scholarly journals Real-Time Detection of Concealed Threats with Passive Millimeter Wave and Visible Images Via Deep Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8456
Author(s):  
Hao Yang ◽  
Dinghao Zhang ◽  
Shiyin Qin ◽  
Tiejun Cui ◽  
Jungang Miao
Keyword(s):  
Millimeter Wave ◽  
Semantic Segmentation ◽  
High Rate ◽  
False Alarms ◽  
Privacy Concerns ◽  
Synthetic Strategy ◽  
Precise Shape ◽  
Visible Images ◽  
Security Inspection ◽  
Segmentation Image

Passive millimeter wave has been employed in security inspection owing to a good penetrability to clothing and harmlessness. However, the passive millimeter wave images (PMMWIs) suffer from low resolution and inherent noise. The published methods have rarely improved the quality of images for PMMWI and performed the detection only based on PMMWI with bounding box, which cause a high rate of false alarm. Moreover, it is difficult to identify the low-reflective non-metallic threats by the differences in grayscale. In this paper, a method of detecting concealed threats in human body is proposed. We introduce the GAN architecture to reconstruct high-quality images from multi-source PMMWIs. Meanwhile, we develop a novel detection pipeline involving semantic segmentation, image registration, and comprehensive analyzer. The segmentation network exploits multi-scale features to merge local and global information together in both PMMWIs and visible images to obtain precise shape and location information in the images, and the registration network is proposed for privacy concerns and the elimination of false alarms. With the grayscale and contour features, the detection for metallic and non-metallic threats can be conducted, respectively. After that, a synthetic strategy is applied to integrate the detection results of each single frame. In the numerical experiments, we evaluate the effectiveness of each module and the performance of the proposed method. Experimental results demonstrate that the proposed method outperforms the existing methods with 92.35% precision and 90.3% recall in our dataset, and also has a fast detection rate.

scholarly journals Identifying the Branch of Kiwifruit Based on Unmanned Aerial Vehicle (UAV) Images Using Deep Learning Method

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4442
Author(s):  
Zijie Niu ◽  
Juntao Deng ◽  
Xu Zhang ◽  
Jun Zhang ◽  
Shijia Pan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Unmanned Aerial Vehicle ◽  
Semantic Segmentation ◽  
Dynamic Monitoring ◽  
Support Vector ◽  
Distribution Maps ◽  
Time Operation ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Segmentation Image

It is important to obtain accurate information about kiwifruit vines to monitoring their physiological states and undertake precise orchard operations. However, because vines are small and cling to trellises, and have branches laying on the ground, numerous challenges exist in the acquisition of accurate data for kiwifruit vines. In this paper, a kiwifruit canopy distribution prediction model is proposed on the basis of low-altitude unmanned aerial vehicle (UAV) images and deep learning techniques. First, the location of the kiwifruit plants and vine distribution are extracted from high-precision images collected by UAV. The canopy gradient distribution maps with different noise reduction and distribution effects are generated by modifying the threshold and sampling size using the resampling normalization method. The results showed that the accuracies of the vine segmentation using PSPnet, support vector machine, and random forest classification were 71.2%, 85.8%, and 75.26%, respectively. However, the segmentation image obtained using depth semantic segmentation had a higher signal-to-noise ratio and was closer to the real situation. The average intersection over union of the deep semantic segmentation was more than or equal to 80% in distribution maps, whereas, in traditional machine learning, the average intersection was between 20% and 60%. This indicates the proposed model can quickly extract the vine distribution and plant position, and is thus able to perform dynamic monitoring of orchards to provide real-time operation guidance.

Design and synthesis of interconnected hierarchically porous anatase titanium dioxide nanofibers as high-rate and long-cycle-life anodes for lithium-ion batteries

Nanoscale ◽  
2018 ◽  
Vol 10 (28) ◽  
pp. 13539-13547 ◽  
Author(s):  
Min Su Jo ◽  
Gi Dae Park ◽  
Yun Chan Kang ◽  
Jung Sang Cho
Keyword(s):  
Titanium Dioxide ◽  
Lithium Ion Batteries ◽  
Anode Materials ◽  
Lithium Ion ◽  
Cycle Life ◽  
High Rate ◽  
Hierarchically Porous ◽  
Long Cycle Life ◽  
Design And Synthesis ◽  
Synthetic Strategy

An efficient and simple synthetic strategy to prepare interconnected hierarchically porous anatase TiO2 nanofibers as anode materials for LIBs is introduced.

Visualization Technique for Intrusion Detection

2018 ◽  
pp. 276-290
Author(s):  
Mohamed Cheikh ◽  
Salima Hacini ◽  
Zizette Boufaida
Keyword(s):  
Intrusion Detection ◽  
Computer Security ◽  
Detection System ◽  
Denial Of Service ◽  
High Rate ◽  
False Alarms ◽  
Dos Attacks ◽  
Network Parameter ◽  
A New Technique ◽  
Parameter Values

Intrusion detection system (IDS) plays a vital and crucial role in a computer security. However, they suffer from a number of problems such as low detection of DoS (denial-of-service)/DDoS (distributed denial-of-service) attacks with a high rate of false alarms. In this chapter, a new technique for detecting DoS attacks is proposed; it detects DOS attacks using a set of classifiers and visualizes them in real time. This technique is based on the collection of network parameter values (data packets), which are automatically represented by simple geometric graphs in order to highlight relevant elements. Two implementations for this technique are performed. The first is based on the Euclidian distance while the second is based on KNN algorithm. The effectiveness of the proposed technique has been proven through a simulation of network traffic drawn from the 10% KDD and a comparison with other classification techniques for intrusion detection.

scholarly journals Boater Safety: Communicating Weather Forecast Information to High-Stakes End Users

2012 ◽  
Vol 4 (1) ◽  
pp. 7-19 ◽  
Author(s):  
Sonia Savelli ◽  
Susan Joslyn
Keyword(s):  
Pacific Northwest ◽  
Online Survey ◽  
Puget Sound ◽  
Weather Forecast ◽  
High Rate ◽  
False Alarms ◽  
High Stakes ◽  
Precautionary Action ◽  
Time Of Year ◽  
Almost All

Abstract Recreational boaters in the Pacific Northwest understand that there is uncertainty inherent in deterministic forecasts as well as some of the factors that increase uncertainty. This was determined in an online survey of 166 boaters in the Puget Sound area. Understanding was probed using questions that asked respondents what they expected to observe when given a deterministic forecast with a specified lead time, for a particular weather parameter, during a particular time of year. It was also probed by asking respondents to estimate the number of observations, out of 100 or out of 10, that they expected to fall within specified ranges around the deterministic forecast. Almost all respondents anticipated some uncertainty in the deterministic forecast as well as specific biases, most of which were born out by an analysis of local National Weather Service verification data. Interestingly, uncertainty and biases were anticipated for categorical forecasts indicating a range of values as well, suggesting that specifying numeric uncertainty would improve understanding. Furthermore, respondents’ answers suggested that they expected a high rate of false alarms among warning and advisory forecasts. Nonetheless, boaters indicated that they would take precautionary action in response to such warnings, in proportions related to the size of boat they were operating. This suggests that uncertainty forecasts would be useful to these experienced forecast consumers, allowing them to adapt the forecast to their specific boating situation with greater confidence.

scholarly journals Real‐Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks

2021 ◽  
Author(s):  
Sandeep Chandra Bollepalli ◽  
Rahul K. Sevakula ◽  
Wan‐Tai M. Au‐Yeung ◽  
Mohamad B. Kassab ◽  
Faisal M. Merchant ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
High Rate ◽  
Superior Performance ◽  
False Alarms ◽  
Arrhythmia Detection ◽  
Arterial Blood ◽  
Life Threatening

Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life‐threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid‐ convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5‐fold cross‐validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.

Text Separation From Document Images

2020 ◽  
pp. 283-313
Author(s):  
Priti P. Rege ◽  
Shaheera Akhter
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Semantic Segmentation ◽  
Document Image ◽  
Training Data ◽  
Document Images ◽  
Learning Techniques ◽  
Extraction Processes ◽  
Segmentation Image

Text separation in document image analysis is an important preprocessing step before executing an optical character recognition (OCR) task. It is necessary to improve the accuracy of an OCR system. Traditionally, for separating text from a document, different feature extraction processes have been used that require handcrafting of the features. However, deep learning-based methods are excellent feature extractors that learn features from the training data automatically. Deep learning gives state-of-the-art results on various computer vision, image classification, segmentation, image captioning, object detection, and recognition tasks. This chapter compares various traditional as well as deep-learning techniques and uses a semantic segmentation method for separating text from Devanagari document images using U-Net and ResU-Net models. These models are further fine-tuned for transfer learning to get more precise results. The final results show that deep learning methods give more accurate results compared with conventional methods of image processing for Devanagari text extraction.

Elimination of Position-Change Alarms in an Alzheimer’s and Dementia Long-Term Care Facility

2011 ◽  
Vol 26 (8) ◽  
pp. 599-605 ◽  
Author(s):  
Katrina Bressler ◽  
Roberta E.Redfern ◽  
Megan Brown
Keyword(s):  
Health Care ◽  
Long Term Care ◽  
Care Facility ◽  
High Rate ◽  
False Alarms ◽  
Position Change ◽  
Term Care ◽  
Term Care Facility ◽  
Long Term Care Facility

In a long-term care facility, whose residents have been diagnosed with Alzheimer’s disease or dementia, falls are a particularly prominent issue. Technology in health care has continued to evolve and play a larger role in how we care for our patients, even in preventing falls. However, overreliance on these types of technologies may have detrimental effects. In our facility, it was felt that staff reliance on position-change alarms was inappropriate due to the high rate of false alarms associated with these devices. We took a tiered approach to removing position-change alarms from our facility, monitoring the fall incidence rate for a period before, during, and after the elimination of these alarms. After discontinuing their use, we found a decrease in the rate of falls, and a decrease in the percentage of our residents who fell. Staff has easily adapted and reports a calmer, more pleasant environment.

scholarly journals CEPTM: A Cross-Edge Model for Diverse Personalization Service and Topic Migration in MEC

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Hongchen Wu ◽  
Huaxiang Zhang ◽  
Lizhen Cui ◽  
Xinjun Wang
Keyword(s):  
Information Disclosure ◽  
Management Strategies ◽  
Mobile User ◽  
High Rate ◽  
Privacy Concern ◽  
Self Disclosure ◽  
Privacy Concerns ◽  
Individual Privacy ◽  
Computing Paradigm ◽  
User Data

For several reasons, the cloud computing paradigm, e.g., mobile edge computing (MEC), is suffering from the problem of privacy issues. MEC servers provide personalization services to mobile users for better QoE qualities, but the ongoing migrated data from the source edge server to the destination edge server cause users to have privacy concerns and unwillingness of self-disclosure, which further leads to a sparsity problem. As a result, personalization services ignore valuable user profiles across edges where users have accounts in and tend to predict users’ potential purchases with insufficient sources, thereby limiting further improvement of QoE through personalization of the contents. This paper proposes a novel model, called CEPTM, which (1) collects mobile user data across multiple MEC edge servers, (2) improves the users’ experience in personalization services by loading collected diverse data, and (3) lowers their privacy concern with the improved personalization. This model also reveals that famous topics in one edge server can migrate into several other edge servers with users’ favorite content tags and that the diverse types of items could increase the possibility of users accepting the personalization service. In the experiment section, we use exploratory factor analysis to mathematically evaluate the correlations among those factors that influence users’ information disclosure in the MEC network, and the results indicate that CEPTM (1) achieves a high rate of personalization acceptance due to the availability of more data as input and highly diverse personalization as output and (2) gains the users’ trust because it collects user data while respecting individual privacy concerns and providing better personalization. It outperforms a traditional personalization service that runs on a single-edge server. This paper provides new insights into MEC diverse personalization services and privacy problems, and researchers and personalization providers can apply this model to merge popular users’ like trends throughout the MEC edge servers and generate better data management strategies.

scholarly journals On the Feasibility of High Speed Railway mmWave Channels in Tunnel Scenario

2017 ◽  
Vol 2017 ◽  
pp. 1-17 ◽  
Author(s):  
Guangkai Li ◽  
Bo Ai ◽  
Danping He ◽  
Zhangdui Zhong ◽  
Bing Hui ◽  
...  
Keyword(s):  
Millimeter Wave ◽  
Communication Systems ◽  
High Speed ◽  
Radio Channel ◽  
Wide Band ◽  
Directional Antenna ◽  
Propagation Loss ◽  
High Rate ◽  
Railway Tunnel ◽  
High Data

Rail traffic is widely acknowledged as an efficient and green transportation pattern and its evolution attracts a lot of attention. However, the key point of the evolution is how to develop the railway services from traditional handling of the critical signaling applications only to high data rate applications, such as real-time videos for surveillance and entertainments. The promising method is trying to use millimeter wave which includes dozens of GHz bandwidths to bridge the high rate demand and frequency shortage. In this paper, the channel characteristics in an arched railway tunnel are investigated owing to their significance of designing reliable communication systems. Meantime, as millimeter wave suffers from higher propagation loss, directional antenna is widely accepted for designing the communication system. The specific changes that directional antenna brings to the radio channel are studied and compared to the performances of omnidirectional antenna. Note that the study is based on enhanced wide-band ray tracing tool where the electromagnetic and scattering parameters of the main materials of the tunnel are measured and fitted with predicting models.

Sign in / Sign up

Export Citation Format

Share Document