Behavior Analysis Techniques Research Articles

Adolescence and the development of social behaviour in giraffes

All mammals experience different life stages as they develop, each of which is characterised by particular physical and behavioural changes. Despite the emergence of sophisticated behaviour analysis techniques, the ways in which social behaviour varies by life stage, and how this is influenced by an individual’s sex, is relatively understudied in most social mammals other than primates and elephants. Understanding the social requirements of mammals should be a central and critical component to their conservation, captive management and welfare. Here, we apply social network analysis techniques to understand how social behaviour differs with life stage in the giraffe, a gregarious fission–fusion mammal. We studied two wild populations of giraffes in Kenya and found that adolescents have significantly stronger associations with adolescents of their own sex first and foremost, then adults of their own sex. Other associations were significantly lower than would be expected, or non-significant. Our results suggest that adolescence in both male and female giraffes shares similar features to adolescence in other social mammal species. We discuss how the application of such knowledge might improve the management and welfare of captive giraffes.

Optimization of APT attack detection based on a model combining ATTENTION and deep learning

Nowadays, early detecting and warning Advanced Persistent Threat (APT) attacks is a major challenge for intrusion monitoring and prevention systems. Current studies and proposals for APT attack detection often focus on combining machine-learning techniques and APT malware behavior analysis techniques based on network traffic. To improve the efficiency of APT attack detection, this paper proposes a new approach based on a combination of deep learning networks and ATTENTION networks. The proposed process for APT attack detection in this study is as follows: Firstly, all data of network traffic is pre-processed, and analyzed by the CNN-LSTM deep learning network, which is a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). Then, instead of being used directly for classification, this data is analyzed and evaluated by the ATTENTION network. Finally, the output data of the ATTENTION network is classified to identify APT attacks. The optimization proposal for detecting APT attacks in this study is a novel proposal. It hasn’t been proposed and applied by any research. Some scenarios for comparing and evaluating the method proposed in this study with other approaches (implemented in section 4.4) show the superior effectiveness of our proposed approach. The results prove that the proposed method not only has scientific significance but also has practical significance because the model combining deep learning with ATTENTION network has helped improve the efficiency of analyzing and detecting APT malware based on network traffic.

An Exploratory Study of the Purchase and Consumption of Beef: Geographical and Cultural Differences between Spain and Brazil.

Beef consumption and production in Spain and Brazil are different with the consumption of beef in Brazil being three times higher than in Spain. In addition, there are variations in the economic value of production and in the traceability system. Therefore, the aim of this research was to understand the purchasing and consumption patterns using the customer behavior analysis technique of focus groups, which analyzed motivations for the consumption of beef, classifying their preferences by the intrinsic and extrinsic attributes at the time of purchase. The key aspect of the consumption of beef, both for Spanish and Brazilian consumers, was personal satisfaction/flavor. Spanish consumers were more conscious than Brazilians of the beneficial and harmful qualities that meat provides. The presence of fat was the factor that most restricted intake in both countries. The most important intrinsic attributes for Spanish and Brazilian consumers were the visual aspects of the meat: color, freshness, and the quantity and disposition of fat. The most important extrinsic characteristics were the price and expiration date. Spanish consumers see packaged meat as convenient and safe, although it is considered by Brazilians to be over-manipulated. The traceability certification on the label provides credibility to the product for the Spanish but only partially for Brazilians.

Организация тьюторского сопровождения учебного процесса младших школьников с РАС. Технология «Классный тьютор»

<p style="text-align: justify;">The heterogeneity and complexity of autism spectrum disorders (ASD) determines the need to develop special education and support environment for children with ASD, considering children special educational needs. Tutor support is a necessary, guaranteed and learning model-independent condition for the effective adaptation of a child with autism in the school environment. The «Class tutor» technology is an original education intervention developed within the framework of the concept of inclusive education. The technology focuses on the group tutor support in a grade for children with ASD. Goals of the intervention are: the adaptation of students to the educational process the individual inclusion of the student in the team; participation of a tutor in group lesson activities and tutor assistance to the group in the mastering of the education program (special type of the educational program for children with ASD); developing of the individual learning conditions, developing of the functional skills and reducing of the episodes of unwanted behavior. The specific tasks of the stages (preliminary, adaptive-diagnostic, main, final) of the technology implementation are presented. During the work with the unwanted behavior tutor uses following applied behavioral analysis techniques implemented in the «Class tutor» intervention: the use of motivational stimuli; the dosed use of prompts of various levels; extinction; positive weakening; the establishment of instructional control; an increase in the period of problem-free behavior; support and consolidation of alternative and replacing forms of behavior, maintaining an adequate pace of work; training functional communication. The game interaction during the break has been chosen as the model for the description of the intervention scheme. The principles of the intervention effectiveness study design include multiple case and multiple-baseline methodology.</p>

Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

Most approaches for detecting network attacks involve threat analyses to match the attack to potential malicious profiles using behavioral analysis techniques in conjunction with packet collection, filtering, and feature comparison. Experts in information security are often required to study these threats, and judging new types of threats accurately in real time is often impossible. Detecting legitimate or malicious connections using protocol analysis is difficult; therefore, machine learning-based function modules can be added to intrusion detection systems to assist experts in accurately judging threat categories by analyzing the threat and learning its characteristics. In this paper, an ensemble learning scheme based on a revised random forest algorithm is proposed for a security monitoring system in the domain of renewable energy to categorize network threats in a network intrusion detection system. To reduce classification error for minority classes of experimental data in model training, the synthetic minority oversampling technique scheme (SMOTE) was formulated to re-balance the original data sets by altering the number of data points for minority class to imbue the experimental data set. The classification performance of the proposed classifier in threat classification when the data set is unbalanced was experimentally verified in terms of accuracy, precision, recall, and F1-score on the UNSW-NB15 and CSE-CIC-IDS 2018 data sets. A cross-validation scheme featuring support vector machines was used to compare classification accuracies.

Brief Report: A Novel Digital Therapeutic that Combines Applied Behavior Analysis with Gaze-Contingent Eye Tracking to Improve Emotion Recognition in Children with Autism Spectrum Disorder.

This study examined the feasibility, acceptability, and efficacy of a video game-based digital therapeutic combining applied behavior analysis techniques and gaze-contingent eye tracking to target emotion recognition in youth with autism spectrum disorder (ASD). Children aged 4-14years with ASD were randomized to complete Lookware™ (n = 25) or a control video game (n = 29). Results from a 2 × 2 mixed ANOVA revealed that children in the intervention condition demonstrated significant improvements in emotion recognition from pre- to post-intervention compared to children in the control condition, F(1,52) = 17.48, p < 0.001. Children and staff perceived high feasibility and acceptability of Lookware™. Study results demonstrated the feasibility, acceptability, and preliminary efficacy of Lookware™.

Privacy and Security in Cognitive Cities: A Systematic Review

The emerging paradigm of the cognitive city, which augments smart cities with learning and behavioral change capabilities, is gaining increasing attention as a promising solution to the challenges of future mega-cities. Cognitive cities are built upon artificial learning and behavioral analysis techniques founded on the exploitation of human-machine collective intelligence. Hence, cognitive cities rely on the sharing of citizens’ daily-life data, which might be considered sensitive personal data. In this context, privacy and security of the shared information become critical issues that have to be addressed to guarantee the proper deployment of cognitive cities and the fundamental rights of people. This article provides a thorough literature review using the recommendations for systematic reviews proposed by Vom Brocke et al. and the PRISMA statement. We analyze peer-reviewed publications indexed in ACM Digital Library, IEEE Xplore, Scopus, and Web of Science until July 2020. We identify the main challenges on privacy and information security within cognitive cities, and the proposals described in the literature to address them. We conclude that many challenges remain open and we suggest several research lines that will require further examination in the years to come.

A novel approach for APT attack detection based on combined deep learning model

Advanced persistent threat (APT) attack is a malicious attack type which has intentional and clear targets. This attack technique has become a challenge for information security systems of organizations, governments, and businesses. The approaches of using machine learning or deep learning algorithms to analyze signs and abnormal behaviors of network traffic for detecting and preventing APT attacks have become popular in recent years. However, the APT attack detection approach that uses behavior analysis and evaluation techniques is facing many difficulties due to the lack of typical data of attack campaigns. To handle this situation, recent studies have selected and extracted the APT attack behaviors which based on datasets are built from experimental tools. Consequently, these properties are few and difficult to obtain in practical monitoring systems. Therefore, although the experimental results show good detection, it does not bring high efficiency in practice. For above reasons, in this paper, a new method based on network traffic analysis using a combined deep learning model to detect APT attacks will be proposed. Specifically, individual deep learning networks such as multilayer perceptron (MLP), convolutional neural network (CNN), and long short-term memory (LSTM) will also be sought, built and linked into combined deep learning networks to analyze and detect signs of APT attacks in network traffic. To detect APT attack signals, the combined deep learning models are performed in two main stages including (i) extracting IP features based on flow: In this phase, we will analyze network traffic into networking flows by IP address and then use the combined deep learning models to extract IP features by network flow; (ii) classifying APT attack IPs: Based on IP features extracted in a task (i), the APT attack IPs and normal IPs will be identified and classified. The proposal of a combined deep learning model to detect APT attacks based on network traffic is a new approach, and there is no research proposed and applied yet. In the experimental section, combined deep learning models proved their superior abilities to ensure accuracy on all measurements from 93 to 98%. This is a very good result for APT attack detection based on network traffic.

The Level of Knowledge of Teachers of Children with Intellectual Disabilities about the Applied Behavior Analysis Approach and Its Techniques in the State of Kuwait

This study aimed to assess the level of knowledge of teachers of children with intellectual disabilities about the applied behavior analysis approach and its techniques in Kuwait. It tested the differences in the level based on: the type of school, experience and gender. The study sample consisted of (160) teachers worked in schools of children with intellectual disabilities in the academic year (2019/2020).To achieve the objectives of this study, the test of "Applied Behavior Analysis Approach and Its Techniques" was applied. The results indicated that the overall level was low. The dimension of “general principles of the Applied Behavior Analysis approach” was the highest with intermediate level score, followed by the “techniques of Applied Behavior Analysis”, and “practical applications of the techniques of applied behavior analysis”. Both of them with low level score.The results showed that there are no significant differences in the total score and all sub-dimensions based on the school type. There are no significant differences in the total score and in the dimensions: techniques of applied behavior analysis and practical applications of applied behavior analysis techniques, based on the experience. Based on the experience, there are significant differences in the general principles of the applied behavior analysis approach, in favor of those teachers with experience of more than 10 years. There are significant differences in the total score, and in the dimensions of: the general principles of the applied behavior analysis approach and techniques of applied behavior analysis based on the variable of gender, in favor of males.This study recommends conducting a study to assess levels of special education teachers in the approach of applied behavior analysis, as a foundation of conduct future training.

Detecting Unauthorized Network Intrusion based on Network Traffic using Behavior Analysis Techniques

Nowadays, network intrusion detection is an essential problem because cyber-attacks are increasing in both the number and extent of the danger. Network intrusion techniques often use various methods to bypass the oversight of anomaly detection and surveillance systems. This paper proposes to use behavior analysis techniques, machine learning, and deep learning algorithms for the task of detecting network intrusions. The practical and scientific significance of our paper includes two issues: (1) Regarding the process of selecting and extracting features: instead of using typical abnormal behaviors of attacks, this study will use statistical behaviors that are easy to calculate and extract while still ensuring the effectiveness of the method; (2) Regarding the detection process, this study proposes to use the Random Forest (RF) classification algorithm, the Multilayer Perceptron (MLP) and the Convolutional Neural Network (CNN) deep learning model. The experimental results in Section IV have proven that our proposal in this paper is completely correct and reasonable. Based on the results shown in Section IV, this study has provided network surveillance systems with a number of abnormal behaviors as the basis for detecting network intrusions.

A multi-layer approach for advanced persistent threat detection using machine learning based on network traffic

Advanced Persistent Threat (APT) is a dangerous network attack method that is widely used by attackers nowadays. During the APT attack process, attackers often use advanced techniques and tools, thus, causing many difficulties for information security systems. In fact, to detect the APT attacks, intrusion detection systems cannot rely on one technique or method but often combine multiple techniques and methods. In addition, the approach for APT attack detection using behavior analysis and evaluation techniques is facing many difficulties due to the lack of characteristic data of attack campaigns. For the above reasons, in this paper, we propose a method for APT attack detection based on a multi-layer analysis. The multi-layer analysis technique in our proposal computes and analyzes various events in Network Traffic to detect and synthesize abnormal signs and behaviors in order to make conclusions about the existence of APT in the system. Specifically, in our proposal, we will use serial 3 main layers for the APT attack detection process including i) Detecting APT attacks based on analyzing abnormal connection; ii) Detecting APT attacks based on analyzing and evaluating Suricata log; iii) Detecting APT attacks based on analyzing behavior profiles that are compiled from layers (i) and (ii). To achieve these goals, the multi-layer analysis technique for APT attack detection will perform 2 main tasks: i) Analyzing and evaluating components of Network Traffic based on abnormal signs and behaviors. ii) building and classifying behavior profile based on each component of network traffic. In the experimental section, we will compare and evaluate the effectiveness of the APT attack detection process of each layer in the multi-layer analysis model using machine learning. Experimental results have shown that the APT attack detection method based on analyzing behavior profile has yielded better results than individual detection methods on all metrics. The research results shown in the paper not only demonstrate the effectiveness of the multilayer analysis model for APT attack detection but also provide a novel approach for detecting several other cyber-attack techniques.

Using post‐incident behavioral analysis techniques to complement incident investigations

AbstractThe hours and days following an incident represent a very critical time to gather important information about the event. Post‐incident investigations are usually accompanied by root cause analyses to determine what led to the incident and to develop corrective actions to reduce the likelihood that the incident will occur again. Often, little thought may be given to the human factors aspect of the incident in terms of correcting the human behavior associated with the incident. As process safety professionals, we work to provide sound engineering solutions that usually involve replacing the human element with an automated system. In many situations, it may not be possible to completely eliminate the human factor component of the front‐line workers that resulted in the incident, but it may be possible to reduce the frequency of human error on future incidents by engaging the front‐line workers in post‐incident discussions that are rooted in behavior‐based safety. This paper describes the tools and techniques that we have developed to effectively facilitate post‐incident behavior‐based discussions. The target of these discussions is identifying how human error plays a key role in the incident and how behavior influences decision‐making during an incident.

A Method of detecting web attacks using behavioral profile analysis technique

A Method of detecting web attacks using behavioral profile analysis technique

A two-step approach for interest estimation from gaze behavior in digital catalog browsing

While eye gaze data contain promising clues for inferring the interests of viewers of digital catalog content, viewers often dynamically switch their focus of attention. As a result, a direct application of conventional behavior analysis techniques, such as topic models, tends to be affected by items or attributes of little or no interest to the viewer. To overcome this limitation, we need to identify “when” the user compares items and to detect “which attribute types/values” reflect the user’s interest. This paper proposes a novel two-step approach to addressing these needs. Specifically, we introduce a likelihood-based short-term analysis method as the first step of the approach to simultaneously determine comparison phases of browsing and detect the attributes on which the viewer focuses, even when the attributes cannot be directly obtained from gaze points. Using probabilistic latent semantic analysis, we show that this short-term analysis step greatly improves the results of the subsequent step. The effectiveness of the framework is demonstrated in terms of the capability to extract combinations of attributes relevant to the viewer’s interest, which we call aspects, and also to estimate the interest described by these aspects.

Improving communication skills of children with autism through support of applied behavioral analysis treatments using multimedia computing: a survey

Naturalistic applied behavior analysis (ABA) techniques have been shown to help children with autism improve their communication skills. Recognizing that individuals who interact with children regularly are in the position to utilize treatments with profound effects, researchers have examined methodologies for training parents, teachers, and peers to implement treatments. These programs are time intensive and often unable to support trainees after training. Technologies need to be examined to determine how they can aid in the educational and support process. Academic publications and publicly available training programs were reviewed to determine the types of participants, methodologies, and training durations that have been reported for instructing interventionists. These resources illustrate a need to make programs more accessible. To address this, selected computer science research is applied to methods of evaluating ABA implementations in order to recommend how the technologies could be utilized to make training and support programs more accessible. Review results of instructional programs, both in research and available in the community, illustrate the challenges in providing training in ABA methodologies. Modern research in multimedia data processing and machine learning could be applied to reduce the human cost of training and support individuals implementing ABA techniques. Utilizing machine learning techniques to analyze video probes of naturalistic ABA treatment implementation could alleviate the human cost of evaluating fidelity, allowing for greater support for individuals interested in the treatments. These technologies could be used in the future to expand data collection to provide more perspective on the treatments.

IEEE Access Special Section Editorial: Wireless Body Area Networks

Wearable devices and wireless communications, combined with personalized health management, are future trends that healthcare practices and procedures are heading toward. To facilitate this progress, new technologies and methods are required to provide reliable measurements, end-to-end communications, and data analysis mechanisms from the data source to medical health records. The wireless body area network (WBAN) is the major element in this process. This Special Section is not only limited to on-body WBAN devices but also focuses on benefitting technologies which can distribute vital information inside a human body or allow control of implantable gadgets. Dependable wireless communications combined with versatile application areas, such as accurate localization or behavior analysis techniques, remote monitoring, adoption of vital sensors, and actuators, can benefit the increased use of new WBAN technologies in various healthcare-related studies. In the end, this will make healthcare processes more effective and user friendly, and simultaneously increase the safety of (out)patients. This Special Section focuses on various theoretical and experimental views on WBAN applications, technologies, implementations, and utilizations based on invited, extended versions of the best-evaluated articles from BodyNets 2018, held at Oulu, Finland, in October 2018, as well as quality articles submitted from the Open Call. This Special Section includes 16 accepted articles which have undergone a rigorous peer-review process. Three of the accepted articles were invited extensions of the articles presented at the BodyNets 2018 conference. The total number of submissions we received for this Special Section was 45; thus, the acceptance rate was 36%.

Mapping behavioral landscapes in Down syndrome animal models.

Down syndrome (DS), caused by trisomy of chromosome 21 (Hsa21), results in a spectrum of phenotypes including learning and memory deficits, motor dysfunction and social constrains. The regions on Hsa21 are conserved with their synteny on mouse chromosome 10, 16 and 17. To date, a wide range of mouse models has been developed to determine genotype-phenotype relationships and identity of the causative dosage-sensitive genes. However, the comparison of behavioral results is not obvious due to the lack of consistency in the genetics background, housing conditions and behavioral protocols used. There is a growing need to standardize some of the classical behavioral test, include automated behavioral phenotyping and sophisticated analysis techniques and move through ethologically inspired tests. Here we present an overview of the status of behavioral phenotyping of DS murine models and the limitations and possibilities to improve their characterization to address genotype-phenotype relationships for understanding the pathophysiology of DS.

Assessment of Canine Temperament: Predictive or Prescriptive?

Canine temperament testing has historically been linked to the predictability of future behavior. A predictive model of canine temperament testing assumes that a dog’s behavior in one situation will likely be similar to its behavior in a variety of other situations. An alternative model is proposed for a canine temperament test that could identify areas in which a dog might fail to perform certain test items, but by using modern behavior analysis techniques, behaviors could be modified through a prescriptive approach. This article describes the AKC Temperament Test (ATT), which is the first prescriptive canine temperament test. The ATT is designed to provide pet dog owners with information about potential problem areas that can be modified through training.

Ransomware detection method based on context-aware entropy analysis

Numerous countermeasures have been proposed since the first appearance of ransomware. However, many ransomware mutants continue to be created, and the damage they cause has been continually increasing. Existing antivirus tools are signature-dependent and cannot easily detect ransomware attack patterns. If the database used by the antivirus program does not contain the signature of the new malicious behavior, it is not possible to detect the new malware. Thus, the need has emerged for a normal/abnormal behavior analysis technique via a context-aware method. Therefore, a multilateral context-aware-based ransomware detection and response system model is presented in this paper. The proposed model is designed to preemptively respond to ransomware, and post-detection management is performed. An evaluation was conducted to obtain evidence that the given files were altered by ransomware through analyses based on multiple-context awareness. Entropy information was then used to detect abnormal behavior.

A survey of malware behavior description and analysis

Behavior-based malware analysis is an important technique for automatically analyzing and detecting malware, and it has received considerable attention from both academic and industrial communities. By considering how malware behaves, we can tackle the malware obfuscation problem, which cannot be processed by traditional static analysis approaches, and we can also derive the as-built behavior specifications and cover the entire behavior space of the malware samples. Although there have been several works focusing on malware behavior analysis, such research is far from mature, and no overviews have been put forward to date to investigate current developments and challenges. In this paper, we conduct a survey on malware behavior description and analysis considering three aspects: malware behavior description, behavior analysis methods, and visualization techniques. First, existing behavior data types and emerging techniques for malware behavior description are explored, especially the goals, principles, characteristics, and classifications of behavior analysis techniques proposed in the existing approaches. Second, the inadequacies and challenges in malware behavior analysis are summarized from different perspectives. Finally, several possible directions are discussed for future research.