Transfer Learning for Image-Based Malware Detection for IoT.

The tremendous growth in online activity and the Internet of Things (IoT) led to an increase in cyberattacks. Malware infiltrated at least one device in almost every household. Various malware detection methods that use shallow or deep IoT techniques were discovered in recent years. Deep learning models with a visualization method are the most commonly and popularly used strategy in most works. This method has the benefit of automatically extracting features, requiring less technical expertise, and using fewer resources during data processing. Training deep learning models that generalize effectively without overfitting is not feasible or appropriate with large datasets and complex architectures. In this paper, a novel ensemble model, Stacked Ensemble-autoencoder, GRU, and MLP or SE-AGM, composed of three light-weight neural network models-autoencoder, GRU, and MLP-that is trained on the 25 essential and encoded extracted features of the benchmark MalImg dataset for classification was proposed. The GRU model was tested for its suitability in malware detection due to its lesser usage in this domain. The proposed model used a concise set of malware features for training and classifying the malware classes, which reduced the time and resource consumption in comparison to other existing models. The novelty lies in the stacked ensemble method where the output of one intermediate model works as input for the next model, thereby refining the features as compared to the general notion of an ensemble approach. Inspiration was drawn from earlier image-based malware detection works and transfer learning ideas. To extract features from the MalImg dataset, a CNN-based transfer learning model that was trained from scratch on domain data was used. Data augmentation was an important step in the image processing stage to investigate its effect on classifying grayscale malware images in the MalImg dataset. SE-AGM outperformed existing approaches on the benchmark MalImg dataset with an average accuracy of 99.43%, demonstrating that our method was on par with or even surpassed them.

Green Operation Strategies in Healthcare for Enhanced Quality of Life.

Healthcare services have now become a fundamental requirement for all individuals owing to rising pollution levels and shifting lifestyles brought on by fast modernization. The hospital is a specialized healthcare facility where doctors, nurses, and other medical professionals offer their services. Academics and professionals have emphasized green operation initiatives such as green design, green purchasing, green supply chain, and green manufacturing to increase public awareness of environmental problems affecting company operations associated with healthcare for the quality of life. The purpose of this research is to use total interpretive structural modeling and MICMAC (matrix cross multiplication applied to a classification) analysis to investigate and analyze the elements impacting green operations strategies in healthcare. The data are gathered using a closed-ended questionnaire together with a scheduled interview. The components' interactions are explored using the total interpretive structural modeling technique, and the MICMAC analysis is used to rank and categorize the green operation strategy variables. The study is a novel effort to address and focus on stakeholders, vision and structure, resources, and capabilities. Green operations strategies have only been the subject of a small number of studies in the past, and those studies were mostly addressed at manufacturing-specific green strategies. Thus, by promoting energy efficiency programs, green building design, alternative sources of energy, low-carbon transportation, local food, waste reduction, and water conservation, the health sector can develop multiple key strategies to become more climate-friendly with significant health, environmental, and social co-benefits for quality of life.

RB stabilizes XPC and promotes cellular NER.

It has long been thought that the G(1)/S cell cycle checkpoint allows time for DNA repair by delaying S-phase entry. The p53 tumor suppressor pathway regulates the G(1)/S checkpoint by regulating the cyclin-dependent kinase inhibitor p21(Waf1/Cip1), but p53 also regulates the nucleotide excision DNA repair protein XPC. Here, using p53-null cell lines we show that additional mechanisms stabilize XPC protein and promote nucleotide excision repair (NER) in concert with the G(1)/S checkpoint. At least one mechanism to stabilize and destabilize XPC involves ubiquitin-mediated degradation of XPC, as the ubiquitin ligase inhibitor MG-132 blocked XPC degradation. The retinoblastoma protein RB, in its unphosphorylated form actually stabilized XPC and promoted NER as measured by host cell reactivation experiments. The data suggest that XPC protein and XPC-mediated NER are tightly linked to the G(1)/S checkpoint, even in cells lacking functional p53.

Selenomethionine or methylseleninic acid inhibits mutagenesis of a reporter gene in mouse bone marrow.

Recent laboratory and clinical studies have utilized selenium in the form of pure seleno-L-methionine (SeMet) in combination with DNA-damaging cancer chemotherapy drugs. In mice, the selenium protected bone marrow and other tissues from dose-limiting toxicity. In fact, because of the protection from dose-limiting toxicity, a doubling or even tripling of the maximum tolerated dose (MTD) was enabled. Previously we showed that SeMet protects bone marrow by a DNA repair mechanism that requires the XPC DNA repair protein. XPC is rate-limiting and is required for repair of cisplatin or carboplatin adducts. Herein we used a mouse strain that carries a lambda phage reporter gene in the genome that serves as a mutagenesis target. SeMet protects from carboplatin mutagenesis in mouse bone marrow. Methylseleninic acid (MSA), a metabolite of SeMet, also protected against mutagenesis in mouse bone marrow.