Search

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that limit their performance: (1) Previous methods primarily use static ground truth for adversarial training, but this often causes robust overfitting; (2) The loss functions are either Mean Squared Error or KL-divergence leading to a sub-optimal performance on clean accuracy. To solve those problems, we propose a dynamic label adversarial training (DYNAT) algorithm that enables the target model to gradually and dynamically gain robustness from the guide model's decisions. Additionally, we found that a budgeted dimension of inner optimization for the target model may contribute to the trade-off between clean accuracy and robust accuracy. Therefore, we propose a novel inner optimization method to be incorporated into the adversarial training. This will enable the target model to adaptively search for adversarial examples based on dynamic labels from the guiding model, contributing to the robustness of the target model. Extensive experiments validate the superior performance of our approach.

We scrutinize the structural and operational aspects of deep learning models, particularly focusing on the nuances of learnable parameters (weight) statistics, distribution, node interaction, and visualization. By establishing correlations between variance in weight patterns and overall network performance, we investigate the varying (optimal and suboptimal) performances of various deep-learning models. Our empirical analysis extends across widely recognized datasets such as MNIST, Fashion-MNIST, and CIFAR-10, and various deep learning models such as deep neural networks (DNNs), convolutional neural networks (CNNs), and vision transformer (ViT), enabling us to pinpoint characteristics of learnable parameters that correlate with successful networks. Through extensive experiments on the diverse architectures of deep learning models, we shed light on the critical factors that influence the functionality and efficiency of DNNs. Our findings reveal that successful networks, irrespective of datasets or models, are invariably similar to other successful networks in their converged weights statistics and distribution, while poor-performing networks vary in their weights. In addition, our research shows that the learnable parameters of widely varied deep learning models such as DNN, CNN, and ViT exhibit similar learning characteristics.

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learning-based HAR requires a large amount of labelled data and extracting HAR features from unlabelled data for effective deep learning training remains challenging. We, therefore, introduce a deep semi-supervised HAR approach, MixHAR, which concurrently uses labelled and unlabelled activities. Our MixHAR employs a linear interpolation mechanism to blend labelled and unlabelled activities while addressing both inter- and intra-activity variability. A unique challenge identified is the activityintrusion problem during mixing, for which we propose a mixing calibration mechanism to mitigate it in the feature embedding space. Additionally, we rigorously explored and evaluated the five conventional/popular deep semi-supervised technologies on HAR, acting as the benchmark of deep semi-supervised HAR. Our results demonstrate that MixHAR significantly improves performance, underscoring the potential of deep semi-supervised techniques in HAR.

We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, where unseen domains are continually learned. Typical methods for mitigating forgetting, such as the use of additional datasets and the retention of private data from earlier tasks, are not viable in federated learning (FL) due to devices' limited resources. Our method, RefFiL, addresses this by learning domain-invariant knowledge and incorporating various domain-specific prompts from the domains represented by different FL participants. A key feature of RefFiL is the generation of local fine-grained prompts by our domain adaptive prompt generator, which effectively learns from local domain knowledge while maintaining distinctive boundaries on a global scale. We also introduce a domain-specific prompt contrastive learning loss that differentiates between locally generated prompts and those from other domains, enhancing RefFiL's precision and effectiveness. Compared to existing methods, RefFiL significantly alleviates catastrophic forgetting without requiring extra memory space, making it ideal for privacy-sensitive and resource-constrained devices.

In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus alleviating the problem of pseudo ground truth inconsistency. TSM enhances the stability and consistency of the model's generated paths during the distillation process. We demonstrate this experimentally and further show that ISM is a special case of TSM. Furthermore, to optimize the current multi-stage optimization process from high-resolution text to 3D generation, we adopt Stable Diffusion XL for guidance. In response to the issues of abnormal replication and splitting caused by unstable gradients during the 3D Gaussian splatting process when using Stable Diffusion XL, we propose a pixel-by-pixel gradient clipping method. Extensive experiments show that our model significantly surpasses the state-of-the-art models in terms of visual quality and performance. Code: \url{https://github.com/xingy038/Dreamer-XL}.

SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and multilingual (Subtask A), multi-class classification (Subtask B), and mixed text detection (Subtask C). This paper focuses on Subtask A & B. Each subtask is supported by three datasets for training, development, and testing. To tackle this task, two methods: 1) using traditional machine learning (ML) with natural language preprocessing (NLP) for feature extraction, and 2) fine-tuning LLMs for text classification. The results show that transformer models, particularly LoRA-RoBERTa, exceed traditional ML methods in effectiveness, with majority voting being particularly effective in multilingual contexts for identifying machine-generated texts.

We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifies the fragility, robustness and antifragility characteristics of DNN parameters. Our proposed analysis investigates if the DNN performance is impacted negatively, invariantly, or positively on both clean and adversarially perturbed test datasets when the DNN undergoes synaptic filtering. We define three \textit{filtering scores} for quantifying the fragility, robustness and antifragility characteristics of DNN parameters based on the performances for (i) clean dataset, (ii) adversarial dataset, and (iii) the difference in performances of clean and adversarial datasets. We validate the proposed systematic analysis on ResNet-18, ResNet-50, SqueezeNet-v1.1 and ShuffleNet V2 x1.0 network architectures for MNIST, CIFAR10 and Tiny ImageNet datasets. The filtering scores, for a given network architecture, identify network parameters that are invariant in characteristics across different datasets over learning epochs. Vice-versa, for a given dataset, the filtering scores identify the parameters that are invariant in characteristics across different network architectures. We show that our synaptic filtering method improves the test accuracy of ResNet and ShuffleNet models on adversarial datasets when only the robust and antifragile parameters are selectively retrained at any given epoch, thus demonstrating applications of the proposed strategy in improving model robustness.

The paper proposes a novel adaptive search space decomposition method and a novel gradient-free optimization-based formulation for the pre- and post-buckling analyses of space truss structures. Space trusses are often employed in structural engineering to build large steel constructions, such as bridges and domes, whose structural response is characterized by large displacements. Therefore, these structures are vulnerable to progressive collapses due to local or global buckling effects, leading to sudden failures. The method proposed in this paper allows the analysis of the load-equilibrium path of truss structures to permanent and variable loading, including stable and unstable equilibrium stages and explicitly considering geometric nonlinearities. The goal of this work is to determine these equilibrium stages via optimization of the Lagrangian kinematic parameters of the system, determining the global equilibrium. However, this optimization problem is non-trivial due to the undefined parameter domain and the sensitivity and interaction among the Lagrangian parameters. Therefore, we propose formulating this problem as a nonlinear, multimodal, unconstrained, continuous optimization problem and develop a novel adaptive search space decomposition method, which progressively and adaptively re-defines the search domain (hypersphere) to evaluate the equilibrium of the system using a gradient-free optimization algorithm. We tackle three benchmark problems and evaluate a medium-sized test representing a real structural problem in this paper. The results are compared to those available in the literature regarding displacement-load curves and deformed configurations. The accuracy and robustness of the adopted methodology show a high potential of gradient-free algorithms in analyzing space truss structures., Comment: Engineering Application of Artificial Intelligence 2022

We present a comprehensive global sensitivity analysis of two single-objective and two multi-objective state-of-the-art global optimization evolutionary algorithms as an algorithm configuration problem. That is, we investigate the quality of influence hyperparameters have on the performance of algorithms in terms of their direct effect and interaction effect with other hyperparameters. Using three sensitivity analysis methods, Morris LHS, Morris, and Sobol, to systematically analyze tunable hyperparameters of covariance matrix adaptation evolutionary strategy, differential evolution, non-dominated sorting genetic algorithm III, and multi-objective evolutionary algorithm based on decomposition, the framework reveals the behaviors of hyperparameters to sampling methods and performance metrics. That is, it answers questions like what hyperparameters influence patterns, how they interact, how much they interact, and how much their direct influence is. Consequently, the ranking of hyperparameters suggests their order of tuning, and the pattern of influence reveals the stability of the algorithms.

This paper proposes a methodological approach with a transfer learning scheme for plastic waste bottle detection and instance segmentation using the \textit{mask region proposal convolutional neural network} (Mask R-CNN). Plastic bottles constitute one of the major pollutants posing a serious threat to the environment both in oceans and on land. The automated identification and segregation of bottles can facilitate plastic waste recycling. We prepare a custom-made dataset of 192 bottle images with pixel-by pixel-polygon annotation for the automatic segmentation task. The proposed transfer learning scheme makes use of a Mask R-CNN model pre-trained on the Microsoft COCO dataset. We present a comprehensive scheme for fine-tuning the base pre-trained Mask-RCNN model on our custom dataset. Our final fine-tuned model has achieved 59.4 \textit{mean average precision} (mAP), which corresponds to the MS COCO metric. The results indicate a promising application of deep learning for detecting waste bottles.

In chaotic dynamical systems such as the weather, prediction errors grow faster in some situations than in others. Real-time knowledge about the error growth could enable strategies to adjust the modelling and forecasting infrastructure on-the-fly to increase accuracy or reduce computation time. One could, e.g., change the ensemble size, or the distribution and type of target observations. Local Lyapunov exponents are known indicators of the rate at which very small prediction errors grow over a finite time interval. However, their computation is very expensive: it requires maintaining and evolving a tangent linear model, orthogonalisation algorithms and storing large matrices. In this feasibility study, we investigate the accuracy of supervised machine learning in estimating the current local Lyapunov exponents, from input of current and recent time steps of the system trajectory, as an alternative to the classical method. Thus machine learning is not used here to emulate a physical model or some of its components, but non intrusively as a complementary tool. We test four popular supervised learning algorithms: regression trees, multilayer perceptrons, convolutional neural networks and long short-term memory networks. Experiments are conducted on two low-dimensional chaotic systems of ordinary differential equations, the R\"ossler and the Lorenz 63 models. We find that on average the machine learning algorithms predict the stable local Lyapunov exponent accurately, the unstable exponent reasonably accurately, and the neutral exponent only somewhat accurately. We show that greater prediction accuracy is associated with local homogeneity of the local Lyapunov exponents on the system attractor. Importantly, the situations in which (forecast) errors grow fastest are not necessarily the same as those where it is more difficult to predict local Lyapunov exponents with machine learning., Comment: 37 pages, 10 Figures

We propose a novel algorithm called Backpropagation Neural Tree (BNeuralT), which is a stochastic computational dendritic tree. BNeuralT takes random repeated inputs through its leaves and imposes dendritic nonlinearities through its internal connections like a biological dendritic tree would do. Considering the dendritic-tree like plausible biological properties, BNeuralT is a single neuron neural tree model with its internal sub-trees resembling dendritic nonlinearities. BNeuralT algorithm produces an ad hoc neural tree which is trained using a stochastic gradient descent optimizer like gradient descent (GD), momentum GD, Nesterov accelerated GD, Adagrad, RMSprop, or Adam. BNeuralT training has two phases, each computed in a depth-first search manner: the forward pass computes neural tree's output in a post-order traversal, while the error backpropagation during the backward pass is performed recursively in a pre-order traversal. A BNeuralT model can be considered a minimal subset of a neural network (NN), meaning it is a "thinned" NN whose complexity is lower than an ordinary NN. Our algorithm produces high-performing and parsimonious models balancing the complexity with descriptive ability on a wide variety of machine learning problems: classification, regression, and pattern recognition.

We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks on the network. Adversarial robustness of neural networks has gained significant attention in recent times and highlights intrinsic weaknesses of deep learning networks against carefully constructed distortion applied to input images. In this paper, we evaluate the robustness of state-of-the-art image classification models trained on the MNIST and CIFAR10 datasets against the fast gradient sign method attack, a simple yet effective method of deceiving neural networks. Our method identifies the specific neurons of a network that are most affected by the adversarial attack being applied. We, therefore, propose to make fragile neurons more robust against these attacks by compressing features within robust neurons and amplifying the fragile neurons proportionally.

We propose a novel deep learning based denoising filter selection algorithm for noisy Electrocardiograph (ECG) signal preprocessing. ECG signals measured under clinical conditions, such as those acquired using skin contact devices in hospitals, often contain baseline signal disturbances and unwanted artefacts; indeed for signals obtained outside of a clinical environment, such as heart rate signatures recorded using non-contact radar systems, the measurements contain greater levels of noise than those acquired under clinical conditions. In this paper, we focus on heart rate signals acquired using non-contact radar systems for use in assisted living environments. Such signals contain more noise than those measured under clinical conditions and thus require a novel signal noise removal method capable of adaptive determining filters. Currently, the most common method of removing noise from such a waveform is through the use of filters; the most popular filtering method amongst which is the wavelet filter. There are, however, circumstances in which using a different filtering method may result in higher signal-to-noise-ratios (SNR) for a waveform; in this paper, we investigate the wavelet and elliptical filtering methods for the task of reducing noise in ECG signals acquired using assistive technologies. Our proposed convolutional neural network architecture classifies (with 92.8% accuracy) the optimum filtering method for noisy signal based on its expected SNR value.

We propose a two-stage multi-objective optimization framework for full scheme solar cell structure design and characterization, cost minimization and quantum efficiency maximization. We evaluated structures of 15 different cell designs simulated by varying material types and photodiode doping strategies. At first, non-dominated sorting genetic algorithm~II (NSGA-II) produced Pareto-optimal-solutions sets for respective cell designs. Then, on investigating quantum efficiencies of all cell designs produced by NSGA-II, we applied a new multi-objective optimization algorithm~II (OptIA-II) to discover the Pareto fronts of select (three) best cell designs. Our designed OptIA-II algorithm improved the quantum efficiencies of all select cell designs and reduced their fabrication costs. We observed that the cell design comprising an optimally doped zinc-oxide-based transparent conductive oxide (TCO) layer and rough silver back reflector (BR) offered a quantum efficiency ($Q_e$) of $0.6031.$ Overall, this paper provides a full characterization of cell structure designs. It derives a relationship between quantum efficiency, $Q_e$ of a cell with its TCO layer's doping methods and TCO and BR layer's material types. Our solar cells design characterization enables us to perform a cost-benefit analysis of solar cells usage in real-world applications, Comment: published in 2021

Automatic Crowd behavior analysis can be applied to effectively help the daily transportation statistics and planning, which helps the smart city construction. As one of the most important keys, crowd counting has drawn increasing attention. Recent works achieved promising performance but relied on the supervised paradigm with expensive crowd annotations. To alleviate the annotation cost in real-world transportation scenarios, in this work we proposed a semi-supervised learning framework $S^{4}\textit{Crowd}$, which can leverage both unlabeled/labeled data for robust crowd counting. In the unsupervised pathway, two \textit{self-supervised losses} were proposed to simulate the crowd variations such as scale, illumination, based on which supervised information pseudo labels were generated and gradually refined. We also proposed a crowd-driven recurrent unit \textit{Gated-Crowd-Recurrent-Unit (GCRU)}, which can preserve discriminant crowd information by extracting second-order statistics, yielding pseudo labels with improved quality. A joint loss including both unsupervised/supervised information was proposed, and a dynamic weighting strategy was employed to balance the importance of the unsupervised loss and supervised loss at different training stages. We conducted extensive experiments on four popular crowd counting datasets in semi-supervised settings. Experimental results supported the effectiveness of each proposed component in our $S^{4}$Crowd framework. Our method achieved competitive performance in semi-supervised learning approaches on these crowd counting datasets.

We propose an algorithm and a new method to tackle the classification problems. We propose a multi-output neural tree (MONT) algorithm, which is an evolutionary learning algorithm trained by the non-dominated sorting genetic algorithm (NSGA)-III. Since evolutionary learning is stochastic, a hypothesis found in the form of MONT is unique for each run of evolutionary learning, i.e., each hypothesis (tree) generated bears distinct properties compared to any other hypothesis both in topological space and parameter-space. This leads to a challenging optimisation problem where the aim is to minimise the tree-size and maximise the classification accuracy. Therefore, the Pareto-optimality concerns were met by hypervolume indicator analysis. We used nine benchmark classification learning problems to evaluate the performance of the MONT. As a result of our experiments, we obtained MONTs which are able to tackle the classification problems with high accuracy. The performance of MONT emerged better over a set of problems tackled in this study compared with a set of well-known classifiers: multilayer perceptron, reduced-error pruning tree, naive Bayes classifier, decision tree, and support vector machine. Moreover, the performances of three versions of MONT's training using genetic programming, NSGA-II, and NSGA-III suggest that the NSGA-III gives the best Pareto-optimal solution., Comment: 19-24 July 2020

This paper provides an in-depth review of the optimal design of type-1 and type-2 fuzzy inference systems (FIS) using five well known computational frameworks: genetic-fuzzy systems (GFS), neuro-fuzzy systems (NFS), hierarchical fuzzy systems (HFS), evolving fuzzy systems (EFS), and multi-objective fuzzy systems (MFS), which is in view that some of them are linked to each other. The heuristic design of GFS uses evolutionary algorithms for optimizing both Mamdani-type and Takagi-Sugeno-Kang-type fuzzy systems. Whereas, the NFS combines the FIS with neural network learning systems to improve the approximation ability. An HFS combines two or more low-dimensional fuzzy logic units in a hierarchical design to overcome the curse of dimensionality. An EFS solves the data streaming issues by evolving the system incrementally, and an MFS solves the multi-objective trade-offs like the simultaneous maximization of both interpretability and accuracy. This paper offers a synthesis of these dimensions and explores their potentials, challenges, and opportunities in FIS research. This review also examines the complex relations among these dimensions and the possibilities of combining one or more computational frameworks adding another dimension: deep fuzzy systems., Comment: 53 pages, 16 figures

This research proposes a framework for signal processing and information fusion of spatial-temporal multi-sensor data pertaining to understanding patterns of humans physiological changes in an urban environment. The framework includes signal frequency unification, signal pairing, signal filtering, signal quantification, and data labeling. Furthermore, this paper contributes to human-environment interaction research, where a field study to understand the influence of environmental features such as varying sound level, illuminance, field-of-view, or environmental conditions on humans' perception was proposed. In the study, participants of various demographic backgrounds walked through an urban environment in Zurich, Switzerland while wearing physiological and environmental sensors. Apart from signal processing, four machine learning techniques, classification, fuzzy rule-based inference, feature selection, and clustering, were applied to discover relevant patterns and relationship between the participants' physiological responses and environmental conditions. The predictive models with high accuracies indicate that the change in the field-of-view corresponds to increased participant arousal. Among all features, the participants' physiological responses were primarily affected by the change in environmental conditions and field-of-view.

Human fatalities are reported due to the excessive proportional presence of hazardous gas components in the manhole, such as Hydrogen Sulfide, Ammonia, Methane, Carbon Dioxide, Nitrogen Oxide, Carbon Monoxide, etc. Hence, predetermination of these gases is imperative. A neural network (NN) based intelligent sensory system is proposed for the avoidance of such fatalities. Backpropagation (BP) was applied for the supervised training of the neural network. A Gas sensor array consists of many sensor elements was employed for the sensing manhole gases. Sensors in the sensor array are responsible for sensing their target gas components only. Therefore, the presence of multiple gases results in cross sensitivity. The cross sensitivity is a crucial issue to this problem and it is viewed as pattern recognition and noise reduction problem. Various performance parameters and complexity of the problem influences NN training. In present chapter the performance of BP algorithm on such a real life application problem was comprehensively studied, compared and contrasted with the several other hybrid intelligent approaches both, in theoretical and in the statistical sense.

The performance of the meta-heuristic algorithms often depends on their parameter settings. Appropriate tuning of the underlying parameters can drastically improve the performance of a meta-heuristic. The Ant Colony Optimization (ACO), a population based meta-heuristic algorithm inspired by the foraging behavior of the ants, is no different. Fundamentally, the ACO depends on the construction of new solutions, variable by variable basis using Gaussian sampling of the selected variables from an archive of solutions. A comprehensive performance analysis of the underlying parameters such as: selection strategy, distance measure metric and pheromone evaporation rate of the ACO suggests that the Roulette Wheel Selection strategy enhances the performance of the ACO due to its ability to provide non-uniformity and adequate diversity in the selection of a solution. On the other hand, the Squared Euclidean distance-measure metric offers better performance than other distance-measure metrics. It is observed from the analysis that the ACO is sensitive towards the evaporation rate. Experimental analysis between classical ACO and other meta-heuristic suggested that the performance of the well-tuned ACO surpasses its counterparts.

Optimization of neural network (NN) significantly influenced by the transfer function used in its active nodes. It has been observed that the homogeneity in the activation nodes does not provide the best solution. Therefore, the customizable transfer functions whose underlying parameters are subjected to optimization were used to provide heterogeneity to NN. For the experimental purpose, a meta-heuristic framework using a combined genotype representation of connection weights and transfer function parameter was used. The performance of adaptive Logistic, Tangent-hyperbolic, Gaussian and Beta functions were analyzed. In present research work, concise comparisons between different transfer function and between the NN optimization algorithms are presented. The comprehensive analysis of the results obtained over the benchmark dataset suggests that the Artificial Bee Colony with adaptive transfer function provides the best results in terms of classification accuracy over the particle swarm optimization and differential evolution.

This paper proposes a design of hierarchical fuzzy inference tree (HFIT). An HFIT produces an optimum treelike structure, i.e., a natural hierarchical structure that accommodates simplicity by combining several low-dimensional fuzzy inference systems (FISs). Such a natural hierarchical structure provides a high degree of approximation accuracy. The construction of HFIT takes place in two phases. Firstly, a nondominated sorting based multiobjective genetic programming (MOGP) is applied to obtain a simple tree structure (a low complexity model) with a high accuracy. Secondly, the differential evolution algorithm is applied to optimize the obtained tree's parameters. In the derived tree, each node acquires a different input's combination, where the evolutionary process governs the input's combination. Hence, HFIT nodes are heterogeneous in nature, which leads to a high diversity among the rules generated by the HFIT. Additionally, the HFIT provides an automatic feature selection because it uses MOGP for the tree's structural optimization that accepts inputs only relevant to the knowledge contained in data. The HFIT was studied in the context of both type-1 and type-2 FISs, and its performance was evaluated through six application problems. Moreover, the proposed multiobjective HFIT was compared both theoretically and empirically with recently proposed FISs methods from the literature, such as McIT2FIS, TSCIT2FNN, SIT2FNN, RIT2FNS-WB, eT2FIS, MRIT2NFS, IT2FNN-SVR, etc. From the obtained results, it was found that the HFIT provided less complex and highly accurate models compared to the models produced by the most of other methods. Hence, the proposed HFIT is an efficient and competitive alternative to the other FISs for function approximation and feature selection.

Machine learning algorithms are inherently multiobjective in nature, where approximation error minimization and model's complexity simplification are two conflicting objectives. We proposed a multiobjective genetic programming (MOGP) for creating a heterogeneous flexible neural tree (HFNT), tree-like flexible feedforward neural network model. The functional heterogeneity in neural tree nodes was introduced to capture a better insight of data during learning because each input in a dataset possess different features. MOGP guided an initial HFNT population towards Pareto-optimal solutions, where the final population was used for making an ensemble system. A diversity index measure along with approximation error and complexity was introduced to maintain diversity among the candidates in the population. Hence, the ensemble was created by using accurate, structurally simple, and diverse candidates from MOGP final population. Differential evolution algorithm was applied to fine-tune the underlying parameters of the selected candidates. A comprehensive test over classification, regression, and time-series datasets proved the efficiency of the proposed algorithm over other available prediction methods. Moreover, the heterogeneous creation of HFNT proved to be efficient in making ensemble system from the final population.

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

Prediction of poly(lactic co glycolic acid) (PLGA) micro- and nanoparticles' dissolution rates plays a significant role in pharmaceutical and medical industries. The prediction of PLGA dissolution rate is crucial for drug manufacturing. Therefore, a model that predicts the PLGA dissolution rate could be beneficial. PLGA dissolution is influenced by numerous factors (features), and counting the known features leads to a dataset with 300 features. This large number of features and high redundancy within the dataset makes the prediction task very difficult and inaccurate. In this study, dimensionality reduction techniques were applied in order to simplify the task and eliminate irrelevant and redundant features. A heterogeneous pool of several regression algorithms were independently tested and evaluated. In addition, several ensemble methods were tested in order to improve the accuracy of prediction. The empirical results revealed that the proposed evolutionary weighted ensemble method offered the lowest margin of error and significantly outperformed the individual algorithms and the other ensemble techniques.

In this work, a computational intelligence (CI) technique named flexible neural tree (FNT) was developed to predict die filling performance of pharmaceutical granules and to identify significant die filling process variables. FNT resembles feedforward neural network, which creates a tree-like structure by using genetic programming. To improve accuracy, FNT parameters were optimized by using differential evolution algorithm. The performance of the FNT-based CI model was evaluated and compared with other CI techniques: multilayer perceptron, Gaussian process regression, and reduced error pruning tree. The accuracy of the CI model was evaluated experimentally using die filling as a case study. The die filling experiments were performed using a model shoe system and three different grades of microcrystalline cellulose (MCC) powders (MCC PH 101, MCC PH 102, and MCC DG). The feed powders were roll-compacted and milled into granules. The granules were then sieved into samples of various size classes. The mass of granules deposited into the die at different shoe speeds was measured. From these experiments, a dataset consisting true density, mean diameter (d50), granule size, and shoe speed as the inputs and the deposited mass as the output was generated. Cross-validation (CV) methods such as 10FCV and 5x2FCV were applied to develop and to validate the predictive models. It was found that the FNT-based CI model (for both CV methods) performed much better than other CI models. Additionally, it was observed that process variables such as the granule size and the shoe speed had a higher impact on the predictability than that of the powder property such as d50. Furthermore, validation of model prediction with experimental data showed that the die filling behavior of coarse granules could be better predicted than that of fine granules.

In this work, we formulated a real-world problem related to sewer pipeline gas detection using the classification-based approaches. The primary goal of this work was to identify the hazardousness of sewer pipeline to offer safe and non-hazardous access to sewer pipeline workers so that the human fatalities, which occurs due to the toxic exposure of sewer gas components, can be avoided. The dataset acquired through laboratory tests, experiments, and various literature sources was organized to design a predictive model that was able to identify/classify hazardous and non-hazardous situation of sewer pipeline. To design such prediction model, several classification algorithms were used and their performances were evaluated and compared, both empirically and statistically, over the collected dataset. In addition, the performances of several ensemble methods were analyzed to understand the extent of improvement offered by these methods. The result of this comprehensive study showed that the instance-based learning algorithm performed better than many other algorithms such as multilayer perceptron, radial basis function network, support vector machine, reduced pruning tree. Similarly, it was observed that multi-scheme ensemble approach enhanced the performance of base predictors.