Node Weight Research Articles

Delivery and organ-preserving surgery in a woman with high-risk uterine myoma

This article presents a clinical case from the practice of the State Budgetary Healthcare Institution of the Republic of Belarus "GKPTs" in Ufa regarding organ-conserving surgery in a woman with high-risk uterine fibroids of isthmus localization with transition to the posterior wall of the uterus. In May 2023, at 39 weeks of pregnancy, patient T. was scheduled for planned surgical delivery by cesarean section, with subsequent expansion of the scope of the operation to conservative myomectomy. The indication for surgery was uterine fibroids of gigantic size and isthmus localization with transition to the posterior wall of the uterus, as a result of which delivery through the natural birth canal is impossible. Uterine fibroids in this patient were discovered during pregnancy. Instrumental research methods used during the examination: ultrasound, magnetic resonance imaging (MRI). During routine ultrasound screenings, uterine fibroids of isthmus localization measuring 123x99x112 mm without disruption of the node's nutrition were diagnosed. According to MRI, the diagnosis of large uterine fibroids was confirmed. A transverse suprapubic laparotomy was performed. The first stage of the combined operation was a cesarean section in the lower segment. As a result, a live full-term boy weighing 3480 g, 53 cm, with 7-8-9 points on the Apgar scale was recovered. Then, during an inspection of the pelvic organs, a myomatous node was discovered in the isthmus area with a transition to the posterior wall of the uterus measuring 10x12 cm, without signs of necrosis. A conservative myomectomy was performed without penetration into the uterine cavity. The bed is sutured with separate sutures. Hemostasis has been achieved. The weight of the myomatous node will be 570 grams. Our clinical case shows that a favorable full-term pregnancy with high-risk, large size, atypical localization uterine fibroids is possible. Also, organ-preserving, combined operations are currently being carried out, which enable a woman to preserve the organ and further realize her reproductive potential.

#525 SGLT2 inhibition in non-diabetic CKD: results in experimental lupus nephritis

Abstract Background and Aims Sodium glucose cotransporter type 2 inhibitors (SGLT2i) potently attenuate cardiovascular morbidity and progression of CKD in patients with type 2 diabetes. It has been proposed that SGLT2 inhibition may also elicit renoprotective effects in non-diabetic CKD. The aim of this work is to evaluate whether the treatment with an SGLT2i improves kidney disease progression in a mouse model of lupus nephritis (LN). Method We performed a single center randomized controlled preclinical trial using female MRLlpr/lpr mice. The animals were randomly assigned to (1) vehicle or (2) empagliflozin (EMP, 10 mg/kg/day) treatment once signs of active systemic lupus erythematosus (SLE) appeared: proteinuria >100 mg/dL (++ in reactive strips) or lymphadenopathy in minimum 2 bilateral sites with proteinuria >30 mg/dL (+ in reactive strips). We included 13 mice per group that were treated during 4 weeks. Empagliflozin was given as an admix into standard chow diet. Reduction of urinary albumin to creatine ratio (UACR) was considered the primary endpoint whereas glomerular filtration rate (GFR), renal histology (LN activity/chronicity index, glomerulosclerosis, interstitial fibrosis) and SLE markers (total serum IgG, anti-dsDNA IgG, glomerular IgG deposits, lymph node weight, spleen weight) were considered secondary endpoints. Results After 4 weeks of treatment, no significant differences in fasting blood glucose levels were found between the experimental groups. As expected, empagliflozin administration notably inhibited SGLT2 in the tubular cells demonstrated by a significant increase of urinary glucose (p < 0.0001). This is consistent with the increased water intake observed in MRLlpr/lpr mice treated with empagliflozin (p < 0.0001). At the end of the experiment, vehicle treated MRLlpr/lpr mice showed a significant increase in UACR (p = 0.0012) consistent with LN progression that was not attenuated by empagliflozin. In line, empagliflozin did not modify GFR and LN activity/chronicity indexes, glomerulosclerosis or interstitial fibrosis in kidney. Finally, regarding SLE markers, 4-weeks empagliflozin treatment was not able to decrease total serum IgG, anti-dsDNA IgG, glomerular IgG deposits or lymph node weight. Only spleen weight was significantly decreased in empagliflozin treated MRLlpr/lpr mice (p = 0.003). Conclusion In our experimental setting, empagliflozin treatment reduced spleen weight suggesting a protective role in SLE in MRLlpr/lpr mice. However, empagliflozin did not modify LN progression in MRLlpr/lpr mice probably because the acute LN phase. It is expected that the positive effect in terms of reducing proteinuria will be observed in patients with LN and residual proteinuria

Benserazide, a cystathionine beta-synthase (CBS) inhibitor, potentially enhances the anticancer effects of paclitaxel via inhibiting the S-sulfhydration of SIRT1 and the HIF1-α/VEGF pathway.

Cancer targeted therapy is essential to minimize damage to normal cells and improve treatment outcomes. The elevated activity of Cystathionine beta-synthase (CBS), an enzyme responsible for producing endogenous hydrogen sulfide (H2S), plays a significant role in promoting tumor growth, invasiveness, and metastatic potential. Consequently, the selective inhibition of CBS could represent a promising therapeutic strategy for cancer. Currently, there is much interest in combining paclitaxel with other drugs for cancer treatment. This study aimed to investigate the efficacy of combining benserazide, a CBS inhibitor, with paclitaxel in treating tumors. Firstly, we demonstrated CBS is indeed involved in the progression of multiple cancers. Then it was observed that the total binding free energy between the protein and the small molecule is -98.241kJ/mol. The release of H2S in the group treated with 100μM benserazide was reduced by approximately 90% compared to the negative control, and the thermal denaturation curve of the complex protein shifted to the right, suggesting that benserazide binds to and blocks the CBS protein. Next, it was found that compared to paclitaxel monotherapy, the combination of benserazide with paclitaxel demonstrated stronger antitumor activity in KYSE450, A549, and HCT8 cells, accompanied by reduced cell viability, cell migration and invasion, as well as diminished angiogenic and lymphangiogenic capabilities. In vivo studies showed that the combined administration of benserazide and paclitaxel significantly reduced the volume and weight of axillary lymph nodes in comparison to the control group and single administration group. Further mechanistic studies revealed that the combination of benserazide and paclitaxel significantly suppressed the S-sulfhydration of SIRT1 protein, thereby inhibiting the expression of SIRT1 protein and activating SIRT1 downstream Notch1/Hes1 signaling pathway in KYSE450, A549, and HCT8 cells. Meanwhile, we observed that benserazide combined with paclitaxel induced a more significant downregulation of HIF-1α, VEGF-A, VEGF-C, and VEGF-D proteins expression levels in KYSE450, A549, and HCT8 cells compared to paclitaxel alone. These findings indicated that benserazide enhances the anticancer effects of paclitaxel via inhibiting the S-sulfhydration of SIRT1 and down-regulating HIF-1α/VEGF signaling pathway. This study suggests that benserazide may have potential as a chemosensitizer in cancer treatment.

NDI-PPO: Node degree increment-based proximal policy optimization method for employment community discovery in online social networks

Purpose: aiming at the limitations of pre-input parameters in the complex network overlapping community discovery algorithm based on tag propagation in real networks and the problems of tag redundancy, method: a node degree increment-based proximal policy optimization method for community discovery in online social networks is proposed (named NDI-PPO). Process: by applying the cohesion idea and introducing the concept of modularity increment, a social network great community is constructed from the bottom up according to the criteria of community division. For the problem that the number of iterative steps is sensitive to the strategy gradient algorithm, we adopt an improved PPO to improve the efficiency of feature extraction. In label updating, the maximum clique is used as the core unit to update the labels and weights of the maximum maximum clique adjacent nodes from the center to the periphery using intimacy, and the weights of the non-maximum maximum clique adjacent nodes are updated by means of the maximum weight. In the post-processing stage, the adaptive threshold method is used to remove the noise in the node label, which effectively overcomes the limitation of the number of pre-input overlapping communities in the real network. Result: The simulation results show that the proposed community discovery algorithm NDI-PPO is superior to other advanced algorithms, the time complexity is greatly reduced, and it is suitable for community discovery in large social networks.

Joint Optimization of Measurement Point Intelligent Selection and End-to-End Network Traffic Calculation in Datacenters

The effective design and management of data centers needs to follow the end-to-end traffic characteristics of data center networks (DCNs). However, directly measuring the end-to-end traffic of the network requires huge software and hardware costs. Since the particularity of the structure of DCNs, the flow estimation method used in the traditional computer network cannot be applied to existing DCNs. In this paper, we study the end-to-end traffic calculation of cloud computing DCNs. We propose <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> , which is an intelligent end-to-end traffic inference algorithm based on network tomography. Only using SNMP (simple network management protocol) data generally supported by switches, end-to-end traffic information can be calculated quickly and accurately. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> first devices a network traffic measurement point intelligent selection scheme based on node weighting. It first assigns weight to nodes through node criticality, and then uses node weighted incidence matrix approximation algorithm to calculate initial solution. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> then designs a network tomography method suitable for cloud computing network traffic calculation. It uses the time correlation of data center traffic to model the algorithm problem into a linear state space model, and finally calculates the traffic carried by each path through the improved Kalman filtering algorithm. Our evaluation and analysis demonstrate that <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> can effectively use the extracted coarse-grained traffic characteristics, and greatly improve the accuracy of the calculation on the premise of ensuring the computational efficiency.

Silicosis and silica-induced autoimmunity in multiple Collaborative Cross strains.

Abstract Background: The connection between pulmonary silica dust exposure and the development of systemic autoimmunity is well established. However, the extent to which genetic differences influence the severity of silica-induced autoimmunity remains unclear. Objective: Investigate the role of silica exposure on disease biomarkers (cytokines/chemokines and antinuclear antibodies (ANA)) and systemic autoimmune disease in genetically diverse Collaborative Cross recombinant inbred (CC RI) mice. Methods: Baseline serum ANA and chemokines/cytokines were assessed from 61 CC RI strains. Six CC RI strains, chosen to represent different baseline immune phenotypes, were exposed to 5 mg crystalline silica or PBS and examined 12 weeks later for serum ANA, bronchoalveolar lavage fluid cell counts, tracheobronchial lymph node and spleen weights, and histological assessment of silicosis and lupus nephritis. Results: All strains developed silicosis; however, two strains with low baseline immune activity did not develop silica-induced autoimmunity. In contrast, strains with higher baseline immune activity developed elevated ANA levels with strain variation in ANA types. One strain developed lupus nephritis, with significantly greater severity compared to controls. Conclusion: Baseline immune activity significantly influences the development of silica-induced autoimmunity and lung inflammation; however, genetics may be mediating silicosis and systemic autoimmunity independently.

Multi-Constraint and Multi-Policy Path Hopping Active Defense Method Based on SDN

Path hopping serves as an active defense mechanism in network security, yet it encounters challenges like a restricted path switching space, the recurrent use of similar paths and vital nodes, a singular triggering mechanism for path switching, and fixed hopping intervals. This paper introduces an active defense method employing multiple constraints and strategies for path hopping. A depth-first search (DFS) traversal is utilized to compute all possible paths between nodes, thereby broadening the path switching space while simplifying path generation complexity. Subsequently, constraints are imposed on residual bandwidth, selection periods, path similitude, and critical nodes to reduce the likelihood of reusing similar paths and crucial nodes. Moreover, two path switching strategies are formulated based on the weights of residual bandwidth and critical nodes, along with the calculation of path switching periods. This facilitates adaptive switching of path hopping paths and intervals, contingent on the network’s residual bandwidth threshold, in response to diverse attack scenarios. Simulation outcomes illustrate that this method, while maintaining normal communication performance, expands the path switching space effectively, safeguards against eavesdropping and link-flooding attacks, enhances path switching diversity and unpredictability, and fortifies the network’s resilience against malicious attacks.

Stabilized bases for high-order, interpolation semi-Lagrangian, element-based tracer transport

In a computational fluid model of the atmosphere, the advective transport of trace species, or tracers, can be computationally expensive. For efficiency, models often use semi-Lagrangian advection methods. High-order interpolation semi-Lagrangian (ISL) methods, in particular, can be extremely efficient, if the problem of property preservation specific to them can be addressed. Atmosphere models often use geometrically and logically nonuniform grids for efficiency and, as a result, element-based discretizations. Such grids and discretizations make stability a particular problem for ISL methods. Generally, high-order, element-based ISL methods that use the natural polynomial interpolant associated with a nodal finite-element discretization are unstable. We derive new bases having order of accuracy up to nine, with positive nodal weights, that stabilize the element-based ISL method. We use these bases to construct the linear advection operator in the property-preserving Interpolation Semi-Lagrangian Element-based Transport (Islet) method. Then we discuss key software implementation details. Finally, we show performance results for the Energy Exascale Earth System Model's atmosphere dynamical core, comparing the original and new transport methods. These simulations used up to 27,600 Graphical Processing Units (GPU) on the Oak Ridge Leadership Computing Facility's Summit supercomputer.

Weighted information index mining of key nodes through the perspective of evidential distance

Many strategies have been developed to mine critical nodes in the networks, however, most of them are based solely on the network topology, with no regard for the diversity of information between nodes. Using a weighted fusion method, we propose a method that considers neighboring nodes of second order and their similarity in this paper. Based on the evidence distance, an information distance Id is computed to find out how similar nodes are, and second-order adjacent nodes are used to reflect node information. Information distance is used to determine the weight of a node, and a weighted information index (WII) is used to evaluate how important a node is by combining the weight and information of nodes. The proposed method is tested by identifying influential nodes in twelve real-world networks and comparing their performance with the other seven methods. The Susceptible–Infected (SI) model and two evaluation indices have been applied to twelve real-world networks to evaluate the feasibility of our method. The findings indicate that the WII exhibits the most effective differentiation, thereby demonstrating the efficacy and practicality of our approach.

Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks are assigned the same set of weights for all graph nodes. However, we observe that some graph nodes whose neighbors are in different groups require significantly different emphases on SSL tasks. In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance. We design an innovative graph clustering approach, namely Dynamically Fusing Self-Supervised Learning (DyFSS). Specifically, DyFSS fuses features extracted from diverse SSL tasks using distinct weights derived from a gating network. To effectively learn the gating network, we design a dual-level self-supervised strategy that incorporates pseudo labels and the graph structure. Extensive experiments on five datasets show that DyFSS outperforms the state-of-the-art multi-task SSL methods by up to 8.66% on the accuracy metric. The code of DyFSS is available at: https://github.com/q086/DyFSS.

Guards: Benchmarks for weighted grid-based pathfinding

The primary objective of this paper is to aid game developers in finding the most suitable pathfinding algorithm for their games. Despite recent advancements in this field, there are few available studies that can be compared due to the absence of a standard benchmark set for weighted environments. This paper presents a new dataset for pathfinding in weighted environments. Furthermore, an investigation was conducted into the impact of node weights on pathfinding speed, and a correlation between them was identified. The complexity added to the maps due to node weights was defined as weight complexity, and two metrics were introduced to estimate it. The weight correlation factor has been identified as the most effective metric for estimating the weight complexity of the map. Another contribution of this paper pertains to the development of a model for estimating the pathfinding speed of algorithms based on weight complexity. This was accomplished through the utilization of the non-linear least squares method, which was applied to create a model for each algorithm, considering both its average search time and weight correlation factor values associated with the map. Finally an overall score metric was developed by using the integral of the models, enabling the evaluation of different algorithms in various scenarios.

Adaptive tree-like neural network: Overcoming catastrophic forgetting to classify streaming data with concept drifts

With the development of deep neural networks (DNNs), classifying streaming data with concept drifts based on DNNs is becoming more and more effective. However, the continuous and infinite characteristic of streaming data makes it difficult to set an appropriate depth for a DNN-based model in advance. Moreover, how to improve the model’s adaptability to concept drifts while overcoming catastrophic forgetting still remains a difficult issue. To address these issues, an Adaptive Tree-like Neural Network (ATNN) is proposed in this paper. ATNN adaptively increases the depth of its active branch according to the weight of the deepest node in the active branch. Once a new concept is detected, it chooses a suitable position on its trunk to grow a branch for the new concept according to the relation between the Fisher information and the gradient of parameters. Experiments demonstrate the rationality of ATNN to adaptively increase the depth of its branch or to choose a suitable position to grow a new branch, and illustrate that ATNN can more quickly adapt to concept drifts, and continuously improve classification performance for recurring concepts. The code of the proposed algorithm is available at https://github.com/mlmmwym/ATNN.

Dynamic planning of edge sensing terminals in distribution network supporting distributed resources observable and controllable

With the advancement of low-carbon distribution networks, the heightened stochasticity introduced by a multitude of renewable energy sources in the power grid has significantly augmented the regulatory challenges faced by the power grid. Dispatching distributed resources emerges as an effective solution to this issue. However, these resources often lack observability and controllability, hindering their participation in power regulation services. To establish a reliable interaction between distributed resources and power grids, the deployment of numerous edge sensing terminals becomes essential, albeit incurring high costs. In light of this, our paper proposes a dynamic network planning method for edge sensing terminals based on node differentiation and resource observability criteria, aiming to facilitate real-time and dependable observation of distributed resources. Initially, the node weight, a metric to gauge the disparity among nodes, is computed, considering communication quality deviation, resource development synergy, and the distribution of distributed resources. Subsequently, an optimal configuration method is introduced, accounting for the terminal’s reliability under faults. Lastly, a method for dynamic terminal networking planning is presented, gradually reducing the depth of unobservable resources. An enhanced genetic algorithm is employed to address this challenge. This method was validated using an IEEE 33 node system and a 91 node actual system, demonstrating significant effectiveness in reducing terminal configuration costs.

Knowledge fusion method of power grid model based on Seq2seq half pointer and half label method

Due to the complexity of the calculation process of the existing methods, the efficiency of data fusion of the power grid model is low. In order to improve the knowledge fusion effect of power grid model, this paper studied the knowledge fusion method of power grid model based on Seq2seq half pointer and half label method. The Text Rank algorithm is used to calculate the weight of semantic nodes of each grid model, and combined with the topological potential method, the semantic information of the grid model is extracted according to the final weight value, and the Seq2Seq semi-pointer semi-label model framework is constructed. The data of the scheduling automation system OMS and the production management system PMS are used as input. The extracted candidate mesh model semantics and the original mesh model semantics are encoded by Seq2Seq half-pointer half-label model. The semantic data of the power grid model is fused and sent to the Seq2Seq encoder. After the training is completed, the effective information is extracted from the power grid model through the Seq2Seq model to complete the knowledge fusion of the power grid model. Experimental results show that this method eliminates the redundant part of the basic attributes of each data source in the substation grid model after knowledge fusion, and the description of each basic attribute is more standardized, unified and perfect. Under different mesh model data dimensions, the support of the proposed method is all above 98%. The model trained by the proposed method tends to be stable after 120 iterations, and the precision, recall and F1 of the test set are 0.98, 0.93 and 0.91, respectively. At the same time, this method has high efficiency in the knowledge fusion processing of the power grid model, and its data processing speed is less than 160 s. The average integrity of the private data of the power grid model is 98.86%, indicating that the proposed method can better ensure the integrity of the data. Finally, compared with the application of other methods under different data amounts, the mean square error obtained by the proposed method is the smallest, indicating that the proposed method effectively improves the fusion accuracy.

Anomaly attribute mining method for topological nodes of power system based on graph theory

Due to the large scale, high dimension and time series characteristics of power system data, and the normal samples far exceed the abnormal samples, the sample imbalance phenomenon occurs, and it is difficult to mine the abnormal attributes of nodes. Therefore, a method of mining abnormal attributes of topological nodes of power systems based on graph theory is developed. The logical relation between nodes is analyzed by graph theory, and directed graph and undirected graph are obtained. The topology structure of the power system is constructed, the noise in data is removed by the adaptive clustering algorithm, the weight of topological nodes is set, and the abnormal malicious attacks of topological nodes are discovered by the double threshold method. The experimental results show that the proposed method can accurately detect the abnormal topological nodes in the network, perform better in the energy consumption of the neighbor topological nodes, and greatly reduce the energy consumption of the neighbor topological nodes during mining.

Carbon dot dressing as a treatment of alkali-induced skin burns

Background. Chemical burns, comprising 5–10 % of total burns but causing 30 % of burn-related deaths, are now a notable concern in Ukraine. Current clinical protocols lack specific approaches for chemical burns, and research on this type of burn is limited. Carbon-based nanoparticles show promise for wound healing because of anti-inflammatory, antioxidant, and antibacterial activities. So, the ability of carbon dots obtained from citric acid and urea (further called CD) to improve the healing of alkali-induced skin burn was aimed to be discovered. Materials and Methods. The study was conducted on male Wistar rats. Burn was modeled by application of gauze disc soaked with 3 M NaOH solution on shaved skin of anesthetized rats for 10 min. A CD dressing, consisting of a CD solution (1 mg/mL) mixed with cellulose-based hydrogel that served as a vehicle, was applied to burned skin daily during a 7-day period. There were following groups: control (healthy rats), a burn-only group (rats that received no dressing), a burn + vehicle group (rats that received vehicle dressing), and a burn + CD group (rats that received CD dressing). The study involved monitoring of burn areas, conducting skin histopathology, and perfor­ming blood biochemical analyses. Results. The daily CD dressing significantly decreased alkali-induced burn area (by 76 % compared to 40 % in burn-only group) after seven daily dressings. The level of inflammation in the burn site was also less expressed in CD-treated animals, compared to respective controls (non-treated animals and animals treated with Vehicle). There was no substantial systemic toxicity of the burn (of such area) and its healing, manifested by absence of body weight loss, and absence of dramatical changes in serum biochemical parameters (indicators of liver and kidney function). However, animals of all the groups that experienced burns had a significantly lower body weight gain and mesenteric lymph nodes weight compared to healthy rats. Conclusions. So, the application of carbon dots mixed with hydrogel speeded up alkali-induced burn healing without negative impact on the organism.

Codium fragile extract prevents atopic dermatitis in DNCB-induced mice.

Atopic dermatitis (AD) is a chronic inflammatory-allergic skin disorder that causes pruritic and eczematous skin lesions. Effect of Codium fragile extract (CFE) on AD has not been reported yet. In this study, inhibitory effects of CFE against skin severity scores, skin lesions, AD characteristics, and histological features of BALB/c mice with AD caused by 2,4-dinitrochlorobenzene (DNCB) were investigated. Results indicated that AD effects of CFE reduced body, skin, ear, spleen, thymus, and lymph node weights. Histopathological changes in skin reactions on the back and ears showed that CFE inhibited thickening of the epidermis and ear. Moreover, CFE reduced epidermal swelling and ear thickness compared with the DNCB group. These results suggest that CFE might be effective in alleviating AD with potential as a promising candidate for therapeutic and cosmetic treatment of inflammatory dermatitis. CFE may be useful in alleviating AD and could be a potential treatment for inflammatory dermatitis.

MSGAFN: Multi-scale graph attention fusion network for machine fault diagnosis

Fault diagnosis is essential in various fields, such as industrial manufacturing and engineering maintenance. Graph neural networks that take graph data as input can explore the relationships between data, which has strong feature expression capabilities. Currently, traditional fault diagnostic methods based on graph neural networks (GNN) are challenging to capture local and global feature information of data effectively. Most GNN models fail to consider the inherent differences between adjacent nodes, and they perform poorly in processing vibration signals in real-world industrial scenarios that commonly have strong noise. To resolve these concerns, this paper proposes a method for fault diagnosis based on a multi-scale graph attention fusion network (MSGAFN). In MSGAFN, data samples are constructed as clan graphs with multiple information scales to effectively represent local and global information of the graph structure data. Additionally, MSGAFN designed a new multi-scale feature fusion layer (MSFFL) to automatically learn the weights of adjacent nodes to represent their importance to the central node and reflect the differences between different adjacent nodes. This method is fully validated on bearing and gear datasets. The experimental results demonstrate that the proposed method exhibits excellent performance under conditions of imbalanced datasets and strong noise, providing a promising approach for bearings and gears fault diagnosis in real-world industrial scenarios with strong noise.

Cooperative communication and relay node selection algorithm based on SWIPT

The development of nanotechnology and the emergence of new materials such as graphene make wireless nanosensor networks (WNSN) based on electromagnetic communication possible. Due to the energy, computing power and transmission distance carried by nano-nodes are extremely limited, nanonetworks are usually ultra-dense, so nanonetworks are usually cluster-managed. Aiming at the problem of data transmission failure caused by poor link quality or insufficient energy in inter-cluster transmission, a relay node selection algorithm (RNS-AHP) based on simultaneous wireless information and power transfer (SWIPT) and analytics hierarchy process (AHP) is proposed. The algorithm is based on the SWIPT cooperative communication model, and uses the AHP to calculate the weights of four factors: the distance of the relay node, the channel capacity, the remaining energy of the relay node and the signal-to-noise ratio of the relay node receiver in the process of relay node selection. According to the weight, the weight of the candidate relay node is obtained as the selection criterion of the relay node. The simulation results show that the RNS-AHP algorithm can improve the average throughput, the success rate of data packet transmission and the energy efficiency.

Stationary Points of a Shallow Neural Network with Quadratic Activations and the Global Optimality of the Gradient Descent Algorithm

We consider the problem of training a shallow neural network with quadratic activation functions and the generalization power of such trained networks. Assuming that the samples are generated by a full rank matrix [Formula: see text] of the hidden network node weights, we obtain the following results. We establish that all full-rank approximately stationary solutions of the risk minimization problem are also approximate global optimums of the risk (in-sample and population). As a consequence, we establish that, when trained on polynomially many samples, the gradient descent algorithm converges to the global optimum of the risk minimization problem regardless of the width of the network when it is initialized at some value [Formula: see text], which we compute. Furthermore, the network produced by the gradient descent has a near zero generalization error. Next, we establish that initializing the gradient descent algorithm below [Formula: see text] is easily achieved when the weights of the ground truth matrix [Formula: see text] are randomly generated and the matrix is sufficiently overparameterized. Finally, we identify a simple necessary and sufficient geometric condition on the size of the training set under which any global minimizer of the empirical risk has necessarily zero generalization error. Funding: The research of E. C. Kizildag is supported by Columbia University, with the Distinguished Postdoctoral Fellowship in Statistics. Support from the National Science Foundation [Grant DMS-2015517] is gratefully acknowledged.