High-utility and diverse itemset mining

High-utility Itemset Mining (HUIM) finds patterns from a transaction database with their utility no less than a user-defined threshold. The utility of an itemset is defined as the sum of the utilities of its items. The utility notion enables a data analyst to associate a profit score with each item and thereof to a pattern. We extend the notion of high-utility with diversity to define a new pattern type called High-utility and Diverse pattern (HUD). The notion of diversity of a pattern captures the extent of the different categories covered by the selected items in the pattern. An application of diverse-pattern lies in the recommendation task where a system can recommend to a customer a set of items from a new class based on her previously bought items. Our notion of diversity is easy to compute and also captures the basic essence of a previously proposed diversity notion. The existing algorithm to compute frequent-diverse patterns is 2-phase, i.e., in the first phase, frequent patterns are computed, out of which diverse patterns are filtered out in the second phase. We, in this paper, give an integrated algorithm that efficiently computes high-utility and diverse patterns in a single phase. Our experimental study shows that our proposed algorithm is very efficient as compared to a 2-phase algorithm that extracts high-utility itemsets in the first phase and filters out the diverse itemsets in the second phase.

     

A novel sine augmented scaled sine cosine algorithm for frequency control issues of a hybrid distributed two-area power system

Neural Computing and Applications - In this research article, a novel approach is proposed by considering the sine augmented scaled sine cosine (SAS-SCA) Algorithm for the load frequency control of...     

Efficient compression and network adaptive video coding for distributed video surveillance

The availability of cheap network based video cameras and the prevalence of wireless networks has lead to a major thrust towards deployment of large scale Distributed Video Surveillance (DVS) systems. This has opened up an important area of research to deal with the issues involved in DVS system for efficient collection and transmission of large scale video streams from the cameras at the guarded sites, to the end users in possibly constrained network conditions. In this paper, we propose a framework based on content-based video classification and scalable compression scheme to provide a robust bandwidth efficient video transmission for DVS. The scheme builds on a Discrete Wavelet Transform (DWT) based Color-Set Partitioning for Hierarchical Trees (CSPIHT) coding to obtain a scalable bitstream. Wavelet domain segmentation and compression assists in development of a DVS architecture. The architecture includes a novel module for dynamic allocation of Network bandwidth based on the current available resources and constraints. Different frame constituents are optimally coded based on their relative significance, perceptual quality, and available estimate of network bandwidth. Experimental result over different video sequences and simulations for Network conditions demonstrate the efficient performance of the approach.     

All Ag Nanoparticles Are Not the Same: Covalent Interactions between Ag Nanoparticles and Nitrile Groups Help Combat Drug- and Ag-Resistant Bacteria

Antimicrobial resistance has long been viewed as a lethal threat to global health. Despite the availability of a wide range of antibacterial medicines all around the world, organisms have evolved a resistance mechanism to these therapies. As a result, a scenario has emerged requiring the development of effective antibacterial drugs/agents. In this article, we exclusively highlight a significant finding reported by Zbořil and associates (Adv. Sci. 2021, 2003090). The authors construct a covalently bounded silver-cyanographene (GCN/Ag) with the antibacterial activity of 30 fold higher than that of free Ag ions or typical Ag nanoparticles (AgNPs). Ascribed to the strong covalent bond between nitrile and Ag, an immense cytocompatibility is shown by the GCN/Ag towards healthy human cells with a minute leaching of Ag ions. Firm interactions between the microbial membrane and the GCN/Ag are confirmed by molecular dynamics simulations, which rule out the dependence of antibacterial activity upon the Ag ions alone. Thus, this study furnishes ample scope to unfold next-generation hybrid antimicrobial drugs to confront infections arising from drug and Ag-resistant bacterial strains.     

AKT Inhibitors: The Road Ahead to Computational Modeling-Guided Discovery

AKT, is a serine/threonine protein kinase comprising three isoforms—namely: AKT1, AKT2 and AKT3, whose inhibitors have been recognized as promising therapeutic targets for various human disorders, especially cancer. In this work, we report a systematic evaluation of multi-target Quantitative Structure-Activity Relationship (mt-QSAR) models to probe AKT’ inhibitory activity, based on different feature selection algorithms and machine learning tools. The best predictive linear and non-linear mt-QSAR models were found by the genetic algorithm-based linear discriminant analysis (GA-LDA) and gradient boosting (Xgboost) techniques, respectively, using a dataset containing 5523 inhibitors of the AKT isoforms assayed under various experimental conditions. The linear model highlighted the key structural attributes responsible for higher inhibitory activity whereas the non-linear model displayed an overall accuracy higher than 90%. Both these predictive models, generated through internal and external validation methods, were then used for screening the Asinex kinase inhibitor library to identify the most potential virtual hits as pan-AKT inhibitors. The virtual hits identified were then filtered by stepwise analyses based on reverse pharmacophore-mapping based prediction. Finally, results of molecular dynamics simulations were used to estimate the theoretical binding affinity of the selected virtual hits towards the three isoforms of enzyme AKT. Our computational findings thus provide important guidelines to facilitate the discovery of novel AKT inhibitors.     

Application of Machine Learning Algorithms With and Without Principal Component Analysis for the Design of New Multiphase High Entropy Alloys

Metallurgical and Materials Transactions A - The design of high entropy alloys (HEAs) can be accelerated using machine learning (ML) algorithms. In the current study, the design parameter’s...     

Effects of temperature and blank holding force on biaxial forming behavior of aluminum sheet alloys

Biaxial forming behavior is investigated for three aluminum sheet alloys (Al 5182 containing 1% Mn (5182+Mn), Al 5754, and 6111-T4) using a heated die and punch in the warm forming temperature range of 200–350 °C. It is found that, while all three alloys exhibit significant improvement in their formability compared with that at room temperature, the non-heat-treatable alloys 5182 + Mn and 5754 give higher part depths than that of heat-treatable 6111-T4. The formability generally increases with decreasing BHP (BHP), but increasing the forming temperature and/or BHP minimizes the wrinkling tendency and improves the forming performance. The stretchability of the sheet alloys increase with increasing temperature and increasing BHP. For the alloys and forming conditions involved in the current study, the formability, measured in terms of part depth, comes mainly from the drawing of metal into the die cavity, although stretching effects do influence the overall forming behavior. The optimum formability is achieved by setting the die temperature 50 °C higher than the punch temperature to enhance the drawing component. Setting the die temperature higher than the punch temperature also improves the strain distribution in a part in such a manner that postpones necking and fracture by altering the location of greatest thinning.     

A unified method for optimal arbitrary pole placement

We consider the classic problem of pole placement by state feedback. We offer an eigenstructure assignment algorithm to obtain a novel parametric form for the pole-placing feedback matrix that can deliver any set of desired closed-loop eigenvalues, with any desired multiplicities. This parametric formula is then exploited to introduce an unconstrained nonlinear optimisation algorithm to obtain a feedback matrix that delivers the desired pole placement with optimal robustness and minimum gain. Lastly we compare the performance of our method against several others from the recent literature.     

Design of novel compact anti-stiction and low insertion loss RF MEMS switch

A novel torsional RF MEMS capacitive switch design on silicon substrate is presented. The optimized switch topology such as reduction in up-state capacitance results in insertion loss better than ?0.1 dB till 20 GHz. Off to on state capacitance ratio is also improved by 18 fold and isolation is better than ?43 dB at 9.5 GHz. The achieved on state return loss is ?38 dB as compared to ?21 dB at 9.5 GHz. An optimized reduction in contact area and use of floating metal layer increases the switching speed from 56 to 46 μsec. It also increases the switch reliability by alleviating the stiction.     

A Simple D 2-Sampling Based PTAS for k-Means and Other Clustering Problems

Given a set of points \(P \subset\mathbb{R}^{d}\) , the k-means clustering problem is to find a set of k centers \(C = \{ c_{1},\ldots,c_{k}\}, c_{i} \in\mathbb{R}^{d}\) , such that the objective function ∑ _x∈P e(x,C)², where e(x,C) denotes the Euclidean distance between x and the closest center in C, is minimized. This is one of the most prominent objective functions that has been studied with respect to clustering. D ²-sampling (Arthur and Vassilvitskii, Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA’07, pp. 1027–1035, SIAM, Philadelphia, 2007) is a simple non-uniform sampling technique for choosing points from a set of points. It works as follows: given a set of points \(P \subset\mathbb{R}^{d}\) , the first point is chosen uniformly at random from P. Subsequently, a point from P is chosen as the next sample with probability proportional to the square of the distance of this point to the nearest previously sampled point. D ²-sampling has been shown to have nice properties with respect to the k-means clustering problem. Arthur and Vassilvitskii (Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA’07, pp. 1027–1035, SIAM, Philadelphia, 2007) show that k points chosen as centers from P using D ²-sampling give an O(logk) approximation in expectation. Ailon et al. (NIPS, pp. 10–18, 2009) and Aggarwal et al. (Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, pp. 15–28, Springer, Berlin, 2009) extended results of Arthur and Vassilvitskii (Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA’07, pp. 1027–1035, SIAM, Philadelphia, 2007) to show that O(k) points chosen as centers using D ²-sampling give an O(1) approximation to the k-means objective function with high probability. In this paper, we further demonstrate the power of D ²-sampling by giving a simple randomized (1+?)-approximation algorithm that uses the D ²-sampling in its core.