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.

Detection and Analysis of Routine Blood Indexes in Guike Pig

[Objectives] In this study,routine blood indexes of Guike pig were detected to clarify quantity variation and morphology distribution of different functional cells（ red blood cells,white blood cells and platelets）,thus providing reference data for immunological evaluation and disease resistance research of Guike pig. [Methods] Blood samples were collected from forty-four 49-day-old healthy Guike pigs（ 22 males and 22 females） once a week for seven consecutive weeks to detect routine blood indexes,and the results were compared with routine blood indexes of Landrace pig and Enshi black pig. [Results]Among red blood cell indexes of Guike pig at different day ages,red blood cell count（ RBC） and hemoglobin count（ HGB） both reached the lowest levels（ 6. 85 × 10^12/L and 97. 1 g/L）at 70 days of age,which were significantly lower than the corresponding indexes at 49,56,63,84 and 91 days of age（ P 〈 0. 05,similarly hereinafter）; mean corpuscular hemoglobin（ MCH） and mean corpuscular hemoglobin concentration（ MCHC） demonstrated basically the same variation pattern,which both reached the lowest levels（ 15. 11 pg and 275. 70 g/L） at 70 days of age and reached the highest levels（ 16. 40 pg and 314. 30 g/L） at 91 days of age; hematocrit（ HCT）,mean corpuscular volume（ MCV） and red blood cell distribution width（ RDW） exhibited relatively stable changes with no significant differences among different day ages（ P 〉 0. 05,similarly hereinafter）. Among white blood cell indexes of Guike pig at different day ages,white blood cell count（ WBC） reached the lowest level（ 13. 71 × 10^9/L） at 63 days of age and reached the highest level（ 17. 52 × 10^9/L） at 84 days of age,with significant differences; neutrophil count（ NEUT）reached the lowest level（ 3. 61 × 10^9/L） at 70 days of age,which was significantly lower than that at 49,56 and 77 days of age; lymphocyte count（ LYMPH） exhibited relatively stable changes and was not significantly affected by the increase in day age. Among platelet indexes of Guike pig at different day ages,platelet count（ PLT）,thrombocytocrit（ PCT） and platelet volume distribution width（ PDW） exhibited relatively stable changes among different day ages,which were not significantly affected by the increase in day age. Compared to 35-day-old Landrace pig and 5-month-old Enshi black pig,most routine blood indexes of Guike pig were similar to or ranged between those of Landrace pig and Enshi black pig except HCT,mean platelet volume（ MPV）,PCT and PDW. [Conclusions]Guike pig has a certain uniqueness in routine blood indexes,which has developed a stable immune system at 49-91 days of age.

Detection and Analysis of Ebola Virus in Sierra Leone-China Friendship Biosafety Laboratory from March 11 to April 20, 2015

Ebola virus disease reemerged in Western Africa in 2014.Chinese Center for Disease Control and Prevention dispatched the first Ebola virus（EBOV）detection team to run newly established Sierra Leone-China Friendship Biological Safety Laboratory.The aims of study were to understand epidemiology,clinical manifestations and survival time of EBOV in patient＇s blood.A total of 913specimens were tested between March 11 and April20, 2015. EBOV positivity occurred in 7.37% of the blood and 0.53% in throat swabs.

An aligned mixture probabilistic principal component analysis for fault detection of multimode chemical processes

A novel approach named aligned mixture probabilistic principal component analysis(AMPPCA) is proposed in this study for fault detection of multimode chemical processes. In order to exploit within-mode correlations,the AMPPCA algorithm first estimates a statistical description for each operating mode by applying mixture probabilistic principal component analysis(MPPCA). As a comparison, the combined MPPCA is employed where monitoring results are softly integrated according to posterior probabilities of the test sample in each local model. For exploiting the cross-mode correlations, which may be useful but are inadvertently neglected due to separately held monitoring approaches, a global monitoring model is constructed by aligning all local models together. In this way, both within-mode and cross-mode correlations are preserved in this integrated space. Finally, the utility and feasibility of AMPPCA are demonstrated through a non-isothermal continuous stirred tank reactor and the TE benchmark process.

Application of Mass Spectrometry (MS)-coupled Techniques in Pesticide Residue Detection

Pesticide residue detection is an important work to ensure the quality safety of agricultural products.In the process of agricultural production,in order to prevent and control agricultural diseases and pests,a certain amount of pesticides need to be used.However,if pesticides are used excessively,there will be certain pesticide residues in crops and related products.Therefore,it is necessary to do a good job in pesticide residue detection.The gas chromatography-mass spectrometry(GC-MS)and liquid chromatography-mass spectrometry(LC-MS)detection methods have good results and can effectively detect pesticide residues in related products.This paper reviewed and analyzed the application of GC-MS and LC-MS in pesticide residue detection,and proposed optimization measures based on practical experience,hoping to provide reference for relevant scholars.

Test analysis of detection of damage to a complicated spatial model structure

A two-stage damage detection approach is proposed and experimentally demonstrated on a complicated spatial model structure with a limited number of measurements. In the experiment,five known damage patterns,including 3 brace damage cases and 2 joint damage cases,were simulated by removing braces and weakening beam鈥揷olumn connections in the structure. The limited acceleration response data generated by hammer impact were used for system identification,and modal parameters were extracted by using the eigensystem realization algorithm. In the first stage,the possible damaged locations are determined by using the damage index and the characteristics of the analytical model itself,and the extent of damage for those substructures identified at stage I is estimated in the second stage by using a second-order eigen-sensitivity approximation method. The main contribution of this paper is to test the two-stage method by using the real dynamic data of a complicated spatial model structure with limited sensors. The analysis results indicate that the two-stage approach is ableto detect the location of both damage cases,only the severity of brace damage cases can be assessed,and the reasonable analytical model is critical for successful damage detection.

NON-AQUEOUS REVERSED PHASE HPLC WITH LOW-WAVELENGTH UV DETECTION FOR TRIGLYCERIDE ANALYSIS

Glycerides are first separated to classes of triglycerides(TGs), diglycerides(DGs) and monoglycerides(MGs) by normal phase HPLC on silica gel column. Individual triglyceride separation is then achieved by non-aqueous reversed phase(NARP) HPLC on C_(18) column with UV detection at 215nm.

Iron-Mediated Oxidative DNA Damage Detected by Fluorometric Analysis of DNA Unwinding in Isolated Rat Liver Nuclei

Studies were performed to determine the extent of nuclear DNA degradation induced by iron, iron-ascorbate, or iron-bleomycin under aerobic conditions in a model system using isolated rat liver nuclei. The effects of five antioxidants (catalase, superoxide dismutase, dimethyl sulfoxide, glutathione and diallyl sulfide) on this oxidative nuclear damage were also investigated. At the 0.05 level for statistical significance, iron induced concentration-dependent DNA degradation, and this effect was enhanced by ascorbate and bleomycin. The antioxidants catalase, dimethyl sulfoxide, and diallyl sulfide significantly reduced the iron-ascorbate-induced DNA damage, whereas superoxide dismutase and dimethyl sulfoxide significantly reduced iron-bleomycin-induced damage. Glutathione significantly increased the iron-bleomycin-induced DNA damage. These results suggest that the reactive oxygen species generated by iron, iron-ascorbate, and iron-bleomycin are responsible for the DNA strand breaks in isolated rat liver nuclei.

SELECTIVE SULFUR DIOXIDE DETERMINATION BY GAS DIFFUSION FLOW INJECTION ANALYSIS WITH CHEMILUMINESCENT DETECTION

Sulfur dioxide has been found to decrease the chemiluminescence of luminol-iodine system.A new determination method for sulfur dioxide in atmosphere is developed by applying this reaction to a flow injection gas diffusion separation system.This permits the determination of sulfur dioxide selectively and rapidly.

Detection and Diagnosis of Gear Fault By the Single Gear Tooth Analysis Technique

This paper presents a procedure of sing le gear tooth analysis for early detection and diagnosis of gear faults. The objec tive of this procedure is to develop a method for more sensitive detection of th e incipient faults and locating the faults in the gear. The main idea of the sin gle gear tooth analysis is that the vibration signals collected with a high samp ling rate are divided into a number of segments with the same time interval. The number of signal segments is equal to that of the gear teeth. The analysis of i ndividual segments reveals more sensitively the changes of the vibration signals in both time and frequency domain caused by gear faults. In addition, the locat ion of a failed tooth can be indicated in terms of the position of the segment t hat deviates from the normal segments. An experimental investigation verified th e advantages of the single gear tooth analysis.

Assessing Spatio-Temporal Land Cover Changes in Dhund River Basin, Eastern Rajasthan (India), Using Multi-Temporal Landsat Data

Land cover is an impression of natural cover on surface of earth such as bare soil, river, grass etc. and utilization of these natural covers for various human needs and purposes by mankind is defined as land use. Land cover identification, delineation and mapping is important for planning activities, resource management and global monitoring studies while baseline mapping and subsequent monitoring is done by application of land use to get timely information about quantity of land that has been used. The present study has been carried out in Dhund river watershed of Jaipur, Rajasthan which covers an area of about 1828 sq∙km. The minimum and maximum elevation of the area is found to be 214 m and 603 m respectively. Land use and land cover changes of three decades from 1991 to 2021 have been interpreted by using remotes sensing and GIS techniques. ArcGIS software (Arc map 10.2), SOI topographic map, Cartosat-1 DEM and satellite data of Landsat 5 and Landsat 8 have been used for interpretation of eleven classes. The study shows an increase in cultivated land, settlement, waterbody, open forest, plantation and mining due to urbanization because of increasing demands of food, shelter and water while a decrease in dense forest, river, open scrub, wasteland and uncultivated land has also been marked due to destruction of aforementioned by anthropogenic activities such as industrialization resulting in environmental degradation that leads to air, soil and water pollution.

Modeling and Global Conflict Analysis of Firewall Policy

The global view of firewall policy conflict is important for administrators to optimize the policy.It has been lack of appropriate firewall policy global conflict analysis,existing methods focus on local conflict detection.We research the global conflict detection algorithm in this paper.We presented a semantic model that captures more complete classifications of the policy using knowledge concept in rough set.Based on this model,we presented the global conflict formal model,and represent it with OBDD(Ordered Binary Decision Diagram).Then we developed GFPCDA(Global Firewall Policy Conflict Detection Algorithm) algorithm to detect global conflict.In experiment,we evaluated the usability of our semantic model by eliminating the false positives and false negatives caused by incomplete policy semantic model,of a classical algorithm.We compared this algorithm with GFPCDA algorithm.The results show that GFPCDA detects conflicts more precisely and independently,and has better performance.

Real-time lane departure warning system based on principal component analysis of grayscale distribution and risk evaluation model

A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and then each search bar was tracked using Kalman filter between frames. The lane detection performance was evaluated and demonstrated in ways of receiver operating characteristic, dice similarity coefficient and real-time performance. For lane departure detection, a lane departure risk evaluation model based on lasting time and frequency was effectively executed on the ARM-based platform. Experimental results indicate that the algorithm generates satisfactory lane detection results under different traffic and lighting conditions, and the proposed warning mechanism sends effective warning signals, avoiding most false warning.

Fingerprint Liveness Detection Based on Multi-Scale LPQ and PCA

Fingerprint authentication system is used to verify users' identification according to the characteristics of their fingerprints.However,this system has some security and privacy problems.For example,some artificial fingerprints can trick the fingerprint authentication system and access information using real users' identification.Therefore,a fingerprint liveness detection algorithm needs to be designed to prevent illegal users from accessing privacy information.In this paper,a new software-based liveness detection approach using multi-scale local phase quantity(LPQ) and principal component analysis(PCA) is proposed.The feature vectors of a fingerprint are constructed through multi-scale LPQ.PCA technology is also introduced to reduce the dimensionality of the feature vectors and gain more effective features.Finally,a training model is gained using support vector machine classifier,and the liveness of a fingerprint is detected on the basis of the training model.Experimental results demonstrate that our proposed method can detect the liveness of users' fingerprints and achieve high recognition accuracy.This study also confirms that multi-resolution analysis is a useful method for texture feature extraction during fingerprint liveness detection.

A novel oil spill detection method from synthetic aperture radar imageries via a bidimensional empirical mode decomposition

Oil spills pose a major threat to ocean ecosystems and their health. Synthetic aperture radar（SAR） sensors can detect oil spills on the sea surface. These oil spills appear as dark spots in SAR images. However, dark formations can be caused by a number of phenomena. It is aimed to distinguishing oil spills or look-alike objects. A novel method based on a bidimensional empirical mode decomposition is proposed. The selected dark formations are first decomposed into several bidimensional intrinsic mode functions and the residue. Subsequently, 64 dimension feature sets are calculated using the Hilbert spectral analysis and five new features are extracted with a relief algorithm. Mahalanobis distances are then used for classification. Three data sets containing oil spills or look-alikes are used to test the accuracy rate of the method. The accuracy rate is more than 90%. The experimental results demonstrate that the novel method can detect oil spills validly and accurately.