Face Recognition Based on Convolution Neural Network (CNN) Applications in Image Processing: A Survey

Sharma, Sudha; Soni, Alpesh; Malviya, Vijay

doi:10.2139/ssrn.3372193

Cited by 9 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adopted CNN is a network that imitates human visual mechanisms and simulates the function of neurons in the human brain through a multilayer convolution kernel. It has been proved that it has better performance than humans in face recognition (Sharma et al, 2019), medical images (Razzak et al, 2018) and so on.…”

Section: Technology Descriptionmentioning

confidence: 99%

Artificial intelligence‐based intelligent surveillance for reducing nurses' working hours in nurse–patient interaction: A two‐wave study

Huang

Jiao

Cai

et al. 2022

J Nursing Management

View full text Add to dashboard Cite

Aim To explore the feasibility of applying artificial intelligence in nurse–patient interaction to assist nurses in grasping patient status and reducing their working hours. Background Artificial intelligence has been reshaping the health care industry and has immense potential in nursing care, but there is still a lack of suitable artificial intelligence methods to improve the efficiency of the nurse–patient interaction that takes much time of nurses. Methods An artificial intelligence‐based intelligent surveillance system was developed to reduce nurses' working hours in nurse–patient interaction, and a two‐wave follow‐up design was adopted in this study. The data were collected in a nursing home in Guangzhou, China. The first and second waves of data were recorded in the same format on the same patients by the same nurses. The only difference is the deployment of artificial intelligence technology between the two waves of data. Results Artificial intelligence‐based intelligent surveillance can provide statistical health data for nurses to grasp the patients' status more intuitively, reducing the average nurse–patient interaction time per patient from 18 to 10 min. In addition, artificial intelligence's real‐time response to the abnormal health status of patients not only avoids more serious secondary injuries for patients but also prevents nurses from consuming energy in detecting emergencies. Conclusion The application of artificial intelligence has great potential to reduce nurses' working hours in nurse–patient interaction. There are still many limitations in artificial intelligence technology at this stage, and it is not feasible to completely rely on artificial intelligence. However, as a tool to assist decision‐making, it can still have beneficial impacts on nursing management. Implications for Nursing Management Artificial intelligence has great potential in daily nurse–patient interaction, and nursing facility managers and nurses need to be more open to this new technology.

show abstract

Section: Technology Descriptionmentioning

confidence: 99%

Artificial intelligence‐based intelligent surveillance for reducing nurses' working hours in nurse–patient interaction: A two‐wave study

Huang

Jiao

Cai

et al. 2022

J Nursing Management

View full text Add to dashboard Cite

show abstract

“…It is an end-to-end deep learning model with powerful feature learning and classification capabilities. It is widely used in image classification, speech recognition, computer vision, and other fields [32].…”

Section: Hybrid-cnnmentioning

confidence: 99%

“…Each column is a model. e input data shape of the DNN part of our proposed hybrid CNN model is (42,1), the data shape through Dense1 is (42,128), the data shape through Dense_2 is (42,64), and then the data shape through Flatten_1 is (2688), the shape of the input data of the CNN is (6,7) through the Conv1D_1 layer, the shape of the data becomes (4,32), followed by Pooling_1, and the shape of the data becomes (2,32). In the Merge layer, the two-channel data are merged into one.…”

Section: Performance Metricsmentioning

confidence: 99%

“…Feature name Category (1) dur Numeric (2) Proto Nonnumeric (3) service Nonnumeric (4) state No-numeric (5) spkts Numeric (6) dpkts Numeric (7) sbytes Numeric (8) dbytes Numeric (9) rate Numeric (10) sttl Numeric (11) dttl Numeric (12) sload Numeric (13) dload Numeric (14) sloss Numeric (15) dloss Numeric (16) sinpakt Numeric (17) dinpakt Numeric (18) sjit Numeric (19) djit Numeric (20) swin Numeric (21) dwin Numeric (22) stcpb Numeric (23) dtcpb Numeric (24) tcprtt Numeric (25) synack Numeric (26) ackdat Numeric (27) smean Numeric (28) dmean Numeric (29) trans_depth Numeric (30) response_body_len Numeric (31) ct_srv_src Numeric (32) ct_state_ttl Numeric (33) ct_dst_ltm Numeric (34) ct_src_dport_ltm Numeric (35) ct_dst_sport_ltm Numeric (36) ct_dst_src_ltm Numeric (37) is_ftp_login Numeric (38) ct_ftp_cmd Table 4 lists the performance comparison between our proposed HYBRID-CNN and some other existing methods. It is worth noting that we select a subset for experiments based on a certain training dataset ratio.…”

Section: Nomentioning

confidence: 99%

See 1 more Smart Citation

HYBRID-CNN: An Efficient Scheme for Abnormal Flow Detection in the SDN-Based Smart Grid

Ding

Wang

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

Software-Defined Network (SDN) can improve the performance of the power communication network and better meet the control demand of the Smart Grid for its centralized management. Unfortunately, the SDN controller is vulnerable to many potential network attacks. The accurate detection of abnormal flow is especially important for the security and reliability of the Smart Grid. Prior works were designed based on traditional machine learning methods, such as Support Vector Machine and Naive Bayes. They are simple and shallow feature learning, with low accuracy for large and high-dimensional network flow. Recently, there have been several related works designed based on Long Short-Term Memory (LSTM), and they show excellent ability on network flow analysis. However, these methods cannot get the deep features from network flow, resulting in low accuracy. To address the above problems, we propose a Hybrid Convolutional Neural Network (HYBRID-CNN) method. Specifically, the HYBRID-CNN utilizes a Deep Neural Network (DNN) to effectively memorize global features by one-dimensional (1D) data and utilizes a CNN to generalize local features by two-dimensional (2D) data. Finally, the proposed method is evaluated by experiments on the datasets of UNSW_NB15 and KDDCup 99. The experimental results show that the HYBRID-CNN significantly outperforms existing methods in terms of accuracy and False Positive Rate (FPR), which successfully demonstrates that it can effectively detect abnormal flow in the SDN-based Smart Grid.

show abstract

“…This loop structure is also found in other widely used numerical methods (e.g., boundary element methods [8]) and applications related to electromagnetism such as, radiated/scattered field, and other fields. There are other fields where we can find the same structure: convolutional neural networks [9], face recognition [10], image processing [11], data spectroscopy [12], among others. These operations are a good example of many algorithms whose parallelism can be naturally exploited both on multi-core CPUs and on many-core GPUs [11,13,14].…”

Section: Introductionmentioning

confidence: 99%

Strategies to parallelize a finite element mesh truncation technique on multi-core and many-core architectures

et al. 2022

View full text Add to dashboard Cite

Achieving maximum parallel performance on multi-core CPUs and many-core GPUs is a challenging task depending on multiple factors. These include, for example, the number and granularity of the computations or the use of the memories of the devices. In this paper, we assess those factors by evaluating and comparing different parallelizations of the same problem on a multiprocessor containing a CPU with 40 cores and four P100 GPUs with Pascal architecture. We use, as study case, the convolutional operation behind a non-standard finite element mesh truncation technique in the context of open region electromagnetic wave propagation problems. A total of six parallel algorithms implemented using OpenMP and CUDA have been used to carry out the comparison by leveraging the same levels of parallelism on both types of platforms. Three of the algorithms are presented for the first time in this paper, including a multi-GPU method, and two others are improved versions of algorithms previously developed by some of the authors. This paper presents a thorough experimental evaluation of the parallel algorithms on a radar cross-sectional prediction problem. Results show that performance obtained on the GPU clearly overcomes those obtained in the CPU, much more so if we use multiple GPUs to distribute both data and computations. Accelerations close to 30 have been obtained on the CPU, while with the multi-GPU version accelerations larger than 250 have been achieved.

show abstract

Face Recognition Based on Convolution Neural Network (CNN) Applications in Image Processing: A Survey

Cited by 9 publications

References 10 publications

Artificial intelligence‐based intelligent surveillance for reducing nurses' working hours in nurse–patient interaction: A two‐wave study

Artificial intelligence‐based intelligent surveillance for reducing nurses' working hours in nurse–patient interaction: A two‐wave study

HYBRID-CNN: An Efficient Scheme for Abnormal Flow Detection in the SDN-Based Smart Grid

Strategies to parallelize a finite element mesh truncation technique on multi-core and many-core architectures

Contact Info

Product

Resources

About