arXiv subjects

Ali Najafi

Publications and source records attributed to Ali Najafi.

At least 19 recordsLinked to original sources

arXiv2026

Social-Annotate: Self-Healing Browser Extension to Annotate and Collect Social Media Data

Human-annotated data remains foundational for machine learning and social media analysis. However, traditional data collection often relies on cumbersome pipelines that isolate content from its original source, compromising ecological validity. To address these challenges, we present Social-Annotate, a flexible browser extension that facilitates direct data collection on online platforms. By injecting customizable forms into webpages, the tool captures annotations while users interact with the native environment. Social-Annotate offers no-code design interface for the survey forms for non-technical users. Since injecting custom elements directly into host platforms creates a brittle dependency on evolving interfaces, we integrate a self-healing agent powered by large language models. This automated pipeline autonomously detects structural changes, regenerates valid target selectors, and validates them within a live browser environment. Our extensible platform readily supports 12 platforms including social media like $\mathbb{X}$, Instagram, TikTok and P2P messaging platforms WhatsApp and Telegram. Social-Annotate significantly reduces data collection overhead and developer maintenance, enabling researchers of all technical backgrounds to focus on data analysis rather than engineering. Moreover, Social-Annotate provides an ecosystem for conducting intervention studies by dynamic content manipulation.

cs.CY↗

arXiv2026

Social Media Data Toolkit: Standardization and Anonymization of Social Network Datasets

The rapid diversification of social media platforms and the increasing restrictions on official APIs have significantly complicated cross-platform analysis. Researchers are often forced to rely on heterogeneous datasets obtained through web scraping and historical archives; however they often lack structural consistency. Prior to conducting cross-platform social media analyses, one needs to answer three critical questions: (1) What makes platforms different and similar? (2) How were the datasets collected? (3) How can we align the datasets of different platforms to conduct fair analyses? To address these questions, we introduce the Social Media Data Toolkit (\projectname{}), a comprehensive Python framework designed for the standardization, anonymization, and enrichment of social network datasets. \projectname{} unifies diverse data structures into a generic schema comprising Communities, Accounts, Posts, Actions, and Entities to facilitate multi-platform research. The framework features a configurable anonymization module to secure Personally Identifiable Information (PII) and an extendable enrichment layer that integrates Large Language Models (LLMs) and network analysis tools for downstream tasks such as stance detection and toxicity scoring without creating codebase for different datasets. We demonstrate the versatility of \projectname{} through four case studies spanning from textual analysis of the content to network analysis across platforms. To offer reproducible social media research, \projectname{} is released as an open-source tool featuring detailed documentation and practical guides for researchers at any skill-level. It can be accessed at github.com/ViralLab/SMDT and varollab.com/SMDT.

cs.SI↗

arXiv2024

Geom-DeepONet: A Point-cloud-based Deep Operator Network for Field Predictions on 3D Parameterized Geometries

Modern digital engineering design process commonly involves expensive repeated simulations on varying three-dimensional (3D) geometries. The efficient prediction capability of neural networks (NNs) makes them a suitable surrogate to provide design insights. Nevertheless, few available NNs can handle solution prediction on varying 3D shapes. We present a novel deep operator network (DeepONet) variant called Geom-DeepONet, which encodes parameterized 3D geometries and predicts full-field solutions on an arbitrary number of nodes. To the best of the authors' knowledge, this is the first attempt in the literature and is our primary novelty. In addition to expressing shapes using mesh coordinates, the signed distance function for each node is evaluated and used to augment the inputs to the trunk network of the Geom-DeepONet, thereby capturing both explicit and implicit representations of the 3D shapes. The powerful geometric encoding capability of a sinusoidal representation network (SIREN) is also exploited by replacing the classical feedforward neural networks in the trunk with SIREN. Additional data fusion between the branch and trunk networks is introduced by an element-wise product. A numerical benchmark was conducted to compare Geom-DeepONet to PointNet and vanilla DeepONet, where results show that our architecture trains fast with a small memory footprint and yields the most accurate results among the three with less than 2 MPa stress error. Results show a much lower generalization error of our architecture on unseen dissimilar designs than vanilla DeepONet. Once trained, the model can predict vector solutions, and speed can be over $10^5$ times faster than implicit finite element simulations for large meshes.

cs.CE↗

arXiv2024

Material-Response-Informed DeepONet and its Application to Polycrystal Stress-strain Prediction in Crystal Plasticity

Crystal plasticity (CP) simulations are a tool for understanding how microstructure morphology and texture affect mechanical properties and are an essential component of elucidating the structure-property relations. However, it can be computationally expensive. Hence, data-driven machine learning models have been applied to predict the mean-field response of a polycrystal representative volume element to reduce computation time. In this work, we proposed a novel Deep Operator Network (DeepONet) architecture for predicting microstructure stress-strain response. It employs a convolutional neural network in the trunk to encode the microstructure. To account for different material properties, boundary conditions, and loading, we proposed using single crystal stress-strain curves as inputs to the branch network, furnishing a material-response-informed DeepONet. Using four numerical examples, we demonstrate that the current DeepONet can be trained on a single material and loading and then generalized to new conditions via transfer learning. Results show that using single crystal responses as input outperforms a similar model using material properties as inputs and overcomes limitations with changing boundary conditions and temporal resolution. In all cases, the new model achieved a $R^2$ value of above 0.99, and over 95\% of predicted stresses have a relative error of $\le$ 5\%, indicating superior accuracy. With as few as 20 new data points and under 1min training time, the trained DeepONet can be fine-tuned to generate accurate predictions on different materials and loading. Once trained, the prediction speed is almost $1\times10^{4}$ times faster the CP simulations. The efficiency and high generalizability of our DeepONet render it a powerful data-driven surrogate model for CP simulations in multi-scale analyses.

cs.CE↗

arXiv2023

TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis

Turkish is one of the most popular languages in the world. Wide us of this language on social media platforms such as Twitter, Instagram, or Tiktok and strategic position of the country in the world politics makes it appealing for the social network researchers and industry. To address this need, we introduce TurkishBERTweet, the first large scale pre-trained language model for Turkish social media built using almost 900 million tweets. The model shares the same architecture as base BERT model with smaller input length, making TurkishBERTweet lighter than BERTurk and can have significantly lower inference time. We trained our model using the same approach for RoBERTa model and evaluated on two text classification tasks: Sentiment Classification and Hate Speech Detection. We demonstrate that TurkishBERTweet outperforms the other available alternatives on generalizability and its lower inference time gives significant advantage to process large-scale datasets. We also compared our models with the commercial OpenAI solutions in terms of cost and performance to demonstrate TurkishBERTweet is scalable and cost-effective solution. As part of our research, we released TurkishBERTweet and fine-tuned LoRA adapters for the mentioned tasks under the MIT License to facilitate future research and applications on Turkish social media. Our TurkishBERTweet model is available at: https://github.com/ViralLab/TurkishBERTweet

cs.CL↗

arXiv2023

Instabilities in a growing system of active particles: scalar and vector systems

The physics of micron-scale biological colonies usually benefits from different out-of-equilibrium sources. In bacterial colonies and cellular tissues, the growth process is among the important active sources that determine the dynamics. In this article, we study the generic dynamical instabilities associated with the growth phenomena that may arise in both scalar and vectorial systems. In vectorial systems, where the rotational degrees of particles play a role, a phenomenological growthmediated torque can affect the rotational dynamics of individual particles. We show that such a growth-mediated torque can result in active traveling waves in the bulk of a growing system. In addition to the bulk properties, we analyze the instabilities in the shape of growing interfaces in both scalar and vectorial systems.

cond-mat.soft↗

arXiv2022

#Secim2023: First Public Dataset for Studying Turkish General Election

In the context of Turkey's upcoming parliamentary and presidential elections ("seçim" in Turkish), social media is playing an important role in shaping public debate. The increasing engagement of citizens on social media platforms has led to the growing use of social media by political actors. It is of utmost importance to capture the upcoming Turkish elections, as social media is becoming an essential component of election propaganda, political debates, smear campaigns, and election manipulation by domestic and international actors. We provide a comprehensive dataset for social media researchers to study the upcoming election, develop tools to prevent online manipulation, and gather novel information to inform the public. We are committed to continually improving the data collection and updating it regularly leading up to the election. Using the Secim2023 dataset, researchers can examine the social and communication networks between political actors, track current trends, and investigate emerging threats to election integrity. Our dataset is available at: https://github.com/ViralLab/Secim2023_Dataset

cs.SI↗

arXiv2021

ComStreamClust: a communicative multi-agent approach to text clustering in streaming data

Topic detection is the task of determining and tracking hot topics in social media. Twitter is arguably the most popular platform for people to share their ideas with others about different issues. One such prevalent issue is the COVID-19 pandemic. Detecting and tracking topics on these kinds of issues would help governments and healthcare companies deal with this phenomenon. In this paper, we propose a novel, multi-agent, communicative clustering approach, so-called ComStreamClust for clustering sub-topics inside a broader topic, e.g., COVID-19. The proposed approach is parallelizable, and can simultaneously handle several data-point. The LaBSE sentence embedding is used to measure the semantic similarity between two tweets. ComStreamClust has been evaluated on two datasets: the COVID-19 and the FA CUP. The results obtained from ComStreamClust approve the effectiveness of the proposed approach when compared to existing methods.

cs.IR↗

arXiv2021

Drowsiness Detection Based On Driver Temporal Behavior Using a New Developed Dataset

Driver drowsiness detection has been the subject of many researches in the past few decades and various methods have been developed to detect it. In this study, as an image-based approach with adequate accuracy, along with the expedite process, we applied YOLOv3 (You Look Only Once-version3) CNN (Convolutional Neural Network) for extracting facial features automatically. Then, LSTM (Long-Short Term Memory) neural network is employed to learn driver temporal behaviors including yawning and blinking time period as well as sequence classification. To train YOLOv3, we utilized our collected dataset alongside the transfer learning method. Moreover, the dataset for the LSTM training process is produced by the mentioned CNN and is formatted as a two-dimensional sequence comprised of eye blinking and yawning time durations. The developed dataset considers both disturbances such as illumination and drivers' head posture. To have real-time experiments a multi-thread framework is developed to run both CNN and LSTM in parallel. Finally, results indicate the hybrid of CNN and LSTM ability in drowsiness detection and the effectiveness of the proposed method.

cs.CV↗

arXiv2019

TinySDR: Low-Power SDR Platform for Over-the-Air Programmable IoT Testbeds

Wireless protocol design for IoT networks is an active area of research which has seen significant interest and developments in recent years. The research community is however handicapped by the lack of a flexible, easily deployable platform for prototyping IoT endpoints that would allow for ground up protocol development and investigation of how such protocols perform at scale. We introduce tinySDR, the first software-defined radio platform tailored to the needs of power-constrained IoT endpoints. TinySDR provides a standalone, fully programmable low power software-defined radio solution that can be duty cycled for battery operation like a real IoT endpoint, and more importantly, can be programmed over the air to allow for large scale deployment. We present extensive evaluation of our platform showing it consumes as little as 30 uW of power in sleep mode, which is 10,000x lower than existing SDR platforms. We present two case studies by implementing LoRa and BLE beacons on the platform and achieve sensitivities of -126 dBm and -94 dBm respectively while consuming 11% and 3% of the FPGA resources. Finally, using tinySDR, we explore the research question of whether an IoT device can demodulate concurrent LoRa transmissions in real-time, within its power and computing constraints.

eess.SP↗

arXiv2019

Electrophoresis of active Janus particles

We theoretically consider the dynamics of a self-propelled active Janus motor moving in an external electric field. The external field can manipulate the route of a Janus particle and enforce it to move towards the desired targets. To investigate the trajectory of this active motor, we use a perturbative scheme. At the leading orders of surface activity of the Janus particle and also the external field, the orientational dynamics of the Janus particles behave like a mathematical pendulum with an angular the velocity that is sensitive to both the electric field and surface activity of the motor.

cond-mat.soft↗

arXiv2018

NetScatter: Enabling Large-Scale Backscatter Networks

We present the first wireless protocol that scales to hundreds of concurrent transmissions from backscatter devices. Our key innovation is a distributed coding mechanism that works below the noise floor, operates on backscatter devices and can decode all the concurrent transmissions at the receiver using a single FFT operation. Our design addresses practical issues such as timing and frequency synchronization as well as the near-far problem. We deploy our design using a testbed of backscatter hardware and show that our protocol scales to concurrent transmissions from 256 devices using a bandwidth of only 500 kHz. Our results show throughput and latency improvements of 14--62x and 15--67x over existing approaches and 1--2 orders of magnitude higher transmission concurrency.

cs.NI↗

arXiv2018

Self-generated gradients stabilize the hydrodynamic instabilities in active suspensions

Ordered phases emerged in active suspensions of polar swimmers are under long-wavelength hydrodynamic mediated instabilities. In this letter, we show that chemical molecules dissolved in aqueous suspensions, as an unavoidable part of most wet active systems, can mediate long-range interactions and subsequently stabilize the ordered phases. Chemoattractant in living suspensions and dissolved molecules producing phoretic forces in synthesized Janus suspensions are reminiscent of such molecules. Communication between swimmers through the gradients of such chemicals generated by individual swimmers, is the foundation of this stabilization mechanism. To classify the stable states of such active systems, we investigate the detailed phase diagrams for two classes of systems with momentum conserving and non-conserving dynamics. Our linear stability analysis shows how the stabilization mechanism can work for swimmers with different dynamical properties, e.g., pushers or pullers and with various static characteristics, e.g., spherical, oblate or prolate geometries.

cond-mat.stat-mech↗

arXiv2017

Long-wavelength instabilities in a system of interacting active particles

Based on a microscopic model, we develop a continuum description for a suspension of microscopic self propelled particles. With this continuum description we study the role of long-range interactions in destabilizing macroscopic ordered phases that are developed by short-range interactions. Long-wavelength fluctuations can destabilize both isotropic and also symmetry broken polar phase in a suspension of dipolar particles. The instabilities in a suspension of pullers (pushers) arise from splay (bend) fluctuations. Such instabilities are not seen in a suspension of quadrupolar particles.

cond-mat.stat-mech↗

arXiv2017

LoRa Backscatter: Enabling The Vision of Ubiquitous Connectivity

The vision of embedding connectivity into billions of everyday objects runs into the reality of existing communication technologies --- there is no existing wireless technology that can provide reliable and long-range communication at tens of microwatts of power as well as cost less than a dime. While backscatter is low-power and low-cost, it is known to be limited to short ranges. This paper overturns this conventional wisdom about backscatter and presents the first wide-area backscatter system. Our design can successfully backscatter from any location between an RF source and receiver, separated by 475 m, while being compatible with commodity LoRa hardware. Further, when our backscatter device is co-located with the RF source, the receiver can be as far as 2.8 km away. We deploy our system in a 4,800 $ft^{2}$ (446 $m^{2}$) house spread across three floors, a 13,024 $ft^{2}$ (1210 $m^{2}$) office area covering 41 rooms, as well as a one-acre (4046 $m^{2}$) vegetable farm and show that we can achieve reliable coverage, using only a single RF source and receiver. We also build a contact lens prototype as well as a flexible epidermal patch device attached to the human skin. We show that these devices can reliably backscatter data across a 3,328 $ft^{2}$ (309 $m^{2}$) room. Finally, we present a design sketch of a LoRa backscatter IC that shows that it costs less than a dime at scale and consumes only 9.25 $μ$W of power, which is more than 1000x lower power than LoRa radio chipsets.

cs.NI↗

arXiv2017

Symplectic and antiplectic waves in an array of beating cilia attached to a closed body

By taking into account the hydrodynamic interactions in a one dimensional array of model cilia attached to a no-slip cylinderical surface, we investigate their synchronized motion. We show, how does the emergence of metachronal waves depend on the initial state of the system and investigate the conditions under which, the formation of symplectic and antiplectic waves are possible.

physics.bio-ph↗

arXiv2016

A 2-D suspension of active agents: the role of fluid mediated interactions

Taking into account simultaneously the Vicsek short range ordering and also the far-field hydrodynamic interactions mediated by the ambient fluid, we investigate the role of long range interactions in the ordering phenomena in a quasi 2-dimensional active suspension. By studying the number fluctuations, the velocity correlation functions and cluster size distribution function, we observe that depending on the number density of swimmers and the strength of noise, the hydrodynamic interactions affect the ordering in a suspension. For a fixed value of noise, at large density of particles, long range interactions enhance the clustering in the system.

physics.bio-ph↗

arXiv2015

Interaction between catalytic micro motors

Starting from a microscopic model for a spherically symmetric active Janus particle, we study the interactions between two such active motors. The ambient fluid mediates a long range hydrodynamic interaction between two motors. This interaction has both direct and indirect hydrodynamic contributions. The direct contribution is due to the propagation of fluid flow that originated from a moving motor and affects the motion of the other motor. The indirect contribution emerges from the re-distribution of the ionic concentrations in the presence of both motors. Electric force exerted on the fluid from this ionic solution enhances the flow pattern and subsequently changes the motion of both motors. By formulating a perturbation method for very far separated motors, we derive analytic results for the transnational and rotational dynamics of the motors. We show that the overall interaction at the leading order, modifies the translational and rotational speeds of motors which scale as ${\cal O}\left([1/D]^3\right)$ and ${\cal O}\left([1/D]^4\right)$ with their separation, respectively. Our findings open up the way for studying the collective dynamics of synthetic micro motors.

cond-mat.soft↗