Subset Of Clusters Research Articles

Multidimensional Dynamic Destination Recommender Search System Employing Clustering: A Machine Learning Approach

Objectives: Recommender Systems (RS) powered by algorithms of machine learning is a popular tool for planning and implementing custom-made travel proficiencies. The persistence of this study is to recommend destinations according to a selection of various dimensions by the user. Methods: This approach uses a hybrid filtering system for recommendation with a weighted K-means clustering algorithm. For this study dataset was taken from Kaggle. Data considers different cities of India with different dimensions like city, name, type, and significance. According to the city first find latitude and longitude for precise clustering. Future work will incorporate optimization techniques to improve cluster formation recommendation accuracy. Findings: Clustering (unsupervised learning) is a separation technique that involves assigning locations to corresponding subsets of related clusters. The weighted K-means clustering algorithm is used with the elbow method which is used for discovering the optimum number of clusters. In weighted K-means algorithm for clustering uses scaling factor wi ​which transforms the impression of individual features to the whole distance calculation. It signifies the meaning of the ith feature in the perspective of the grouping task. Offering a scaling factor permits additional tractability in modifying the outcome of specific features on the distance calculation. It enables customization of the distance metric constructed on the specific requirements and characteristics of the records and clustering task. In this study, user can select multiple dimensions of their choice and get recommendations according to their choice. The proposed weighted K-means algorithm shows a significant improvement in accuracy which considers the proportion of correct recommendations out of all recommendations. A comparison with traditional K-means was conducted, where the weighted algorithm achieved a 17% higher accuracy due to its ability to give importance to specific features. The future version of the proposed system will incorporate optimization techniques for enhanced performance. Novelty: The suggested solution in this paper demonstrates that the user can enter the city of their choice. The recommended method indicates the city and nearby predilections once the user has selected their parameters, such as consuming formations or name or type. The ratio of relevant destinations that have been successfully recommended is 18% more compared to the K-means clustering algorithm. Keywords: Recommender System, Clustering, Destination Recommender System (DRS), Machine Learning, Weighted K-means clustering Algorithm

The WDR11 complex is a receptor for acidic-cluster-containing cargo proteins

Vesicle trafficking is a fundamental process that allows for the sorting and transport of specific proteins (i.e.,"cargoes") to different compartments of eukaryotic cells. Cargo recognition primarily occurs through coats and the associated proteins at the donor membrane. However, it remains unclear whether cargoes can also be selected at other stages of vesicle trafficking to further enhance the fidelity of the process. The WDR11-FAM91A1 complex functions downstream of the clathrin-associated AP-1 complex to facilitate protein transport from endosomes to the TGN. Here, we report the cryo-EM structure of human WDR11-FAM91A1 complex. WDR11 directly and specifically recognizes a subset of acidic clusters, which we term super acidic clusters (SACs). WDR11 complex assembly and its binding to SAC-containing proteins are indispensable for the trafficking of SAC-containing proteins and proper neuronal development in zebrafish. Our studies thus uncover that cargo proteins could be recognized in a sequence-specific manner downstream of a protein coat.

Natural variation in response to combined water and nitrogen deficiencies in Arabidopsis.

Understanding plant responses to individual stresses does not mean that we understand real-world situations, where stresses usually combine and interact. These interactions arise at different levels, from stress exposure to the molecular networks of the stress response. Here, we built an in-depth multiomic description of plant responses to mild water (W) and nitrogen (N) limitations, either individually or combined, among 5 genetically different Arabidopsis (Arabidopsis thaliana) accessions. We highlight the different dynamics in stress response through integrative traits such as rosette growth and the physiological status of the plants. We also used transcriptomic and metabolomic profiling during a stage when the plant response was stabilized to determine the wide diversity in stress-induced changes among accessions, highlighting the limited reality of a "universal" stress response. The main effect of the W × N interaction was an attenuation of the N-deficiency syndrome when combined with mild drought, but to a variable extent depending on the accession. Other traits subject to W × N interactions are often accession specific. Multiomic analyses identified a subset of transcript-metabolite clusters that are critical to stress responses but essentially variable according to the genotype factor. Including intraspecific diversity in our descriptions of plant stress response places our findings in perspective.

SWIFT clustering analysis of intracellular cytokine staining flow cytometry data of the HVTN 105 vaccine trial reveals high frequencies of HIV-specific CD4+ T cell responses and associations with humoral responses.

The HVTN 105 vaccine clinical trial tested four combinations of two immunogens - the DNA vaccine DNA-HIV-PT123, and the protein vaccine AIDSVAX B/E. All combinations induced substantial antibody and CD4+ T cell responses in many participants. We have now re-examined the intracellular cytokine staining flow cytometry data using the high-resolution SWIFT clustering algorithm, which is very effective for enumerating rare populations such as antigen-responsive T cells, and also determined correlations between the antibody and T cell responses. Flow cytometry samples across all the analysis batches were registered using the swiftReg registration tool, which reduces batch variation without compromising biological variation. Registered data were clustered using the SWIFT algorithm, and cluster template competition was used to identify clusters of antigen-responsive T cells and to separate these from constitutive cytokine producing cell clusters. Registration strongly reduced batch variation among batches analyzed across several months. This in-depth clustering analysis identified a greater proportion of responders than the original analysis. A subset of antigen-responsive clusters producing IL-21 was identified. The cytokine patterns in each vaccine group were related to the type of vaccine - protein antigens tended to induce more cells producing IL-2 but not IFN-γ, whereas DNA vaccines tended to induce more IL-2+ IFN-γ+ CD4 T cells. Several significant correlations were identified between specific antibody responses and antigen-responsive T cell clusters. The best correlations were not necessarily observed with the strongest antibody or T cell responses. In the complex HVTN105 dataset, alternative analysis methods increased sensitivity of the detection of antigen-specific T cells; increased the number of identified vaccine responders; identified a small IL-21-producing T cell population; and demonstrated significant correlations between specific T cell populations and serum antibody responses. Multiple analysis strategies may be valuable for extracting the most information from large, complex studies.

Multi-agent reinforcement learning clustering algorithm based on silhouette coefficient

As an important branch of emerging artificial intelligence algorithms, multi-agent reinforcement learning (MARL) has shown strong performance in collaborative environments. It can utilize multiple agents to find the optimal set of strategies for solving sequential decision problem through trial-and-error. One of the main challenges facing multi-agent system is the non-stationarity problem, which brings poor convergence and seriously affects its performance. Clustering is a commonly used unsupervised analytical method in machine learning, which aims to group samples with similar internal properties into the same cluster. In this paper, we propose a MARL clustering algorithm based on silhouette coefficient (SC-MARLC), and use the trial-and-error strategy to find the best cluster groups. In SC-MARLC, we establish a mapping relationship between multi-agent and samples, construct a novel clustering model based on MARL, and design a good clustering subset structure based on the sample silhouette coefficient. The designed structure is helpful for multi-agent system to solve the non-stationary problem. Finally, we compare the performance of SC-MARLC with 11 existing clustering algorithms on fifteen public datasets. The results show that the new clustering algorithm performs best on ten datasets.

Equivalence between Graph Spectral Clustering and Column Subset Selection (Student Abstract)

The common criteria for evaluating spectral clustering are NCut and RatioCut. The seemingly unrelated column subset selection (CSS) problem aims to compute a column subset that linearly approximates the entire matrix. A common criterion is the approximation error in the Frobenius norm (ApproxErr). We show that any algorithm for CSS can be viewed as a clustering algorithm that minimizes NCut by applying it to a matrix formed from graph edges. Conversely, any clustering algorithm can be seen as identifying a column subset from that matrix. In both cases, ApproxErr and NCut have the same value. Analogous results hold for RatioCut with a slightly different matrix. Therefore, established results for CSS can be mapped to spectral clustering. We use this to obtain new clustering algorithms, including an optimal one that is similar to A*. This is the first nontrivial clustering algorithm with such an optimality guarantee. A variant of the weighted A* runs much faster and provides bounds on the accuracy. Finally, we use the results from spectral clustering to prove the NP-hardness of CSS from sparse matrices.

SOLAMEN syndrome in a toddler

BackgroundSegmental overgrowth, lipomatosis, arteriovenous malformation, and epidermal nevus (SOLAMEN) syndrome is a segmental overgrowth syndrome that is part of Cowden’s Syndrome, a subset of the PTEN hamartoma tumor syndrome cluster. Due to SOLAMEN disease’s rarity, clinical suspicion should arise if multiple small nonspecific variably low-attenuated nodular lesions in the back, shoulders, and upper arms are present on CT, which are associated with mucocutaneous lesions. We present a rare case of SOLAMEN syndrome with widespread lipomatous growth, greater than reported in literature, with confirmed PTEN genetic testing.Case presentationWe describe a case of a 2-year-old boy with a slowly growing left neck mass since birth. Physical exam revealed macrocephaly and epidermal nevi on left axilla, arm, and fingers, appearing as pink verrucous and has visible veins on chest wall/abdomen. CT and MRI imaging showed a lipomatous hibernoma extending from the leftward neck to the abdominal cavity, encasing vascular structures form the left carotid and subclavian arteries to the diaphragmatic hiatus, in addition to the spleen and kidney. Biopsy of the left shoulder revealed hibernoma, a fatty neoplasm of benign brown fat. Patient had a resection of his left shoulder hibernoma and is currently asymptomatic, undergoing surveillance.ConclusionDue to SOMAMEN syndrome’s rarity, clinical suspicion should arise if a patient presents with multiple small-nonspecific variably low-attenuated nodular lesions on CT and mucocutaneous lesions. Ongoing monitoring should be done as there is an increased risk of cancer.

Proapoptotic protein Bim regulates the suppressive function of Treg cells.

Regulatory T (Treg) cells are a special immunosuppressive subset of cluster of differentiation 4-positive (CD4+‍)‍-T lymphocytes and play a pivotal role in the establishment of immune homeostasis in vivo (Zhang et al., 2021). The transcription factor forkhead box protein P3 (Foxp3) is the master marker of Treg cells, which is highly expressed in Treg cells and is also essential for their suppressive function (Hori et al., 2003). In addition to Foxp3, other regulators of Treg cells have been discovered (Wu et al., 2017, 2022; Wu and Sun, 2023a, 2023b); however, a deeper understanding of the regulation of these cells is required.

Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders

We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation for image tiles derived from remote sensing satellite imagery. The proposed methodology consists of two main stages. Firstly, an autoencoder network is utilised to reduce the high-dimensional image tile data into a compact and expressive latentfeature representation. Subsequently, features are further reduced to a two-dimensional embedding space using the manifold learning algorithm Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbour Embedding (t-SNE). This step enables the visualization of the image tile clusters in a 2D plot, providing an intuitive and interactive representation that can be used to aid rapid and geographically distributed image labelling. To facilitate the labelling process, our approach allows users to interact with the 2D visualization and label clusters based on their domain knowledge. In cases where certain classes are not effectively separated, users can re-apply dimension reduction to interactively refine subsets of clusters and achieve better class separation, enabling a comprehensively labelled dataset. We evaluate the proposed approach on real-world remote sensing satellite image datasets and demonstrate its effectiveness in achieving accurate and efficient image tile clustering and labelling. Users actively participate in the labelling process through our interactive approach, leading to enhanced relevance of the labelled data, by allowing domain experts to contribute their expertise and enrich the dataset for improved downstream analysis and applications.

Explainable survival analysis with uncertainty using convolution-involved vision transformer

Image-based precision medicine research is able to help doctors make better decisions on treatments. Among all kinds of medical images, a special form is called Whole Slide Image (WSI), which is used for diagnosing patients with cancer, aiming to enable more accurate survival prediction with its high resolution. However, One unique challenge of the WSI-based prediction models is processing the gigabyte-size or even terabyte-size WSIs, which would make most models computationally infeasible. Although existing models mostly use a pre-selected subset of key patches or patch clusters as input, they might discard some important morphology information, making the prediction inferior. Another challenge is improving the prediction models’ explainability, which is crucial to help doctors understand the predictions given by the models and make faithful decisions with high confidence. To address the above two challenges, in this work, we propose a novel explainable survival prediction model based on Vision Transformer. Specifically, we adopt dual-channel convolutional layers to utilize the complete WSIs for more accurate predictions. We also introduce the aleatoric uncertainty into our model to understand its limitation and avoid overconfidence in using the prediction results. Additionally, we present a post-hoc explainable method to identify the most salient patches and distinct morphology features as supporting evidence for predictions. Evaluations of two large cancer datasets show that our proposed model is able to make survival predictions more effectively and has better explainability for cancer diagnosis.

Comparing forecasting performance with panel data

We develop new methods for testing equal predictive accuracy for panels of forecasts, exploiting information in both the time-series and cross-sectional dimensions of the data. We examine general tests of equal forecasting performance averaged across all time periods and individual units, along with tests that focus on subsets of time or clusters of units. Properties of our tests are demonstrated through Monte Carlo simulations and in an empirical application that compares International Monetary Fund forecasts of country-level real gross domestic product growth and inflation to private-sector survey forecasts and forecasts from a simple time-series model.

Selective clustered traveling salesman problem

In this study, we introduce the Selective Clustered Travelling Salesman Problem, an extension of the well-known Travelling Salesman Problem where customers are grouped in clusters, and a profit is associated with each customer. The purpose of this problem is to find the most beneficial tour within a certain time budget, which consists of a subset of clusters and all nodes in each cluster visited on the tour. We formulate the problem as a mixed integer linear programming odel and develop a metaheuristic, using three constructive algorithms, by proposing a problem-specific neighbourhood structures to solve the problem effectively. The proposed algorithm has a sort of large variable neighbourhood search structure. Computational tests are made on benchmark instances with up to 400 vertices. Results show that the mathematical formulation is able to find the optimal solutions of all instances up to 358 vertices. Also, it is found that the proposed algorithm in spite of one parameter unlike the metaheuristics have several, significantly reduces the solution time, and besides, it gives high quality solutions especially for large-size problems.

The NSL complex is required for piRNA production from telomeric clusters.

The NSL complex is a transcriptional activator. Germline-specific knockdown of NSL complex subunits NSL1, NSL2, and NSL3 results in reduced piRNA production from a subset of bidirectional piRNA clusters, accompanied by widespread transposon derepression. The piRNAs most transcriptionally affected by NSL2 and NSL1 RNAi map to telomeric piRNA clusters. At the chromatin level, these piRNA clusters also show decreased levels of H3K9me3, HP1a, and Rhino after NSL2 depletion. Using NSL2 ChIP-seq in ovaries, we found that this protein specifically binds promoters of telomeric transposons HeT-A, TAHRE, and TART Germline-specific depletion of NSL2 also led to a reduction in nuclear Piwi in nurse cells. Our findings thereby support a role for the NSL complex in promoting the transcription of piRNA precursors from telomeric piRNA clusters and in regulating Piwi levels in the Drosophila female germline.

404-P: Single-Cell RNA Profiling Changes in Glomerular Cells in Diabetic Nephropathy (DN)

Hyperglycemia, the main risk factor for DN, causes complex pathological damages in glomeruli. To characterize detail changes in cell differentiation and gene expressions induced by diabetes, we performed unbiased single-cell RNA sequencing (scRNA-seq) on glomerular cells from diabetic and nondiabetic mice of long duration. Glomerular cells were isolated from C57 mice after 7-months of STZ-induced diabetes, when clear glomerular pathologies have been documented. Total number of 48,337 high-qualitied glomerular cells were isolated and sequenced from WT and STZ-treated mice. Based on clustering analysis and cell-type specific markers, 12 different cell types were identified, including endothelial cells (EC), podocytes, mesangial cells (MC), proximal tubule cells, parietal epithelial cells (PEC), collecting duct cells, ascending loop of Henle, macrophages, B cells, T cells, NK cells and neutrophils. Over 90% of the cells were from glomeruli (41% EC, 34 % podocytes, 14% MC, 2% of PEC), and 6% immune cells. Interestingly, gene profiling identified 9 clusters of EC, 5 clusters of MC and 7 clusters of podocytes. Diabetes did not change the total cell numbers for EC, MC and podocytes, although macrophage and B cell numbers were increased from 2.2% to 4.8% and 0.35% to 1%, respectively. Cluster subset analysis of EC, MC and podocytes showed that diabetes induced substantial changes. For podocytes, diabetes increased those clusters (5% to 37%) with high expressions of stressed proteins such as Hspa1a, Hspa1b and Hsp90aa1, while decreased those clusters with high expressions of ECM production and CDC42 GTPase cycle, that were involved in cytoskeleton stabilization and foot process formation. Findings from scRNA-seq of glomeruli showed there were multiple subsets of podocytes, EC and MC, which appear to have different functions and their distributions were changed by diabetes. Understanding the mechanism for the distribution changes of the subsets may provide new insight in the pathogenesis of DN. Disclosure J. Fu: None. Q. Li: None. K. Park: None. Q. Huang: None. I. Wu: None. G.L. King: Research Support; Janssen Research & Development, LLC.

Studying NF-κB signaling during neuroinflammation in Alzheimer’s Diseases in vitrousing hiPSC-derived brain models

Abstract Neuroinflammation is a key pathological driver of various neurological diseases, including Alzheimer’s disease (AD). NF-κB signaling pathway is widely recognized as a hallmark of inflammation and cellular senescence in which aged microglia may undergo cellular senescence partly influenced by NF-κB. Our previous data indicated that ex vivo microglia comprised of two distinct subpopulations distinguished by morphology and motility. Most microglia cells formed a tight cell cluster, termed “clustered microglia”. The rest was a subpopulation of microglia with smaller cell size and high motility, termed “free-roaming microglia”. In microglia from aged animals, the composition of clustered versus free-roaming subsets was shifted toward a higher prevalence of free-roaming microglia where c-Rel is expressed and the canonical NF-κB signaling is more sustained. To study NF-κB signaling in the context of neuroinflammation, we are developing 3D models, using hiPSC neurons derived from healthy donors of various age groups and co-culturing them with primary microglia from knock-in mice in which their endogenous c-Rel was labeled with a fluorescent protein. Moreover, individuals with APOE-e4 genotype have an increased risk of developing AD. To develop 3D brain models for AD, we will use co-culture of microglia and neurons derived from hiPSCs of APOE-e4 carriers. Live cell imaging and biomarker assessment of microglia and neurons activated by Amyloid β (1–42) will uncover important molecular mechanisms associated with age-dependent interactions between neurons from healthy versus AD-risk individuals, and resident macrophages of the young and aged brains.

Abstract 703: Transient G1 cell cycle arrest with trilaciclib enhances the generation of polyfunctional CD4+ and CD8+ T cells

Abstract When administered prior to chemotherapy, intravenous trilaciclib transiently arrests cyclin-dependent kinase 4/6-dependent cells in the G1 phase of the cell cycle, which has been shown to augment antitumor immunity. In an open-label, phase 2 trial in patients with metastatic triple-negative breast cancer (NCT02978716), administering trilaciclib prior to gemcitabine plus carboplatin improved overall survival, potentially through protection and direct activation of immune function. To determine the impact of trilaciclib on effector T-cell function, we conducted in vitro studies to assess the kinetics of cytotoxic function and generation of polyfunctional T cells. Peripheral blood mononuclear cells (PBMCs) or naïve CD4+ and CD8+ T cells were purified from 6 healthy human donors and activated with CD2/3/28 beads. On days 0, 1, and 3 post activation, 100 nM trilaciclib was added to the cells. To visualize phenotypic and functional changes, T cells that had been activated for 3, 7, or 14 days with or without trilaciclib were restimulated with phorbol myristate acetate (PMA) and ionomycin. Dimension-reduction analysis of flow cytometric data was used to identify polyfunctional subpopulations of CD4+ and CD8+ T cells. T-cell clusters with polyfunctional profiles were identified based on the coproduction of IFNγ, TNFα, and IL-2 cytokines. Subsets of polyfunctional clusters were defined according to other immune phenotypic profiles, including T-cell exhaustion (PD-1 and LAG-3), degranulation (granzyme B), proliferation (Ki-67), and transcription factors (TOX, TCF-1, and T-bet). For both CD4+ and CD8+ T cells, 3 polyfunctional subpopulations were identified based on differential expression of granzyme B, PD-1, and TOX. When CD4+ and CD8+ T cells were activated in the presence of trilaciclib and restimulated with PMA and ionomycin, there was an increase in the frequency of polyfunctional T-cell subsets producing granzyme B. This was compensated by a decrease in granzyme Blow polyfunctional cells, which was associated with increased PD-1high and TOXhigh expression. Clustering analysis of trilaciclib-treated PBMCs also revealed a reduction in proliferating CD8+ T cells with undetectable effector cytokine function based on a decrease in the frequency of CD8+ T cells expressing TOXhigh and Ki-67high. Transient G1 cell cycle arrest in T cells may limit T-cell hyperactivation, which has been shown to induce immunopathological responses. The increased generation of polyfunctional CD8+ T cells is associated with enhanced effector T-cell responses and memory T-cell differentiation. In combination with previous data showing increased differentiation of naïve T cells into memory T cells upon exposure to trilaciclib, these data support a beneficial role for trilaciclib in enhancing antitumor T-cell responses. Citation Format: Sarah Ahn, Subing Cao, Melissa A. Russo, John S. Yi. Transient G1 cell cycle arrest with trilaciclib enhances the generation of polyfunctional CD4+ and CD8+ T cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 703.

Covariate-constrained randomization with cluster selection and substitution.

An ongoing cluster-randomized trial for the prevention of arboviral diseases utilizes covariate-constrained randomization to balance two treatment arms across four specified covariates and geographic sector. Each cluster is within a census tract of the city of Mérida, Mexico, and there were 133 eligible tracts from which to select 50. As some selected clusters may have been subsequently found unsuitable in the field, we desired a strategy to substitute new clusters while maintaining covariate balance. We developed an algorithm that successfully identified a subset of clusters that maximized the average minimum pairwise distance between clusters in order to reduce contamination and balanced the specified covariates both before and after substitutions were made. Simulations were performed to explore some limitations of this algorithm. The number of selected clusters and eligible clusters were varied along with the method of selecting the final allocation pattern. The algorithm is presented here as a series of optional steps that can be added to the standard covariate-constrained randomization process in order to achieve spatial dispersion, cluster subsampling, and cluster substitution. Simulation results indicate that these extensions can be used without loss of statistical validity, given a sufficient number of clusters included in the trial.

Developmental mRNA clearance by PIWI-bound endo-siRNAs in Paramecium

The clearance of untranslated mRNAs by Argonaute proteins is essential for embryonic development in metazoans. However, it is currently unknown whether similar processes exist in unicellular eukaryotes. The ciliate Paramecium tetraurelia harbors a vast array of PIWI-clade Argonautes involved in various small RNA (sRNA) pathways, many of which have not yet been investigated. Here, we investigate the function of a PIWI protein, Ptiwi08, whose expression is limited to a narrow time window during development, concomitant with the start of zygotic transcription. We show that Ptiwi08 acts in an endogenous small interfering RNA (endo-siRNA) pathway involved in the clearance of untranslated mRNAs. These endo-siRNAs are found in clusters that are strictly antisense to their target mRNAs and are a subset of siRNA-producing clusters (SRCs). Furthermore, the endo-siRNAs are 2'-O-methylated by Hen1 and require Dcr1 for their biogenesis. Our findings suggest that sRNA-mediated developmental mRNA clearance extends beyond metazoans and may be a more widespread mechanism than previously anticipated.

Oxygen toxicity causes cyclic damage by destabilizing specific Fe-S cluster-containing protein complexes

Oxygen is toxic across all three domains of life. Yet, the underlying molecular mechanisms remain largely unknown. Here, we systematically investigate the major cellular pathways affected by excess molecular oxygen. We find that hyperoxia destabilizes a specific subset of Fe-S cluster (ISC)-containing proteins, resulting in impaired diphthamide synthesis, purine metabolism, nucleotide excision repair, and electron transport chain (ETC) function. Our findings translate to primary human lung cells and a mouse model of pulmonary oxygen toxicity. We demonstrate that the ETC is the most vulnerable to damage, resulting in decreased mitochondrial oxygen consumption. This leads to further tissue hyperoxia and cyclic damage of the additional ISC-containing pathways. In support of this model, primary ETC dysfunction in the Ndufs4 KO mouse model causes lung tissue hyperoxia and dramatically increases sensitivity to hyperoxia-mediated ISC damage. This work has important implications for hyperoxia pathologies, including bronchopulmonary dysplasia, ischemia-reperfusion injury, aging, and mitochondrial disorders.

TSDroid: A Novel Android Malware Detection Framework Based on Temporal & Spatial Metrics in IoMT

In the era of smart healthcare tremendous growth, plenty of smart devices facilitate cognitive computing for the purposes of lower cost, smarter diagnostic, etc. Android system has been widely used in the field of IoMT, and as the main operating system. However, Android malware is becoming one major security concern for healthcare, by the serious threat for our medical software assets, like the leakage of private information, the abusing of critical operations, etc. Unfortunately, the existing methods focus on building sustainable classification models, without fully considering system API which is the key to model aging. Compared to the traditional methods, we apply the lifeCycle of API as temporal metric. In addition to the temporal view, the “sizes” of the APPs are utilized as spatial metric in the spatial view. Based on this, we firstly discuss the temporal and spatial metrics together in terms of clustering, and then propose our novel framework-TSDroid. In this framework, we use TS-based clustering algorithm to obtain clustering subsets to enhance the detection capability. We have carried out an experimental verification on three existing excellent methods (i.e., Drebin, HinDroid, and DroidEvolver) and obtain good promotion effects by our framework.