Unravelling CO2 Reduction Reaction Intermediates on High Entropy Alloy Catalysts: An Interpretable Machine Learning Approach to Establish Scaling Relations.

Establishment of a scaling relation among the reaction intermediates is highly important but very much challenging on complex surfaces, such as surfaces of high entropy alloys (HEAs). Herein, we designed an interpretable machine learning (ML) approach to establish a scaling relation among CO2 reduction reaction (CO2 RR) intermediates adsorbed at the same adsorption site. Local Interpretable Model-Agnostic Explanations (LIME), Accumulated Local Effects (ALE), and Permutation Feature Importance (PFI) are used for the global and local interpretation of the utilized black box models. These methods were successfully applied through an iterative way and validated on CuCoNiZnMg and CuCoNiZnSnbased HEAs data. Finally, we successfully predicted adsorption energies of *H2 CO (MAE: 0.24 eV) and *H3 CO (MAE: 0.23 eV) by using the *HCO training data. Similarly, adsorption energy of *O (MAE: 0.32 eV) is also predicted from *H training data. We believe that our proposed method can shift the paradigm of state-of-the-art ML in catalysis towards better interpretability.

Energy level alignments between organic and inorganic layers in 2D layered perovskites: conjugation vs. substituent.

2D layered hybrid perovskites have attracted huge attention due to their interesting optoelectronic properties and chemical flexibility. Depending upon their electronic structures and properties, these materials can be utilised in various optoelectronic devices like photovoltaics, LEDs and so on. In this context, study of the excited energy levels of the organic spacers can help us to align the excited energy levels of the organic unit with the excitonic level of the inorganic unit according to the requirement of a particular optoelectronic device. We have explored the role of 3-phenyl-2-propenammonium on the electronic structure of a perovskite containing this cation as a spacer. Our results clearly demonstrate the active participation of conjugated ammonium spacers in the electronic structure of a perovskite. Also, we have considered a variety of amines to identify the best alignment with common inorganic units and studied the role of substituents and conjugation on the energy level alignment. Placing the triplet excited level of an organic spacer below the lowest excitonic level of the inorganic unit can induce energy transfer from the inorganic to organic unit, finally resulting in phosphorescence emission. We have shown that the triplet energy level of 3-anthracene-2-propeneamine/3-pyrene-2-propeneamine can be tuned in such a way that there can be an excitonic energy transfer from the Pb2I7/PbI4 inorganic unit-based perovskites. Therefore, perovskite material with such combinations of organic spacer cations will be very useful for light emission applications.

Performance Evaluation and Cyberattack Mitigation in a Blockchain-Enabled Peer-to-Peer Energy Trading Framework.

With the electric power grid experiencing a rapid shift to the smart grid paradigm over a deregulated energy market, Internet of Things (IoT)-based solutions are gaining prominence, and innovative peer-to-peer (P2P) energy trading at a micro level is being deployed. Such advancement, however, leaves traditional security models vulnerable and paves the path for blockchain, a distributed ledger technology (DLT), with its decentralized, open, and transparency characteristics as a viable alternative. However, due to deregulation in energy trading markets, most of the prototype resilience regarding cybersecurity attack, performance and scalability of transaction broadcasting, and its direct impact on overall performances and attacks are required to be supported, which becomes a performance bottleneck with existing blockchain solutions such as Hyperledger, Ethereum, and so on. In this paper, we design a novel permissioned Corda framework for P2P energy trading peers that not only mitigates a new class of cyberattacks, i.e., delay trading (or discard), but also disseminates the transactions in a optimized propagation time, resulting in a fair transaction distribution. Sharing transactions in a permissioned R3 Corda blockchain framework is handled by the Advanced Message Queuing Protocol (AMQP) and transport layer security (TLS). The unique contribution of this paper lies in the use of an optimized CPU and JVM heap memory scenario analysis with P2P metric in addition to a far more realistic multihosted testbed for the performance analysis. The average latencies measured are 22 ms and 51 ms for sending and receiving messages. We compare the throughput by varying different types of flow such as energy request, request + pay, transfer, multiple notary, sender, receiver, and single notary. In the proposed framework, request is an energy asset that is based on payment state and contract in the P2P energy trading module, so in request flow, only one node with no notary appears on the vault of the node.Energy request + pay flow interaction deals with two nodes, such as producer and consumer, to deal with request and transfer of asset ownership with the help of a notary. Request + repeated pay flow request, on node A and repeatedly transfers a fraction of energy asset state to another node, B, through a notary.

Machine Learning Aided Interpretable Approach for Single Nucleotide-Based DNA Sequencing using a Model Nanopore.

Solid-state nanopore-based electrical detection of DNA nucleotides with the quantum tunneling technique has emerged as a powerful strategy to be the next-generation sequencing technology. However, experimental complexity has been a foremost obstacle in achieving a more accurate high-throughput analysis with industrial scalability. Here, with one of the nucleotide training data sets of a model monolayer gold nanopore, we have predicted the transmission function for all other nucleotides with root-mean-square error scores as low as 0.12 using the optimized eXtreme Gradient Boosting Regression (XGBR) model. Further, the SHapley Additive exPlanations (SHAP) analysis helped in exploring the interpretability of the XGBR model prediction and revealed the complex relationship between the molecular properties of nucleotides and their transmission functions by both global and local interpretable explanations. Hence, experimental integration of our proposed machine-learning-assisted transmission function prediction method can offer a new direction for the realization of cheap, accurate, and ultrafast DNA sequencing.

GaitRec-Net: A Deep Neural Network for Gait Disorder Detection Using Ground Reaction Force.

Walking (gait) irregularities and abnormalities are predictors and symptoms of disorder and disability. In the past, elaborate video (camera-based) systems, pressure mats, or a mix of the two has been used in clinical settings to monitor and evaluate gait. This article presents an artificial intelligence-based comprehensive investigation of ground reaction force (GRF) pattern to classify the healthy control and gait disorders using the large-scale ground reaction force. The used dataset comprised GRF measurements from different patients. The article includes machine learning- and deep learning-based models to classify healthy and gait disorder patients using ground reaction force. A deep learning-based architecture GaitRec-Net is proposed for this classification. The classification results were evaluated using various metrics, and each experiment was analysed using a fivefold cross-validation approach. Compared to machine learning classifiers, the proposed deep learning model is found better for feature extraction resulting in high accuracy of classification. As a result, the proposed framework presents a promising step in the direction of automatic categorization of abnormal gait pattern.

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning.

Cost-efficient electrocatalysts to replace precious platinum group metals- (PGMs-) based catalysts for the hydrogen evolution reaction (HER) carry significant potential for sustainable energy solutions. Machine learning (ML) methods have provided new avenues for intelligent screening and predicting efficient heterogeneous catalysts in recent years. We coalesce density functional theory (DFT) and supervised ML methods to discover earth-abundant active heterogeneous NiCoCu-based HER catalysts. An intuitive generalized microstructure model was designed to study the adsorbate's surface coverage and generate input features for the ML process. The study utilizes optimized eXtreme Gradient Boost Regression (XGBR) models to screen NiCoCu alloy-based catalysts for HER. We show that the most active HER catalysts can be screened from an extensive set of catalysts with this approach. Therefore, our approach can provide an efficient way to discover novel heterogeneous catalysts for various electrochemical reactions.

JSQE: Joint Surveillance Quality and Energy Conservation for Barrier Coverage in WSNs.

Barrier coverage is a fundamental issue in wireless sensor networks (WSNs). Most existing works have developed centralized algorithms and applied the Boolean Sensing Model (BSM). However, the critical characteristics of sensors and environmental conditions have been neglected, which leads to the problem that the developed mechanisms are not practical, and their performance shows a large difference in real applications. On the other hand, the centralized algorithms also lack scalability and flexibility when the topologies of WSNs are dynamically changed. Based on the Elfes Sensing Model (ESM), this paper proposes a distributed Joint Surveillance Quality and Energy Conservation mechanism (JSQE), which aims to satisfy the requirements of the desired surveillance quality and minimize the number of working sensors. The proposed JSQE first evaluates the sensing probability of each sensor and identifies the location of the weakest surveillance quality. Then, the JSQE further schedules the sensor with the maximum contribution to the bottleneck location to improve the overall surveillance quality. Extensive experiment results show that our proposed JSQE outperforms the existing studies in terms of surveillance quality, the number of working sensors, and the efficiency and fairness of surveillance quality. In particular, the JSQE improves the surveillance quality by 15% and reduces the number of awake sensors by 22% compared with the relevant TOBA.

Machine Learning Assisted Exploration of High Entropy Alloy-Based Catalysts for Selective CO2 Reduction to Methanol.

Catalytic conversion of CO2 to carbon neutral fuels can be ecofriendly and allow for economic replacement of fossil fuels. Here, we have investigated high-throughput screening of high entropy alloy (Cu, Co, Ni, Zn, and Sn) based catalysts through machine learning (ML) for CO2 hydrogenation to methanol. Stability and catalytic activity studies of these catalysts have been performed for all possible combinations, where different elemental, compositional, and surface microstructural features were used as input parameters. Adsorption energy values of CO2 reduction intermediates on the CuCoNiZnMg- and CuCoNiZnSn-based catalysts have been used to train the ML models. Successful prediction of adsorption energies of the adsorbates using CuCoNiZnMg-based training data is achieved except for two intermediates. Hence, we show that activity and selectivity of these catalysts can be successfully predicted for CO2 hydrogenation to methanol and have screened a series of high entropy-based catalysts (from 36750 considered catalysts) which could be promising for methanol synthesis.

A Novel Blockchain-Based Healthcare System Design and Performance Benchmarking on a Multi-Hosted Testbed.

As a result of the proliferation of digital and network technologies in all facets of modern society, including the healthcare systems, the widespread adoption of Electronic Healthcare Records (EHRs) has become the norm. At the same time, Blockchain has been widely accepted as a potent solution for addressing security issues in any untrusted, distributed, decentralized application and has thus seen a slew of works on Blockchain-enabled EHRs. However, most such prototypes ignore the performance aspects of proposed designs. In this paper, a prototype for a Blockchain-based EHR has been presented that employs smart contracts with Hyperledger Fabric 2.0, which also provides a unified performance analysis with Hyperledger Caliper 0.4.2. The additional contribution of this paper lies in the use of a multi-hosted testbed for the performance analysis in addition to far more realistic Gossip-based traffic scenario analysis with Tcpdump tools. Moreover, the prototype is tested for performance with superior transaction ordering schemes such as Kafka and RAFT, unlike other literature that mostly uses SOLO for the purpose, which accounts for superior fault tolerance. All of these additional unique features make the performance evaluation presented herein much more realistic and hence adds hugely to the credibility of the results obtained. The proposed framework within the multi-host instances continues to behave more successfully with high throughput, low latency, and low utilization of resources for opening, querying, and transferring transactions into a healthcare Blockchain network. The results obtained in various rounds of evaluation demonstrate the superiority of the proposed framework.

Machine Learning-Driven High-Throughput Screening of Alloy-Based Catalysts for Selective CO2 Hydrogenation to Methanol.

The revolutionary development of machine learning and data science and exploration of its application in material science are huge achievements of the scientific community in the past decade. In this work, we have reported an efficient approach of machine learning-aided high-throughput screening for finding selective earth-abundant high-entropy alloy-based catalysts for CO2 to methanol formation using a machine learning algorithm and microstructure model. For this, we have chosen earth-abundant Cu, Co, Ni, Zn, and Mg metals to form various alloy-based compositions (bimetallic, trimetallic, tetrametallic, and high-entropy alloys) for selective CO2 reduction reaction toward CH3OH. Since there are several possible surface microstructures for different alloys, we have used machine learning along with DFT calculations for high-throughput screening of the catalysts. In this study, the stability of various 8-atom fcc periodic (111) surface unit cells has been calculated using the atomic-size difference factor (δ) as well as the ratio taken from Gibbs free energy of mixing (Ω). Thinking about the simplicity and accuracy, microstructure models by considering the neighboring atoms of the adsorption sites and others as Cu atoms have been considered for different adsorption sites (on-top, bridge, and hollow-hcp). Moreover, the adsorption energies of the *H, *O, *CO, *HCO, *H2CO, and *H3CO intermediates have been predicted using the best fitted algorithm of the training set. The predicted adsorption energies have been screened based on the pure Cu adsorption energy. Furthermore, the screened catalysts have been correlated among different adsorption site microstructures. At the end, we were able to find seven active catalysts, among which two catalysts are CuCoNiZn-based tetrametallic, three catalysts are CuNiZn-based trimetallic, and two catalysts are CuCoZn-based trimetallic alloys. Hence, this work demonstrates not an ultimate but an efficient approach for finding new product-selective catalysts, and we expect that it can be convenient for other similar types of reactions in forthcoming days.

Towards a Clustering Guided Hierarchical Framework for Sensor-Based Activity Recognition.

Human activity recognition plays a prominent role in numerous applications like smart homes, elderly healthcare and ambient intelligence. The complexity of human behavior leads to the difficulty of developing an accurate activity recognizer, especially in situations where different activities have similar sensor readings. Accordingly, how to measure the relationships among activities and construct an activity recognizer for better distinguishing the confusing activities remains critical. To this end, we in this study propose a clustering guided hierarchical framework to discriminate on-going human activities. Specifically, we first introduce a clustering-based activity confusion index and exploit it to automatically and quantitatively measure the confusion between activities in a data-driven way instead of relying on the prior domain knowledge. Afterwards, we design a hierarchical activity recognition framework under the guidance of the confusion relationships to reduce the recognition errors between similar activities. Finally, the simulations on the benchmark datasets are evaluated and results show the superiority of the proposed model over its competitors. In addition, we experimentally evaluate the key components of the framework comprehensively, which indicates its flexibility and stability.

Synthesis of 1-indolyl-3,5,8-substituted γ-carbolines: one-pot solvent-free protocol and biological evaluation.

1,5-Disubstituted indole-2-carboxaldehyde derivatives 1a-h and glycine alkyl esters 2a-c are shown to undergo a novel cascade imination-heterocylization in the presence of the organic base DIPEA to provide 1-indolyl-3,5,8-substituted γ-carbolines 3aa-ea in good yields. The γ-carbolines are fluorescent and exhibit anticancer activities against cervical, lung, breast, skin, and kidney cancer cells.

Hybrid Disease Diagnosis Using Multiobjective Optimization with Evolutionary Parameter Optimization.

With the widespread adoption of e-Healthcare and telemedicine applications, accurate, intelligent disease diagnosis systems have been profoundly coveted. In recent years, numerous individual machine learning-based classifiers have been proposed and tested, and the fact that a single classifier cannot effectively classify and diagnose all diseases has been almost accorded with. This has seen a number of recent research attempts to arrive at a consensus using ensemble classification techniques. In this paper, a hybrid system is proposed to diagnose ailments using optimizing individual classifier parameters for two classifier techniques, namely, support vector machine (SVM) and multilayer perceptron (MLP) technique. We employ three recent evolutionary algorithms to optimize the parameters of the classifiers above, leading to six alternative hybrid disease diagnosis systems, also referred to as hybrid intelligent systems (HISs). Multiple objectives, namely, prediction accuracy, sensitivity, and specificity, have been considered to assess the efficacy of the proposed hybrid systems with existing ones. The proposed model is evaluated on 11 benchmark datasets, and the obtained results demonstrate that our proposed hybrid diagnosis systems perform better in terms of disease prediction accuracy, sensitivity, and specificity. Pertinent statistical tests were carried out to substantiate the efficacy of the obtained results.