Single-cell analysis is crucial for deciphering cellular heterogeneity and understanding complex biological systems.However,most existing single-cell sample manipulation(SCSM)systems suffer from various drawbacks such...Single-cell analysis is crucial for deciphering cellular heterogeneity and understanding complex biological systems.However,most existing single-cell sample manipulation(SCSM)systems suffer from various drawbacks such as high cost,low throughput,and heavy reliance on human interventions.Currently,large language models(LLMs)have been used in robotic platforms,but a limited number of studies have reported the application of LLMs in the field of lab-ona-chip automation.Consequently,we have developed an active-matrix digital microfluidic(AM-DMF)platform that realizes fully automated biological procedures for intelligent SCSM.By combining this with a fully programmable labon-a-chip system,we present a breakthrough for SCSM by combining LLMs and object detection technologies.With the proposed platform,the single-cell sample generation rate and identification precision reach up to 25%and 98%,respectively,which are much higher than the existing platforms in terms of SCSM efficiency and performance.Furthermore,a three-class detection method considering droplet edges is implemented to realize the automatic identification of cells and oil bubbles.This method achieves a 1.0%improvement in cell recognition accuracy according to the AP_(75)^(test)metric,while efficiently distinguishing obscured cells at droplet edges,where approximately 20%of all droplets contain cells at their edges.More importantly,as the first attempt,a ubiquitous tool for automatic SCSM workflow generation is developed based on the LLMs,thus advancing the development and progression of the field of single-cell analysis in the life sciences.展开更多
Nowadays,Wireless Sensor Network(WSN)is a modern technology with a wide range of applications and greatly attractive benefits,for example,self-governing,low expenditure on execution and data communication,long-term fu...Nowadays,Wireless Sensor Network(WSN)is a modern technology with a wide range of applications and greatly attractive benefits,for example,self-governing,low expenditure on execution and data communication,long-term function,and unsupervised access to the network.The Internet of Things(IoT)is an attractive,exciting paradigm.By applying communication technologies in sensors and supervising features,WSNs have initiated communication between the IoT devices.Though IoT offers access to the highest amount of information collected through WSNs,it leads to privacy management problems.Hence,this paper provides a Logistic Regression machine learning with the Elliptical Curve Cryptography technique(LRECC)to establish a secure IoT structure for preventing,detecting,and mitigating threats.This approach uses the Elliptical Curve Cryptography(ECC)algorithm to generate and distribute security keys.ECC algorithm is a light weight key;thus,it minimizes the routing overhead.Furthermore,the Logistic Regression machine learning technique selects the transmitter based on intelligent results.The main application of this approach is smart cities.This approach provides continuing reliable routing paths with small overheads.In addition,route nodes cooperate with IoT,and it handles the resources proficiently and minimizes the 29.95%delay.展开更多
A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without dec...A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without decompressing. The correlation between redundancy of sensor data and compression ratio is explored. Further, a parallel compression algorithm based on MapReduce [1] is proposed. Meanwhile, data partitioner which plays an important role in performance of MapReduce application is discussed along with performance evaluation criteria proposed in this paper. Experiments demonstrate that random sampler is suitable for highly redundant sensor data and the proposed compression algorithms can compress those highly redundant sensor data efficiently.展开更多
基金the National Key R&D Program of China(2023YFF0721500)The National Natural Science Foundation of China(Nos.62374102,82172077,22201298,and 62027825)+3 种基金The Innovation and Entrepreneurship Team of Jiangsu Province(JSSCTD202145)The Science and Technology Innovation Project of Foshan,Guangdong Province,China(No.1920001000047)The Science and Technology Development Project of Jilin Province(No.20210204110YY and 20250204092YY)The Suzhou Basic Research Project(SSD2023013).
文摘Single-cell analysis is crucial for deciphering cellular heterogeneity and understanding complex biological systems.However,most existing single-cell sample manipulation(SCSM)systems suffer from various drawbacks such as high cost,low throughput,and heavy reliance on human interventions.Currently,large language models(LLMs)have been used in robotic platforms,but a limited number of studies have reported the application of LLMs in the field of lab-ona-chip automation.Consequently,we have developed an active-matrix digital microfluidic(AM-DMF)platform that realizes fully automated biological procedures for intelligent SCSM.By combining this with a fully programmable labon-a-chip system,we present a breakthrough for SCSM by combining LLMs and object detection technologies.With the proposed platform,the single-cell sample generation rate and identification precision reach up to 25%and 98%,respectively,which are much higher than the existing platforms in terms of SCSM efficiency and performance.Furthermore,a three-class detection method considering droplet edges is implemented to realize the automatic identification of cells and oil bubbles.This method achieves a 1.0%improvement in cell recognition accuracy according to the AP_(75)^(test)metric,while efficiently distinguishing obscured cells at droplet edges,where approximately 20%of all droplets contain cells at their edges.More importantly,as the first attempt,a ubiquitous tool for automatic SCSM workflow generation is developed based on the LLMs,thus advancing the development and progression of the field of single-cell analysis in the life sciences.
文摘Nowadays,Wireless Sensor Network(WSN)is a modern technology with a wide range of applications and greatly attractive benefits,for example,self-governing,low expenditure on execution and data communication,long-term function,and unsupervised access to the network.The Internet of Things(IoT)is an attractive,exciting paradigm.By applying communication technologies in sensors and supervising features,WSNs have initiated communication between the IoT devices.Though IoT offers access to the highest amount of information collected through WSNs,it leads to privacy management problems.Hence,this paper provides a Logistic Regression machine learning with the Elliptical Curve Cryptography technique(LRECC)to establish a secure IoT structure for preventing,detecting,and mitigating threats.This approach uses the Elliptical Curve Cryptography(ECC)algorithm to generate and distribute security keys.ECC algorithm is a light weight key;thus,it minimizes the routing overhead.Furthermore,the Logistic Regression machine learning technique selects the transmitter based on intelligent results.The main application of this approach is smart cities.This approach provides continuing reliable routing paths with small overheads.In addition,route nodes cooperate with IoT,and it handles the resources proficiently and minimizes the 29.95%delay.
基金supported by the National Natural Science Foundation of China(60933011,61170258)
文摘A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without decompressing. The correlation between redundancy of sensor data and compression ratio is explored. Further, a parallel compression algorithm based on MapReduce [1] is proposed. Meanwhile, data partitioner which plays an important role in performance of MapReduce application is discussed along with performance evaluation criteria proposed in this paper. Experiments demonstrate that random sampler is suitable for highly redundant sensor data and the proposed compression algorithms can compress those highly redundant sensor data efficiently.
