arXiv subjects

Mojtaba Moattari

Publications and source records attributed to Mojtaba Moattari.

8 recordsLinked to original sources

arXiv2026

Interpretable Multimodal Classification with Linear Discriminant Tree Ensembles

Multimodal affect and behaviour classifiers that fuse heterogeneous text, audio, and visual streams must simultaneously achieve competitive accuracy and produce human-understandable explanations of the cues driving their decisions -- a dual objective that current high-capacity models, notably Transformers, only partially address. While Transformers attain strong predictive performance, their distributed representations and deep nonlinearity make it difficult to assign meaningful importance weights to individual multimodal features, limiting their use in trust-sensitive applications such as clinical affect monitoring and educational assessment. We address this gap by developing a framework based on tree-based ensembles that balances accuracy and interpretability. The framework encodes each modality into tokens, extracts and clusters concepts to reduce dimensionality, routes the fused modalities through tree-based ensemble classifiers, and interprets trends using a novel modified feature importance metric. The modified importance reduces the influence of the negative class in binary classification tasks, thereby improving indicator or marker detection. The proposed tree-based ensembles -- Linear Discriminant Tree (LDT), Linear Discriminant Forest (LDF), and Linear Discriminant AdaBoost (LDAB) -- achieve F1-mod gains of 4.3\% over the Multimodal Transformer and accuracy gains of 3.0\% over the primary interpretable multimodal baseline, Interpretable Multimodal Routing (IMR). The proposed multimodal feature importance extracts salient inter-modal concepts with substantially higher human-annotator agreement scores than default feature importance (62.2\% vs.\ 43.2\% on IEMOCAP; 46.7\% vs.\ 32.1\% on CMU-MOSI).

cs.AI↗

arXiv2025

Precise classification of low quality G-banded Chromosome Images by reliability metrics and data pruning classifier

In the last decade, due to high resolution cameras and accurate meta-phase analyzes, the accuracy of chromosome classification has improved substantially. However, current Karyotyping systems demand large number of high quality train data to have an adequately plausible Precision per each chromosome. Such provision of high quality train data with accurate devices are not yet accomplished in some out-reached pathological laboratories. To prevent false positive detections in low-cost systems and low-quality images settings, this paper improves the classification Precision of chromosomes using proposed reliability thresholding metrics and deliberately engineered features. The proposed method has been evaluated using a variation of deep Alex-Net neural network, SVM, K Nearest-Neighbors, and their cascade pipelines to an automated filtering of semi-straight chromosome. The classification results have highly improved over 90% for the chromosomes with more common defections and translocations. Furthermore, a comparative analysis over the proposed thresholding metrics has been conducted and the best metric is bolded with its salient characteristics. The high Precision results provided for a very low-quality G-banding database verifies suitability of the proposed metrics and pruning method for Karyotyping facilities in poor countries and lowbudget pathological laboratories.

cs.CV↗

arXiv2025

Yet Unnoticed in LSTM: Binary Tree Based Input Reordering, Weight Regularization, and Gate Nonlinearization

LSTM models used in current Machine Learning literature and applications, has a promising solution for permitting long term information using gating mechanisms that forget and reduce effect of current input information. However, even with this pipeline, they do not optimally focus on specific old index or long-term information. This paper elaborates upon input reordering approaches to prioritize certain input indices. Moreover, no LSTM based approach is found in the literature that examines weight normalization while choosing the right weight and exponent of Lp norms through main supervised loss function. In this paper, we find out which norm best finds relationship between weights to either smooth or sparsify them. Lastly, gates, as weighted representations of inputs and states, which control reduction-extent of current input versus previous inputs (~ state), are not nonlinearized enough (through a small FFNN). As analogous to attention mechanisms, gates easily filter current information to bold (emphasize on) past inputs. Nonlinearized gates can more easily tune up to peculiar nonlinearities of specific input in the past. This type of nonlinearization is not proposed in the literature, to the best of author's knowledge. The proposed approaches are implemented and compared with a simple LSTM to understand their performance in text classification tasks. The results show they improve accuracy of LSTM.

cs.LG↗

arXiv2025

Beyond Correlation: Learning Supervised, Sample-Distinct, and Eigenimage-Interpretable Representations

Conventional dimensionality reduction methods mainly optimize variance or correlation, leaving statistical dependence, data diversity, contrast, and interpretability under addressed. We propose three new independence criteria for designing supervised and unsupervised dimensionality reduction (DR) methods, aiming to improve feature extraction and representation quality. Our framework combines linear and nonlinear formulations and is evaluated using contrast, classification accuracy, and interpretability measures. The interpretability of eigenfaces helps to effectively summarize dominant class-specific structures and trends within representative images. Evaluated on MNIST and a Gender face dataset for classification and reconstruction, our methods achieve significant improvements in contrast (up to $+$20.1\%), accuracy (up to $+$17.4\%), and interpretability (up to $+$120.0\%) over Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), Linear Discriminant Analysis (LDA), and Variational Autoencoder (VAE) baselines, while also improving VAE reconstruction performance by 9.5\%. These results suggest a promising direction for interpretable representation learning based on statistical dependence and independence criteria.

cs.LG↗

arXiv2022

ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion

Knowledge Graph Embedding (KGE) methods have gained enormous attention from a wide range of AI communities including Natural Language Processing (NLP) for text generation, classification and context induction. Embedding a huge number of inter-relationships in terms of a small number of dimensions, require proper modeling in both cognitive and computational aspects. Recently, numerous objective functions regarding cognitive and computational aspects of natural languages are developed. Among which are the state-of-the-art methods of linearity, bilinearity, manifold-preserving kernels, projection-subspace, and analogical inference. However, the major challenge of such models lies in their loss functions that associate the dimension of relation embeddings to corresponding entity dimension. This leads to inaccurate prediction of corresponding relations among entities when counterparts are estimated wrongly. ProjE KGE, published by Bordes et al., due to low computational complexity and high potential for model improvement, is improved in this work regarding all translative and bilinear interactions while capturing entity nonlinearity. Experimental results on benchmark Knowledge Graphs (KGs) such as FB15K and WN18 show that the proposed approach outperforms the state-of-the-art models in entity prediction task using linear and bilinear methods and other recent powerful ones. In addition, a parallel processing structure is proposed for the model in order to improve the scalability on large KGs. The effects of different adaptive clustering and newly proposed sampling approaches are also explained which prove to be effective in improving the accuracy of knowledge graph completion.

cs.AI↗

arXiv2020

Uncertainty Principle based optimization; new metaheuristics framework

To more flexibly balance between exploration and exploitation, a new meta-heuristic method based on Uncertainty Principle concepts is proposed in this paper. UP is is proved effective in multiple branches of science. In the branch of quantum mechanics, canonically conjugate observables such as position and momentum cannot both be distinctly determined in any quantum state. In the same manner, the branch of Spectral filtering design implies that a nonzero function and its Fourier transform cannot both be sharply localized. After delving into such concepts on Uncertainty Principle and their variations in quantum physics, Fourier analysis, and wavelet design, the proposed framework is described in terms of algorithm and flowchart. Our proposed optimizer's idea is based on an inherent uncertainty in performing local search versus global solution search. A set of compatible metrics for each part of the framework is proposed to derive preferred form of algorithm. Evaluations and comparisons at the end of paper show competency and distinct capability of the algorithm over some of the well-known and recently proposed metaheuristics.

cs.NE↗

arXiv2020

A New Approach for Optimizing Highly Nonlinear Problems Based on the Observer Effect Concept

A lot of real-world engineering problems represent dynamicity with nests of nonlinearities due to highly complex network of exponential functions or large number of differential equations interacting together. Such search spaces are provided with multiple convex regions peaked with diverse nonlinear slopes and in non-homogenous ways. To find global optima, a new meta-heuristic algorithm is proposed based on Observer Effect concepts for controlling memory usage per localities without pursuing Tabu-like cut-off approaches. Observer effect in physics (or psychology) regards bias in measurement (or perception) due to the interference of instrument (or knowledge). Performance analysis of the proposed algorithms is sought in two real-world engineering applications, i.e., Electroencephalogram feature learning and Distributed Generator parameter tuning, each of which having nonlinearity and complex multi-modal peaks distributions as their characteristics. In addition, the effect of version improvement has been assessed. The performance comparison with other optimizers in the same context suggests that proposed algorithm is useful both solely and in hybrid Gradient Descent settings where problem's search space is nonhomogeneous in terms of local peaks density.

cs.NE↗

arXiv2020

Modified swarm-based metaheuristics enhance Gradient Descent initialization performance: Application for EEG spatial filtering

Gradient Descent (GD) approximators often fail in the solution space with multiple scales of convexities, i.e., in subspace learning and neural network scenarios. To handle that, one solution is to run GD multiple times from different randomized initial states and select the best solution over all experiments. However, this idea is proved impractical in plenty of cases. Even Swarm-based optimizers like Particle Swarm Optimization (PSO) or Imperialistic Competitive Algorithm (ICA), as commonly used GD initializers, have failed to find optimal solutions in some applications. In this paper, Swarm-based optimizers like ICA and PSO are modified by a new optimization framework to improve GD optimization performance. This improvement is for applications with high number of convex localities in multiple scales. Performance of the proposed method is analyzed in a nonlinear subspace filtering objective function over EEG data. The proposed metaheuristic outperforms commonly used baseline optimizers as GD initializers in both the EEG classification accuracy and EEG loss function fitness. The optimizers have been also compared to each other in some of CEC 2014 benchmark functions, where again our method outperforms other algorithms.

cs.NE↗