Real-time rodent behavior classifier using color-based body segmentation (R2C2).

The goal of this paper is to evaluate the deep learning algorithm for people placed in the Autism Spectrum Disorder (ASD) classification. ASD is a developmental disability that causes the affected people to have significant communication, social, and behavioural challenges. People with autism are saddled with communication problems, difficulties in social interaction and displaying repetitive behaviours. Several methods have been used to classify the ASD from non-ASD people. However, there is a need to explore more algorithms that can yield better classification performance. Recently, deep learning methods have significantly sharpened the cutting edge of learning algorithms in a wide range of artificial intelligence tasks. These artificial intelligence tasks refer to object detection, speech recognition, and machine translation. In this research, the convolutional neural network (CNN) is employed. This algorithm is used to find processes that can classify ASD with a higher level of accuracy. The image data is pre-processed; the CNN algorithm is then applied to classify the ASD and non-ASD, and the steps of implementing the CNN algorithm are clearly stated. Finally, the effectiveness of the algorithm is evaluated based on the accuracy performance. The support vector machine (SVM) is utilised for the purpose of comparison. The CNN algorithm produces better results with an accuracy of 97.07%, compared with the SVM algorithm. In the future, different types of deep learning algorithms need to be applied, and different datasets can be tested with different hyper-parameters to produce more accurate ASD classifications.

The rapid development of Internet technology has led to increasingly complex web service systems. The resulting large number of component interactions pose a challenge to anomaly detection, which is realized primarily by operation and maintenance (OM) personnel through the deployment, management, and monitoring of various key performance indicators (KPIs). Anomalous behaviors during daily OM often cause problems in KPI data; these problems include high noise, high dimensionality, and large-scale data streams. In addition, anomalies in KPI data occur infrequently and are of various types. These factors are the cause of the very low accuracy currently observed in conventional machine learning methods for detecting anomalies in large OM systems. Hence, a convolutional long short-term memory (C-LSTM) neural network is presented in this study to detect anomalies in small datasets that contain a variety of anomalies. First, a sliding window is used to preprocess the KPI data. Then, a C-LSTM neural network, which combines the features of the convolutional neural network (CNN) and LSTM algorithms, is employed to effectively model the time and numerical information contained in the preprocessed KPI data. Finally, the C-LSTM algorithm is tested on the datasets used in the competition of the Artificial Intelligence for Information Technology Operations (AIOPs) Active Network Management (ANM) 2018 Fall Project. The results show that the C-LSTM prediction algorithm outperforms the conventional LSTM and CNN algorithms in terms of its capacity to detect anomalies in small datasets that contain various anomalies, with a 12.90% higher accuracy, 5.68% higher recall, and 9.58% higher F1-score.

The lateral occipitotemporal cortex (LOTC) is a part of the brain network thatprocesses human body recognition. It has been implicated in variousneurodevelopmental conditions, including autism spectrum disorder (ASD). Intypically developing (TD) individuals, functional magnetic resonance imaging(fMRI) studies have shown three distinct response patterns to three categoriesof body parts in the LOTC, namely, action effector body parts, non-effector bodyparts, and facial parts. It is currently unclear whether the similar topologicalorganization of the LOTC is observed in individuals with ASD, and if socialinteraction difficulties in this group may partially result from differences inbody part recognition in this area. In this fMRI study, adults with ASD and TDadults viewed photographs of hands, feet, arms, legs, chests, waists,upper/lower faces, whole bodies, and chairs. Mass univariate analysis showed nodifferences in the LOTC response to whole-body images (relative to images ofchairs) in the bilateral LOTC between adults with ASD and TD adults. Inaddition, there were no group differences in the responses to body parts.Furthermore, multivariate (representational similarity) analyses revealed asignificant similar body part representation organized into three clusters(limbs, torsos, and faces) in the bilateral LOTC between TD adults and thosewith ASD. These results indicate that TD adults and those with ASD havecomparable neural representations within the LOTC for whole bodies and bodyparts.

In order to improve the classification effect of the 3D CAD model, this paper combines the knowledge recognition algorithm of convolutional neural network to construct the 3D CAD model classification model. Moreover, this paper analyzes the application of the convolutional neural network algorithm in the classification of 3D CAD models, improves the knowledge recognition algorithm, and builds the basic structure of the convolutional neural network. In addition, this paper builds an intelligent recognition model with the support of the improved algorithm, designs experiments to verify the effect of this paper, and draws a visual display statistical graph based on the statistical test results. Through experimental research, it can be known that the 3D CAD classification model based on the knowledge recognition algorithm of convolutional neural network proposed in this paper can effectively improve the classification effect of the CAD model.

Autism spectrum disorders (ASDs) were originally described by Kanner (1943). The relatively consistent clinical phenotype will likely be shown to comprise numerous etiologic subtypes. Approximately 10% of ASD cases are linked to disorders of genetic etiology, such as Fragile X syndrome, tuberous sclerosis, and Rett disorder. The majority of cases, however, remain idiopathic. A role for immunological involvement in ASDs has long been hypothesized. Kanner did not comment on this in his initial descriptions, but a detailed review of the original 11 cases reveals important observations. One patient was ‘kept in bed often because of colds, bronchitis, chickenpox, streptococcus infection, impetigo and rheumatic fever'. Another was ‘given anterior pituitary and thyroid preparations and her father, aged 36 years, was one of those chronically thin persons, nervous energy readily expended', suggesting hyperthyroidism. In our clinical work and review of the literature, we have been impressed by the possible role of autoimmune disorders as influencing the pathophysiology of a distinct, objectively defined etiologic subtype of ASDs. Money et al (1971) published what is widely accepted as the first connection between autism and autoimmune disorders. They described a family in which the youngest child had multiple diagnoses, including autism, Addison's disease, moniliasis, and diabetes mellitus. The next older brother had hypoparathyroidism, Addison's disease, moniliasis, and alopecia totalis. The oldest son was symptom-free. The mother had ulcerative colitis, the father had ‘chronic athlete's foot', and a paternal uncle had diabetes mellitus. Consistent with these observations, we showed that first- and second-degree relatives of children with an ASD have a higher number of autoimmune disorders than family members of healthy children (Sweeten et al, 2003). In a recent post-mortem study of 13 males with autism and 9 control cases, microglia appeared markedly activated in 5 of 13 cases with autism, including 2 of 3 under the age of 6 years, and marginally activated in an additional 4 of 13 cases (Morgan et al, 2010), suggesting ongoing inflammatory processes in brain. Observations in humans are supported by experiments in laboratory animals. As one example, Martin et al (2008) exposed pregnant rhesus monkeys to human IgG collected from mothers of children diagnosed with ASDs, while controls received IgG collected from mothers of normally developing children. Those offspring that were gestationally exposed to IgG class antibodies from mothers of children with ASDs consistently demonstrated increases in stereotypies and hyperactivity. These findings suggest that some ASD-like behaviors can be triggered by environmental (non-genetic) manipulations. The notion that environmental factors contribute to ASD prevalence continues to evolve. Once-influential theories suggesting links among exposure to vaccines containing attenuated virus or toxins, conditions such as inflammatory bowel disease, and ASDs have fallen from favor since the retraction of a key study (Wakefield et al, 1998). It is important to emphasize, however, that the major reason for retraction was poor scientific method rather than theoretical flaws. Although ASDs are currently within the realm of psychiatrists and neurologists, it is becoming clear that at least some subtypes represent whole-body disorders, offering exciting new possibilities for therapy.

he percentage of fertile land for agriculture in India is above 50%, but the agricultural production, despite having such a high percentage of fertile land for agriculture, is not at the level expected. As most of the times, the expectations fail to be fulfilled as a result of the various plant diseases that affect the production of food. The purpose of this study is to propose a multilayered convolutional neural network algorithm that is used to predict the type of disease, type of fertilizer, and pesticide that should be used, thus helping farmers to initiate necessary action at the earliest stages of disease. As a result of using datasets that are readily available on GitHub, the proposed system is able to predict the disease on the basis of the datasets. A convolutional neural network algorithm is used for the implementation of the system in order to classify the diseased leaves of the plants using a convolutional neural network algorithm. Using the high-resolution camera, real-time images are taken of the plant leaves and are compared with the available data sets that have been collected for healthy and unhealthy plant leaves. Predictions are then made based on the test vectors from the trained model with the optimum outcomes. Depending on whether or not the plant is healthy, the prediction results are displayed on the screen.

Increasingly, the interface of the nervous system and bacteria is being investigated with respect to wellbeing, given that the communications between the gut and the brain are recognized to be integral in health and disease. In this topic, the microbial profiles were studied in relation to behavioural changes, genetic and environmental influences, as well as patient pathophysiology. The focus of these studies included Autism Spectrum Disorder (ASD), schizophrenia, and neurodegenerative diseases such as Alzheimer's Disease, Parkinson's Disease, Amyotrophic lateral sclerosis (ALS), and frontotemporal dementia (FTD).Altered gut-brain signaling has been implicated in several brain disorders, such as autism spectrum disorders (ASD). Accordingly, gut microbiota are increasingly considered a promising therapeutic target in ASD. Liu et al. showed that GW4064, an agonist of the Farnesoid X receptor (FXR), ameliorates the ASD-like behavior of BTBR mice, an animal model for ASD (Liu et al., 2022). In particular, the administration of GW4064 positively affected social behaviours as well as increased microbial abundance in the faeces. The high Firmicutes to Bacteroidetes ratio that has been proposed as a typical ASD phenotype was counteracted. In addition, GW4064 normalized elevated Lactobacillus and decreased Allobaculum levels. The data provides further evidence that targeting microbiota composition is a potential strategy for ameliorating ASD symptoms. Schizophrenia (SZ) still has a largely unknown aetiology and pathogenesis, but the gut microbiome is suggested to play a role. Ling et al. undertook a study of 161 elderly patients with and without SZ. Beta diversity could be used to cluster the two groups distinctly and identify SZ-associated bacteria, including Faecalibacterium, Roseburia, Actinomyces, Butyricicoccus, and Prevotella. IL-1β, a proinflammatory cytokine, was greatly increased in SZ patients as were anti-inflammatory cytokines such as IFN-γ were markedly decreased. Functional prediction indicated that the metabolic changes could lead to the production of immunomodulatory metabolites by the SZ microbiome.This study provided novel insights into structural and functional changes in SZ patients, paving the way for non-invasive diagnosis and the potential to use microbiome engineering as a target for treatment.Several clinical and preclinical studies relevant to ASD have described alterations in faecal microbial populations; however, it has been unclear whether similarities occur across models and in humans with ASD and mouse models. AlAmoudi and co-authors aimed to understand the similarities and differences between microbial profiles in humans and preclinical models of autism. A systematic review of the literature was undertaken to clarify the overlap or differences between previous clinical studies of the microbiome in patients with autism. Next, the fecal microbial communities were examined in a variety of mouse models of autism, including transgenic (i.e., NL3 R451C , Shank3 KO, 15q dup mice), the behaviourally identified BTBR mouse model, and the Poly-I:C and Maternal Inflammation Activation (MIA) and valproate environmental models. These authors identified that some genera were altered in fecal samples from both human autism and mouse model studies. Interestingly, Bilophila, Clostridium, Dorea, and Lactobacillus were increased in abundance in both clinical and mouse studies, whereas a decrease in Blautia was identified from the literature in both species. Some bacterial genera appeared to be susceptible to modification in both ASD patients and mouse models of autism, but the directional changes were non-uniform. These genera susceptible to change included Akkermansia, Bacteroides, Bifidobacterium, Parabacteroides, and Prevotella. Characterising these changes in microbial profiles in both clinical cohorts and mice relevant to ASD can assist in designing potential therapies that modulate the gut microbial populations for individuals with ASD.In a similar vein to AlAmoudi and colleagues, Hashim and Makpol compared clinical and preclinical studies of the microbiome but in the context of neurodegenerative diseases and the current state of the field in terms of a range of approaches being explored to shape the gut microbiome. Potential therapeutic approaches examined in this review include the use of probiotics, dietary modifications, fecal microbiota transplantation (FMT), and alterations in physical activity with the view to reduce or prevent the effects of ageing and neurodegenerative diseases. Specifically, microbial dysbiosis reported in clinical studies focusing on Alzheimer's Disease, Parkinson's Disease, Amyotrophic lateral sclerosis (ALS), and frontotemporal dementia (FTD) were reviewed. The potential benefits of this selected group of interventions for reducing or preventing the progression of these diseases were discussed, given that significant correlative evidence supporting the role of the brain-gut microbiota (BGM) axis in these disorders exists.In summary, these studies add to the growing evidence of a significant role for the microbiota-gut-brain axis in human health and highlight the critical need for multidisciplinary projects in this field.

Background:Brain-derived neurotrophic factor (BDNF) is a key factor in neurodevelopment of autism spectrum disorder (ASD), yet the variability of peripheral BDNF levels in ASD remains debated. We sought to investigate the relationship between circulating oxidative stress and peripheral BDNF in children with ASD.Methods:We analyzed plasma BDNF levels and redox status in both plasma and peripheral blood mononuclear cells (PBMCs) among children with ASD and typically developing (TD) children aged 2–5 years. We generated an autism-like mouse model via prenatal exposure to medroxyprogesterone acetate (MPA). To modulate circulating redox balance, we employed tyrosine kinase–driven lentiviral expression of superoxide dismutase 2 (Sod2) and hematopoietic stem cell (HSC) transplantation with Sod2 overexpression. We then assessed circulating redox balance, gene expression, epigenetic changes, peripheral BDNF levels, and autism-like behaviours in offspring.Results:We included 78 children in the ASD group and 63 children in the TD group. Children with ASD exhibited elevated plasma BDNF levels and an altered redox balance compared with TD controls. In the mouse model, MPA-exposed autism-like offspring demonstrated increased peripheral BDNF levels and heightened oxidative stress in hematopoietic stem cells, endothelial cells, and PBMCs. Tyrosine kinase–Sod2 lentiviral expression in the endothelium fully normalized peripheral BDNF levels, while HSC transplantation with Sod2 overexpression not only reduced plasma BDNF levels, but also alleviated autism-like behaviours.Limitations:This study’s cross-sectional data limit causal inference between oxidative stress and BDNF levels among children with ASD. The mouse model, while informative, may not fully recapitulate human ASD heterogeneity.Conclusion:In ASD, elevated peripheral BDNF levels are associated with circulating oxidative stress. Prenatal progestin exposure induces both increased peripheral BDNF and oxidative stress, effects that can be completely reversed through SOD2 modulation in circulation among mouse offspring.

Ovarian cancer is the deadliest among gynecologic cancers. It is partly due to the mild symptoms in early stages and relatively high diagnostic age (about 63-year-old median age). These factors contribute to the short chemotherapy response time and survival time with about 18- and 36-months median progression-free survival and overall survival duration, respectively. The advancements of convolutional neural network (CNN) machine learning algorithms provide opportunities for the development of cost- and time-effective models which is urgently needed for ovarian cancer patients, especially for those with elevated risk. A CNN model was trained with hematoxylin and eosin (H&E) stained tumor whole slide images (WSIs) from ovarian cancer patients with advanced stages. 773 WSIs of 335 patients from TCGA-OV dataset were separated randomly for training and testing cohort. The model was then applied on testing cohort with advanced stage and age patients for H&E survival score. The c-index of the predicted risk on overall survival (OS) and progression-free survival (PFS) were 0.66 and 0.63, respectively. The log-rank p-values of patients between low and high risk were 0.00137 and 0.00138, respectively. The model was then further evaluated with an external dataset. The c-index of the predicted risk were 0.64 and 0.72 for OS and PFS, respectively. And the log-rank test between patients with low and high risk achieved p-values 0.017 and 0.0047 for OS and PFS, respectively. In conclusion, a novel prognostic CNN model was developed for ovarian cancer patients with advanced age and stage for better disease management. Citation Format: Chun Wai Ng, Kwong-kwok Wong, Berrett Lawson, Sammy Ferri-Borgogno, Samuel Mok. Convolutional neural network algorithms and hematoxylin-and-eosin-stained images predict clinical outcomes in high-grade serous ovarian cancer patients with advanced age and stage [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7662.

Marine fish are one of the many natural resources that frequently consumed by people. However, several types of marine fish are prohibited from consumption due to being nearly extinct. Additionally, some fish species contain high levels of mercury that can be harmful to human if consumed. Because of the large number of marine fish species, it becomes challenging to identify them without knowledge of fisheries. Moreover, computers have become highly advanced devices that facilitate various human activities. This advancement allows for the creation of systems capable of processing information from images, known as image classification. There are numerous methods that can be employed in designing an image classification system, one of which is transfer learning. This study was aimed to design an image classification system using the transfer learning method with a pre-trained VGG16 model and Convolutional Neural Network algorithm. The research results showed a training data accuracy of 100% and a validation data accuracy of 99.3%, with an overall accuracy of 84% and a loss value of 0.6591.

BackgroundThe Clock Drawing Test (CDT) and Rey–Osterrieth Complex Figure Test (RCFT) are widely used as a part of neuropsychological test batteries to assess cognitive function. Our objective was to confirm the prediction accuracies of the RCFT-copy and CDT for cognitive impairment (CI) using convolutional neural network algorithms as a screening tool.MethodsThe CDT and RCFT-copy data were obtained from patients aged 60–80 years who had more than 6 years of education. In total, 747 CDT and 980 RCFT-copy figures were utilized. Convolutional neural network algorithms using TensorFlow (ver. 2.3.0) on the Colab cloud platform (www.colab.research.google.com) were used for preprocessing and modeling. We measured the prediction accuracy of each drawing test 10 times using this dataset with the following classes: normal cognition (NC) vs. mildly impaired cognition (MI), NC vs. severely impaired cognition (SI), and NC vs. CI (MI + SI).ResultsThe accuracy of the CDT was better for differentiating MI (CDT, 78.04 ± 2.75; RCFT-copy, not being trained) and SI from NC (CDT, 91.45 ± 0.83; RCFT-copy, 90.27 ± 1.52); however, the RCFT-copy was better at predicting CI (CDT, 77.37 ± 1.77; RCFT, 83.52 ± 1.41). The accuracy for a 3-way classification (NC vs. MI vs. SI) was approximately 71% for both tests; no significant difference was found between them.ConclusionsThe two drawing tests showed good performance for predicting severe impairment of cognition; however, a drawing test alone is not enough to predict overall CI. There are some limitations to our study: the sample size was small, all the participants did not perform both the CDT and RCFT-copy, and only the copy condition of the RCFT was used. Algorithms involving memory performance and longitudinal changes are worth future exploration. These results may contribute to improved home-based healthcare delivery.

The primary goal of this study is to propose and compare an automatic melanoma cancer detection system based on mobilenet architecture algorithm and convolutional neural network algorithm (CNN) to detect melanoma cancer. With a sample size of 10, Group 1 was the MobileNet architecture, and Group 2 was the Convolutional Neural Network algorithm. They were iterated 20 times to predict the accuracy percentage of melanoma cancer detection. The accuracy of the Mobilenet architecture algorithm (75%) is significantly higher than that of the Convolutional Neural Network (60%). The mobilenet architecture algorithm has a high statistical significance (p0.05 Independent Sample T-test). Within the scope of this study, the Mobilenet architecture algorithm outperforms Convolutional Neural networks in melanoma skin cancer detection.

Autism spectrum disorder (ASD) is a pervasive neurodevelopmental syndrome with a high human and economic burden. The pathophysiology of ASD is largely unclear, thus hampering development of pharmacological treatments for the core symptoms of the disorder. Abnormalities in glutamate and GABA signaling have been hypothesized to underlie ASD symptoms, and may form a therapeutic target, but it is not known whether these abnormalities are recapitulated in humans with ASD, as well as in rodent models of the disorder. We used translational proton magnetic resonance spectroscopy ([1H]MRS) to compare glutamate and GABA levels in adult humans with ASD and in a panel of six diverse rodent ASD models, encompassing genetic and environmental etiologies. [1H]MRS was performed in the striatum and the medial prefrontal cortex, of the humans, mice, and rats in order to allow for direct cross-species comparisons in specific cortical and subcortical brain regions implicated in ASD. In humans with ASD, glutamate concentration was reduced in the striatum and this was correlated with the severity of social symptoms. GABA levels were not altered in either brain region. The reduction in striatal glutamate was recapitulated in mice prenatally exposed to valproate, and in mice and rats carrying Nlgn3 mutations, but not in rodent ASD models with other etiologies. Our findings suggest that glutamate/GABA abnormalities in the corticostriatal circuitry may be a key pathological mechanism in ASD; and may be linked to alterations in the neuroligin–neurexin signaling complex.

Recent advances in human genetics identified genetic variants involved in causing autism spectrum disorders (ASDs). Mouse models that mimic mutations found in patients with ASD exhibit behavioral phenotypes consistent with ASD symptoms. These mouse models suggest critical biological factors of ASD etiology. Another important implication of ASD genetics is the enrichment of ASD risk genes in molecules involved in developing synapses and regulating neural circuit function. Sophisticated in vivo imaging technologies applied to ASD mouse models identify common synaptic impairments in the neocortex, with genetic-mutation-specific defects in local neural circuits. In this article, we review synapse- and circuit-level phenotypes identified by in vivo two-photon imaging in multiple mouse models of ASD and discuss the contributions of altered synapse properties and neural circuit activity to ASD pathogenesis.

Autism spectrum disorder (ASD) is a lifelong condition, yet most existing research focuses on autistic children, with limited understanding of aging in middle and old aged autistic adults. Several epidemiological studies and clinical observations found a striking prevalence of Parkinsonism in autistic adults, highlighting the urgent need to comprehensively understand the neuromotor degenerative processes in ASD. To fill this critical gap, we administered the Unified Parkinson’s Disease Rating Scale Part 3 (UPDRS-III) subtasks 3.4-3.8 in 35 autistic adults aged 30-73 and 25 matched neurotypical controls. During the assessment, our team identified a novel behavioral atypicality in autistic adults. This behavior, termed atypical rhythmic (AR) movements, differs from other repetitive behaviors in ASD and involves unintentional, rhythmic, small-amplitude movements in non-target body parts when the target body part was engaged in the assessment. For example, rhythmic toe-tapping, finger-tapping, and head-nodding of non-target limbs would qualify as AR behavior. We hypothesize that autistic individuals will have higher UPDRS scores than the general population and that the AR behavior will be qualitatively outlined. We report two key observations. First, autistic individuals scored significantly higher on UPDRS-III subtasks 3.4b, 3.7b, 3.8a, and 3.8b compared to neurotypical controls. Second, AR behaviors were found to manifest contralaterally, ipsilaterally, and centrally across various body appendages in autistic adults. Defining this behavior is clinically significant as it may reflect brain connectivity deficits commonly seen in autistic individuals. We speculate compromised corpus callosum circuitry and neural compensation may concurrently underlie AR behaviors in autistic adults. Future fMRI studies are needed to confirm its neural origins.