Article
Plant Sciences
Qian Xu, Jianrong Cai, Lixin Ma, Bin Tan, Ziqi Li, Li Sun
Summary: Huanglongbing (HLB) is a highly contagious and devastating citrus disease that causes huge economic losses to the citrus industry. Timely detection of the HLB infection status of plants and removal of diseased trees are effective ways to reduce losses. In this study, a vision system was developed for rapid HLB detection in the field, using reflection-transmission image acquisition and a step-by-step classification model.
Article
Genetics & Heredity
Antonio Di Maria, Salvatore Alaimo, Lorenzo Bellomo, Fabrizio Billeci, Paolo Ferragina, Alfredo Ferro, Alfredo Pulvirenti
Summary: The inference of novel knowledge and new hypotheses from current literature analysis is crucial for making new scientific discoveries. The BioTAGME system in bio-medicine combines an entity-annotation framework with a network-based inference methodology to create an extensive Knowledge Graph.
FRONTIERS IN GENETICS
(2022)
Article
Computer Science, Artificial Intelligence
Aditi Ghosh, Parthajit Roy, Paramartha Dutta
Summary: Many features of leaves are used in automated leaf recognition models, but the curvature feature has been the least studied. This is due to the fact that curvature is not invariant and can fluctuate significantly in different positions of a single leaf. However, this study found that curvature can be used as a distinguishing feature for leaf identification and provided a step-by-step method for handling curvature.
Article
Computer Science, Artificial Intelligence
David Sosa-Trejo, Antonio Bandera, Martin Gonzalez, Santiago Hernandez-Leon
Summary: Since the 19th century, scientists have tried to quantify species distributions using techniques such as direct counting and microscopes. Automatic image processing and classification methods are now being utilized to avoid manual procedures for classifying marine plankton. This article summarizes the techniques proposed for classifying marine plankton from the beginning of this field to the present day, focusing on automatic methods that utilize image processing.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Sining Wu, Xiang Gao, Xiaopeng Hu
Summary: Data hallucination methods in few-shot learning generate additional training examples for novel classes by training a general embedding model with base class data, and then building hallucinators to generate data for novel classes. However, these methods often rely on general-purpose embeddings, limiting their ability to generate task-oriented samples. This paper proposes a task-oriented hallucination method that uses a task-specific embedding model to perform task-oriented generation.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Information Systems
Agnieszka Jastrzebska
Summary: This paper proposes a new approach to time series classification by transforming scalar time series into a two-dimensional space of amplitude and change of amplitude and using visual pattern recognition for classification. The effectiveness of the method is demonstrated through experiments and comparison with state-of-the-art approaches. The conversion of raw time series into images and feature extraction opens up possibilities for applying standard clustering algorithms.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Multidisciplinary Sciences
Shintaro Oka, Kazunori Nozaki, Mikako Hayashi
Summary: In order to prevent needlestick injury and leftover instruments and improve the efficiency of dental treatment, it is crucial to have knowledge about the necessary instruments for dental treatment. Therefore, we developed an image recognition system to detect dental treatment instruments during treatment and evaluated its performance using two metrics: detection accuracy and average precision.
SCIENTIFIC REPORTS
(2023)
Article
Materials Science, Multidisciplinary
Atul Dhall, Ravikiran Ramjee, Min Jun Oh, Kevin Tao, Geelsu Hwang
Summary: This manuscript presents a customizable platform compatible with off-the-shelf well plates that can monitor microbial adhesion, growth, and associated parameters under various relevant scenarios by taking advantage of 3D printing. This platform liberates designing experimental strategies for investigations of biofilms under various conditions.
ADVANCED MATERIALS TECHNOLOGIES
(2022)
Article
Chemistry, Analytical
Su Yang, Sanaul Hoque, Farzin Deravi
Summary: This paper presents and evaluates a novel instance-based algorithm for pattern classification. The proposed method addresses the challenge of limited and/or noisy training data in pattern classifications. It transforms the query data and training templates based on their distributions in the feature space. The technique is effective for classification of both images and time-series signals, even with small amounts of training samples.
Article
Biotechnology & Applied Microbiology
Matthew R. Lueder, Regina Z. Cer, Miles Patrick, Logan J. Voegtly, Kyle A. Long, Gregory K. Rice, Kimberly A. Bishop-Lilly
Summary: Manual Annotation Studio (MAS) is a software tool designed to improve the efficiency of manual functional annotation for prokaryotic and viral genomes. It allows users to upload, edit, and track annotations, provides structure to projects, and reduces errors. MAS can interface with HPC clusters, support multiple users, and export data in various formats.
Review
Agronomy
Normaisharah Mamat, Mohd Fauzi Othman, Rawad Abdoulghafor, Samir Brahim Belhaouari, Normahira Mamat, Shamsul Faisal Mohd Hussein
Summary: The implementation of intelligent technology in agriculture, specifically the use of deep learning techniques for image annotation, is carefully investigated in this article. The advancements in deep learning architecture employed in various applications such as plant recognition, disease detection, counting, classification, and yield estimation are thoroughly explored. The article also reviews recent publications on the application of deep learning in agriculture, providing valuable insights and helping researchers gain a deeper understanding of this technology's future potential in agriculture.
Article
Chemistry, Analytical
Torben Moeller, Tim W. Nattkemper
Summary: In recent years, there has been an increase in the deployment of cabled Fixed Underwater Observatories (FUOs) equipped with digital cameras recording high-resolution digital image time series. A new strategy combining active learning procedure and deep learning feature representations has been proposed for machine learning-based observatory image interpretation, showing promising results on two different data sets. The proposed ALMI method achieves high classification accuracy with fewer training samples compared to the reference method.
Article
Radiology, Nuclear Medicine & Medical Imaging
Mingrui Zhuang, Zhonghua Chen, Hongkai Wang, Hong Tang, Jiang He, Bobo Qin, Yuxin Yang, Xiaoxian Jin, Mengzhu Yu, Baitao Jin, Taijing Li, Lauri Kettunen
Summary: The development of medical image analysis algorithm is a complex process that involves multiple sub-steps such as model training, data visualization, human-computer interaction and GUI construction. To accelerate this process, a software tool that supports training data annotation and GUI construction is highly desired, especially for deep learning algorithms. In this work, a software platform called AnatomySketch was constructed, which provides a friendly GUI and a flexible plugin interface for integrating user-developed algorithm modules. Through this platform, algorithm developers can quickly create GUI-based software prototypes for clinical validation.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Engineering, Electrical & Electronic
Hyeyun Lee, Soyoung Lee, Jaeseong Kim, Heesoo Jung, Kyung Jae Yoon, Srinivas Gandla, Hogun Park, Sunkook Kim
Summary: With the help of AI-based algorithms, the accuracy of gesture recognition using sEMG signals has increased. An array of bipolar stretchable sEMG electrodes, combined with a self-attention-based graph neural network, is developed to achieve highly accurate gesture recognition. The system can differentiate static and dynamic gestures with about 97% accuracy using a single trial per gesture. The array also has skin-like attributes and can provide stable EMG signals even after long-term testing and multiple reuses.
NPJ FLEXIBLE ELECTRONICS
(2023)
Article
Computer Science, Artificial Intelligence
Ebrahim Al-wajih, Rozaida Ghazali
Summary: In recent years, deep learning approaches have been widely used in handwritten digit recognition. This paper proposes a new model called center-symmetric local binary convolutional neural networks (CS-LBCNN) based on center-symmetric local binary patterns (CS-LBPs). Compared to existing LBCNN models, the CS-LBCNN model achieves better accuracy and classification rate.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Biology
Gabriella R. Sterne, Hideo Otsuna, Barry J. Dickson, Kristin Scott
Summary: This study provides a detailed analysis of 138 different types of SEZ cells in adult Drosophila, finding that they cluster into six supergroups based on morphology. Most local SEZ interneurons exhibit rich local processing, while SEZ projection neurons tend to be classically polarized, conveying information to a limited number of higher brain regions.
Article
Biology
Stefanie Engert, Gabriella R. Sterne, Davi D. Bock, Kristin Scott
Summary: This study reveals the structure and connectivity of gustatory sensory neurons in fruit flies, identifies distinct neuronal groups involved in recognizing different taste modalities, and uncovers the impact of synaptic connections on gustatory signal transmission.
Article
Neurosciences
Monika Singh, Bing Ye, Jung Hwan Kim
Summary: Dual leucine zipper kinase (DLK) plays a crucial role in the development, degeneration, and regeneration of neurons, but its mechanism is not well understood. A study found that the Drosophila DLK regulates the growth of presynaptic arbor by controlling the expression of Down syndrome cell adhesion molecule (Dscam) through RNA binding proteins (RBPs). They also identified the cytoplasmic poly(A)-binding protein, pAbp, as an RBP that mediates the increase in Dscam expression induced by DLK.
JOURNAL OF NEUROSCIENCE
(2022)
Article
Neurosciences
Tao Yang, Macy W. Veling, Xiao-Feng Zhao, Nicholas P. Prin, Limei Zhu, Ty Hergenreder, Hao Liu, Lu Liu, Zachary S. Rane, Masha G. Savelieff, Peter G. Fuerst, Qing Li, Kenneth Y. Kwan, Roman J. Giger, Yu Wang, Bing Ye
Summary: This study reveals the importance of Down syndrome cell adhesion molecule (DSCAM) in the migration of neurons during neocortex development. DSCAM is required for migrating neurons to bypass their predecessors and reach their final positions. The mechanism involves weakening cell adhesion mediated by N-cadherin.
JOURNAL OF NEUROSCIENCE
(2022)
Article
Biology
Philip K. Shiu, Gabriella R. Sterne, Stefanie Engert, Barry J. Dickson, Kristin Scott
Summary: This study combines synaptic resolution circuit reconstruction with genetic access to specific neurons to elucidate a gustatory sensorimotor circuit in adult Drosophila melanogaster. The circuit integrates external taste detection and internal hunger signals to flexibly execute feeding decisions.
Article
Biochemistry & Molecular Biology
Molly J. Kirk, Arya Gold, Ashvin Ravi, Gabriella R. Sterne, Kristin Scott, Evan W. Miller
Summary: To achieve rapid anatomical staining in live brains, researchers used genetically targeted membrane tethers that link fluorescent dyes for in vivo neuronal labeling. By expressing extracellular HaloTag-CD4 and SNAPf-CD4 enzymes, they directly labeled transgene-expressing cells with commercially available ligand-substituted fluorescent dyes. This method was successfully applied in live Drosophila brains, allowing for the labeling of expression patterns and anatomical comparisons.
ACS CHEMICAL NEUROSCIENCE
(2023)
Article
Biochemistry & Molecular Biology
Geng Pan, Ruonan Li, Guozhong Xu, Shijun Weng, Xiong-li Yang, Limin Yang, Bing Ye
Summary: By studying Drosophila larvae, it was found that gentle mechanical stimuli can inhibit nociceptive responses. This study reveals a novel cross-modal gating mechanism that filters weak nociceptive inputs.
Article
Biochemical Research Methods
Linus Manubens-Gil, Zhi Zhou, Hanbo Chen, Arvind Ramanathan, Xiaoxiao Liu, Yufeng Liu, Alessandro Bria, Todd Gillette, Zongcai Ruan, Jian Yang, Miroslav Radojevic, Ting Zhao, Li Cheng, Lei Qu, Siqi Liu, Kristofer E. Bouchard, Lin Gu, Weidong Cai, Shuiwang Ji, Badrinath Roysam, Ching-Wei Wang, Hongchuan Yu, Amos Sironi, Daniel Maxim Iascone, Jie Zhou, Erhan Bas, Eduardo Conde-Sousa, Paulo Aguiar, Xiang Li, Yujie Li, Sumit Nanda, Yuan Wang, Leila Muresan, Pascal Fua, Bing Ye, Hai-yan He, Jochen F. Staiger, Manuel Peter, Daniel N. Cox, Michel Simonneau, Marcel Oberlaender, Gregory Jefferis, Kei Ito, Paloma Gonzalez-Bellido, Jinhyun Kim, Edwin Rubel, Hollis T. Cline, Hongkui Zeng, Aljoscha Nern, Ann-Shyn Chiang, Jianhua Yao, Jane Roskams, Rick Livesey, Janine Stevens, Tianming Liu, Chinh Dang, Yike Guo, Ning Zhong, Georgia Tourassi, Sean Hill, Michael Hawrylycz, Christof Koch, Erik Meijering, Giorgio A. Ascoli, Hanchuan Peng
Summary: BigNeuron is an open community platform that sets open standards for accurate and fast automatic neuron tracing. They collected diverse image volumes from different species to generate gold standard manual annotations and measure the quality of 35 automatic tracing algorithms. They developed an interactive web application for data analysis and benchmarking, and observed that combining diverse algorithms can generate more accurate results. They also used machine learning to predict the quality of automatic reconstructions. This resource provides a gold standard for testing automated tracing algorithms.
Editorial Material
Biochemistry & Molecular Biology
Bing Ye
Summary: A major challenge in brain organoid technologies is the absence of vasculature. However, innovative approaches have been developed in recent years to address this issue. A 2020 paper published in PLOS Biology exemplifies the methods used in this rapidly advancing field.
Article
Biochemistry & Molecular Biology
Hao Liu, Rene N. M. Caballero-Floran, Ty Hergenreder, Tao Yang, Jacob W. Hull, Geng Pan, Ruonan Li, Macy Veling, Lori G. Isom, Kenneth M. Kwan, Z. Josh Huang, Peter Fuerst, Paul Jenkins, Bing Ye
Summary: Down syndrome is caused by the trisomy of human chromosome 21. This study found that DSCAM levels regulate GABAergic synapse formation on pyramidal neurons, and overexpression of DSCAM leads to excessive GABAergic input and increased inhibition. Conversely, loss of DSCAM impairs GABAergic synapse development and function.
Article
Biology
Meghan Laturney, Gabriella R. Sterne, Kristin Scott
Summary: This study discovered that mated female fruit flies increase their sugar intake, which is regulated by sexually dimorphic insulin receptor (Lgr3) neurons. After mating, the inhibition of specific neurons is reduced, promoting sugar intake. This circuit transforms the mating signal into a hunger signal, providing a mechanism for the energetic costs associated with reproduction.
Article
Biology
Geoffrey W. Meissner, Aljoscha Nern, Zachary Dorman, Gina M. DePasquale, Kaitlyn Forster, Theresa Gibney, Joanna H. Hausenfluck, Yisheng He, Nirmala A. Iyer, Jennifer Jeter, Lauren Johnson, Rebecca M. Johnston, Kelley Lee, Brian Melton, Brianna Yarbrough, Christopher T. Zugates, Jody Clements, Cristian Goina, Hideo Otsuna, Konrad Rokicki, Robert R. Svirskas, Yoshinori Aso, Gwyneth M. Card, Barry J. Dickson, Erica Ehrhardt, Jens Goldammer, Masayoshi Ito, Dagmar Kainmueller, Wyatt Korff, Lisa Mais, Ryo Minegishi, Shigehiro Namiki, Gerald M. Rubin, Gabriella R. Sterne, Tanya Wolff, Oz Malkesman, FlyLight Project Team
Summary: Precise and repeatable genetic access to specific neurons is important in Drosophila neuroscience, and the GAL4/UAS method is commonly used for neuronal targeting. However, current methods lack single-cell resolution for reliable cell type identification. This study introduces the use of MultiColor FlpOut labeling to generate cellular resolution confocal images at a large scale, and provides searchable images of 74,000 adult central nervous systems on the NeuronBridge website. This resource can bridge the gap between electron microscopy and light microscopy in identifying individual neurons and improve prediction of split-GAL4 combinations targeting specific neurons.
Article
Cell Biology
Sarah Pizzano, Gabriella R. Sterne, Macy W. Veling, L. Amanda Xu, Ty Hergenreder, Bing Ye
Summary: This study reveals the functional interaction between HSA21 genes, providing insights into the pathogenesis of neuronal aberrations in DS.
DISEASE MODELS & MECHANISMS
(2023)
Article
Biochemical Research Methods
Yujia Hu, Carrie R. Ferrario, Alexander D. Maitland, Rita B. Ionides, Anjesh Ghimire, Brendon Watson, Kenichi Iwasaki, Hope White, Yitao Xi, Jie Zhou, Bing Ye
Summary: Quantifying animal behavior is crucial in biological research, and identifying behaviors is a necessary prerequisite for this quantification. The current computational tools for behavioral quantification often use high-level properties to identify behaviors, which limits a holistic assessment. This study introduces LabGym, an open-source computational tool that overcomes this limitation by using pattern images and animations to accurately identify and measure animal behaviors. LabGym is user-friendly, applicable to experiments with multiple animals, and provides visualizations of behavioral datasets, demonstrating its efficacy in capturing subtle behavioral changes across different animal species.
CELL REPORTS METHODS
(2023)