Seyedali Mirjalili

Rebin M. Ahmed, Tarik A. Rashid, Polla Fattah et al.

Handwriting recognition is one of the active and challenging areas of research in the field of image processing and pattern recognition. It has many applications that include: a reading aid for visual impairment, automated reading and processing for bank checks, making any handwritten document searchable, and converting them into structural text form, etc. Moreover, high accuracy rates have been recorded by handwriting recognition systems for English, Chinese Arabic, Persian, and many other languages. Yet there is no such system available for offline Kurdish handwriting recognition. In this paper, an attempt is made to design and develop a model that can recognize handwritten characters for Kurdish alphabets using deep learning techniques. Kurdish (Sorani) contains 34 characters and mainly employs an Arabic\Persian based script with modified alphabets. In this work, a Deep Convolutional Neural Network model is employed that has shown exemplary performance in handwriting recognition systems. Then, a comprehensive dataset was created for handwritten Kurdish characters, which contains more than 40 thousand images. The created dataset has been used for training the Deep Convolutional Neural Network model for classification and recognition tasks. In the proposed system, the experimental results show an acceptable recognition level. The testing results reported a 96% accuracy rate, and training accuracy reported a 97% accuracy rate. From the experimental results, it is clear that the proposed deep learning model is performing well and is comparable to the similar model of other languages' handwriting recognition systems.

Dler O. Hasan, Aso M. Aladdin, Hardi Sabah Talabani et al.

Fifteen Puzzle problem is one of the most classical problems that have captivated mathematical enthusiasts for centuries. This is mainly because of the huge size of the state space with approximately 1013 states that have to be explored and several algorithms have been applied to solve the Fifteen Puzzle instances. In this paper, to deal with this large state space, Bidirectional A* (BA*) search algorithm with three heuristics, such as Manhattan distance (MD), linear conflict (LC), and walking distance (WD) has been used to solve the Fifteen Puzzle problems. The three mentioned heuristics will be hybridized in a way that can dramatically reduce the number of generated states by the algorithm. Moreover, all those heuristics require only 25KB of storage but help the algorithm effectively reduce the number of generated states and expand fewer nodes. Our implementation of BA* search can significantly reduce the space complexity, and guarantee either optimal or near-optimal solutions.1

Junhao Wei, Yanxiao Li, Seyedali Mirjalili et al.

The Whale Optimization Algorithm (WOA) has shown strong optimization ability but still suffers from premature convergence and weak search diversity. To address these issues, this paper proposes an enhanced WOA variant called CICDWOA. The proposed algorithm introduces a Good Nodes Set (GNS) method for uniform population initialization, a Collective Cognitive Sharing (CCS) mechanism to enhance group collaboration, and an Enhanced Spiral Updating strategy based on the Cauchy Inverse Cumulative Distribution (CICD) to strengthen global exploration and local exploitation balance. In addition, a nonlinear convergence factor and a Hybrid Gaussian-Cauchy mutation based on Differential Evolution (DE) further improve convergence efficiency and population diversity. CICDWOA was evaluated on 23 benchmark functions, 2D robot path planning problems, 3D UAV path planning tasks and 10 engineering design problems. Statistical experiment results show that CICDWOA achieves faster convergence, higher accuracy, and better robustness than classical WOA and other advanced metaheuristic algorithms. CICDWOA gained average Friedman value of 1.6790, ranking first among the SOTA algorithms. And the results of engineering simulations confirm that CICDWOA provides an effective and general framework for solving complex optimization and engineering problems. The code of CICDWOA are available on \href{URL}{https://github.com/JunhaoWei-mpu/ROBIS-Lab/tree/CICDWOA}.

Mehdi Neshat, Michael Phipps, Chris A. Browne et al.

Predicting hospital length of stay (LoS) stands as a critical factor in shaping public health strategies. This data serves as a cornerstone for governments to discern trends, patterns, and avenues for enhancing healthcare delivery. In this study, we introduce a robust hybrid deep learning model, a combination of Multi-layer Convolutional (CNNs) deep learning, Gated Recurrent Units (GRU), and Dense neural networks, that outperforms 11 conventional and state-of-the-art Machine Learning (ML) and Deep Learning (DL) methodologies in accurately forecasting inpatient hospital stay duration. Our investigation delves into the implementation of this hybrid model, scrutinising variables like geographic indicators tied to caregiving institutions, demographic markers encompassing patient ethnicity, race, and age, as well as medical attributes such as the CCS diagnosis code, APR DRG code, illness severity metrics, and hospital stay duration. Statistical evaluations reveal the pinnacle LoS accuracy achieved by our proposed model (CNN-GRU-DNN), which averages at 89% across a 10-fold cross-validation test, surpassing LSTM, BiLSTM, GRU, and Convolutional Neural Networks (CNNs) by 19%, 18.2%, 18.6%, and 7%, respectively. Accurate LoS predictions not only empower hospitals to optimise resource allocation and curb expenses associated with prolonged stays but also pave the way for novel strategies in hospital stay management. This avenue holds promise for catalysing advancements in healthcare research and innovation, inspiring a new era of precision-driven healthcare practices.

Abdulhady Abas Abdullah, Fatemeh Daneshfar, Seyedali Mirjalili et al.

Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimization (DPO). While DPO is stable and RL-free, it treats preferences as flat winner vs. loser signals and is sensitive to noisy or brittle preferences arising from fragile chains of thought. We propose TUR-DPO, a topology- and uncertainty-aware variant of DPO that rewards how answers are derived, not only what they say, by eliciting lightweight reasoning topologies and combining semantic faithfulness, utility, and topology quality into a calibrated uncertainty signal. A small learnable reward is factorized over these signals and incorporated into an uncertainty-weighted DPO objective that remains RL-free and relies only on a fixed or moving reference policy. Empirically, across open 7-8B models and benchmarks spanning mathematical reasoning, factual question answering, summarization, and helpful/harmless dialogue, TUR-DPO improves judge win-rates, faithfulness, and calibration relative to DPO while preserving training simplicity and avoiding online rollouts. We further observe consistent gains in multimodal and long-context settings, and show that TUR-DPO matches or exceeds PPO on reasoning-centric tasks while maintaining operational simplicity.

Rizwan Qureshi, Ranjan Sapkota, Abbas Shah et al.

Can machines truly think, reason and act in domains like humans? This enduring question continues to shape the pursuit of Artificial General Intelligence (AGI). Despite the growing capabilities of models such as GPT-4.5, DeepSeek, Claude 3.5 Sonnet, Phi-4, and Grok 3, which exhibit multimodal fluency and partial reasoning, these systems remain fundamentally limited by their reliance on token-level prediction and lack of grounded agency. This paper offers a cross-disciplinary synthesis of AGI development, spanning artificial intelligence, cognitive neuroscience, psychology, generative models, and agent-based systems. We analyze the architectural and cognitive foundations of general intelligence, highlighting the role of modular reasoning, persistent memory, and multi-agent coordination. In particular, we emphasize the rise of Agentic RAG frameworks that combine retrieval, planning, and dynamic tool use to enable more adaptive behavior. We discuss generalization strategies, including information compression, test-time adaptation, and training-free methods, as critical pathways toward flexible, domain-agnostic intelligence. Vision-Language Models (VLMs) are reexamined not just as perception modules but as evolving interfaces for embodied understanding and collaborative task completion. We also argue that true intelligence arises not from scale alone but from the integration of memory and reasoning: an orchestration of modular, interactive, and self-improving components where compression enables adaptive behavior. Drawing on advances in neurosymbolic systems, reinforcement learning, and cognitive scaffolding, we explore how recent architectures begin to bridge the gap between statistical learning and goal-directed cognition. Finally, we identify key scientific, technical, and ethical challenges on the path to AGI.

Abdulhady Abas Abdullah, Amir H. Gandomi, Tarik A Rashid et al.

In natural language processing, multilingual models like mBERT and XLM-RoBERTa promise broad coverage but often struggle with languages that share a script yet differ in orthographic norms and cultural context. This issue is especially notable in Arabic-script languages such as Kurdish Sorani, Arabic, Persian, and Urdu. We introduce the Arabic Script RoBERTa (AS-RoBERTa) family: four RoBERTa-based models, each pre-trained on a large corpus tailored to its specific language. By focusing pre-training on language-specific script features and statistics, our models capture patterns overlooked by general-purpose models. When fine-tuned on classification tasks, AS-RoBERTa variants outperform mBERT and XLM-RoBERTa by 2 to 5 percentage points. An ablation study confirms that script-focused pre-training is central to these gains. Error analysis using confusion matrices shows how shared script traits and domain-specific content affect performance. Our results highlight the value of script-aware specialization for languages using the Arabic script and support further work on pre-training strategies rooted in script and language specificity.

Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili et al.

This review surveys the rapid evolution of Meta AI's LLaMA (Large Language Model Meta AI) series - from LLaMA 1 through LLaMA 4 and the specialized parameter-efficient fine-tuning (PEFT) methods developed for these models. We first describe the LLaMA family of foundation models (7B-65B to 288B parameters), their architectures (including native multimodal and Mixtureof-Experts variants), and key performance characteristics. We then describe and discuss the concept of PEFT, which adapts large pre-trained models by updating only a small subset of parameters, and review five PEFT methods that have been applied to LLaMA: LoRA (Low-Rank Adaptation), LLaMA-Adapter V1 and V2, LLaMA-Excitor, and QLoRA (Quantized LoRA). We discuss each method's mechanism, parameter savings, and example application to LLaMA (e.g., instruction tuning, multimodal tasks). We provide structured discussion and analysis of model and adapter architectures, parameter counts, and benchmark results (including examples where fine-tuned LLaMA models outperform larger baselines). Finally, we examine real-world use cases where LLaMA-based models and PEFT have been successfully applied (e.g., legal and medical domains), and we discuss ongoing challenges and future research directions (such as scaling to even larger contexts and improving robustness). This survey paper provides a one-stop resource for ML researchers and practitioners interested in LLaMA models and efficient fine-tuning strategies.

Hossein Shahbeik, Alireza Shafizadeh, Mohammad Hossein Nadian et al.

Co-pyrolysis of biomass feedstocks with polymeric wastes is a promising strategy for improving the quantity and quality parameters of the resulting liquid fuel. Numerous experimental measurements are typically conducted to find the optimal operating conditions. However, performing co-pyrolysis experiments is highly challenging due to the need for costly and lengthy procedures. Machine learning (ML) provides capabilities to cope with such issues by leveraging on existing data. This work aims to introduce an evolutionary ML approach to quantify the (by)products of the biomass-polymer co-pyrolysis process. A comprehensive dataset covering various biomass-polymer mixtures under a broad range of process conditions is compiled from the qualified literature. The database was subjected to statistical analysis and mechanistic discussion. The input features are constructed using an innovative approach to reflect the physics of the process. The constructed features are subjected to principal component analysis to reduce their dimensionality. The obtained scores are introduced into six ML models. Gaussian process regression model tuned by particle swarm optimization algorithm presents better prediction performance (R2 > 0.9, MAE < 0.03, and RMSE < 0.06) than other developed models. The multi-objective particle swarm optimization algorithm successfully finds optimal independent parameters.

Bestan B. Maaroof, Tarik A. Rashid, Jaza M. Abdulla et al.

Shuffled Frog Leaping Algorithm (SFLA) is one of the most widespread algorithms. It was developed by Eusuff and Lansey in 2006. SFLA is a population-based metaheuristic algorithm that combines the benefits of memetics with particle swarm optimization. It has been used in various areas, especially in engineering problems due to its implementation easiness and limited variables. Many improvements have been made to the algorithm to alleviate its drawbacks, whether they were achieved through modifications or hybridizations with other well-known algorithms. This paper reviews the most relevant works on this algorithm. An overview of the SFLA is first conducted, followed by the algorithm's most recent modifications and hybridizations. Next, recent applications of the algorithm are discussed. Then, an operational framework of SLFA and its variants is proposed to analyze their uses on different cohorts of applications. Finally, future improvements to the algorithm are suggested. The main incentive to conduct this survey to provide useful information about the SFLA to researchers interested in working on the algorithm's enhancement or application

Chnoor M. Rahman, Tarik A. Rashid, Aram Mahmood Ahmed et al.

In this work, a new multiobjective optimization algorithm called multiobjective learner performance-based behavior algorithm is proposed. The proposed algorithm is based on the process of transferring students from high school to college. The proposed technique produces a set of non-dominated solutions. To judge the ability and efficacy of the proposed multiobjective algorithm, it is evaluated against a group of benchmarks and five real-world engineering optimization problems. Additionally, to evaluate the proposed technique quantitatively, several most widely used metrics are applied. Moreover, the results are confirmed statistically. The proposed work is then compared with three multiobjective algorithms, which are MOWCA, NSGA-II, and MODA. Similar to the proposed technique, the other algorithms in the literature were run against the benchmarks, and the real-world engineering problems utilized in the paper. The algorithms are compared with each other employing descriptive, tabular, and graphical demonstrations. The results proved the ability of the proposed work in providing a set of non-dominated solutions, and that the algorithm outperformed the other participated algorithms in most of the cases.

Deeam Najmadeen Hama Rashid, Tarik A. Rashid, Seyedali Mirjalili

In this paper, a novel swarm intelligent algorithm is proposed called ant nesting algorithm (ANA). The algorithm is inspired by Leptothorax ants and mimics the behavior of ants searching for positions to deposit grains while building a new nest. Although the algorithm is inspired by the swarming behavior of ants, it does not have any algorithmic similarity with the ant colony optimization (ACO) algorithm. It is worth mentioning that ANA is considered a continuous algorithm that updates the search agent position by adding the rate of change (e.g., step or velocity). ANA computes the rate of change differently as it uses previous, current solutions, fitness values during the optimization process to generate weights by utilizing the Pythagorean theorem. These weights drive the search agents during the exploration and exploitation phases. The ANA algorithm is benchmarked on 26 well-known test functions, and the results are verified by a comparative study with genetic algorithm (GA), particle swarm optimization (PSO), dragonfly algorithm (DA), five modified versions of PSO, whale optimization algorithm (WOA), salp swarm algorithm (SSA), and fitness dependent optimizer (FDO). ANA outperformances these prominent metaheuristic algorithms on several test cases and provides quite competitive results. Finally, the algorithm is employed for optimizing two well-known real-world engineering problems: antenna array design and frequency-modulated synthesis. The results on the engineering case studies demonstrate the proposed algorithm's capability in optimizing real-world problems.

Vahid Reza Gharehbaghi, Hashem Kalbkhani, Ehsan Noroozinejad Farsangi et al.

In this article, an original data-driven approach is proposed to detect both linear and nonlinear damage in structures using output-only responses. The method deploys variational mode decomposition (VMD) and a generalised autoregressive conditional heteroscedasticity (GARCH) model for signal processing and feature extraction. To this end, VMD decomposes the response signals into intrinsic mode functions (IMFs). Afterwards, the GARCH model is utilised to represent the statistics of IMFs. The model coefficients of IMFs construct the primary feature vector. Kernel-based principal component analysis (PCA) and linear discriminant analysis (LDA) are utilised to reduce the redundancy of the primary features by mapping them to the new feature space. The informative features are then fed separately into three supervised classifiers, namely support vector machine (SVM), k-nearest neighbour (kNN), and fine tree. The performance of the proposed method is evaluated on two experimentally scaled models in terms of linear and nonlinear damage assessment. Kurtosis and ARCH tests proved the compatibility of the GARCH model.

Vahidreza Gharehbaghi, Hashem Kalbkhani, Ehsan Noroozinejad Farsangi et al.

In this paper, a novel deterioration and damage identification procedure (DIP) is presented and applied to building models. The challenge associated with applications on these types of structures is related to the strong correlation of responses, which gets further complicated when coping with real ambient vibrations with high levels of noise. Thus, a DIP is designed utilizing low-cost ambient vibrations to analyze the acceleration responses using the Stockwell transform (ST) to generate spectrograms. Subsequently, the ST outputs become the input of two series of Convolutional Neural Networks (CNNs) established for identifying deterioration and damage to the building models. To the best of our knowledge, this is the first time that both damage and deterioration are evaluated on building models through a combination of ST and CNN with high accuracy.

Bryar A. Hassan, Tarik A. Rashid, Seyedali Mirjalili

It is beneficial to automate the process of deriving concept hierarchies from corpora since a manual construction of concept hierarchies is typically a time-consuming and resource-intensive process. As such, the overall process of learning concept hierarchies from corpora encompasses a set of steps: parsing the text into sentences, splitting the sentences and then tokenising it. After the lemmatisation step, the pairs are extracted using FCA. However, there might be some uninteresting and erroneous pairs in the formal context. Generating formal context may lead to a time-consuming process, so formal context size reduction is required to remove uninterested and erroneous pairs, taking less time to extract the concept lattice and concept hierarchies accordingly. In this premise, this study aims to propose two frameworks: (1) A framework to review the current process of deriving concept hierarchies from corpus utilising FCA; (2) A framework to decrease the formal contexts ambiguity of the first framework using an adaptive version of ECA*. Experiments are conducted by applying 385 sample corpora from Wikipedia on the two frameworks to examine the reducing size of formal context, which leads to yield concept lattice and concept hierarchy. The resulting lattice of formal context is evaluated to the standard one using concept lattice-invariants. Accordingly, the homomorphic between the two lattices preserves the quality of resulting concept hierarchies by 89% in contrast to the basic ones, and the reduced concept lattice inherits the structural relation of the standard one. The adaptive ECA* is examined against its four counterpart baseline algorithms to measure the execution time on random datasets with different densities (fill ratios). The results show that adaptive ECA* performs concept lattice faster than other mentioned competitive techniques in different fill ratios.

Bryar A. Hassan, TarikA. Rashid, Seyedali Mirjalili

This article presents the data used to evaluate the performance of evolutionary clustering algorithm star (ECA*) compared to five traditional and modern clustering algorithms. Two experimental methods are employed to examine the performance of ECA* against genetic algorithm for clustering++ (GENCLUST++), learning vector quantisation (LVQ) , expectation maximisation (EM) , K-means++ (KM++) and K-means (KM). These algorithms are applied to 32 heterogenous and multi-featured datasets to determine which one performs well on the three tests. For one, ther paper examines the efficiency of ECA* in contradiction of its corresponding algorithms using clustering evaluation measures. These validation criteria are objective function and cluster quality measures. For another, it suggests a performance rating framework to measurethe the performance sensitivity of these algorithms on varos dataset features (cluster dimensionality, number of clusters, cluster overlap, cluster shape and cluster structure). The contributions of these experiments are two-folds: (i) ECA* exceeds its counterpart aloriths in ability to find out the right cluster number; (ii) ECA* is less sensitive towards dataset features compared to its competitive techniques. Nonetheless, the results of the experiments performed demonstrate some limitations in the ECA*: (i) ECA* is not fully applied based on the premise that no prior knowledge exists; (ii) Adapting and utilising ECA* on several real applications has not been achieved yet.

Quoc-Viet Pham, Dinh C. Nguyen, Seyedali Mirjalili et al.

Due to the proliferation of smart devices and emerging applications, many next-generation technologies have been paid for the development of wireless networks. Even though commercial 5G has just been widely deployed in some countries, there have been initial efforts from academia and industrial communities for 6G systems. In such a network, a very large number of devices and applications are emerged, along with heterogeneity of technologies, architectures, mobile data, etc., and optimizing such a network is of utmost importance. Besides convex optimization and game theory, swarm intelligence (SI) has recently appeared as a promising optimization tool for wireless networks. As a new subdivision of artificial intelligence, SI is inspired by the collective behaviors of societies of biological species. In SI, simple agents with limited capabilities would achieve intelligent strategies for high-dimensional and challenging problems, so it has recently found many applications in next-generation wireless networks (NGN). However, researchers may not be completely aware of the full potential of SI techniques. In this work, our primary focus will be the integration of these two domains: NGN and SI. Firstly, we provide an overview of SI techniques from fundamental concepts to well-known optimizers. Secondly, we review the applications of SI to settle emerging issues in NGN, including spectrum management and resource allocation, wireless caching and edge computing, network security, and several other miscellaneous issues. Finally, we highlight open challenges and issues in the literature, and introduce some interesting directions for future research.

Anuradha Banerjee, Abu Sufian, Ali Safaa Sadiq et al.

Routing in Software-Defined Wireless sensor networks (SD-WSNs) can be either single or multi-hop, whereas the network is either static or dynamic. In static SD-WSN, the selection of the optimum route from source to destination is accomplished by the SDN controller(s). On the other hand, if moving sensors are there, then SDN controllers of zones cannot handle route discovery sessions by themselves; they can only store information about the most recent zone state. Moving sensors find lots of robotics applications where robots continue to move from one room to another to sensing the environment. A huge amount of energy can be saved in these networks if transmission range control is applied. Multiple power levels exist in each node, and each of these levels takes possible actions after a potential sender node decides to transmit/forward a message. Based on each such activity, the next states of the concerned sender node and the communication session are re-determined while the router receives a reward. The Epsilon-greedy algorithm is applied in this study to decide the optimum power level in the next iteration. It is determined anew depending upon the present network scenario. Simulation results show that our proposed work leads the network to equilibrium by reducing energy consumption and maintaining network throughput.

Ritam Guha, Manosij Ghosh, Shyok Mutsuddi et al.

Classification accuracy provided by a machine learning model depends a lot on the feature set used in the learning process. Feature Selection (FS) is an important and challenging pre-processing technique which helps to identify only the relevant features from a dataset thereby reducing the feature dimension as well as improving the classification accuracy at the same time. The binary version of Whale Optimization Algorithm (WOA) is a popular FS technique which is inspired from the foraging behavior of humpback whales. In this paper, an embedded version of WOA called Embedded Chaotic Whale Survival Algorithm (ECWSA) has been proposed which uses its wrapper process to achieve high classification accuracy and a filter approach to further refine the selected subset with low computation cost. Chaos has been introduced in the ECWSA to guide selection of the type of movement followed by the whales while searching for prey. A fitness-dependent death mechanism has also been introduced in the system of whales which is inspired from the real-life scenario in which whales die if they are unable to catch their prey. The proposed method has been evaluated on 18 well-known UCI datasets and compared with its predecessors as well as some other popular FS methods.

Chnoor M. Rahman, Tarik A. Rashid, Abeer Alsadoon et al.

The dragonfly algorithm was developed in 2016. It is one of the algorithms used by researchers to optimize an extensive series of uses and applications in various areas. At times, it offers superior performance compared to the most well-known optimization techniques. However, this algorithm faces several difficulties when it is utilized to enhance complex optimization problems. This work addressed the robustness of the method to solve real-world optimization issues, and its deficiency to improve complex optimization problems. This review paper shows a comprehensive investigation of the dragonfly algorithm in the engineering area. First, an overview of the algorithm is discussed. Besides, we also examined the modifications of the algorithm. The merged forms of this algorithm with different techniques and the modifications that have been done to make the algorithm perform better are addressed. Additionally, a survey on applications in the engineering area that used the dragonfly algorithm is offered. The utilized engineering applications are the applications in the field of mechanical engineering problems, electrical engineering problems, optimal parameters, economic load dispatch, and loss reduction. The algorithm is tested and evaluated against particle swarm optimization algorithm and firefly algorithm. To evaluate the ability of the dragonfly algorithm and other participated algorithms a set of traditional benchmarks (TF1-TF23) were utilized. Moreover, to examine the ability of the algorithm to optimize large-scale optimization problems CEC-C2019 benchmarks were utilized. A comparison is made between the algorithm and other metaheuristic techniques to show its ability to enhance various problems.

Majdi Mafarja, Seyedali Mirjalili

Feature selection is an important preprocessing step for classification problems. It deals with selecting near optimal features in the original dataset. Feature selection is an NP-hard problem, so meta-heuristics can be more efficient than exact methods. In this work, Ant Lion Optimizer (ALO), which is a recent metaheuristic algorithm, is employed as a wrapper feature selection method. Six variants of ALO are proposed where each employ a transfer function to map a continuous search space to a discrete search space. The performance of the proposed approaches is tested on eighteen UCI datasets and compared to a number of existing approaches in the literature: Particle Swarm Optimization, Gravitational Search Algorithm, and two existing ALO-based approaches. Computational experiments show that the proposed approaches efficiently explore the feature space and select the most informative features, which help to improve the classification accuracy.