Using deep learning to detecting abnormal behavior in internet of things

<span lang="EN-US">The development of the internet of things (IoT) has increased exponentially, creating a rapid pace of changes and enabling it to become more and more embedded in daily life. This is often achieved through integration: IoT is being integrated into billions of intelligent objects, commonly labeled “things,” from which the service collects various forms of data regarding both these “things” themselves as well as their environment. While IoT and IoT-powered decices can provide invaluable services in various fields, unauthorized access and inadvertent modification are potential issues of tremendous concern. In this paper, we present a process for resolving such IoT issues using adapted long short-term memory (LSTM) recurrent neural networks (RNN). With this method, we utilize specialized deep learning (DL) methods to detect abnormal and/or suspect behavior in IoT systems. LSTM RNNs are adopted in order to construct a high-accuracy model capable of detecting suspicious behavior based on a dataset of IoT sensors readings. The model is evaluated using the Intel Labs dataset as a test domain, performing four different tests, and using three criteria: F1, Accuracy, and time. The results obtained here demonstrate that the LSTM RNN model we create is capable of detecting abnormal behavior in IoT systems with high accuracy.</span>

Tranquillizing Effect of Passiflora incarnata Extract: Outcome on Behavioral and Physiological Indicators in Weaning Pigs with Intact Tails

Tail docking has been used in the pig industry to decrease the occurrence of tail biting behavior. This abnormal behavior has a multifactorial origin since it is a response to simultaneous environmental, nutritional and management changes. Given the calming properties of Passiflora incarnata, we hypothesized that dietary supplementation with the extract in weaned pigs could result in a modification of behavior and physiologic indicators linked to stress. Weaned piglets (n = 120, mean body weight 9.07 ± 2.30 kg) were randomly allocated to one of two dietary treatments: control diet (CON) and CON supplemented with 1 kg/t of P. incarnata (PAS). The trial was 28 days long. The presence of skin lesions was assessed at d-1, d-10, d-19, and d-28, and saliva samples were collected for IgA and cortisol determinations at the same sampling times. Results showed the PAS group was characterized by equal growth performance as the CON group, fewer ear lesions (p < 0.05), less aggressive behavior (p < 0.001), higher enrichment exploration (p < 0.001) and lower cortisol levels (p < 0.01). Time effect was observed for tail lesions (p < 0.001) and behavioral observations (p < 0.001). Additional research is required to determine the effect of P. incarnata extract using a larger number of animals and longer period of supplementation when risks associated with tail biting are uncontrolled.

Clinical Features and Early Recognition of 242 Cases of Autoimmune Encephalitis

Objective: To analyze the clinical features of common autoimmune encephalitis and evaluate the sensitivity of antibodies contributing to focal epilepsy signs and symptoms (ACES) score.Methods: Collecting and analyzing the data of 242 patients with autoimmune encephalitis (AE) diagnosed in the First Affiliated Hospital of Zhengzhou University from August 2015 to December 2020 in this retrospective study. The six items of the ACES score (cognitive symptoms, behavioral changes, autonomic symptoms, speech problems, autoimmune diseases, temporal MRI hyperintensities) were screened in patients with complete clinical data.Results: (1) In total, 242 patients were included, with 147 cases of anti-N-methyl-D-aspartate receptor encephalitis, 47 cases of anti-γ-aminobutyric acid type B (GABA-B) receptor encephalitis, and 48 cases of anti-leucine-rich glioma inactivating protein 1 (LGI1) encephalitis. The most common clinical symptoms are cognitive impairment (77%), behavioral changes (79%), and seizures (71%). In total, 129 cases (54%) combined with autonomic dysfunction, such as gastrointestinal dysmotility, sinus tachycardia, and central hypoventilation. Twelve patients had autoimmune diseases, most of which were of thyroid diseases. (2) One hundred and twenty-seven patients with complete clinical data evaluated ACES score, 126 cases of whom (126/127, 99.2%) were equal to or &gt;2 points, 1 case (1/127, 0.8%) was of &lt;2 points.Interpretation: (1) Cognitive impairment, abnormal behavior, and seizures are the most common manifestations of AE and autonomic symptoms. Thyroid disease is the most autoimmune disease in AE. Clinically, for patients of suspected AE, increasing the knowledge and testing of thyroid function and rheumatism is necessary. (2) ACES score is a simple, effective, and easy-to-operate score, with a certain screening value for most patients suspected of AE.

A Quantitative Method for Measuring Health of Authoritative Name Servers

The Domain Name System - DNS is regarded as one of the critical infrastructure component of the global Internet because a large-scale DNS outage would effectively take a typical user offline. Therefore, the Internet community should ensure that critical components of the DNS ecosystem - that is, root name servers, top-level domain registrars and registries, authoritative name servers, and recursive resolvers - function smoothly. To this end, the community should monitor them periodically and provide public alerts about abnormal behavior. The authors propose a novel quantitative approach for evaluating the health of authoritative name servers – a critical, core, and a large component of the DNS ecosystem. The performance is typically measured in terms of response time, reliability, and throughput for most of the Internet components. This research work proposes a novel list of parameters specifically for determining the health of authoritative name servers: DNS attack permeability, latency comparison, and DNSSEC validation.

Anomaly Detection using system logs

Anomaly detection is a very important step in building a secure and trustworthy system. Manually it is daunting to analyze and detect failures and anomalies. In this paper, we proposed an approach that leverages the pattern matching capabilities of Convolution Neural Network (CNN) for anomaly detection in system logs. Features from log files are extracted using a windowing technique. Based on this feature, a one-dimensional image (1×n dimension) is generated where the pixel values of an image correlate with the features of the logs. On these images, the 1D Convolution operation is applied followed by max pooling. Followed by Convolution layers, a multi-layer feed-forward neural network is used as a classifier that learns to classify the logs as normal or abnormal from the representation created by the convolution layers. The model learns the variation in log pattern for normal and abnormal behavior. The proposed approach achieved improved accuracy compared to existing approaches for anomaly detection in Hadoop Distributed File System (HDFS) logs.

Dynamic model of macro crowd merging based on abnormal pedestrian posture

Crowd merging is a complex process, and any sudden external or internal disturbance will destroy the stability of the crowd. The occurrence of abnormal behavior will affect the crowd flow process and inevitably affect the stability of the crowd flow system. The position information of the joint points is obtained through the OpenPose algorithm, and the kinematics characteristics of each node are studied. It is judged whether the number of pedestrians in the crowd and the scale of the building scene are greater than the empirical setting value based on engineering statistical data and expert experience. When the number of pedestrians is more than 2,000 and the total area of the passage is more than 2,000 square meters, the appropriate macro-dynamic model is selected. The Aw-Rascle (AR) fluid dynamics model is selected in this study. The joint point information obtained through the OpenPose is combined with the macroscopic fluid dynamics model to construct a macroscopic crowd flow dynamics model based on the pedestrian's abnormal posture.

Facets of the Evolving Healthcare Management Model

The pandemic represents an opportunity to reimagine future healthcare and rethink healthcare management unbound by preconceived notions based on the following three main drivers that emerged during the pandemic. These include transformed business models, new care delivery models disrupted by ubiquitous data and technology, intelligent spaces, and digitally-enabled hospitality. In this context, it is imperative to reexamine all facets of healthcare management, considering that applying linear models to healthcare management has improved our understanding of their system structure and function. However, such models often fall short of explaining experimental results or predicting future abnormalities in complex nonlinear systems. Nonlinear models may better explain how the individual components collectively act and interact to produce a dynamic system in constant flux. They also assist in filling in some of the results which linear models do not adequately explain. Finally, chaos theory might provide new insights into standard as well as abnormal behavior within systems.