Diagnostic Value of the Padua Score Combined with Thrombotic Biomarker Tissue Plasminogen Activator Inhibitor-1 (tPAI-1) Detection for the Risk of Deep Vein Thrombosis in Patients with Pulmonary Heart Disease

This study explores the diagnostic value of combining the Padua score with the thrombotic biomarker tissue plasminogen activator inhibitor-1(tPAI-1)for assessing the risk of deep vein thrombosis(DVT)in patients with pulmonary heart disease.These patients often exhibit symptoms similar to venous thrombosis,such as dyspnea and bilateral lower limb swelling,complicating differential diagnosis.The Padua Prediction Score assesses the risk of venous thromboembolism(VTE)in hospitalized patients,while tPAI-1,a key fibrinolytic system inhibitor,indicates a hypercoagulable state.Clinical data from hospitalized patients with cor pulmonale were retrospectively analyzed.ROC curves compared the diagnostic value of the Padua score,tPAI-1 levels,and their combined model for predicting DVT risk.Results showed that tPAI-1 levels were significantly higher in DVT patients compared to non-DVT patients.The Padua score demonstrated a sensitivity of 82.61%and a specificity of 55.26%at a cutoff value of 3.The combined model had a significantly higher AUC than the Padua score alone,indicating better discriminatory ability in diagnosing DVT risk.The combination of the Padua score and tPAI-1 detection significantly improves the accuracy of diagnosing DVT risk in patients with pulmonary heart disease,reducing missed and incorrect diagnoses.This study provides a comprehensive assessment tool for clinicians,enhancing the diagnosis and treatment of patients with cor pulmonale complicated by DVT.Future research should validate these findings in larger samples and explore additional thrombotic biomarkers to optimize the predictive model.

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

Design of a Lightweight Compressed Video Stream-Based Patient Activity Monitoring System

Inpatient falls from beds in hospitals are a common problem.Such falls may result in severe injuries.This problem can be addressed by continuous monitoring of patients using cameras.Recent advancements in deep learning-based video analytics have made this task of fall detection more effective and efficient.Along with fall detection,monitoring of different activities of the patients is also of significant concern to assess the improvement in their health.High computation-intensive models are required to monitor every action of the patient precisely.This requirement limits the applicability of such networks.Hence,to keep the model lightweight,the already designed fall detection networks can be extended to monitor the general activities of the patients along with the fall detection.Motivated by the same notion,we propose a novel,lightweight,and efficient patient activity monitoring system that broadly classifies the patients’activities into fall,activity,and rest classes based on their poses.The whole network comprises three sub-networks,namely a Convolutional Neural Networks(CNN)based video compression network,a Lightweight Pose Network(LPN)and a Residual Network(ResNet)Mixer block-based activity recognition network.The compression network compresses the video streams using deep learning networks for efficient storage and retrieval;after that,LPN estimates human poses.Finally,the activity recognition network classifies the patients’activities based on their poses.The proposed system shows an overall accuracy of approx.99.7% over a standard dataset with 99.63% fall detection accuracy and efficiently monitors different events,which may help monitor the falls and improve the inpatients’health.

How crystal configuration affects the position detection accuracy in pixelated molecular SPECT imaging systems?

It is well known that inter-crystal scattering and penetration(ICS-P) are major spatial resolution limiting parameters in dedicated SPECT scanners with pixelated crystal.In this study,the effect of ICS-P on crystal identification in different crystal configurations was evaluated using GATE Monte Carlo simulation.A ^(99m)Tc pencil-beam toward central crystal element was utilized.Beam incident angle was assumed to vary from 0° to 45° in 5° steps.The effects of various crystal configurations such as pixel-size,pixel-gap,and crystal material were studied.The influence of photon energy on the crystal identification(CI) was also investigated.Position detection accuracy(PDA) was defined as a factor indicating performance of the crystal.Furthermore,a set of ^(99m)Tc point-source simulations was performed in order to calculate peak-to-valley(PVR) ratio for each configuration.The results show that the CsI(Na)manifests higher PDA than NaI(TI) and YAP(Ce).In addition,as the incident angle increases,the crystal becomes less accurate in positioning of the events.Beyond a crystal-dependent critical angle,the PDA monotonically reduces.The PDA reaches 0.44 for the CsI(Na) at 45° beam angle.The PDAs obtained by the point-source evaluation also behave the same as for the pencil-beam irradiations.In addition,the PVRs derived from flood images linearly correlate their corresponding PDAs.In conclusion,quantitative assessment of ICS-P is mandatory for scanner design and modeling the system matrix during iterative reconstruction algorithms for the purpose of resolution modeling in ultra-high-resolution SPECT.

Using of Synthetic Images on Accuracy Assessment of Change Detection

Land cover change detection is the major goal in multitemporal remote sensing studies. It is well known that remotely-sensed images of the same area acquired on different dates tend to be affected by radiometric differences and registration problems. These influences are considered as noise in the process and may induce the user to both： signalling false changes and masking real surface changes. The difference image produced by subtracting two co-registered images is a standard initial step in change detection algorithms. This image naturally appears to be noisier than the original ones and has at least two populations： （1） the noise-like and （2） the real changes. The problem that arises is how to discriminate them. There are several approaches to perform change detection reported in the literature and some studies have employed synthetic images. By using synthetic images, the accuracy assessment of specific algorithm can be done more accurately. The question at this point is： what is the acceptable noise level to be added on the synthetic images to simulate a real problem？ This paper attempts to answer this question by suggesting values of SNR （signal-to-noise ratio） obtained from experiments performed on TM-Landsat-5 and CCD-CBERS-2B images.

Analysis and optimization of drilling parameters for tool wear and hole dimensional accuracy in B_4C reinforced Al-alloy

Cutting parameters were evaluated and optimized based on multiple performance characteristics including tool wear and size error of drilled hole. Taguchi＇s L27, 3-level, 4-factor orthogonal array was used for the tests. It is shown that generally abrasive wear and built up edge （BUE） formation were seen in the tool wear, and the comer wear was also of major importance. Flank wear of the cutting tool was found to be mostly dependent upon particle mass fraction, followed by feed rate, drill hardness and spindle speed, respectively. Among the tools used, TiAlN coated carbide drills showed the best performance with regard to the tool wear as well as hole size. Grey relational analysis indicated that drill material was the more influential parameter than feed rate and spindle speed. The results revealed that optimal combination of the drilling parameters could be used to obtain both minimum tool wear and diametral error.

Application of Dual-Energy X-Ray Image Detection of Dangerous Goods Based on YOLOv7

X-ray security equipment is currently a more commonly used dangerous goods detection tool, due to the increasing security work tasks, the use of target detection technology to assist security personnel to carry out work has become an inevitable trend. With the development of deep learning, object detection technology is becoming more and more mature, and object detection framework based on convolutional neural networks has been widely used in industrial, medical and military fields. In order to improve the efficiency of security staff, reduce the risk of dangerous goods missed detection. Based on the data collected in X-ray security equipment, this paper uses a method of inserting dangerous goods into an empty package to balance all kinds of dangerous goods data and expand the data set. The high-low energy images are combined using the high-low energy feature fusion method. Finally, the dangerous goods target detection technology based on the YOLOv7 model is used for model training. After the introduction of the above method, the detection accuracy is improved by 6% compared with the direct use of the original data set for detection, and the speed is 93FPS, which can meet the requirements of the online security system, greatly improve the work efficiency of security personnel, and eliminate the security risks caused by missed detection.

Object detection of artifact threaded hole based on Faster R-CNN

In order to improve the accuracy of threaded hole object detection,combining a dual camera vision system with the Hough transform circle detection,we propose an object detection method of artifact threaded hole based on Faster region-ased convolutional neural network(Faster R-CNN).First,a dual camera image acquisition system is established.One industrial camera placed at a high position is responsible for collecting the whole image of the workpiece,and the suspected screw hole position on the workpiece can be preliminarily selected by Hough transform detection algorithm.Then,the other industrial camera is responsible for collecting the local images of the suspected screw holes that have been detected by Hough transform one by one.After that,ResNet50-based Faster R-CNN object detection model is trained on the self-built screw hole data set.Finally,the local image of the threaded hole is input into the trained Faster R-CNN object detection model for further identification and location.The experimental results show that the proposed method can effectively avoid small object detection of threaded holes,and compared with the method that only uses Hough transform or Faster RCNN object detection alone,it has high recognition and positioning accuracy.

Influence of Range Gate Width on Detection Probability and Ranging Accuracy of Single Photon Laser Altimetry Satellite

The influence of the single photon laser altimeter range-gate width on the detection probability and ranging accuracy is discussed and analyzed,according to the LiDAR equation,single photon detection equation and the Monte Carlo method to simulate the experiment.The simulated results show that the probability of detection is not affected by the range gate,while the probability of false alarm is relative to the gate width.When the gate width is 100 ns,the ranging accuracy can accord with the requirements of satellite laser altimeter.But when the range gate width exceeds 400 ns,ranging accuracy will decline sharply.The noise ratio will be more as long as the range gate to get larger,so the refined filtering algorithm during the data processing is important to extract the useful photons effectively.In order to ensure repeated observation of the same point for 25 times,we deduce the quantitative relation between the footprint size,footprint,and frequency repetition according to the parameters of ICESat-2.The related conclusions can provide some references for the design and the development of the domestic single photon laser altimetry satellite.

A Secure Framework for WSN-IoT Using Deep Learning for Enhanced Intrusion Detection

The security of the wireless sensor network-Internet of Things(WSN-IoT)network is more challenging due to its randomness and self-organized nature.Intrusion detection is one of the key methodologies utilized to ensure the security of the network.Conventional intrusion detection mechanisms have issues such as higher misclassification rates,increased model complexity,insignificant feature extraction,increased training time,increased run time complexity,computation overhead,failure to identify new attacks,increased energy consumption,and a variety of other factors that limit the performance of the intrusion system model.In this research a security framework for WSN-IoT,through a deep learning technique is introduced using Modified Fuzzy-Adaptive DenseNet(MF_AdaDenseNet)and is benchmarked with datasets like NSL-KDD,UNSWNB15,CIDDS-001,Edge IIoT,Bot IoT.In this,the optimal feature selection using Capturing Dingo Optimization(CDO)is devised to acquire relevant features by removing redundant features.The proposed MF_AdaDenseNet intrusion detection model offers significant benefits by utilizing optimal feature selection with the CDO algorithm.This results in enhanced Detection Capacity with minimal computation complexity,as well as a reduction in False Alarm Rate(FAR)due to the consideration of classification error in the fitness estimation.As a result,the combined CDO-based feature selection and MF_AdaDenseNet intrusion detection mechanism outperform other state-of-the-art techniques,achieving maximal Detection Capacity,precision,recall,and F-Measure of 99.46%,99.54%,99.91%,and 99.68%,respectively,along with minimal FAR and Mean Absolute Error(MAE)of 0.9%and 0.11.

Implementation of a Multi-sampling-frequency System for RR-interval Timing and Blood Pressure Detection

In order to analyze the experimental cardiovascular signal with high accuracy, a system, integrating real-time monitoring and off-line further analysis, was developed and verified. The design, data processing and analysis methods as well as testing results are described. With 5 sampling frequency choices and 8 channel data acquisition, the system achieved high performances in beat-to-beat monitoring, signal processing and analysis. Tests were carried out to validate its performance in real-time monitoring, effectiveness of digital filters, QRS and blood pressure detection reliability, and RR-interval timing accuracy. The QRS detection rate was at least 99.46% for the records with few noises from MIT-BIH arrhythmia database using the algorithm for real-time monitoring, and no less than 96.43% for the records with some noises. In the condition that noise amplitude levels were less than 80%,the standard deviations for RR-interval timing were less than 1 ms with a generated ECG corrupted with various noises from MIT-BIH Noise Stress Test Database. Besides, the system is open for function expansion to meet further study-specific needs.

Coordinate-free k-coverage hole detection algorithm in wireless sensor networks

For wireless sensor networks, a simple and accurate coordinate-free k-coverage hole detection scheme is proposed. First, an algorithm is presented to detect boundary cycles of 1-coverage holes. The algorithm consists of two components, named boundary edge detection and boundary cycle detection. Then, the 1-coverage hole detection algorithm is extended to k-coverage hole scenarios. A coverage degree reduction scheme is proposed to find an independent covering set of nodes in the covered region of the target field and to reduce the coverage degree by one through sleeping those nodes. Repeat the 1-coverage hole detection algorithm and the higher order of coverage holes can be found. By iterating the above steps for k-1 times, the boundary edges and boundary cycles of all k-coverage holes can be discovered. Finally, the proposed algorithm is compared with a location-based coverage hole detection algorithm. Simulation results indicate that the proposed algorithm can accurately detect over 99% coverage holes.

Black Hole and Sink Hole Attack Detection in Wireless Body Area Networks

In Wireless Body Area Networks(WBANs)with respect to health care,sensors are positioned inside the body of an individual to transfer sensed data to a central station periodically.The great challenges posed to healthcare WBANs are the black hole and sink hole attacks.Data from deployed sensor nodes are attracted by sink hole or black hole nodes while grabbing the shortest path.Identifying this issue is quite a challenging task as a small variation in medicine intake may result in a severe illness.This work proposes a hybrid detection framework for attacks by applying a Proportional Coinciding Score(PCS)and an MK-Means algorithm,which is a well-known machine learning technique used to raise attack detection accuracy and decrease computational difficulties while giving treatments for heartache and respiratory issues.First,the gathered training data feature count is reduced through data pre-processing in the PCS.Second,the pre-processed features are sent to the MK-Means algorithm for training the data and promoting classification.Third,certain attack detection measures given by the intrusion detection system,such as the number of data packages trans-received,are identified by the MK-Means algorithm.This study demonstrates that the MK-Means framework yields a high detection accuracy with a low packet loss rate,low communication overhead,and reduced end-to-end delay in the network and improves the accuracy of biomedical data.

Application of Weighted Cross-Entropy Loss Function in Intrusion Detection

The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.

Monitoring Land Cover Change Using Remote Sensing (RS) and Geographical Information System (GIS): A Case of Golden Pride and Geita Gold Mines, Tanzania

This study monitored land cover change in the mining sites of Golden Pride Gold Mine (GPGM) and Geita Gold Mine (GGM), Tanzania. The satellite data for land cover classification for the years 1997, 2010 and 2017 were obtained from the United States Geologic Survey Departments (USGS) online database and were analyzed using Arc GIS 10 software. Supervised classification composed of seven classes namely forest, bushland, agriculture, water, bare soil, urban area and grassland, was designed for this study, in order to classify Landsat images into thematic maps. In addition, future land cover changes for the year 2027 were simulated using a Cellular Automata (CA)-Markov model after validating the model using the Land Cover for the year 2017. The results from the LULC analysis showed that forest was the most dominant land cover type in 1997 at GPGM and GGM covering 510 ha (52.1%) and 9833 ha (49.7%) respectively. In 2017, the forest area decreased and the bushland replaced forest to be the most dominant land cover type covering 219 ha (22.4%) for GPGM and 8878 ha (44.9%) for GGM. Based on the CA-Markov model, a predicted land cover map for 2027 was dominated by forest covering 340 ha (34.7%) and 8639 ha (43.7%) for GPGM and GGM respectively. An overall accuracy and kappa coefficient for GPGM were 74.7% and 70.2% respectively and for GGM were 71.4% and 66.1% respectively. Thus, land cover changes resulting from mining activities involve reduction of forest land hence endangers biodiversity. GIS and remote sensing technologies are potential to detect the trend of changes and predict future land cover. The findings are crucial as it provides basis for land use planning and intensifies monitoring programs in the mining areas of Tanzania.

Change Detection of Land Use and Land Cover over a Period of 20 Years in Papua New Guinea

People have an inherent tenacity to throng coastal regions in pursuit of better living conditions. As such the brisk dynamism of land use/land cover activities in a coastal region becomes obvious. The former keeps changing rapidly due to burgeoning population. A digital change detection analysis is performed with the help of Geographic Information System (GIS) on the Remote Sensing data spanning over last 20 years, complemented by in-situ data and ground truth information. This current research briefly endeavours to find out the nature of change happening in the major three coastal cities of Papua New Guinea (PNG), namely Alotau, capital of Milnebay province;Lae, capital of Morobe province and Port Moresby, capital of Papua New Guinea. Changes in land use and land cover that took place over 20 years have been recorded using Landsat 5 thematic mapper (TM) data of 1992 and Landsat 8 operational land imager (OLI) data. Land use and land cover maps of 1992, and 2013/14, and change detection matrix of 1992-2013/14 are derived. Results show an immensely sprawling urban landscape, evincing about five times growth during 1992 to 2014. At the same time “natural forests” dwindled by 444.96 hectares in Alotau, 6977.25 hectares in Lae and “mangrove” and “grass/shrub land” decreased by 127.78 and 4859.39 hectares respectively around Port Moresby. The above changes owe to ever increasing population pressure, land tenure shift, agriculture and industrial development.

In-Line Inspection of Pipeline Defects Detection Using Ring-Type Laser

Pipeline plays a vital role in transporting fluids like oils, water, and petrochemical substances for longer distances. Based on the materials they carry, prolonged usage may cause the initiation of defects in the pipeline. These defects occur due to the formed salt deposits, chemical reaction happens between the inner surface and the transferring substance, prevailing environmental conditions, etc. These defects, if not identified earlier may lead to significant losses to the industry. In this work, an in-line inspection system utilizes the nondestructive way for analyzing the internal defects in the petrochemical pipeline. This system consists of a pipeline inspection robot having two major units namely the visual inspection unit and the power carrier unit. The visual inspection unit makes use of a ring-type laser diode and the camera. The laser diode serves as a light source for capturing good quality images of inspection. This unit is controlled by the Arduino in the power carrier unit which provides the necessary movement throughout the pipe. The inspected images captured by the camera are further processed with the aid of NI vision assistant software. After applying the processing function parameters provided by this software, the defect location can be clearly visualized with high precision. Three sets of defects are introduced in a Polylactide (PLA) pipe based on its position and angle along the circumference of the pipe. Further, this robot system serves as a real-time interactive image synchronization system for acquiring the inspected images. By comparing the actual and calculated defect size, the error percentage obtained was less than 5%.

Analysis on the Characteristics of GPS-PWV during Heavy Rainfall in Huaihua Region

Using GPS precipitable water vapor( GPS-PWV) inverted based on the advanced ZHD model and localized T_m model,as well as hourly meteorological data from automatic weather station,the variation characteristics of atmospheric water vapor and evolution features of GPS-PWV during 14 heavy rainfall events at Huaihua in 2017 were analyzed. As the results shown,GPS-PWV could reveal the variation characteristics of atmospheric water vapor in Huaihua region well. The monthly change of precipitable water vapor-pressure( PWV-P) data pair was evident. The PWV appeared a lower value with a smaller range accompanied by a 14.75 hPa higher surface air pressure than that in summer when precipitation occurred during winter,which gradually increased with a lower surface air pressure while precipitation occurred during spring. In summer,the PWV rose to the annual peak value with the lowest surface air pressure under rainfall,and it scattered to low-value area in autumn. In 14 heavy rainfall events at Huaihua during flood season of 2017,all of the PWV values exceeded corresponding monthly mean,besides there was a well corresponded relationship between the maximum rainfall and the maximum PWV in hourly scale. Before the heavy rainfall occurred,the PWV increased comparatively distinctly with a clear decrease of the surface air pressure,and that could be a preferably reference point in the local strong precipitation nowcasting.

Algorithm of Detecting and Filling Small Holes in Triangular Mesh Surface

In some scattered point cloud triangular mesh restoration algorithm, small triangular mesh holes problem will often affect the quality of the model. For small holes at the details, this paper propose a method for identifying and extracting hollow edge,and use a triangle growth way based on boundary edge angle to fill the empty void. First, according the relationship of the point, side and face of the triangle mesh model to identify the hole, then extracting the holes boundary edge and classifying it. Finally, using a triangle growth method based on holes boundary edge angle to fill each small holes separated from the boundary. Compared with other algorithm of filling holes, this method is high efficiency for small holes of smooth surface,and itimprovesthe quality of the triangular mesh model.

A DEVELOPMENT OF MICROCOMPUTER-BASED MULTICHANNEL DIGITAL THERMOMETER

In this paper, the construction and performance of the microprocessor-based multi-chan-nel digital thermometric instrument together with its deisgn and fabrication are systematicallydescribed. The principle, method and practical softwares for the entire reference-junction com-pensation processing by microcomputer and the linearization of the characteristic ofthermocouples are also exhaustively expounded with a detailed analysis of the error existing inthe thermometric instrument. The practiced result shows that the apparatus is featured with asimple construction, high accuracy and high ability of anti-disturbance. It is proved to be ofpractical value.