Mobility Data Driven Privacy-preserving Model for Detecting High Risk Infection Cases

Graphs are a common and important data structure, and networks such as the Internet and social networks can be represented by graph structures. The proposal of Graph Convolutional Network (GCN) brings graph research into the era of deep learning and has achieved better results than traditional methods on various tasks. For ordinary neural networks, more layers can often achieve better results. However, for GCN, the deepening of the number of layers will cause a catastrophic decline in performance, including the gradual indistinguishability of node features, the disappearance of gradients, and the inability to update weights. This phenomenon is called over-smoothing. The occurrence of over-smoothing makes training deep GCNs a difficult problem. Compared with deep GCNs, shallow GCNs tend to perform better. Therefore, we design a contrastive learning model such that the deep GCN learns the features of the same node (positive samples) of the shallow GCN while alienating the features of other nodes (negative samples) , so that the deep GCN can learn the performance of the shallow GCN. Experiments show that our method can effectively alleviate the over-smoothing phenomenon. At the same time, we apply this model to other over-smoothing methods, and also achieve better results.KeywordsGraph convolutional networkGraph contrastive learningOver-smoothing

Global animal protein consumption has been steadily increasing as a result of population growth and the increasing demand for nutritious diets. The poultry industry provides a large portion of meat and eggs for human consumption. The early detection and warning of poultry infectious diseases play a critical role in the poultry breeding and production systems, improving animal welfare and reducing losses. However, inadequate methods for the early detection and prevention of infectious diseases in poultry farms sometimes fail to prevent decreased productivity and even widespread mortality. The health status of poultry is often reflected by its individual physiological, physical and behavioral clinical symptoms, such as higher body temperature resulting from fever, abnormal vocalization caused by respiratory disease and abnormal behaviors due to pathogenic infection. Therefore, the use of technologies for symptom detection can monitor the health status of broilers and laying hens in a continuous, noninvasive and automated way, and potentially assist in the early warning decision-making process. This review summarized recent literature on poultry disease detection and highlighted clinical symptom-monitoring technologies for sick poultry. The review concluded that current technologies are already showing their superiority to manual inspection, but the clinical symptom-based monitoring systems have not been fully utilized for on-farm early detection.

This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. We show that the proposed QSGCNN model can significantly reduce either the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models. Experiments on benchmark graph datasets demonstrate the effectiveness of the proposed QSGCNN model.

Book Review: Prophylaxis and Early Detection of HPV-Related Neoplasia, Herbert Pfister, Editor

This research presents a diagnosis model of single biomarker of Alzheimer’s diseases using graph convolutional network (GCN). Alzheimer’s disease is quite a challenging disease to diagnose early and accurately due to its complexity and progression nature. Traditional approaches used troponin and various other enzymes as well as clinical procedures such as coronary imaging – techniques that are expensive and require time. This approach makes diagnosis less complex because it utilizes a single measure of neurodegeneration combined with GCNs, which rely on structural analysis of the brain’s neural network. The preclinical research entertaining requires assembling and standardizing a sizable amount of data to make certain that the chosen biomarker generates coherent signals of Alzheimer’s disease. To this end, the GCN model is designed to be able to discern between healthy and diseased states by fine-tuning graph convolutions to capture such nuances. Empirical results of key performance indicators show that using our model yields better results in diagnostic outcomes than conventional methods. This innovative approach not only brings down the diagnostic costs, but also helps diagnose Alzheimer’s faster and more accurately thus helping a patient’s condition, and quality of life.

Deep learning methods, especially convolutional neural networks(CNN), have been widely used in hyperspectral image(HSI) classification. Recently, graph convolutional networks (GCN) have shown great potential in HSI classification problem. However, the existing GCN-based methods have several problems. First, the existing methods rely too much on the adjacency matrix, which cannot be changed during training. Furthermore, most of them can only use a single kind of feature, and fail to extract the spectral-spatial information from the HSI. Finally, for the existing GCN-based methods, it is difficult to achieve the same accuracy as the mature CNN methods. In this paper, we propose a spectral-spatial hypergraph convolutional neural network (S²HCN) for HSI classification. Compared with the existing GCN-based methods, S²HCN has the following advantages. Different from the adjacency matrix that is fixed during training of GCN, S²HCN can dynamically update the weight of the hyperedge during training, which reduces the reliance on prior information to a certain extent. In addition, S²HCN generates hyperedges from the spectral and spatial features independently, and adopts the incidence matrix composed of all hyperedges to replace the adjacency matrix in GCN. In this way, the spectral and spatial features can be better integrated. Finally, compared to a simple graph structure, the hypergraph structure can express the high-dimensional relationships in the data, which is beneficial to classification problems. Sufficient experiments on two popular HSI datasets have proved the effectiveness of S²HCN.

The developments of Information and Communication Technology (ICT) and Internet of Things (IoT) are being used to enhance quality, performance and interactivity of urban services. The developments of Information and Communication Technology (ICT) and Internet of Things (IoT) are being used to enhance quality, performance and interactivity of urban services. Benefited from the widespread adoption of mobile devices, we can collect amount of mobile data for user mobility analysis. Mining hidden information from users' mobile data is important for builders of smart city to provide better location-based service. This paper focuses on two classical domain-independent prediction models and one improved Markov model that are capable of estimating the next location. By using 27-day-long traffic data of mobile network, we extract trajectories of 4914 individuals for experiments. We find that the original Markov algorithm has a better performance in resource consumption than LZ family algorithms, but its prediction accuracy is lower than prediction accuracy of LeZi Update and Active LeZi algorithm. In order to improve the prediction accuracy of Markov and overcome drawbacks of traditional prediction algorithms, we present a new method based on Markov, which considers both temporal and spatial factors. Extensive experiments demonstrate our improved method has a better performance in location prediction. In addition, we further study the relationship between prediction accuracy and trajectory's regularity, to identify the most suitable prediction algorithm for a trajectory.

In large-scale wireless sensor networks the data- gathering mechanism to introducing mobility into the network. . We consider the location service in a WSN, where each sensor needs to maintain its location information by 1) frequently updating its location information within its neighboring set of polling points in the network. In the previous work a mobile data collector, for convenience called an M-collector for gathering information from the sensor and send to sink node. M- collector could be a mobile robot or a vehicle equipped with a powerful transceiver and battery, working like a mobile base station and gathering data while moving through the field. An M-collector starts the data-gathering tour periodically from the static data sink, polls each sensor while traversing its transmission range, then directly collects data from the sensor in single-hop communications, and finally transports the data to the static sink. Since data packets are directly gathered without relays and collisions, the lifetime of sensors is expected to be prolonged. In this paper, we mainly focus on the problem of minimizing the length of each data-gathering tour and remove the redundancy for data gathering. We develop a stochastic sequential decision framework to analyze this problem. Under a Markovian mobility model, the location update decision problem is modeled as a Markov Decision Process (MDP). For the work with strict distance/ time and energy constraints, we consider utilizing single and multiple M-collectors and propose a data- gathering algorithm where multiple M-collectors traverse through several shorter subtours concurrently to satisfy the distance/time and energy constraints. To identify the redundancy of data from the sensor using Pearson auto correlated technique. Our proposed system for mobile data gathering scheme can improve the scalability and balance the energy consumption among sensors.

Patent landscape and key technology interaction roadmap using graph convolutional network – Case of mobile communication technologies beyond 5G

Most existing graph convolutional networks focus on utilizing supervised information for training semi-supervised graph learning. However, the inherent randomness of supervised information can reduce the robustness of graph convolutional network models in some cases. To cope with this problem, in this paper, we propose a novel semi-supervised graph representation learning method RUGCN by leveraging explicit unsupervised information into training. We first propose a practical training method to ensure unsupervised information measurable by preserving both unsupervised (ranking smoothing) and semi-supervised (Laplacian smoothing) information. And then, we introduce a broadcast cross-entropy function to ensure ranking smoothing run in harmony with Laplacian smoothing. Experiments show that RUGCN achieves competitive results and stronger robustness.

The global prevalence of leprosy has decreased substantially, and cases of leprosy infection are extremely rare in China. In this report, we present a case of recurrent choriocarcinoma complicated by leprosy infection during chemotherapy. A 24-year-old Chinese woman (gravida 3, para 2) presented to a local hospital with vaginal bleeding. Her medical history included a previous diagnosis of hydatidiform mole. The patient was diagnosed with choriocarcinoma and received chemotherapy in 6 cycles. Shortly after the initial treatment was completed, the disease recurred twice with resistance to multiple chemotherapeutic agents. In her second recurrence of choriocarcinoma, she was diagnosed with leprosy with many cutaneous nodules throughout her entire body. The patient was administered chemical treatment for leprosy with the multidrug therapy regimen after being diagnosed. To prevent exacerbating the infection, no immunotherapy was utilized to treat cancer, and the infection was well-controlled at the conclusion of anticancer therapy. Because of immunological reduction, cancer patients are susceptible to a variety of infections. For patients with cancer, prevention and early detection of rare infectious diseases should receive special attention. Immunotherapy must be used with caution when treating patients with cancer and infections.

In a wide range of social unrest events prediction, the dynamic graph convolutional network (DGCN) have been successfully leveraged to achieve reliable performance. The innovation of dynamic graph convolutional networks mainly focuses on capturing the temporal features of unrest events. Inspired by the dynamic graph convolutional network, we propose a new graph convolutional network model called Contextual Gated Graph Convolutional Network (CGGCN). We apply CGGCN to predict and analyze social unrest events. The CGGCN uses the contextual gated layer, which improves the layer-wise propagation rules of graph convolutional networks. The contextual gated layer can re-learn the keyword representation to capture the contextual semantic features of unrest events by using squeeze & excitation module. The principle of the squeeze & excitation module is to increase the weight of meaningful words for event prediction and suppress weaker ones. In this paper, we obtain historical texts including published news and short tweets related to social unrest events. Based on these historical texts data, the CGGCN can predict the occurrence of social unrest events. In addition, we propose a method for establishing the evolution graph of unrest events. In this way, we can use several core words to summarize the evolution of the event. Finally, we design experiments on the specific unrest events data sets. The experimental results show that the CGGCN leads by about 5% - 7% in the performance of prediction compared with other popular methods.

The early detection of infectious diseases and microorganisms is critical for effective disease treatment, control, and prevention. Currently, nucleic acid testing and antigen-antibody serum reaction are the two methods most commonly used for the detection of infectious diseases. The former is highly accurate, specific, and sensitive, but it is time-consuming, expensive, and has special technician and instrument requirements. The latter is rapid and economical, but it may not be accurate and sensitive enough. Therefore, it is necessary to develop a quick and on-site diagnostic test for point-of-care testing (POCT) to enable the clinical detection of infectious diseases that is accurate, sensitive, convenient, cheap, and portable. Here, CRISPR/Cas-based detection methods are detailed and discussed in depth. The powerful capacity of these methods will facilitate the development of diagnostic tools for POCT, though they still have some limitations. This review explores and highlights POCT based on the class 2 CRISPR/Cas assay, such as Cas12 and Cas13 proteins, for the detection of infectious diseases. We also provide an outlook on perspectives, multi-application scenarios, clinical applications, and limitations for POCT based on class 2 CRISPR/Cas technology.

Background Malaria remains a global health challenge, yet its occurrence in non-endemic regions presents unique diagnostic and clinical management difficulties. The most advanced hematology analyzers provide key RBC parameters like INR (infected RBC), which enable early detection of malaria. The digital morphology analyzer is an important complement in such cases, as it quickly helps identify irregular RBCs, saving time to trigger the confirmatory testing and prompt intervention. This case highlights the role of integrated hematology and digital morphology tools in detecting Plasmodium vivax in a pediatric patient in Chile, a malaria-free country. Methods Initial hematology tests using Mindray BC-6200 hematology analyzer indicated mild anemia, thrombocytopenia. INR (Infected Red Blood Cells) refers to the percentage of RBCs infected with malaria parasites, which is used to aid in the early detection of malaria triggering the examination of the smear. Digital morphology analysis with the MC-80 identified parasitized erythrocytes. After these findings, a thick blood smear and immunochromatographic rapid test were performed showing positive results. Polymerase Chain Reaction (PCR) confirmed P. vivax. Follow-up assessments post-treatment included additional CBC tests, INR% monitoring, and peripheral blood smears. Results Initial Admission: A 11-years-old male patient is admitted to the hospital on 16/04/2024, having fever for 4 consecutive days, prompting further tests. The patient came to Chile from a Malaria endemic country. The initial blood test showed alarm signals for abnormal dispersion and RBC resistance to the lysing reagent, suggesting the onset of anemia. Platelet count was 40 10^3/uL. The INR% test revealed 1.77%, leading to the suspicion of malaria. For confirmation, a peripheral blood smear was performed using May-Grünwald Giemsa stain. The digital morphology system Mindray MC-80 could efficiently photograph large numbers of parasitized cells in the smear. These findings sped up the laboratory process and allowed for quicker activation of the malaria protocol. The positive result by chromatography rapid test and the findings on the thick drop examination on microscope confirmed the plasmodium diagnostic. A molecular test (PCR) test verified a load of 5,310 parasites per mL, identifying Plasmodium vivax as the species. On Post-Treatment control, no alarms detected in RBC/WBC parameters. Hemoglobin, hematocrit, platelet counts normalized. INR% dropped to 0%, confirming no parasitized RBCs. On the Follow-up appointment (July 1, 2024), there was a slight decrease in hemoglobin and hematocrit values. INR% of 0.02% suggested a possible relapse. MC-80 imaging detected one parasitized RBC. Thick drop examination on microscope did not find infection and chromatography rapid test was negative, but molecular PCR test confirmed the presence of Plasmodium vivax DNA Conclusion This case highlights the significance of using advanced hematology analyzers and digital morphology systems for diagnosing and monitoring malaria, even in non-endemic regions. The combined use of advanced RBCs parameters such as INR and precise cell identification through digital morphology tools enhanced clinical decision-making and minimized human error, leading to timely intervention. Continuous monitoring is essential in preventing relapse in cases with low parasitic loads, demonstrating the potential of these integrated tools in managing imported infectious diseases.

Molecular genetic and molecular biology methods enable one to reveal pathogenetic basis of oncohematological diseases, they are particular useful for diagnostic purpouses, to control and evaluate treatment efficiency. In leukemia patients there are two different types of chromosomal anomalities: some of them give rise for chimeric oncogenes, others activate hyperexpression of regulatory genes. It is necessary to take into account this difference in order to proparely develop molecular genetic tests. Molecular tests are more sensitive to compare with other approaches, due to this fact they are especially useful to monitor residual leukemia cells and for early detection of relapse.