Intelligent perception

The Road for 2D Semiconductors in the Silicon Age

Continued reduction in transistor size can improve the performance of silicon integrated circuits (ICs). However, as Moore's law approaches physical limits, high-performance growth in silicon ICs becomes unsustainable, due to challenges of scaling, energy efficiency, and memory limitations. The ultrathin layers, diverse band structures, unique electronic properties, and silicon-compatible processes of 2D materials create the potential to consistently drive advanced performance in ICs. Here, the potential of fusing 2D materials with silicon ICs to minimize the challenges in silicon ICs, and to create technologies beyond the von Neumann architecture, is presented, and the killer applications for 2D materials in logic and memory devices to ease scaling, energy efficiency bottlenecks, and memory dilemmas encountered in silicon ICs are discussed. The fusion of 2D materials allows the creation of all-in-one perception, memory, and computation technologies beyond the von Neumann architecture to enhance system efficiency and remove computing power bottlenecks. Progress on the 2D ICs demonstration is summarized, as well as the technical hurdles it faces in terms of wafer-scale heterostructure growth, transfer, and compatible integration with silicon ICs. Finally, the promising pathways and obstacles to the technological advances in ICs due to the integration of 2D materials with silicon are presented.

Intelligent Traffic Flow Prediction and Analysis Based on Internet of Things and Big Data

Nowadays, the problem of road traffic safety cannot be ignored. Almost all major cities have problems such as poor traffic environment and low road efficiency. Large-scale and long-term traffic congestion occurs almost every day. Transportation has developed rapidly, and more and more advanced means of transportation have emerged. However, automobile is one of the main means of transportation for people to travel. In the world, there are serious traffic jams in almost all cities. The excessive traffic flow every day leads to the paralysis of the urban transportation system, which brings great inconvenience and impact to people's travel. Various countries have also actively taken corresponding measures, i.e., traffic diversion, number restriction, or expanding the scale of the road network, but these measures can bring little effect. Traditional intelligent traffic flow forecasting has some problems, such as low accuracy and delay. Aiming at this problem, this paper uses the model of the combination of Internet of Things and big data to apply and analyze its social benefits in intelligent traffic flow forecasting and analyzes its three-tier network architecture model, namely, perception layer, network layer, and application layer. Research and analyze the mode of combining cloud computing and edge computing. From the multiperspective linear discriminant analysis algorithm of the combination method of combining the same points and differences between data and data into multiple atomic services, intelligent traffic flow prediction based on the combination of Internet of Things and big data is performed. Through the monitoring and extraction of relevant traffic flow data, data analysis, processing and storage, and visual display, improve the accuracy and effectiveness and make it easier to improve the prediction accuracy of overall traffic flow. The traffic flow prediction of the system of Internet of Things and big data is given through the case experiment. The method proposed in this paper can be applied in intelligent transportation services and can predict the stability of transportation and traffic flow in real time so as to optimize traffic congestion, reduce manual intervention, and achieve the goal of intelligent traffic management.

Intelligent Perception-Based Cattle Lameness Detection and Behaviour Recognition: A Review

Simple Summary

Cattle lameness detection as well as behaviour recognition are the two main objectives in the applications of precision livestock farming (PLF). Over the last five years, the development of smart sensors, big data, and artificial intelligence has offered more automatic tools. In this review, we discuss over 100 papers that used automated techniques to detect cattle lameness and to recognise animal behaviours. To assist researchers and policy-makers in promoting various livestock technologies for monitoring cattle welfare and productivity, we conducted a comprehensive investigation of intelligent perception for cattle lameness detection and behaviour analysis in the PLF domain. Based on the literature review, we anticipate that PLF will develop in an objective, autonomous, and real-time direction. Additionally, we suggest that further research should be dedicated to improving the data quality, modeling accuracy, and commercial availability.

Abstract

The growing world population has increased the demand for animal-sourced protein. However, animal farming productivity is faced with challenges from traditional farming practices, socioeconomic status, and climate change. In recent years, smart sensors, big data, and deep learning have been applied to animal welfare measurement and livestock farming applications, including behaviour recognition and health monitoring. In order to facilitate research in this area, this review summarises and analyses some main techniques used in smart livestock farming, focusing on those related to cattle lameness detection and behaviour recognition. In this study, more than 100 relevant papers on cattle lameness detection and behaviour recognition have been evaluated and discussed. Based on a review and a comparison of recent technologies and methods, we anticipate that intelligent perception for cattle behaviour and welfare monitoring will develop towards standardisation, a larger scale, and intelligence, combined with Internet of things (IoT) and deep learning technologies. In addition, the key challenges and opportunities of future research are also highlighted and discussed.

A mobile, high-throughput semi-automated system for testing cognition in large non-primate animal models of Huntington disease

BACKGROUND

For reasons of cost and ethical concerns, models of neurodegenerative disorders such as Huntington disease (HD) are currently being developed in farm animals, as an alternative to non-human primates. Developing reliable methods of testing cognitive function is essential to determining the usefulness of such models. Nevertheless, cognitive testing of farm animal species presents a unique set of challenges. The primary aims of this study were to develop and validate a mobile operant system suitable for high throughput cognitive testing of sheep.

NEW METHOD

We designed a semi-automated testing system with the capability of presenting stimuli (visual, auditory) and reward at six spatial locations. Fourteen normal sheep were used to validate the system using a two-choice visual discrimination task. Four stages of training devised to acclimatise animals to the system are also presented.

RESULTS

All sheep progressed rapidly through the training stages, over eight sessions. All sheep learned the 2CVDT and performed at least one reversal stage. The mean number of trials the sheep took to reach criterion in the first acquisition learning was 13.9±1.5 and for the reversal learning was 19.1±1.8.

COMPARISON WITH EXISTING METHOD(S)

This is the first mobile semi-automated operant system developed for testing cognitive function in sheep.

CONCLUSIONS

We have designed and validated an automated operant behavioural testing system suitable for high throughput cognitive testing in sheep and other medium-sized quadrupeds, such as pigs and dogs. Sheep performance in the two-choice visual discrimination task was very similar to that reported for non-human primates and strongly supports the use of farm animals as pre-clinical models for the study of neurodegenerative diseases.

Zoomorphism and anthropomorphism: fruitful fallacies?

Zoo- and anthropomorphism may both be scientific heresies but both may serve as a basis for thought (and real) experiments designed to explore our ability to assess quality of life as perceived by another sentient animal. Sentience, a major contributor to evolutionary fitness in a complex environment, implies ‘feelings that matter’. Strength of motivation is a measure of how much they matter. Since humans and most domestic animals share the property of sentience, it follows that some aspects of feeling may be similar, and where we differ, the differences may be of degree rather than absolute. One of the assumed absolutes that I shall challenge is the concept that non-human animals live only in the present. I explore how domestic animals may experience the feelings of hunger, pain, fear and hope. Hunger is indisputably a primitive sensation. Pain and fear are primitive sensations with emotional overtones. The problem is to discover how they may affect quality of life. Acute pain and fear are positive signals for action to avoid harm. These actions and their consequences (‘how well did I cope?’) will be committed to memory and affect how an animal feels when they recur, or it fears they may recur. Hope (and its antithesis, despair) are considered by many philosophers (who do not own dogs) as emotions restricted to humans since only we can imagine the future. However, by application of zoomorphism we may classify hope with hunger as a primitive feeling of dissatisfaction with the status quo. Either may lead to action directed towards the goal of feeling better or encourage the belief that things will get better (food will arrive). Both are feelings of expectation for the future modulated in the light of past experience. With all these four emotions quality of life may be expressed in terms of how well the animal feels it can cope, both in the present and in the future. When it feels it cannot cope, then it will suffer.

Challenge by a novel object does not impair the capacity of ewes and lambs selected for a nervous temperament to display early preference for each other

Novelty, a powerful fear-inducing and stressful stimulus, could be detrimental on the capacity of ewes and lambs to recognise each other. The effect of a novel object on the ability of ewes and lambs, selected for their calm or nervous temperament, to show a preference for each other was tested in a two-choice discrimination test. Both calm and nervous temperament mothers showed a preference towards their own offspring rather than the alien lambs. Nervous temperament ewes also looked at their own lamb more than the alien. In contrast, nervous lambs showed a greater preference and took less time to reach their own mother than calm lambs. Nervous temperament does not seem to impair the capacity of ewes and lambs to display an early preference for each other, and might be an advantage in some challenging postnatal situations because of the increased motivation of nervous lambs to reunite with their mother.

Cattle discriminate between familiar and unfamiliar conspecifics by using only head visual cues

Faces have features characteristic of the identity, age and sex of an individual. In the context of social communication and social recognition in various animal species, facial information is relevant for discriminating between familiar and unfamiliar individuals. Here, we present two experiments aimed at testing the ability of cattle (Bos taurus) to visually discriminate between heads (including face views) of familiar and unfamiliar conspecifics represented as 2D images. In the first experiment, we observed the spontaneous behaviour of heifers when images of familiar and unfamiliar conspecifics were simultaneously presented. Our results show that heifers were more attracted towards the image of a familiar conspecific (i.e., it was chosen first, explored more, and given more attention) than towards the image of an unfamiliar one. In the second experiment, the ability to discriminate between images of familiar and unfamiliar conspecifics was tested using a food-rewarded instrumental conditioning procedure. Eight out of the nine heifers succeeded in discriminating between images of familiar and unfamiliar conspecifics and in generalizing on the first trial to a new pair of images of familiar and unfamiliar conspecifics, suggesting a categorization process of familiar versus unfamiliar conspecifics in cattle. Results of the first experiment and the observation of ear postures during the learning process, which was used as an index of the emotional state, provided information on picture processing in cattle and lead us to conclude that images of conspecifics were treated as representations of real individuals.

Behavioural and neurophysiological evidence for face identity and face emotion processing in animals

Visual cues from faces provide important social information relating to individual identity, sexual attraction and emotional state. Behavioural and neurophysiological studies on both monkeys and sheep have shown that specialized skills and neural systems for processing these complex cues to guide behaviour have evolved in a number of mammals and are not present exclusively in humans. Indeed, there are remarkable similarities in the ways that faces are processed by the brain in humans and other mammalian species. While human studies with brain imaging and gross neurophysiological recording approaches have revealed global aspects of the face-processing network, they cannot investigate how information is encoded by specific neural networks. Single neuron electrophysiological recording approaches in both monkeys and sheep have, however, provided some insights into the neural encoding principles involved and, particularly, the presence of a remarkable degree of high-level encoding even at the level of a specific face. Recent developments that allow simultaneous recordings to be made from many hundreds of individual neurons are also beginning to reveal evidence for global aspects of a population-based code. This review will summarize what we have learned so far from these animal-based studies about the way the mammalian brain processes the faces and the emotions they can communicate, as well as associated capacities such as how identity and emotion cues are dissociated and how face imagery might be generated. It will also try to highlight what questions and advances in knowledge still challenge us in order to provide a complete understanding of just how brain networks perform this complex and important social recognition task.

Transfer between views of conspecific faces at different ages or in different orientations by sheep

Sheep are able to discriminate photographs of conspecific faces. The present study investigates adult ewe's recognition of faces of the same animal between different ages or between different orientations. Twelve adult sheep were first trained to discriminate between faces of two unfamiliar animals, one of which was associated with a food reward. Transfer of discrimination from this pair to the same pair but at a different age, or in a different orientation, was then evaluated (transfer test), and compared with a new pair of the same condition (control test). Learned discrimination of a frontal view of unfamiliar 3-month-old lambs' faces improved subsequent discrimination of the same pair when they were 1-month-old in comparison to discrimination of new 1-month-old faces. Moreover, sheep that were trained to discriminate frontal views of unfamiliar adult individuals discriminated profile views of the same animals more accurately than that of novels. However, learned discrimination of the profile view of unfamiliar adult faces had no effect on subsequent discrimination of the frontal view of that same pair. These results suggest that to some extent sheep recognise faces of unfamiliar animals at different ages and in different orientations.

Stockmanship and Farm Animal Welfare

Human factors (attitudes, personality traits, self-esteem, job satisfaction) strongly determine our behaviour towards animals, animal production and animal welfare. Recent studies have emphasised positive human contacts as indicators of a stockperson's positive attitude towards animals and towards animal welfare in general. Stockmanship can be improved by careful selection of people and/or by training. However, little is known of the biological basis of the effect of stock handling procedures on the welfare of animals. The animal's perception of the stockperson (based both on emotional responses and cognitive aspects such as anticipation, recognition and categorisation), and the existence of sensitive periods in an animal's life, need to be explored in more depth, especially under farm conditions. We need to consider the complexity of human behaviour (eg husbandry practices, balance between positive and negative interactions, predictability, controllability) and its effect on animal welfare from the animal's point of view throughout its whole life. This paper identifies the importance of positive human contacts for both animals and stockpeople, and highlights the challenge to maintain such positive contacts despite the trend in modern agriculture to increase the number of animals per stockperson. This requires better knowledge of animal genetics, socialisation to humans during sensitive periods, and management of the social group. We emphasise the ethical importance of the human-animal relationship in the context of farm animal welfare and productivity.

Involvement of central muscarinic receptors in social and nonsocial learning in sheep

Within 12 h following parturition, ewes develop visual and auditory recognition of their lamb. To investigate whether central cholinergic muscarinic transmission plays a specific role in this social learning, we studied the effects of a muscarinic antagonist on neonate recognition via visual/auditory cues and acquisition of a nonsocial visual discrimination. Injections of scopolamine (100 microg/kg; a muscarinic antagonist crossing the blood-brain barrier) after birth did not affect maternal behavior but impaired visual/auditory recognition of the offspring. Recognition impairment did not occur in mothers treated with methylscopolamine (100 microg/kg; a peripheral muscarinic antagonist), indicating that central muscarinic transmission is specifically involved in this social learning. Similar doses of scopolamine strongly delayed learning of a nonsocial, visual discrimination task in comparison to either control or methylscopolamine-treated ewes. Performance on this task was not affected when scopolamine treatment was applied after learning, demonstrating that central muscarinic receptors are necessary for acquisition but not for retrieval. These results suggest that the central muscarinic transmission participates in the establishment of visual/auditory recognition of conspecifics. Moreover, activation of central muscarinic receptors is critical for learning regardless of the social properties of the stimulus.

Distribution and co-localization of choline acetyltransferase and p75 neurotrophin receptors in the sheep basal forebrain: implications for the use of a specific cholinergic immunotoxin

The basal forebrain cholinergic system is involved in different forms of memory. To study its role in social memory in sheep, an immunotoxin, ME20.4 immunoglobulin G (IgG)-saporin, was developed that is specific to basal forebrain cholinergic neurons bearing the p75 neurotrophin receptor. The distribution of sheep cholinergic neurons was mapped with an antibody against choline acetyltransferase. To assess the localization of the p75 receptor on basal forebrain cholinergic neurons, the distribution of p75 receptor-immunoreactive neurons with ME20.4 IgG was examined, and a double-labeling study with antibodies against choline acetyltransferase and p75 receptor was undertaken. The loss of basal forebrain cholinergic neurons and acetylcholinesterase fibers in basal forebrain projection areas was assessed in ewes that had received intracerebroventricular injections of the immunotoxin (50, 100 or 150 microg) alone, as well as, in some of the ewes treated with the highest dose, with bilateral immunotoxin injections in the nucleus basalis (11 microg/side). Results indicated that choline acetyltransferase- and p75 receptor-immunoreactive cells had similar distributions in the medial septum, the vertical and horizontal limbs of the band of Broca, and the nucleus basalis. The double-labeling procedure revealed that 100% of the cholinergic neurons are also p75 receptor positive in the medial septum and in the vertical and horizontal limbs of the band of Broca, and 82% in the nucleus basalis. Moreover, 100% of the p75 receptor-immunoreactive cells of these four nuclei were cholinergic. Combined immunotoxin injections into ventricles and the nucleus basalis produced a near complete loss (80-95%) of basal forebrain cholinergic neurons and acetylcholinesterase-positive fibers in the hippocampus, olfactory bulb and entorhinal cortex. This study provides the first anatomical data concerning the basal forebrain cholinergic system in ungulates. The availability of a selective cholinergic immunotoxin effective in sheep provides a new tool to probe the involvement of basal forebrain cholinergic neurons in cognitive processes in this species.

Behavioural and Neural Correlates of Mental Imagery in Sheep Using Face Recognition Paradigms

Determining objective measures for proof of consciousness in non-human animals has been helped by improved understanding of neural correlates of human consciousness. Functional imaging and neuropsychological studies have shown remarkable overlap between structures involved in actual perception of social and non-social objects and those involved in forming mental images of them. One area of particular interest is individual face recognition. This involves regions of the temporal lobe that are mainly only activated by actual perception or mental imagery of faces. Using behavioural, neuroanatomical and neurophysiological approaches in sheep, we have found that they have similar specialized abilities for recognizing many individuals from their faces. They have developed the same specialized neural processing regions in the temporal lobe for aiding such recognition. Furthermore, parallel activation of other brain regions controlling behavioural and emotional responses only occurs when they are overtly interested in the individuals whose faces they perceive. Such interest might therefore equate to their becoming consciously aware of them. Preliminary experiments have indicated that sheep may form and use mental images and that the regions of the temporal lobe that respond to faces can also do so under conditions where faces are suggested but do not actually appear. Such similarities between humans and sheep in this form of social recognition make it difficult to claim that humans can form mental images of faces whereas sheep cannot. While the ability to form and use mental imagery is not in itself definitive proof of consciousness, it is an important component part.