Reducing the Cognitive Workload While Operating in Complex Sensory Environments

This report proposes an adaptive recognition system, which is based on Kohonen self-organization network (KSOM). As the goals in the research on artificial neural network are to improve the recognition capability of the network and at the same time minimize the time needed for learning the patterns, these goals could be achieved by combining two types of learning, i.e. supervised learning and unsupervised learning. We have developed a new kind of hybrid neural learning system, combining unsupervised KSOM and supervised back-propagation learning rules. This hybrid neural system will henceforth be referred to as hybrid adaptive SOM with winning probability function and supervised BP or KSOM(WPF)-BP. This hybrid neural system could estimate the cluster distribution of given data, and directed it into predefined number of cluster neurons through creation and deletion mechanism. Comparison with other developed hybrid neural system is done for determination of various odors from Martha Tilaar Cosmetics product in an artificial odor recognition system. The performance of our developed learning system in term of its recognition ability and its learning time is explored in this report.

A real-time artificial intelligence (AI) recognition system is newly used for applications of selecting unqualified in chicken cages. The proposed recognition system can detect dirty eggs from those clean ones by using the developed artificial intelligence. Furthermore, the recognition system can classify those contaminated eggs into three categories by a covered contamination area. Performing this functionality of the proposed real-time AI recognition system, the system can successfully detect unqualified eggs in cage. In addition, by deleting the unnecessary predicted bounding boxes and performing the non-maximum suppression algorithm utilized in the experiment, the time spending on every picture will be fewer than normal videos. The proposed recognition system could be used for selecting unqualified eggs applications.

A fundamental assumption in relevance theory is that human cognition has evolved in the direction of increased efficiency and, as such, tends, as Sperber and Wilson (Relevance: Communication and cognition, 2nd ed. Oxford: Blackwell, 1995: 38–46, 260–66) put it in their cognitive principle, to be naturally geared towards the maximisation of relevance. The cognitive principle inter alia explains the selectivity of human agency and attention: for an input to merit the attention of the human cognitive system, it must seem relevant enough to be worth attending to. But what makes an input relevant? The relevance-theoretic account proposes that relevance for an individual organism at any specific time involves a balancing of mental effort and a particular type of worthwhile modifications, cognitive effects, that are representational in nature and amount to improvements in knowledge. The type of relevance yielded by such effects could be described as a cognitive type of relevance. However, inputs such as artistic stimuli – including literary ones – invite us to widen the scope of the causal engineering behind the selective directedness of our mental lives. Artistic stimuli merit the attention of the human cognitive system at various time-scales (momentary, developmental, and evolutionary). Following Kolaiti (The limits of expression: Language, literature, mind. Cambridge: Cambridge University Press, 2019: 76–94) and drawing on neuroscientific evidence from the last 25 years, I will make tentative suggestions that artistic stimuli may also yield non-representational worthwhile modifications or effects. My discussion focuses on one such type of effects involving the human perceptual system: perceptual effects. Being partly or wholly embodied, perceptual effects could extend the machinery of relevance theory in an embodied direction and widen its interdisciplinary implications.

How much about our interactions with—and experience of—our world can be deduced from basic principles? This paper reviews recent attempts to understand the self-organised behaviour of embodied agents, like ourselves, as satisfying basic imperatives for sustained exchanges with the environment. In brief, one simple driving force appears to explain many aspects of perception, action and the perception of action. This driving force is the minimisation of surprise or prediction error, which—in the context of perception—corresponds to Bayes-optimal predictive coding (that suppresses exteroceptive prediction errors) and—in the context of action—reduces to classical motor reflexes (that suppress proprioceptive prediction errors). In what follows, we look at some of the phenomena that emerge from this single principle, such as the perceptual encoding of spatial trajectories that can both generate movement (of self) and recognise the movements (of others). These emergent behaviours rest upon prior beliefs about itinerant (wandering) states of the world—but where do these beliefs come from? In this paper, we focus on the nature of prior beliefs and how they underwrite the active sampling of a spatially extended sensorium. Put simply, to avoid surprising states of the world, it is necessary to minimise uncertainty about those states. When this minimisation is implemented via prior beliefs—about how we sample the world—the resulting behaviour is remarkably reminiscent of searches seen in foraging or visual searches with saccadic eye movements.

While episodic memory impairments are at the core of Alzheimer's disease (AD), recent evidence has accumulated for early deficits in selective attention (focusing on a single relevant stimulus while inhibiting distracting stimuli). A diminished inhibitory system appears to contribute to selective attention deficits in mild AD; however, the role of selective attention is unknown in patients with amnestic Mild Cognitive Impairment (MCI). Regardless of a conversion to AD, evaluating selective attention is important in differentiating normal- and abnormal age-related attentional deficits. While several cognitive tests assess frontal function [Stroop Neuropsychological Inventory Test (Stroop) and Wisconsin Card Sorting Test (WCST)], saccadic eye movements (SEM; series of rapid eye movements in changing the point of fixation) also provide for a means to investigate age-related changes in frontal lobe systems. SEM may be automatic (eye movement made toward a visible stimulus-a prosaccade) or they can be generated voluntarily (eye movement away from a visible stimulus-an antisaccade). To analyze the relationship between scores of cognitive tests of frontal function and SEM in cognitively normal older adults and in patients with MCI and mild AD. Thirty-five cognitively normal older adults (mean ± SD age, 73.74 ± 5.67), eighteen MCI patients (78.11 ± 7.04), and fourteen mild AD patients (75.64 ± 6.02) completed the Stroop and WCST. Participants also performed one block (120 trials) of pro-saccades and two blocks (240 trials) of anti-saccades. Spearman correlations were performed to assess the relationship between cognitive test scores and SEM parameters (reaction time and direction errors). In cognitively normal older adults, a higher Stroop score significantly correlated with shorter reaction time (r=-.358, p=.038) and fewer direction errors (r=-.443, p=.010). A higher Stroop score significantly correlated with shorter reaction time in patients with MCI (r=-.558, p=.031) and mild AD (r=-.602, p=.038). These results show significant correlations between cognitive tests of frontal function and SEM parameters in cognitively normal older adults and in patients with MCI and mild AD. Measures of attention (Stroop and SEM scores) appear to be intact in cognitively normal older adults, yet impaired in patients with MCI and mild AD.

Based on neural network and local binary pattern algorithm, this paper builds a lightweight artificial face recognition system on chip Firefly-RK3399, with high speed, strong robustness and high recognition accuracy. Our embedded artificial intelligent face recognition system mainly consists of face detection, feature extraction and recognition. Multi-task convolutional neural network (MTCNN) under the CaffeOnACL framework is utilized for face detection, and the local binary pattern (LBP) is applied as face recognition algorithm. Experiments illustrate that our artificial intelligent embedded face recognition system has high speed and accuracy, which is easy-carrying and of high commercial value as well.

Most state-of-the-art service selection approaches assume user preferences can be provided by the target user with sufficient precision and ignore historical service usage data for all users. It is desirable for ordinary users to possess a new service selection approach that can recommend satisfactory services to them even when their service selection preferences are specified imprecisely in terms of vagueness, inaccuracy, and incompleteness. This paper proposes a novel service selection approach that resolves the imprecise characteristics of user preferences and can recommend satisfactory services for users with varying cognitive levels in terms of service experience. The proposed service selection approach is comprised of four major tasks: 1) employ user-friendly linguistic variables to collect apparent user preferences (AUP) and convert the linguistic variables to standardized fuzzy weights as AUP weights; 2) evaluate all users' respective cognitive levels for the target service type and obtain the cognitive level threshold for that type of services; 3) adjust the AUP weights based on the calculated cognitive levels and the threshold, and supplement the potential user preferences weights; and 4) prioritize candidate services per a user satisfaction maximization objective. In-depth comparative experimental evaluations were performed using two real-world datasets. The results show that our service selection model outperforms three other representative ones and could provide a stable and reliable selection of services for the users with low service cognitive levels.

Over the past two decades face recognition has gained immense interest and is one of the most interesting research areas. The reason for this could be the need for designing automatic recognition and surveillance systems or a human-computer interface. This involves knowledge and contribution not only from various fields of pattern recognition, machine learning, computer vision, and image processing but also in psychology and neuroscience. There are several challenging factors in face recognition like illumination, scale, expression, and pose which are addressed by several researchers to achieve a good recognition rate, but still, there is no robust technique that is available against uncontrolled factors from the environment, hardware, and software of the system. A facial recognition system is a technology that can recognize a human face by pinpointing and measuring facial features in an image. Face recognition allows access to buildings without the need for a key or even faster transits in airport security. But fraudsters can target this face recognition system like any other privacy technology with spoofing. Such a spoofing attack can be quite severe. Hackers will be able to gain access to secure facilities or buildings and homes resulting in the sabotage of critical and confidential data. In this work, a face recognition system with anti-spoofing features is proposed. ResNet50 neural network architecture is used for training the model for face recognition. For anti-spoofing, eye blink detection for photo attacks, and reflection of light for video attacks are incorporated. A prototype is built that implements these functions in hardware.

An automatic road sign recognition system based on a computational model of human recognition processing

Recognition-directed recovering of temporal information from handwriting images

1. Visual attention is often profoundly disturbed in humans after damage to the cortex of the posterior parietal lobe, particularly of the minor hemisphere, with some patients being totally unaware of visual stimuli in the hemifield of extrapersonal space contralateral to the cortical damage. This severe form of visual inattention is usually called contralateral neglect and has occasionally been reported following posterior parietal lesions in monkeys. However, in monkeys, only qualitative observations have been published and those reports are not in agreement concerning the severity of the deficit. The present experiments were designed to measure quantitatively the amount of disruption of selective visual attention which is produced by lesions of posterior parietal and parietooccipital cortical lesions in monkeys. 2. Five monkeys were trained to visually fixate and follow with their gaze a small visual stimulus as it suddenly moved varying distances (8, 16, or 24 degrees) from the midline into the left or right visual hemifields. Two animals then received a unilateral cortical lesion limited to the inferior parietal lobule (IPL). Three animals received unilateral lesions which included both the inferior parietal lobule and a portion of adjacent dorsal prestriate cortex (IPL-PS). 3. Visual inattention is commonly divided into two levels of severity. The more severe form, contralateral neglect, is the complete absence of behavioral response to a stimulus in the visual field contralateral to hemisphere damage. The less severe deficit, usually called visual extinction, is a tendency to ignore the contralateral of two visual stimuli when they appear simultaneously and symmetrically placed with respect to the center of the subject's surroundings. The five monkeys in this study were tested on a stimulus paradigm which simultaneously measured the severity of visual neglect and also the amount and duration of visual extinction which were produced by the cortical lesions. 4. All monkeys displayed contralateral visual extinction after unilateral posterior parietal or parietooccipital lesions. Three of the five monkeys showed a reversal of the visual extinction after a second, symmetrical lesion was placed in the opposite hemisphere. No monkey showed evidence of full-blown contralateral neglect after lesions limited to the parietooccipital cortex, either in the formal testing situation or during informal neurological examinations. The severity of the observed inattention did not appear to be related to the size of the cortical lesions.(ABSTRACT TRUNCATED AT 400 WORDS)

Decision Making in Recurrent Neuronal Circuits

Functional movement disorders (FMD) can overlap with Parkinson's disease (PD), and distinguishing between the two clinical conditions can be complex. Framing social cognition (theory of mind) (TOM) disorder, attention deficit, and psychodynamic features of FMD and PD may improve diagnosis. Subjects with FMD and PD and healthy controls (HC) were administered tasks assessing TOM abilities and attention. The psychodynamic hypothesis of conversion disorder was explored by a questionnaire assessing dissociative symptoms. A comprehensive battery of neuropsychological tasks was also administered to FMD and PD. Although both FMD and PD scored lower than HC on all TOM tests, significant correlations between TOM and neuropsychological tasks were found only in PD but not in FMD. Only PD showed a reduction in attentional control. Dissociative symptoms occurred only in FMD. Cognitive-affective disturbances are real in FMD, whereas they are largely dependent on cognitive impairment in PD. Attentional control is preserved in FMD compared to PD, consistent with the hypothesis that overload of voluntary attentional orientation may be at the basis of the onset of functional motor symptoms. On a psychodynamic level, the confirmation of dissociative symptoms in FMD supports the conversion disorder hypothesis. FMD and PD can be distinguished on an affective and cognitive level. At the same time, however, the objective difficulty often encountered in distinguishing between the two pathologies draws attention to how blurred the boundary between 'organic' and 'functional' can be.

Human factors were reported by researchers to be the reason behind the majority of car accidents; examples of these factors were: inattention, stress, distraction, decision making, drugs and alcohol abuses. Most of such studies were conducted based on western countries and on simulated driving situations, and very few of which used samples of participants who had accidents and/or driving violations in real life situations. To date, no studies at least in the Arab world generally and Gulf area specifically, conducted a comprehensive examination of cognitive functioning as potential predictors of car accidents and driving violations. Thus, the present study aimed at examining the role of cognitive functions (i.e., verbal working memory, attentional control, behavioral control, emotional control, cognitive failure, everyday memory failure, analytical cognitive style, mental planning, and general decision-making) as predictors of traffic accidents and driving violations. This was done based on empirical data from a hundred and thirty two men participants who aged between 24 and 31 years. All participants had driving licenses for more than five years and driving experiences of 8000000 KM and more. They were classified into violators and non-violators as well as accident free and accident involved groups. The cognitive functioning was measured using 5 self-reports and 2 tasks performance: Executive Functioning Scale, General Decision Making Scale, Cognitive Style Index, Cognitive Failure Questionnaire, Everyday Memory Questionnaire, Verbal Working Memory Task and Tower of London Task. A series of ANOVAS as well as stepwise multiple regressions were conducted to test the research hypothesis. Findings showed that there were significant differences between violators and non-violators and between the accident free and accident involved groups in almost all of the considered cognitive factors (P < .01), except for the decision making factor (P>.05). Results also indicated that the attentional control, behavioral control, emotional control, cognitive failure and mental planning factors were the major predictors of traffic violating behaviors and traffic accidents. Moreover, Pearson product-moment correlations showed that there were significant negative correlations between age, driving violations, and cognitive performance and the accidents. These obtained findings underscore the involvement of cognitive functioning in driving behavior and road accidents. Thus, when drivers working memory and/or executive functioning are overloaded, more demands on the cognitive recourses are imposed, which in result makes them vulnerable to wrong or hazardous driving decisions. It was also noted that those with higher mental planning abilities were involved in less moving violations and road accidents. This result was expected because as detected through the study, the more the time people take to move in the planning task, the more accidents and moving violations they report. It was also found that individuals with more driving mileage and holding driving licenses for a longer time period had more violations and driving accidents. In result, our findings contribute to the literature that human cognition such as executive functioning, mental planning and verbal working memory are key factors for predicting driving behavior and traffic accidents, and have many implications in diagnosing and preventing or at least reducing driving violations and road accidents.

In Chinese, word order is a powerful linguistic device indicating relations between constituents, on a semantic, syntactic and pragmatic level, and has been the focus of linguistic inquiry over the past decades. Particular attention has been given to the preverbal position, with heated debate on the notion of topic and other pragmatic-related phenomena. This study is a first step towards a better understanding of the order of preverbal NPs and verb modifiers, analyzing them in light of relevant cognition-based word order principles investigated within the cognitive- functional approach. Particular attention is given to the notion of 'scope', which pertains both to the discourse and the cognitive level ('topic scope' vs. 'temporal, spatial and semantic scope'), and which seems to better explain the order and the pragmatic role of preverbal NPs. On this ba- sis, this paper suggests a research path towards a deeper cognitive-functional comprehension of the preverbal position that takes into account the interplay of different word order related factors. Summary 1. Introduction. 2. Research Lines on Word Order in Chinese. 3. The Cognition-based Functional Approach: Observations and Assumptions. 4. Research on Conceptual Principles Un- derlying Chinese Language Patterns. 5. Relevant WO Principles and their Application in Explaining Preverbal Elements and Constructions. 5.1. The Principle of Temporal Sequence (PTS). 5.2. The Whole-Before-Part principle (WBP) . 5.3. Principle of Information Center (PIC) . 6. Cognitive Prin- ciples, Topic Scopes and Preverbal Elements. 7. Conclusions.