Evaluating Behavior Recognition Pipeline of Laying Hens Using Wearable Inertial Sensors.

Recently, animal welfare has gained worldwide attention. The concept of animal welfare encompasses the physical and mental well-being of animals. Rearing layers in battery cages (conventional cages) may violate their instinctive behaviors and health, resulting in increased animal welfare concerns. Therefore, welfare-oriented rearing systems have been explored to improve their welfare while maintaining productivity. In this study, we explore a behavior recognition system using a wearable inertial sensor to improve the rearing system based on continuous monitoring and quantifying behaviors. Supervised machine learning recognizes a variety of 12 hen behaviors where various parameters in the processing pipeline are considered, including the classifier, sampling frequency, window length, data imbalance handling, and sensor modality. A reference configuration utilizes a multi-layer perceptron as a classifier; feature vectors are calculated from the accelerometer and angular velocity sensor in a 1.28 s window sampled at 100 Hz; the training data are unbalanced. In addition, the accompanying results would allow for a more intensive design of similar systems, estimation of the impact of specific constraints on parameters, and recognition of specific behaviors.

New Position Candidate Identification via Clustering toward an Extensible On-Body Smartphone Localization System.

On-body device position awareness plays an important role in providing smartphone-based services with high levels of usability and quality. Traditionally, the problem assumed that the positions that were supported by the system were fixed at the time of design. Thus, if a user stores his/her terminal into an unsupported position, the system forcibly classifies it into one of the supported positions. In contrast, we propose a framework to discover new positions that are not initially supported by the system, which adds them as recognition targets via labeling by a user and re-training on-the-fly. In this article, we focus on a component of identifying a set of samples that are derived from a single storing position, which we call new position candidate identification. Clustering is applied as a key component to prepare a reliable dataset for re-training and to reduce the user's burden of labeling. Specifically, density-based spatial clustering of applications with noise (DBSCAN) is employed because it does not require the number of clusters in advance. We propose a method of finding an optimal value of a main parameter, Eps-neighborhood (eps), which affects the accuracy of the resultant clusters. Simulation-based experiments show that the proposed method performs as if the number of new positions were known in advance. Furthermore, we clarify the timing of performing the new position candidate identification process, in which we propose criteria for qualifying a cluster as the one comprising a new position.

Estimating Visibility of Annotations for View Management in Spatial Augmented Reality Based on Machine-Learning Techniques.

Augmented Reality (AR) is a class of "mediated reality" that artificially modifies the human perception by superimposing virtual objects on the real world, which is expected to supplement reality. In visual-based augmentation, text and graphics, i.e., label, are often associated with a physical object or a place to describe it. View management in AR is to maintain the visibility of the associated information and plays an important role on communicating the information. Various view management techniques have been investigated so far; however, most of them have been designed for two dimensional see-through displays, and few have been investigated for projector-based AR called spatial AR. In this article, we propose a view management method for spatial AR, VisLP, that places labels and linkage lines based on the estimation of the visibility. Since the information is directly projected on objects, the nature of optics such as reflection and refraction constrains the visibility in addition to the spatial relationship between the information, the objects, and the user. VisLP employs machine-learning techniques to estimate the visibility that reflects human's subjective mental workload in reading information and objective measures of reading correctness in various projection conditions. Four classes are defined for a label, while the visibility of a linkage line has three classes. After 88 and 28 classification features for label and linkage line visibility estimators are designed, respectively, subsets of features with 15 and 14 features are chosen to improve the processing speed of feature calculation up to 170%, with slight degradation of classification performance. An online experiment with new users and objects showed that 76.0% of the system's judgments were matched with the users' evaluations, while 73% of the linkage line visibility estimations were matched.

Ascending contraction and descending relaxation in the distal colon of mice lacking interstitial cells of Cajal.

Recently an essential role of interstitial cells of Cajal (ICC) within myenteric plexus (ICC-MY) was suggested in ascending contraction and descending relaxation in the mouse ileum. The role of ICC in these neural reflexes was examined in the distal colonic segments prepared from the wild type and c-kit mutant, W/W(V) mice, in the present study. Localized distension of the segments from the wild type mice by using a small balloon resulted in ascending contraction and descending relaxation. In the segments from the mutant mice, localized distension also induced these neural reflexes similar to those observed in the wild type mice. Immunohistochemical examination demonstrated that ICC-MY and ICC present in muscle layers (ICC-IM) were severely disrupted in the mutant mouse, but only ICC, present within submucosal plexus (ICC-SMP), remained unchanged. In the small strips with ICC-SMP absent prepared from the mutant mouse, electrical field stimulation induced contraction or relaxation in the absence or presence of atropine, respectively. It was suggested that ICC have no important role in the ascending and descending neural reflexes in the mouse distal colon, this is in direct contrast to the role of ICC-MY in the ileum.

Examination of the role of cholinergic myenteric neurons with the impairment of neural reflexes in the ileum of c-kit mutant mice.

Our previous study showed that impairment of ascending and descending neural reflexes in the ileum of the c-kit mutant, W/W(V), mice is due to a loss of interstitial cells of Cajal present at the myenteric plexus region (ICC-MY) in the mutant. In the present study, cholinergic interneurons were thought to be involved in these pathways, since hexamethonium, an antagonist of the nicotinic ACh receptor, significantly inhibited both neural reflexes in wild type mice. Therefore, we examined whether the loss of ICC-MY affects cholinergic interneurons involved in these pathways. Immunohistochemistry with anti-choline acetyltransferase revealed that there was no difference in the numbers of immunopositive cells in the myenteric plexus region between the wild type and mutant mice. In addition, there was no difference in the extent of spontaneous and EFS-evoked ACh release from longitudinal muscle with myenteric plexus preparations between the wild type and mutant mice. Exogenously added nicotine induced contraction or relaxation of ileal circular muscle in the absence or presence of atropine, respectively, to a similar extent in both the wild type and mutant mice. These results suggest that loss of ICC-MY resulted in an impairment of the ascending and descending reflex pathways at the step before activation of cholinergic interneurons.

Roles of M2 and M4 muscarinic receptors in regulating acetylcholine release from myenteric neurons of mouse ileum.

We investigated the subtype of presynaptic muscarinic receptors associated with inhibition of acetylcholine (ACh) release in the mouse small intestine. We measured endogenous ACh released from longitudinal muscle with myenteric plexus (LMMP) preparations obtained from M1-M5 receptor knockout (KO) mice. Electrical field stimulation (EFS) increased ACh release in all LMMP preparations obtained from M1-M5 receptor single KO mice. The amounts of ACh released in all preparations were equal to that in the wild-type mice. Atropine further increased EFS-induced ACh release in the wild-type mice. Unexpectedly, atropine also increased, to a similar extent, EFS-induced ACh release to the wild-type mice in all M1-M5 receptor single KO mice. In M2 and M4 receptor double KO mice, the amount of EFS-induced ACh release was equivalent to an atropine-evoked level in the wild-type mouse, and further addition of atropine had no effect. M2 receptor immunoreactivity was located in both smooth muscle cells and enteric neurons. M4 receptor immunoreactivity was located in the enteric neurons, being in co-localization with M2 receptor immunoreactivity. These results indicate that both M2 and M4 receptors mediate the muscarinic autoinhibition in ACh release in the LMMP preparation of the mouse ileum, and loss of one of these subtypes can be compensated functionally by a receptor that remained. M1, M3, and M5 receptors do not seem to be involved in this mechanism.

Role of the interstitial cells distributed in the myenteric plexus in neural reflexes in the mouse ileum.

We examined the role of interstitial cells of Cajal (ICC) in the ascending and descending neural reflexes in the ileal segments prepared from wild type mice and c-kit mutant W/WV mice. Localized distension of the ileal segments from wild type mice with a small balloon caused contraction or relaxation of the circular muscle on the oral or anal side of the distended region, respectively. However, these intestinal reflexes were not induced in the ileal segments from the mutant mice. In the small strips that include the step of the pathways from efferent motor neurons to smooth muscle cells, nerve stimulation induced contraction of circular muscle in the absence of atropine and relaxation in the presence of atropine. The extent of nerve stimulation-induced contractions and relaxations of the ileal circular muscle were similar in wild type and W/WV mice. The responsiveness of ileal circular muscle to exogenously added acetylcholine and Nor-1, a nitric oxide donor, was also unaffected in the mutant ileum. Since previous immunohistochemical study had revealed selective loss of ICC within the myenteric plexus (ICC-MY) in the mutant ileum, it was concluded that ICC-MY have an essential role in ascending and descending neural pathways in the mouse ileum.

Essential role of the interstitial cells of Cajal in nitric oxide-mediated relaxation of longitudinal muscle of the mouse ileum.

The role of interstitial cells of Cajal (ICC) in electrical field stimulation (EFS)-induced neurogenic responses in ileum was studied by using the ICC-deficient mutant (SLC-W/W(V)) mouse and its wild type. In the immunohistochemical study with anti-c-Kit antibody, ICC was observed in the myenteric plexus (MY) and deep muscular plexus (DMP) region in the wild type. In the mutant, ICC-MY were lost, only ICC-DMP were present. EFS induced a rapid contraction of the ileal segments from the wild type mouse in the direction of longitudinal muscle. In the mutant mouse, onset of contraction was delayed and its rate was slowed. EFS induced nonadrenergic, noncholinergic (NANC) relaxation in the presence of atropine and guanethidine in the wild type. A nitric oxide synthase inhibitor inhibited the relaxation and L-arginine reversed it. In the mutant, EFS did not induce NANC relaxation. There was no difference between the responsiveness of the segments from wild type and mutant mice to exogenously added acetylcholine or Nor-1. Taking into account the selective loss of ICC-MY in the mutant mice, it seems likely that ICC-MY have an essential role in inducing nitric oxide-mediated relaxation of longitudinal muscle of the mouse ileum and that ICC-MY partly participate in EFS-induced contraction.

Changes in mechanism of PACAP-induced relaxation in longitudinal muscle of the distal colon of Wistar rats with age.

Mechanisms of relaxation of longitudinal muscle of the distal colon induced by exogenously added pituitary adenylate cyclase activating peptide (PACAP) were studied in 2- to 30-week-old Wistar rats. Exogenous PACAP induced very significant relaxation of the longitudinal muscle in 2-week-old rats, but this effect decreased significantly with age. The cyclic AMP-cyclic AMP-dependent protein kinase (PKA) pathway and the tyrosine kinase-small conductance Ca2+-activated K+ channel (SK channel) pathway were found to be involved in the mechanism of PACAP-induced relaxation. In 2-week-old rats, PACAP-induced relaxation was significantly inhibited by tetrodotoxin (TTX). Since relaxation was also significantly inhibited by NG-nitro-L-arginine (N5-nitro-amidino-L-2,5-diamino-pentanoic acid: L-NOARG), the neurogenic effect of PACAP seems to be mediated mainly through nitric oxide neurons. In 8-week-old rats, L-NOARG and TTX had little effect on PACAP-induced relaxation, suggesting that the relaxant effect in 8-week-old rats is a direct action on longitudinal smooth muscle cells. Changes in the mechanisms of PACAP-induced relaxation with age were examined in the distal colon in relation to changes in the neurogenic and the direct effects of PACAP. The neurogenic effect in the exogenous PACAP-induced relaxation of the longitudinal muscle of the Wistar rat distal colon is dominant in tissue isolated from 2-week-old and lost in tissue isolated from 8-week-old rats.

A possible role of neurotensin in NANC relaxation of longitudinal muscle of the jejunum and ileum of Wistar rats.

The mediators of nonadrenergic, noncholinergic (NANC) relaxation in longitudinal muscle of the jejunum and ileum of Wistar rats were examined in vitro. Treatment of the jejunal and ileal segments with alpha-chymotrypsin resulted in decreases in the NANC relaxations induced by electrical field stimulation (EFS) by about one half. The NANC relaxations were also decreased by about one half after the segments had been desensitized to neurotensin. A neurotensin receptor antagonist, SR48692 (10 microM) inhibited the NANC relaxation by 56 and 34% in the jejunal and ileal segments, respectively. An inhibitor of small conductance Ca2+ -activated K+ channel (SK channel), apamin (100 nM) also inhibited the NANC relaxation by 83 and 63%, respectively. Exogenous neurotensin-induced relaxations of the two segments were abolished by apamin. In the ileal segments, N(G)-nitro-L-arginine (L-NOARG, 100 micro M), inhibited the NANC relaxation by 43%. L-NOARG, but not apamin, further inhibited the relaxation which persisted after the desensitization to neurotensin. Apamin with SR48692 inhibited the relaxation only to the same extent as apamin alone. EFS induced inhibitory junction potentials (i.j.ps) in the longitudinal muscle cells of the ileum. I.j.ps consisted of a rapid and a delayed phase. L-NOARG significantly inhibited only the delayed phase. EFS induced only a rapid i.j.ps in the jejunum. SR48692 and apamin inhibited the i.j.ps. These findings suggest that neurotensin and unknown substance(s) mediate NANC relaxation via SK channels in the jejunum of Wistar rats, and that neurotensin via SK channels and nitric oxide not via SK channels separately mediate the relaxation in the ileum.