Ternary organic solar cells (OSCs) have progressed significantly in recent years due to the sufficient photon harvesting of the blend photoactive layer including three absorption‐complementary ...materials. With the rapid development of highly efficient ternary OSCs in photovoltaics, the precise energy‐level alignment of the three active components within ternary OSC devices should be taken into account. The machine‐learning technique is a computational method that can effectively learn from previous historical data to build predictive models. In this study, a dataset of 124 fullerene derivatives‐based ternary OSCs is manually constructed from a diverse range of literature along with their frontier molecular orbital theory levels, and device structures. Different machine‐learning algorithms are trained based on these electronic parameters to predict photovoltaic efficiency. Thus, the best predictive capability is provided by using the Random Forest approach beyond other machine‐learning algorithms in the dataset. Furthermore, the Random Forest algorithm yields valuable insights into the crucial role of lowest unoccupied molecular orbital energy levels of organic donors in the performance of ternary OSCs. The outcome of this study demonstrates a smart strategy for extracting underlying complex correlations in fullerene derivatives‐based ternary OSCs, thereby accelerating the development of ternary OSCs and related research fields.
Machine‐learning approaches are utilized to build models for the prediction of efficiency using important frontier molecular orbital energy levels of organic materials as features. Furthermore, a versatile Random Forest model reveals that the lowest unoccupied molecular orbital energy of donor can be considered as a critical feature in design of ternary organic solar cells.
Deep learning (DL) is playing an increasingly important role in our lives. It has already made a huge impact in areas, such as cancer diagnosis, precision medicine, self-driving cars, predictive ...forecasting, and speech recognition. The painstakingly handcrafted feature extractors used in traditional learning, classification, and pattern recognition systems are not scalable for large-sized data sets. In many cases, depending on the problem complexity, DL can also overcome the limitations of earlier shallow networks that prevented efficient training and abstractions of hierarchical representations of multi-dimensional training data. Deep neural network (DNN) uses multiple (deep) layers of units with highly optimized algorithms and architectures. This paper reviews several optimization methods to improve the accuracy of the training and to reduce training time. We delve into the math behind training algorithms used in recent deep networks. We describe current shortcomings, enhancements, and implementations. The review also covers different types of deep architectures, such as deep convolution networks, deep residual networks, recurrent neural networks, reinforcement learning, variational autoencoders, and others.
This paper introduces a novel approach GPTFX, an AI-based mental detection with GPT frameworks. This approach leverages GPT embeddings and the fine-tuning of GPT-3. This approach exhibits superior ...performance in both classifying mental health disorders and generating explanations with accuracy of around 87% in classification and Rouge-L of around 0.75. We utilized GPT embeddings with machine learning models for the classification of mental health disorders. Additionally, GPT-3 was fine-tuned for generating explanations related to the predictions made by these machine learning models. Notably, the proposed algorithm proves well-suited for real-time monitoring of mental health by deploying in AI-IoMT devices, as it has demonstrated greater reliability when compared to traditional algorithms.
Learning and predicting the dynamics of physical systems requires a profound understanding of the underlying physical laws. Recent works on learning physical laws involve the extension of the ...equation discovery frameworks to the discovery of Hamiltonian and Lagrangian of physical systems. While the existing methods parameterize the Lagrangian using neural networks, we propose an alternate framework for learning interpretable Lagrangian descriptions of physical systems from limited data using the sparse Bayesian approach. Unlike existing neural network-based approaches, the proposed approach (a) yields an interpretable description of Lagrangian, (b) exploits Bayesian learning to quantify the epistemic uncertainty due to limited data, (c) automates the distillation of Hamiltonian from the learned Lagrangian using Legendre transformation, and (d) provides ordinary (ODE) and partial differential equation (PDE) based descriptions of the observed systems. Six different examples involving both discrete and continuous systems illustrate the efficacy of the proposed approach.
•A probabilistic framework is introduced for discovering interpretable Lagrangian.•It is applicable to both discrete and continuous systems.•The proposed framework can discover Lagrangian from limited data.•The identified models have long term predictive ability and generalize to high-dimensional systems.
Current battery modelling methodologies including equivalent circuital modelling and electrochemical modelling do not maintain accuracy over diverse operating conditions of current rates, ...depth-of-discharge and temperatures. To address this limitation, this article proposes the Universal Differential Equations (UDE) framework from scientific machine learning (SciML) as a methodology to generate battery models with improved generalisability. The effectiveness of UDE in enhancing generalisability is demonstrated through a specific battery modelling example. The approach starts with the Thermal Equivalent Circuital Model with Diffusion (TECMD), a state-of-the-art battery model, which is then enhanced through the integration of neural networks into its state equations, resulting in the Neural-TECMD; a UDE model. Additionally, a two-stage UDE parameterisation method is introduced, combining collocation-based pretraining with mini-batch training. The parameterisation method enables the neural networks in the Neural-TECMD to efficiently learn battery dynamics from multiple time series data sets, covering a wide operating spectrum. Consequently, the Neural-TECMD model offers accurate predictions over broader operating conditions, thus enhancing model generalisability. The Neural-TECMD model was validated using 20 data sets covering current rates of 0 to 2C and temperatures from 0 to 45 °C. This validation revealed substantial improvements in accuracy, with an average of 34.51% decrease in RMSE for voltage and a 24.94% decrease for temperature predictions compared to the standard TECMD model.
•UDE approach from SciML can create generalisable battery models.•Neural networks are added within the state equations of a mechanistic model.•A cost-effective two-step UDE parameterisation method is proposed.•The efficiency of the method is proved by creating and validating Neural TECMD model.
Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, ...biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field.
Machine learning (ML) provides effective means to learn from spectrum data and solve complex tasks involved in wireless communications. Supported by recent advances in computational resources and ...algorithmic designs, deep learning (DL) has found success in performing various wireless communication tasks such as signal recognition, spectrum sensing and waveform design. However, ML in general and DL in particular have been found vulnerable to manipulations thus giving rise to a field of study called adversarial machine learning (AML). Although AML has been extensively studied in other data domains such as computer vision and natural language processing, research for AML in the wireless communications domain is still in its early stage. This paper presents a comprehensive review of the latest research efforts focused on AML in wireless communications while accounting for the unique characteristics of wireless systems. First, the background of AML attacks on deep neural networks is discussed and a taxonomy of AML attack types is provided. Various methods of generating adversarial examples and attack mechanisms are also described. In addition, an holistic survey of existing research on AML attacks for various wireless communication problems as well as the corresponding defense mechanisms in the wireless domain are presented. Finally, as new attacks and defense techniques are developed, recent research trends and the overarching future outlook for AML in next-generation wireless communications are discussed.
Many-body descriptors are widely used to represent atomic environments in the construction of machine-learned interatomic potentials and more broadly for fitting, classification, and embedding tasks ...on atomic structures. There is a widespread belief in the community that three-body correlations are likely to provide an overcomplete description of the environment of an atom. We produce several counterexamples to this belief, with the consequence that any classifier, regression, or embedding model for atom-centered properties that uses three- (or four)-body features will incorrectly give identical results for different configurations. Writing global properties (such as total energies) as a sum of many atom-centered contributions mitigates the impact of this fundamental deficiency-explaining the success of current "machine-learning" force fields. We anticipate the issues that will arise as the desired accuracy increases, and suggest potential solutions.
Machine learning based Intrusion Detection Systems (IDS) allow flexible and efficient automated detection of cyberattacks in Internet of Things (IoT) networks. However, this has also created an ...additional attack vector; the machine learning models which support the IDS’s decisions may also be subject to cyberattacks known as Adversarial Machine Learning (AML). In the context of IoT, AML can be used to manipulate data and network traffic that traverse through such devices. These perturbations increase the confusion in the decision boundaries of the machine learning classifier, where malicious network packets are often miss-classified as being benign. Consequently, such errors are bypassed by machine learning based detectors, which increases the potential of significantly delaying attack detection and further consequences such as personal information leakage, damaged hardware, and financial loss. Given the impact that these attacks may have, this paper proposes a rule-based approach towards generating AML attack samples and explores how they can be used to target a range of supervised machine learning classifiers used for detecting Denial of Service attacks in an IoT smart home network. The analysis explores which DoS packet features to perturb and how such adversarial samples can support increasing the robustness of supervised models using adversarial training. The results demonstrated that the performance of all the top performing classifiers were affected, decreasing a maximum of 47.2 percentage points when adversarial samples were present. Their performances improved following adversarial training, demonstrating their robustness towards such attacks.