Search results

The purpose of the research work is to detect camouflaged objects in autonomous systems of military applications and civilian applications such as detecting insects in paddy fields, identifying duplicate products in different texture environments.

Camouflaged objects detection is performed by smoothing texture with nonlinear models and characterizing with statistical methods to detect the objects.

There are few challenges in existing camouflaged objects detection due to the complexities involved in the detection process. This work proposes a constructive approach with texture statistical characterization for camouflage detection. The proposed technique is found to be better than existing methods while assessing its performance using precision and recall.

Even though there is lot of research work carried, there are few challenges for autonomous systems in camouflage detection due to the complexities involved in the detection process such as texture modeling and dynamic background problems and environment conditions for autonomous system.

Camouflage detection finds potential applications in security systems, surveillance, military and autonomous systems. The proposed work is implemented in different environments for camouflage detection.

Social problems such as image acquisition environment, time of day, desert, forest and grass fields of paddy.

The proposed method detects camouflaged objects in autonomous systems where it is applied for images of different kinds. It is found to be effective on images recorded in battlefield and challenging environments.

This paper aims to develop a robofish with oscillating pectoral fins, and control it to mimic the bionic prototype by central pattern generators (CPGs).

First, the oscillation characteristics of the cownose ray were analyzed quantitatively. Second, a robofish with multi-joint pectoral fins was developed according to the bionic morphology and kinematics. Third, the improved phase oscillator was established, which contains a spatial asymmetric coefficient and a temporal asymmetric coefficient. Moreover, the CPG network is created to mimic the cownose ray and accomplish three-dimensional (3D) motions. Finally, the experiments were done to test the authors ' works.

The results demonstrate that the CPGs is effective to control the robofish to imitate the cownose ray realistically. In addition, the robofish is able to accomplish 3D motions of high maneuverability, and change among different swimming modes quickly and smoothly.

The research provides the method to develop a robofish from both 3D morphology and kinematics. The motion analysis and CPG control make sure that the robofish has the features of high maneuverability and camouflage. It is useful for military underwater applications and underwater detections in narrow environments. Second, this work lays the foundation for the autonomous 3D control. Moreover, the robotic fish can be taken as a scientific tool for the fluid bionics research.

In the traffic monitoring system, the detection of stirring vehicles is monitored by fitting static cameras in the traffic scenarios. Background subtraction a commonly used method detaches poignant objects in the foreground from the background. The method applies a Gaussian Mixture Model, which can effortlessly be contaminated through slow-moving or momentarily stopped vehicles.

This paper proposes the Enhanced Gaussian Mixture Model to overcome the addressed issue, efficiently detecting vehicles in complex traffic scenarios.

The model was evaluated with experiments conducted using real-world on-road travel videos. The evidence intimates that the proposed model excels with other approaches showing the accuracy of 0.9759 when compared with the existing Gaussian mixture model (GMM) model and avoids contamination of slow-moving or momentarily stopped vehicles.

The proposed method effectively combines, tracks and classifies the traffic vehicles, resolving the contamination problem that occurred by slow-moving or momentarily stopped vehicles.

Fire smoke detection in petrochemical plant can prevent fire and ensure production safety and life safety. The purpose of this paper is to solve the problem of missed detection and false detection in flame smoke detection under complex factory background.

This paper presents a flame smoke detection algorithm based on YOLOv5. The target regression loss function (CIoU) is used to improve the missed detection and false detection in target detection and improve the model detection performance. The improved activation function avoids gradient disappearance to maintain high real-time performance of the algorithm. Data enhancement technology is used to enhance the ability of the network to extract features and improve the accuracy of the model for small target detection.

Based on the actual situation of flame smoke, the loss function and activation function of YOLOv5 model are improved. Based on the improved YOLOv5 model, a flame smoke detection algorithm with generalization performance is established. The improved model is compared with SSD and YOLOv4-tiny. The accuracy of the improved YOLOv5 model can reach 99.5%, which achieves a more accurate detection effect on flame smoke. The improved network model is superior to the existing methods in running time and accuracy.

Aiming at the actual particularity of flame smoke detection, an improved flame smoke detection network model based on YOLOv5 is established. The purpose of optimizing the model is achieved by improving the loss function, and the activation function with stronger nonlinear ability is combined to avoid over-fitting of the network. This method is helpful to improve the problems of missed detection and false detection in flame smoke detection and can be further extended to pedestrian target detection and vehicle running recognition.

The purpose of this paper is to examine the hypothesis that a period of sustained supernormal firm performance (for up to five years before fraud commission) creates financial pressure on actors/agents so they have a propensity to behave fraudulently to keep the good times (apparently) rolling.

Applying the Fama and French (1993) three-factor model using a range of calendar time portfolio methodologies, the authors measure abnormal drifts in stock performance in periods up to five years before alleged fraud commission dates. The authors examine a sample of 561 US firms subject to enforcement actions initiated by the Securities and Exchange Commission (SEC) and the Department of Justice (DOJ) over 1968-2009.

The authors find that sustained firm-specific positive stock price performance for up to five years followed by the almost inevitable adverse shock, which eventually brings the good times to an end, generally precedes corporate fraud. Fraud occurs when firm managers engage in misconduct in a misguided attempt to keep the good times (apparently) rolling despite the negative shock.

The sample is restricted to firms with trading histories on the stock market prior to the misconduct, and to firms contained in the Federal Securities Regulation database of US firms subject to enforcement actions initiated by the SEC and the DOJ over 1968-2009.

The desire to keep the good times rolling appears to be a very important driver of fraudulent behavior, even after controlling for the executive compensation incentive effects and business cycle effects emphasized in prior studies. The robust findings of positive abnormal returns for up to five years preceding initial fraud commission suggest that regulators and investors would be well-advised to scrutinize the behavior of firms that exhibit surprisingly persistent superior performance over an extended period. If the financial results appear too good to be true, a closer examination might just reveal that they indeed are.

While most investors generally like to see the “good times keep rolling” this pressure can create ethical dilemmas for managers.

Unlike most other papers in this area of the literature, which concentrate on the pre-fraud disclosure, the authors investigate the firm’s performance in the pre-fraud commission period. The authors find that the commission of the alleged fraud is preceded by a sustained period of surprisingly good performance of up to five years in length. The authors believe that the paper provides empirical evidence that supports the hypothesis that a period of sustained supernormal firm performance (for up to five years before fraud commission) creates financial pressure on actors/agents so they have a propensity to behave fraudulently to keep the good times (apparently) rolling.

APPARENT at the 31st Salon d'Aeronautique et Spatiale held at Le Bourget was greater military interest than had been indicated for some years. The announcement of the Belgian order for F 16 aircraft added some more controversy to an already tense re‐equipment atmosphere. News of the F 1E which is the French competitor was also prominently available. Making its first Paris Show appearance was the HS Hawk which is the third to be produced with three more due to fly within the next month or so. No less than four Alpha Jets were present, two of these being on static exhibition. The SF 37 reconnaissance version of the Saab Viggen was also present as well as other variants of this aircraft, but as with other types one only was allowed in the air at a time. The most notable exception from the flying programme was the MRCA although good progress has been reported in the test programme now that earlier difficulties have been overcome.

Creditor reliance on accounting‐based numbers as a persistent and traditional standard to assess a firm's financial soundness and viability suggests that the integrity of financial statements is essential to credit decisions. The purpose of this paper is to provide an approach to explore fraudulent financial reporting (FFR) via growing hierarchical self‐organizing map (GHSOM), an unsupervised neural network tool, to help capital providers evaluate the integrity of financial statements, and to facilitate analysis further to reach prudent credit decisions.

This paper develops a two‐stage approach: a classification stage that well trains the GHSOM to cluster the sample into subgroups with hierarchical relationship, and a pattern‐disclosure stage that uncovers patterns of the common FFR techniques and relevant risk indicators of each subgroup.

An application is conducted and its results show that the proposed two‐stage approach can help capital providers evaluate the reliability of financial statements and accounting numbers‐based decisions.

Following the SOM theories, it seems that common FFR techniques and relevant risk indicators extracted from the GHSOM clustering result are applicable to all samples clustered in the same leaf node (subgroup). This principle and any pre‐warning signal derived from the identified indicators can be applied to assessing the reliability of financial statements and forming a basis for further analysis in order to reach prudent decisions. The limitation of this paper is the subjective parameter setting of GHSOM.

This is the first application of GHSOM to financial data and demonstrates an alternative way to help capital providers such as lenders to evaluate the integrity of financial statements, a basis for further analysis to reach prudent decisions. The proposed approach could be applied to other scenarios that rely on accounting numbers as a basis for decisions.

Foreign object debris (FOD) poses a significant hazard to aviation safety and brings huge economic losses to the aerospace industry due to aircraft damage and out‐of‐service delays. Different schemes and sensors have been utilized for FOD detection. This paper aims to look into a video‐based FOD detection system for airport runway security and propose a scheme for FOD surveillance network establishment.

The FOD detection algorithm for the system is analyzed in detail, including four steps of pre‐processing, background subtraction, post‐processing and FOD location.

The overall algorithm is applied to two sets of live video images. The results show that the algorithm is effective for FOD targets of different shades under different lighting conditions. The proposed system is also evaluated by the ground‐truth data collected at Nanyang Airport.

The runway security can be greatly increased by designing an affordable video‐based FOD detection system.

The paper presents critical techniques of video‐based FOD detection system. The scheme for FOD surveillance network, as a significant part of aviation risk management at airports, is applicable and extensible.

Females with autism spectrum disorder (ASD) may display superficial social skills which may mask their ASD symptomology impacting on the identification of the disorder – known as the “camouflage” hypothesis. Compared to males with ASD, it is increasingly recognised that females with ASD have a stronger ability to imitate behaviour which is socially acceptable, particularly those females who have higher cognitive abilities (i.e. intelligence considered to be within the normal range) (Ehlers and Gillberg, 1993). The paper aims to discuss this issue.

This paper will explore the literature on camouflaging or masking behaviour in females with ASD. A systematic PRISMA review was conducted.

The capacity to “camouflage” social difficulties in social situations is considered to be one of the main features of the female phenotype of ASD (e.g. Kenyon, 2014). Social imitation or camouflaging enables some level of success and coping, which results in some females never receiving a diagnosis of ASD. They typically may not exhibit any observable functional impairments. However, under the surface of the camouflage, females may experience high levels of subjective stress, anxiety and exhaustion and a need to re-charge or recuperate by withdrawing from any social interaction.

There is relatively little understanding and knowledge of the female phenotype of ASD. This lack of understanding and knowledge impacts significantly on the ability to identify females with ASD (Lai et al., 2015; Bargiela et al., 2016), which can have a number of negative consequence (Adamou et al., 2018; National Collaborating Centre for Mental Health (UK), 2012).

There is a need for the development of a camouflaging measure.

There is a real need for further research exploring the positive and negative impact of the phenomenon of “camouflaging”, or “pretending to be normal” in females with ASD.