Modeling Human Guidance Behavior Based on Patterns in Agent–Environment Interactions

With fresh development in the area of artificial intelligence and machine learning, the analysis of human physiological and psychological behavior has received greater attention around the world. In this paper, we have provided a detailed survey of the approaches used for human behavior detection considering different modalities with physiological behavior, psychological behavior, and emotion detection with the help of sensors EEG, ECG, GSR, and temperature. At long last, it finishes up with the results of this study and represents the thoughts for future exploration in the zone of human behavior understanding. A rundown and comparison among the ongoing investigations is done that uncovers the currently existing issues. In addition, future work has been examined.

An Agent-Based Approach to Aircraft Conflict Resolution with Constraints

Human behavior is often affected by sudden emergency directly or indirectly. In this paper, we focus on two groups of people under different types of medical emergency calls. Based on the quantitative analysis of calling volume and call interval distribution before and after the emergency call, we find that during most types of emergencies, calling volume will increase after the emergency call made and maintain a high level in the next several hours. Medical emergency makes influence on call volumes, but not affects power-law distribution in human communication behavior. From studying entropy of call detail records, we found that during the medical emergency, the richness of outgoing call numbers increases and falls after that. In this paper, we do quantitative analysis of temporal patterns of medical emergency call based on the combination of medical emergency call data and call detail record data, which not only study on the characteristics of human communication behavior in emergency situations, but also provide data basis for scientific rational allocation of aid resources and effective emergency measures.

Social media contain rich information that can be used to help understand human mind and behavior. Social media data, however, are mostly unstructured (e.g., text and image) and a large number of features may be needed to represent them (e.g., we may need millions of unigrams to represent social media texts). Moreover, accurately assessing human behavior is often difficult (e.g., assessing addiction may require medical diagnosis). As a result, the ground truth data needed to train a supervised human behavior model are often difficult to obtain at a large scale. To avoid overfitting, many state-of-the-art behavior models employ sophisticated unsupervised or self-supervised machine learning methods to leverage a large amount of unsupervised data for both feature learning and dimension reduction. Unfortunately, despite their high performance, these advanced machine learning models often rely on latent features that are hard to explain. Since understanding the knowledge captured in these models is important to behavior scientists and public health providers, we explore new methods to build machine learning models that are not only accurate but also interpretable. We evaluate the effectiveness of the proposed methods in predicting Substance Use Disorders (SUD). We believe the methods we proposed are general and applicable to a wide range of data-driven human trait and behavior analysis applications.

This research constructs a conceptual model describing correlation between human behavior in software development and resulting product (software) quality. This model supplements collaboration model that exists before which approaches collaboration from the method (process) and technology viewpoint. The model in this research is constructed by mapping human behavior property (human behavior model) into software development collaboration process. The human behavior model were adopted from HBR model. The collaboration process in this research are classified into 4 collaboration layers, which is spatial distribution, temporal distribution, direction, and intensity. In the resulting model there are correlation between human behavior property and collaboration process, correlation between collaboration process and product quality, and correlation between human behavior and product quality. Some of properties of this model have been tested using open source and observation data. The result of these test wasnumber of commit (in construction phase of software development process) has negative relation with source code quality.

The suppression of reproductive function is known to occur in women engaging in activities that require high energetic expenses, such as sport participation and subsistence work. It is still unclear, however, if reproductive suppression is a response to high levels of energy expenditure, or only to the resulting state of negative energy balance. To our knowledge, this study provides the first evidence that work-related energy expenditure alone, without associated negative energy balance, can lead to the suppression of reproductive function in women. We document suppression of ovarian function expressed as lowered salivary progesterone levels in women from an agricultural community who work hard, but remain in neutral energy balance. We propose two alternative evolutionary explanations (the 'pre-emptive ovarian suppression' hypothesis and the 'constrained down-regulation' hypothesis) for the observed results.

The research on human spatial-temporal behavior has always been the focus of urban geographic studies. In today’s society, social networks, smart phones and smart cards can provide massive data for researchers to analysis human behavior. From mobile phone trajectories, this paper presents algorithms for mining human spatial-temporal behavior pattern, which includes not only the regular movement pattern of individuals, but also the co-occurrence pattern among user groups. The parallel algorithms in this paper are proposed for big data of user trajectories, and the experimental results show that the proposed algorithms are effective. The research on human spatial-temporal behavior pattern can be applied to urban spatial-temporal behavior analysis, smart city construction and other areas.

Controversies in the evolutionary social sciences: a guide for the perplexed

Recent technological advances have enabled the continuous and unobtrusive monitoring of human behaviour. However, most of the existing studies focus on detecting human behaviour under the limitation of one behavioural aspect, such as physical behaviour and not addressing human behaviour in a broad sense. For this reason, we propose a novel framework that will serve as the principal generator of knowledge on the user’s behaviour. The proposed framework moves beyond the current trends in automatic behaviour analysis by detecting and inferring human behaviour automatically, based on multimodal sensor data. In particular, the framework analyses human behaviour in a holistic approach, focusing on different behavioural aspects at the same time; namely physical, social, emotional and cognitive behaviour. Furthermore, the suggested framework investigates user’s behaviour over different periods, introducing the concept of short-term and long-term behaviours and how these change over time.

Owing to the complexity of human behaviors in risk situation and the harsh physical environment of underground mine, current researches on coalmine virtual environment have paid little attention on modeling human risk behaviors. Based on Artificial Life method, an intelligent virtual miner agent model was proposed to yield better understandings of human factors in emergency situation and to assist risk behaviors analysis in underground coalmine. The virtual miner agent is a comprehensive model of 3D virtual human and combines perceptual, behavioral, internal states and cognitive modules. And then, behavioral model of virtual miner was introduced in detail. Behaviors of virtual miner are constructed by a set of parameterized basic actions and are controlled by personalized action selection mechanism, which incorporate miners' cognitive processes and internal state characteristics to explore human behavioral mechanism of risk accidents. The preliminary results of application case show the effectiveness of our method to simulate human risk behaviors in coalmine virtual environment.

We analyze if large language models are able to predict patterns of human reading behavior. We compare the performance of language-specific and multilingual pretrained transformer models to predict reading time measures reflecting natural human sentence processing on Dutch, English, German, and Russian texts. This results in accurate models of human reading behavior, which indicates that transformer models implicitly encode relative importance in language in a way that is comparable to human processing mechanisms. We find that BERT and XLM models successfully predict a range of eye tracking features. In a series of experiments, we analyze the cross-domain and cross-language abilities of these models and show how they reflect human sentence processing.

A novel model is presented to explain human social behavior. In recent years, a cephalo-caudal directionality to behavior has been reported in a few mammals including rodents, cattle and cats. This model shows how complex human behavior also follows this rule of cephalo-caudal directionality. The positions of the lower motor neurons mediating the specific acts in the cephalo-caudal neural axis are considered to be an important correlate of the act. The model consists of a primary layer, consisting of the orienting modules – eyes, head and body and a secondary layer consisting of the six transmitting channels – the eyes, facial expression, speech, upper limbs, lower limbs and the external genitalia. The model demonstrates through multiple examples that complex human behavior also follows a cephalo caudal directionality, both in the orienting modules as well as in the transmitting channels. In this paradigm, conciliatory and agonistic communications are examined as prototypes for analysis of more complex dominant and submissive behavior as well as psychiatric conditions such as mania and depression. The model is sensitive to the social context of behavior which is without precedent in the literature. Further, the concept of ‘mobility gradient’ is applied to human behavior to understand motor behavior in depression and mania and catatonic behavior. Finally, certain issues pertinent to difficulties of behavioral description and model building in human behavior are discussed. The model emphasizes the role of objective behavioral description paradigms that borrow from concepts in comparative psychology and animal behavior.

Nowadays, the development of modern technologies in the transportation area has increased rapidly. The latest technology is focused on autonomous vehicles. The most important aspect in autonomous vehicle control systems is safety, smooth operation and comfort. It can be provided by the natural element which is from human behavior as a reference to the autonomous control system. This paper is briefly describing the human behavior during braking for autonomous electric vehicle (AEV) control system development. To obtain the human behaviour during accelerating and braking, two units of angle sensors were installed to the accelerator and brake pedal of an electric car to measure the angle of both pedals. Real-time speed is recorded by using a GPS unit. The experiment is focused on braking characteristic of the electric vehicle. It was carried out based on four different distances with fixed initial speed before braking action was recorded. A software interface was designed to display and control real-time speed and pedal angle value during operation.

Mining human behaviors has always been an important subarea of Data Mining. While it provides empirical evidences to psychological/behavioral studies, it also builds the foundation of various big-data systems, which rely heavily on the prediction of human behaviors. In recent years, the ubiquitous spreading of mobile phones and the massive amount of spatio-temporal data collected from them make it possible to keep track of the daily commute behaviors of mobile subscribers and further conduct routine mining on them. In this article, we propose to model mobile subscribers’ daily commute behaviors by three levels: location trajectory, one-day pattern, and routine pattern. We develop the model Spatio-Temporal Routine Mining Model (STRMM) to characterize the generative process between these three levels. From daily trajectories, the STRMM model unsupervisedly extracts spatio-temporal routine patterns that contain two aspects of information: (1) How people’s typical commute patterns are. (2) How much their commute behaviors vary from day to day. Compared to traditional methods, STRMM takes into account the different degrees of behavioral uncertainty in different timespans of a day, yielding more realistic and intuitive results. To learn model parameters, we adopt Stochastic Expectation Maximization algorithm. Experiments are conducted on two real world datasets, and the empirical results show that the STRMM model can effectively discover hidden routine patterns of human commute behaviors and yields higher accuracy results in trajectory prediction task.

Nowadays, close monitoring of daily activities of elders is enabled by employment of the advanced wireless sensor networks, whose large quantity data are then analyzed by activity recognition techniques whereby their behavior patterns can be accurately modelled. In general, behavior patterns are important information about how elders live, and caregivers can thus take care of elders easily with the help from that informaiton. So far, there are many research results related to learning of human behavior; however, their assumptions are usually either too simple or inflexible to account for complex human behaviors in real life, which change dynamically depending on contexts. We here present a context-aware framework for human behavior learning and prediction. Such framework discovers contexts from resident's real life data and adapts correspoinding behavior patterns next accordingly. We evaluate the framework on two public datasets, and the experimental results show promising results.