- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
ZF-AutoML: An Easy Machine-Learning-Based Method to Detect Anomalies in Fluorescent-Labelled Zebrafish
摘要： Background: Zebra?sh are e?cient animal models for conducting whole organism drug testing and toxicological evaluation of chemicals. They are frequently used for high-throughput screening owing to their high fecundity. Peripheral experimental equipment and analytical software are required for zebra?sh screening, which need to be further developed. Machine learning has emerged as a powerful tool for large-scale image analysis and has been applied in zebra?sh research as well. However, its use by individual researchers is restricted due to the cost and the procedure of machine learning for speci?c research purposes. Methods: We developed a simple and easy method for zebra?sh image analysis, particularly ?uorescent labelled ones, using the free machine learning program Google AutoML. We performed machine learning using vascular- and macrophage-Enhanced Green Fluorescent Protein (EGFP) ?shes under normal and abnormal conditions (treated with anti-angiogenesis drugs or by wounding the caudal ?n). Then, we tested the system using a new set of zebra?sh images. Results: While machine learning can detect abnormalities in the ?sh in both strains with more than 95% accuracy, the learning procedure needs image pre-processing for the images of the macrophage-EGFP ?shes. In addition, we developed a batch uploading software, ZF-ImageR, for Windows (.exe) and MacOS (.app) to enable high-throughput analysis using AutoML. Conclusions: We established a protocol to utilize conventional machine learning platforms for analyzing zebra?sh phenotypes, which enables ?uorescence-based, phenotype-driven zebra?sh screening.
关键词： ?uorophores,in vivo screening,arti?cial intelligence
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Correlation of advanced accelerated stress testing with polyamide-based photovoltaic backsheet field-failures
摘要： Patients have been known to regain consciousness during surgery while still paralyzed by the anesthesia and unable to communicate their distress. Recently, electronic engineers have helped resolve this problem by improving the real-time monitoring of depth of anesthesia. Electronic measurements of the brain’s activity are used for many clinical and research purposes. This is possible because the brain uses electrochemical phenomena in order to process data. Many researchers have taken this to mean that advances in computer science will eventually result in sentient computers. Some con?ate arti?cial consciousness with arti?cial intelligence even though consciousness and intelligence are not positively correlated. Those not trained in neurology, or at least medicine, understandably fail to comprehend what the rich, complex word ‘‘consciousness’’ actually means as a term of art. Human consciousness can only be evaluated with surrogate markers and is a broad and complex spectrum that ranges from minimally conscious to waking consciousness (what the reader is experiencing right now). The necessary conditions for waking consciousness include a brain in just the right electrical, chemical, and thermal states with suf?cient blood pressure. These conditions, in turn, require the brain to have a body that is maintained in the right environment. Hence, waking consciousness is a proper subset of spectrum consciousness and cannot be considered an independent phenomenon capable of being disembodied or sliced off of the spectrum. The Theory of Mind (TOM) from developmental psychology infers that a brain similar to that of humans is a suf?cient condition for spectrum consciousness. But this theory is precluded for computers because a child would not recognize a computer as being a living organism that is just like the child. Although TOM could be applied to an ideal android, there is a classic mathematical theorem from systems science that makes such an android seem infeasible.
关键词： synthetic biology,electroencephalography,arti?cial intelligence,Anesthesia,theory of mind
更新于2025-09-16 10:30:52
-
Smart Plant Factory (The Next Generation Indoor Vertical Farms) || Plant Factories with Artificial Lighting (PFALs): Benefits, Problems, and Challenges
摘要： The bene?ts, unsolved problems, and challenges for plant factories with arti?cial lighting (PFALs) are discussed. The remarkable bene?ts are high resource use ef?ciency, high annual productivity per unit land area, and production of high-quality plants without using pesticides. Major unsolved problems are high initial investment, electricity cost, and labor cost. A major challenge for the next-generation smart PFAL is the introduction of advanced technologies such as arti?cial intelligence with the use of big data, genomics, and phenomics (or methodologies and protocols for noninvasive measurement of plant-speci?c traits related to plant structure and function).
关键词： Smart LED lighting system,Cultivation system module (CSM),Phenotyping,Annual productivity,Standardization,Arti?cial intelligence,Resource use ef?ciency (RUE)
更新于2025-09-10 09:29:36
-
[Lecture Notes in Computer Science] Neural Information Processing Volume 11307 (25th International Conference, ICONIP 2018, Siem Reap, Cambodia, December 13–16, 2018, Proceedings, Part VII) || Hopfield Neural Network with Double-Layer Amorphous Metal-Oxide Semiconductor Thin-Film Devices as Crosspoint-Type Synapse Elements and Working Confirmation of Letter Recognition
摘要： Arti?cial intelligences are essential concepts in smart societies, and neural networks are typical schemes that imitate human brains. However, the neural networks are conventionally realized using complicated software and high-performance hardware, and the machine size and power consumption are huge. On the other hand, neuromorphic systems are composed solely of optimized hardware, and the machine size and power consumption can be reduced. Therefore, we are investigating neuromorphic systems especially with amorphous metal-oxide semiconductor (AOS) thin-?lm devices. In this study, we have developed a Hop?eld neural network with double-layer AOS thin-?lm devices as crosspoint-type synapse elements. Here, we propose modi?ed Hebbian learning done locally without extra control circuits, where the conductance deterioration of the crosspoint-type synapse elements can be employed as synaptic plasticity. In order to validate the fundamental operation of the neuromorphic system, ?rst, double-layer AOS thin-?lm devices as crosspoint-type synapse elements are actually fabricated, and it is found that the electric current continuously decreases along the bias time. Next, a Hop?eld neural network is really assembled using a ?eld-programmable gate array (FPGA) chip and the double-layer AOS thin-?lm devices, and it is con?rmed that a necessary function of the letter recognition is obtained after learning process. Once the fundamental operations are con?rmed, more advanced functions will be obtained by scaling up the devices and circuits. Therefore, it is expected the neuromorphic systems can be three-dimensional (3D) large-scale integration (LSI) chip, the machine size can be compact, power consumption can be low, and various functions of human brains will be obtained. What has been developed in this study will be the sole solution to realize them.
关键词： Neural network,Hop?eld neural network,Letter recognition,Arti?cial intelligence,Crosspoint-type synapse elements,Double-layer amorphous metal-oxide semiconductor (AOS) thin-?lm device,Modi?ed hebbian learning
更新于2025-09-09 09:28:46