent transport layer for the photogenerated excitons generated in MoSe2. By extracting work function values from UPS, the actual energy band diagram of the MoSe2/MXene interface is analyzed. The MoSe2/MXene photodetector exhibits high Responsivity to visible and NIR light illumination.
MATERIALS SCIENCE IN SEMICONDUCTOR PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Neelam Gupta, Vivek Adepu, Manav Tathacharya, Sohel Siraj, Subhradeep Pal, Parikshit Sahatiya, Biplab Kumar Kuila
Summary: The report demonstrates the development of a flexible piezoresistive sensor based on a conjugated polymer framework (CPF) and its application in real time pedometer and smart tactile glove.
SENSORS AND ACTUATORS A-PHYSICAL
(2023)
Article
Materials Science, Multidisciplinary
Vivek Adepu, Manav Tathacharya, Venkat Mattela, Parikshit Sahatiya
Summary: This report presents the development of a WS2/Ti3C2T (X) nanohybrid-based multifunctional physical sensor on a textile cloth, capable of sensing pressure, strain, and humidity. The sensor shows outstanding sensitivity and gauge factor for each stimulus, with long-term stability over a large number of cycles. The piezoresistive effect and modulation of the Schottky barrier height at the heterojunctions are the underlying mechanisms for the sensor's performance. A smartphone-based application is utilized to demonstrate various healthcare applications, showcasing the potential of this sensor in smart healthcare, e-textiles, and flexible electronics.
FLEXIBLE AND PRINTED ELECTRONICS
(2023)
Article
Engineering, Electrical & Electronic
Gowtham Polumati, Aditya Tiwari, Chandra Sekhar Reddy Kolli, Sayan Kanungo, Andres De Luna Bugallo, Parikshit Sahatiya
Summary: This letter presents the fabrication and theoretical analysis of a MoS2 monolayer-based breath sensor using first-principle calculations. The analysis reveals that water molecules preferentially adsorb on sulfur vacancy sites on the monolayer, resulting in increased electronic conductivity and drain current. The sensor shows response to various breath frequencies, suggesting potential applications in disease detection through breath pattern analysis.
IEEE SENSORS LETTERS
(2023)
Article
Materials Science, Multidisciplinary
Vivek Adepu, Manav Tathacharya, Rikitha S. Fernandes, Aditya Tiwari, Sohel Siraj, Sayan Kanungo, Nilanjan Dey, Parikshit Sahatiya
Summary: This study presents a Perylene Diimide (PDI)-based multifunctional sensor for breath-sensing and Geriatric Emergency Signalling applications. The sensor is fabricated using an economically viable vacuum filtration deposition technique, which forms a moderately conducting percolating molecular network on a flexible substrate. The sensor exhibits superior pressure and breath-sensing performance, with fast response and recovery times.
ADVANCED MATERIALS TECHNOLOGIES
(2023)
Article
Nanoscience & Nanotechnology
Payal Chauhan, Sohel Siraj, K. Simmy Joseph, Shweta Dabhi, Gopala R. R. Bhadu, Parikshit Sahatiya, C. K. Sumesh
Summary: The use of alternative energy sources to replace fossil fuels is a pressing issue. Efficient catalysts for water splitting and energy storage technologies have become crucial for achieving sustainability. In this study, CoCr-LDH@VNiS2 was synthesized and demonstrated high performance in water splitting and electrochemical capacitors. The findings provide new insights for the rational design and synthesis of bifunctional catalysts.
ACS APPLIED MATERIALS & INTERFACES
(2023)
Article
Physics, Applied
Vivek Adepu, Changhyeon Yoo, Yeonwoong Jung, Parikshit Sahatiya
Summary: In this study, a MoSe2/Ti3C2Tx nanohybrid-based fabricated flexible physical sensor with an elevated pressure sensitivity of 14.70 kPa(-1) and robust nature withstanding up to similar to 2500 cycles was developed. The underlying transduction mechanism of the pressure sensor involves the piezoresistive effect and the variation of the Schottky barrier height at the MoSe2/Ti3C2Tx interface, elucidated through comprehensive band structures obtained by ultraviolet photoelectron spectroscopy. Moreover, the sensors were used to create a 7 x 7 sensor matrix for tactile sensing and integrated onto a volunteer's hand for artificial skin application.
APPLIED PHYSICS LETTERS
(2023)
Article
Electrochemistry
Payal Chauhan, Dattatray J. Late, Vikas Patel, Parikshit Sahatiya, C. K. Sumesh
Summary: In this study, a novel hierarchical NiCo-LDH@MoS2/CuS heterostructure was prepared by facile two-step hydrothermal synthesis, exhibiting excellent electrochemical performance in water splitting and supercapacitor applications.
ELECTROCHIMICA ACTA
(2023)
Article
Engineering, Electrical & Electronic
Soumi Saha, C. J. Keerthi, Sounak Roy, Parikshit Sahatiya, Surya Shankar Dan, Subhradeep Pal
Summary: This study reports a high-performance photodetector based on CeO2, which is synthesized using a solution combustion method to narrow the bandgap and increase the oxygen vacancies through nitrogen or carbon doping. The fabricated photodetector exhibits excellent photodetection capability with a fast response speed, and can be applied in visible light communication systems.
IEEE PHOTONICS TECHNOLOGY LETTERS
(2023)
Article
Engineering, Electrical & Electronic
C. J. Keerthi, Sayan Halder, Sohel Siraj, Chanchal Chakraborty, Parikshit Sahatiya, Subhradeep Pal
Summary: In this letter, we present a MoSSe-based wideband photodetector (PD) synthesized hydrothermally, which exhibits excellent responsivity and sub-second response time. The device structure consists of MXene/MoSSe/Ag on a Si substrate, with MXene (Ti(3)C(2)Tx) and Ag serving as the cathode and anode contact of the PD, respectively. The Ti(3)C(2)Tx and MoSSe layers are deposited using the spin-coating method, while the Ag electrode is deposited through thermal evaporation. The fabricated PD shows outstanding photodetection capability from 350 nm to 950 nm, with a peak responsivity of 8.89 A.W-1 at 460 nm. The measured external quantum efficiency (EQE) and detectivity (D*) at 420 nm are 24.96% and 9.07 x 10(9) Jones, respectively. Additionally, the PD demonstrates good linearity performance up to 343 K, and the rise and fall times are approximately 0.12 sec and 0.13 sec, respectively.
IEEE PHOTONICS TECHNOLOGY LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Vivek Adepu, Manav Tathacharya, C. S. Raghuram, Parikshit Sahatiya
Summary: The impacts of volunteer's heavy backpacks and chronic neck pain are concerns in the scientific community. Existing alert systems can tackle these issues, but evaluating them is costly and complicated. This study fabricated flexible sensors using low-cost vacuum filtration technique and integrated them into cervical collar strain and shoulder load detection alert systems. The fabricated sensors showed excellent performance and durability, making them suitable for practical applications.
JOURNAL OF MICROMECHANICS AND MICROENGINEERING
(2023)
Article
Materials Science, Multidisciplinary
Gowtham Polumati, Barbara A. Muniz Martinez, Chandra Sekhar Reddy Kolli, Venkatarao Selamneni, Mario Flores Salazar, David Emanuel Sanchez, Andres Fest Carreno, Mauricio Terrones, Andres De Luna Bugallo, Parikshit Sahatiya
Summary: This work demonstrates the band-type engineering and charge transport mechanism of vertically stacked monolayers of MoS2-ReS2 under visible light illumination. The study investigates the impact of stacking order on band alignment and validates the formation of the vertically stacked heterostructure. The results show the significant role of stacking configuration in the optoelectronic properties.
