arXiv subjects

Mohammad Heydari

Publications and source records attributed to Mohammad Heydari.

16 recordsLinked to original sources

arXiv2026

HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: https://github.com/heydarimo/Night-Time-Dehazing

cs.CV↗

arXiv2026

Federated Learning-Assisted Optimization of Mobile Transmission with Digital Twins

A Digital Twin (DT) may protect information that is considered private to its associated physical system. For a mobile device, this may include its mobility profile, recent location(s), and experienced channel conditions. Online schedulers, however, typically use this type of information to perform tasks such as shared bandwidth and channel time slot assignments. In this paper, we consider three transmission scheduling problems with energy constraints, where such information is needed, and yet must remain private: minimizing total transmission time when (i) fixed-power or (ii) fixed-rate time slotting with power control is used, and (iii) maximizing the amount of data uploaded in a fixed time period. Using a real-time federated optimization framework, we show how the scheduler can iteratively interact only with the DTs to produce global fractional solutions to these problems, without the latter revealing their private information. Then dependent rounding is used to round the fractional solution into a channel transmission schedule for the physical systems. Experiments show consistent makespan reductions with near-zero bandwidth/energy violations and millisecond-order end-to-end runtime for typical edge server hardware. To the best of our knowledge, this is the first framework that enables channel sharing across DTs using operations that do not expose private data.

cs.NI↗

arXiv2024

Persian Slang Text Conversion to Formal and Deep Learning of Persian Short Texts on Social Media for Sentiment Classification

The lack of a suitable tool for the analysis of conversational texts in the Persian language has made various analyses of these texts, including Sentiment Analysis, difficult. In this research, we tried to make the understanding of these texts easier for the machine by providing PSC, Persian Slang Converter, a tool for converting conversational texts into formal ones, and by using the most up-to-date and best deep learning methods along with the PSC, the sentiment learning of short Persian language texts for the machine in a better way. be made More than 10 million unlabeled texts from various social networks and movie subtitles (as Conversational texts) and about 10 million news texts (as formal texts) have been used for training unsupervised models and formal implementation of the tool. 60,000 texts from the comments of Instagram social network users with positive, negative, and neutral labels are considered supervised data for training the emotion classification model of short texts. Using the formal tool, 57% of the words of the corpus of conversation were converted. Finally, by using the formalizer, FastText model, and deep LSTM network, an accuracy of 81.91 was obtained on the test data.

cs.CL↗

arXiv2024

Deep Learning-based Sentiment Analysis in Persian Language

Recently, there has been a growing interest in the use of deep learning techniques for tasks in natural language processing (NLP), with sentiment analysis being one of the most challenging areas, particularly in the Persian language. The vast amounts of content generated by Persian users on thousands of websites, blogs, and social networks such as Telegram, Instagram, and Twitter present a rich resource of information. Deep learning techniques have become increasingly favored for extracting insights from this extensive pool of raw data, although they face several challenges. In this study, we introduced and implemented a hybrid deep learning-based model for sentiment analysis, using customer review data from the Digikala Online Retailer website. We employed a variety of deep learning networks and regularization techniques as classifiers. Ultimately, our hybrid approach yielded an impressive performance, achieving an F1 score of 78.3 across three sentiment categories: positive, negative, and neutral.

cs.CL↗

arXiv2024

Distributed Record Linkage in Healthcare Data with Apache Spark

Healthcare data is a valuable resource for research, analysis, and decision-making in the medical field. However, healthcare data is often fragmented and distributed across various sources, making it challenging to combine and analyze effectively. Record linkage, also known as data matching, is a crucial step in integrating and cleaning healthcare data to ensure data quality and accuracy. Apache Spark, a powerful open-source distributed big data processing framework, provides a robust platform for performing record linkage tasks with the aid of its machine learning library. In this study, we developed a new distributed data-matching model based on the Apache Spark Machine Learning library. To ensure the correct functioning of our model, the validation phase has been performed on the training data. The main challenge is data imbalance because a large amount of data is labeled false, and a small number of records are labeled true. By utilizing SVM and Regression algorithms, our results demonstrate that research data was neither over-fitted nor under-fitted, and this shows that our distributed model works well on the data.

cs.DC↗

arXiv2024

Challenges and Experiences of Iranian Developers with MLOps at Enterprise

Data is becoming more complex, and so are the approaches designed to process it. Enterprises have access to more data than ever, but many still struggle to glean the full potential of insights from what they have. This research explores the challenges and experiences of Iranian developers in implementing the MLOps paradigm within enterprise settings. MLOps, or Machine Learning Operations, is a discipline focused on automating the continuous delivery of machine learning models. In this study, we review the most popular MLOps tools used by leading technology enterprises. Additionally, we present the results of a questionnaire answered by over 110 Iranian Machine Learning experts and Software Developers, shedding light on MLOps tools and the primary obstacles faced. The findings reveal that data quality problems, a lack of resources, and difficulties in model deployment are among the primary challenges faced by practitioners. Collaboration between ML, DevOps, Ops, and Science teams is seen as a pivotal challenge in implementing MLOps effectively.

cs.SE↗

arXiv2024

Analysis of Persian News Agencies on Instagram, A Words Co-occurrence Graph-based Approach

The rise of the Internet and the exponential increase in data have made manual data summarization and analysis a challenging task. Instagram social network is a prominent social network widely utilized in Iran for information sharing and communication across various age groups. The inherent structure of Instagram, characterized by its text-rich content and graph-like data representation, enables the utilization of text and graph processing techniques for data analysis purposes. The degree distributions of these networks exhibit scale-free characteristics, indicating non-random growth patterns. Recently, word co-occurrence has gained attention from researchers across multiple disciplines due to its simplicity and practicality. Keyword extraction is a crucial task in natural language processing. In this study, we demonstrated that high-precision extraction of keywords from Instagram posts in the Persian language can be achieved using unsupervised word co-occurrence methods without resorting to conventional techniques such as clustering or pre-trained models. After graph visualization and community detection, it was observed that the top topics covered by news agencies are represented by these graphs. This approach is generalizable to new and diverse datasets and can provide acceptable outputs for new data. To the author's knowledge, this method has not been employed in the Persian language before on Instagram social network. The new crawled data has been publicly released on GitHub for exploration by other researchers. By employing this method, it is possible to use other graph-based algorithms, such as community detections. The results help us to identify the key role of different news agencies in information diffusion among the public, identify hidden communities, and discover latent patterns among a massive amount of data.

cs.SI↗

arXiv2024

Convolutional Neural Networks Towards Facial Skin Lesions Detection

Facial analysis has emerged as a prominent area of research with diverse applications, including cosmetic surgery programs, the beauty industry, photography, and entertainment. Manipulating patient images often necessitates professional image processing software. This study contributes by providing a model that facilitates the detection of blemishes and skin lesions on facial images through a convolutional neural network and machine learning approach. The proposed method offers advantages such as simple architecture, speed and suitability for image processing while avoiding the complexities associated with traditional methods. The model comprises four main steps: area selection, scanning the chosen region, lesion diagnosis, and marking the identified lesion. Raw data for this research were collected from a reputable clinic in Tehran specializing in skincare and beauty services. The dataset includes administrative information, clinical data, and facial and profile images. A total of 2300 patient images were extracted from this raw data. A software tool was developed to crop and label lesions, with input from two treatment experts. In the lesion preparation phase, the selected area was standardized to 50 * 50 pixels. Subsequently, a convolutional neural network model was employed for lesion labeling. The classification model demonstrated high accuracy, with a measure of 0.98 for healthy skin and 0.97 for lesioned skin specificity. Internal validation involved performance indicators and cross-validation, while external validation compared the model's performance indicators with those of the transfer learning method using the Vgg16 deep network model. Compared to existing studies, the results of this research showcase the efficacy and desirability of the proposed model and methodology.

eess.IV↗

arXiv2023

Analysis of Insect-Plant Interactions Affected by Mining Operations, A Graph Mining Approach

The decline in ecological connections signifies the potential extinction of species, which can be attributed to disruptions and alterations. The decrease in interconnections among species reflects their susceptibility to changes. For example, certain insects and plants that rely on exclusive interactions with a limited number of species, or even a specific species, face the risk of extinction if they lose these crucial connections. Currently, mining activities pose significant harm to natural ecosystems, resulting in various adverse environmental impacts. In this study, we utilized network science techniques to analyze the ecosystem in a graph-based structure, aiming to conserve the ecosystem affected by mining operations in the northern region of Scotland. The research encompasses identifying the most vital members of the network, establishing criteria for identifying communities within the network, comparing, and evaluating them, using models to predict secondary extinctions that occur when a species is removed from the network, and assessing the extent of network damage. Our study's novelty is utilizing network science approaches to investigate the biological data related to interactions between insects and plants.

q-bio.PE↗

arXiv2023

Graph Representation Learning Towards Patents Network Analysis

Patent analysis has recently been recognized as a powerful technique for large companies worldwide to lend them insight into the age of competition among various industries. This technique is considered a shortcut for developing countries since it can significantly accelerate their technology development. Therefore, as an inevitable process, patent analysis can be utilized to monitor rival companies and diverse industries. This research employed a graph representation learning approach to create, analyze, and find similarities in the patent data registered in the Iranian Official Gazette. The patent records were scrapped and wrangled through the Iranian Official Gazette portal. Afterward, the key entities were extracted from the scrapped patents dataset to create the Iranian patents graph from scratch based on novel natural language processing and entity resolution techniques. Finally, thanks to the utilization of novel graph algorithms and text mining methods, we identified new areas of industry and research from Iranian patent data, which can be used extensively to prevent duplicate patents, familiarity with similar and connected inventions, Awareness of legal entities supporting patents and knowledge of researchers and linked stakeholders in a particular research field.

cs.SI↗

arXiv2023

Analysis of ResearchGate, A Community Detection Approach

We are living in the data age. Communications over scientific networks creates new opportunities for researchers who aim to discover the hidden pattern in these huge repositories. This study utilizes network science to create collaboration network of Iranian Scientific Institutions. A modularity-based approach applied to find network communities. To reach a big picture of science production flow, analysis of the collaboration network is crucial. Our results demonstrated that geographic location closeness and ethnic attributes has important roles in academic collaboration network establishment. Besides, it shows that famous scientific centers in the capital city of Iran, Tehran has strong influence on the production flow of scientific activities. These academic papers are mostly viewed and downloaded from the United State of America, China, India, and Iran. The motivation of this research is that by discovering hidden communities in the network and finding the structure of intuitions communications, we can identify each scientific center research potential separately and clear mutual scientific fields. Therefore, an efficient strategic program can be designed, developed and tested to keep scientific centers in progress way and navigate their research goals into a straight useful roadmap to identify and fill the unknown gaps.

cs.SI↗

arXiv2023

A Robust Site Selection Model under uncertainty for Special Hospital Wards in Hong Kong

This paper process two robust models for site selection problems for one of the major Hospitals in Hong Kong. Three parameters, namely, level of uncertainty, infeasibility tolerance as well as the level of reliability, are incorporated. Then, 2 kinds of uncertainty; that is, the symmetric and bounded uncertainties have been investigated. Therefore, the issue of scheduling under uncertainty has been considered wherein unknown problem factors could be illustrated via a given probability distribution function. In this regard, Lin, Janak, and Floudas (2004) introduced one of the newly developed strong optimisation protocols. Hence, computers as well as the chemical engineering [1069-1085] has been developed for considering uncertainty illustrated through a given probability distribution. Finally, our accurate optimisation protocol has been on the basis of a min-max framework and in a case of application to the (MILP) problems it produced a precise solution that has immunity to uncertain data.

econ.GN↗

arXiv2023

Investigation User Reviews FRO to Determine the Level of Customer Loyalty Model Shahrvand Chain Stores

In this study, focusing on organizations in a rapid-response component model (FRO), the relative importance of each one, from the point of view of customers and their impact on the purchase of Shahrvand chain stores determined to directors and managers of the shops, according to customer needs and their priorities in order to satisfy the customers and take steps to strengthen their competitiveness. For this purpose, all shahrvand chain stores in Tehran currently have 10 stores in different parts of Tehran that have been studied are that of the 10 branches; Five branches were selected. The sampling method is used in this study population with a confidence level of 95% and 8% error; 150 are more specifically typically 30 were studied in each branch. In this study, a standard questionnaire of 26 questions which is used FRO validity using Cronbach's alpha values of "0/95" is obtained. The results showed that each of the six factors on customer loyalty model FRO effective Shahrvand chain stores. The effect of each of the six Foundation FRO customer loyalty model shahrvand is different chain stores.

econ.GN↗

arXiv2023

The Relationship Between Burnout Operators with the Functions of Family Tehran Banking Melli Iran Bank in 2015

In this study, the relationship between burnout and family functions of the Melli Iran Bank staff will be studied. A number of employees within the organization using appropriate scientific methods as the samples were selected by detailed questionnaire and the appropriate data is collected burnout and family functions. The method used descriptive statistical population used for this study consisted of 314 bank loan officers in branches of Melli Iran Bank of Tehran province and all the officials at the bank for >5 years of service at Melli Iran Bank branches in Tehran. They are married and men constitute the study population. The Maslach Burnout Inventory in the end internal to 0/90 alpha emotional exhaustion, depersonalization and low personal accomplishment Cronbach alpha of 0/79 and inventory by 0/71 within the last family to solve the problem 0/70, emotional response 0/51, touch 0/70, 0/69 affective involvement, roles, 0/59, 0/68 behavior is controlled. The results indicate that the hypothesis that included the relationship between burnout and 6, the family functioning, problem solving, communication, roles, affective responsiveness, affective fusion there was a significant relationship between behavior and the correlation was negative. The burnout is high; the functions within the family will be in trouble.

econ.GN↗

arXiv2023

A simple and efficient preprocessing step for convex hull problem

The present paper is concerned with a recursive algorithm as a preprocessing step to find the convex hull of $n$ random points uniformly distributed in the plane. For such a set of points, it is shown that eliminating all but $O(\log n)$ of points can derive the same convex hull as the input set. Finally it will be shown that the running time of the algorithm is $O(n)

cs.DS↗

arXiv2020

Sentiment Analysis Challenges in Persian Language

The rapid growth in data on the internet requires a data mining process to reach a decision to support insight. The Persian language has strong potential for deep research in any aspect of natural language processing, especially sentimental analysis approach. Thousands of websites and blogs updates and modifies by Persian users around the world that contains millions of Persian context. This range of application requires a comprehensive structured framework to extract beneficial information for helping enterprises to enhance their business and initiate a customer-centric management process by producing effective recommender systems. Sentimental analysis is an intelligent approach for extracting useful information from huge amounts of data to help an enterprise for smart management process. In this road, machine learning and deep learning techniques will become very helpful but there is the number of challenges which are face to them. This paper tried to present and assert the most important challenges of sentimental analysis in the Persian language. This language is an Indo-European language which spoken by over 110 million people around the world and is an official language in Iran, Tajikistan, and Afghanistan. Its also widely used in Uzbekistan, Pakistan and Turkish by order.

cs.IR↗