arXiv subjects

Mojtaba Mohammadi

Publications and source records attributed to Mojtaba Mohammadi.

9 recordsLinked to original sources

arXiv2026

The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis

Detecting infection-related behavioral changes in mosquitoes from video data is challenging because mosquitoes are small, move rapidly and irregularly, and are affected by environmental factors such as background, lighting, and shadows, which can make reliable feature extraction difficult. In this study, a YOLO- and Contrastive Language-Image Pre-training (CLIP)-based vision-language framework is proposed to classify mosquito flight frames of uninfected and Dengue virus serotype 2 (DENV2)-infected mosquitoes. First, YOLO is used to isolate mosquito regions from the background. Then, visual features extracted from video frames are aligned with biologically meaningful textual prompts in a shared embedding space. The multimodal model was fine-tuned using supervised bidirectional contrastive learning and evaluated through frame-level image-text similarity-based classification. The results show that the proposed method achieved 98.54% accuracy and 99.91% sensitivity at the frame level. After temporal aggregation of frame-level information, the model achieved complete video-level performance. The ablation results showed that fine-tuning and CLIP-based representations were essential for this domain, while the textual branch provided semantic image-text alignment rather than an accuracy advantage over the vision-only model. These findings suggest that vision-language models can provide a useful framework for analyzing infection-related biological behaviors from video data.

cs.AI↗

arXiv2026

Ternary-composition tuning of the anomalous Nernst effect in amorphous-like Gd-Co-Pt films

We report composition tuning of the anomalous Nernst effect in amorphous-like Gd-Co-Pt ternary films. Pt incorporation into Gd-Co films modifies the anomalous Nernst coefficient and induces a sign reversal of S_ANE, whereas Gd incorporation into Co-Pt films suppresses S_ANE but reduces thermal conductivity. Owing to the balance between transverse thermoelectric response and thermal transport, the heat-flux sensitivity reaches approximately 0.24 μm/A. Composition maps reveal that the magnitude and heat-flux sensitivity of the anomalous Nernst effect can be systematically tuned in the Gd-Co-Pt ternary composition space. This work extends ANE material design from binary-alloy optimization to ternary-composition engineering.

cond-mat.mtrl-sci↗

arXiv2026

SSI-GAN: Semi-Supervised Swin-Inspired Generative Adversarial Networks for Neuronal Spike Classification

Mosquitos are the main transmissive agents of arboviral diseases. Manual classification of their neuronal spike patterns is very labor-intensive and expensive. Most available deep learning solutions require fully labeled spike datasets and highly preprocessed neuronal signals. This reduces the feasibility of mass adoption in actual field scenarios. To address the scarcity of labeled data problems, we propose a new Generative Adversarial Network (GAN) architecture that we call the Semi-supervised Swin-Inspired GAN (SSI-GAN). The Swin-inspired, shifted-window discriminator, together with a transformer-based generator, is used to classify neuronal spike trains and, consequently, detect viral neurotropism. We use a multi-head self-attention model in a flat, window-based transformer discriminator that learns to capture sparser high-frequency spike features. Using just 1 to 3% labeled data, SSI-GAN was trained with more than 15 million spike samples collected at five-time post-infection and recording classification into Zika-infected, dengue-infected, or uninfected categories. Hyperparameters were optimized using the Bayesian Optuna framework, and performance for robustness was validated under fivefold Monte Carlo cross-validation. SSI-GAN reached 99.93% classification accuracy on the third day post-infection with only 3% labeled data. It maintained high accuracy across all stages of infection with just 1% supervision. This shows a 97-99% reduction in manual labeling effort relative to standard supervised approaches at the same performance level. The shifted-window transformer design proposed here beat all baselines by a wide margin and set new best marks in spike-based neuronal infection classification.

cs.LG↗

arXiv2025

Efficient spin-orbit torque driven magnetization switching of GdFe using phosphorus-implanted platinum layers

The capability of the spin-orbit torque (SOT) generated via phenomena such as the spin Hall effect in heavy metals, in switching the magnetization of an adjacent magnetic material, has been studied extensively over the last decade. The efficiency of SOT generation is commonly quantified in terms of the spin Hall angle θ_SH. In this work, we demonstrate experimentally that implanting platinum (Pt) with phosphorus (P), resulting in Pt (P) d, where d denotes the implantation dose, increases θ_SH by a factor of 7, from 0.06 (d = 0) to 0.43 (d = 10*10^16 ions/cm^2). The enhanced θ_SH, along with factors such as perpendicular magnetic anisotropy and resistivity, lead to reduction of the critical current density for switching the perpendicular magnetization of ferrimagnetic rare earth-transition metal alloy Gd26Fe74, by a factor of nearly 27, from 4.0*1011 A/m^2 (d = 0) to 1.5*10^10 A/m^2 (d = 10*10^16 ions/cm^2). Further, the switching current density at zero thermal fluctuations and thermal stability factor were evaluated and found to be 2.0*10^10 A/m^2 and 61.4 (d = 10*10^16 ions/cm^2), with the latter being sufficiently above the required threshold for commercial memory applications. Our results suggest that Pt (P) could be a strong candidate in realizing efficient SOT driven magnetization switching leading to the development of improved memory and logic devices in the future.

cond-mat.mtrl-sci↗

arXiv2023

A Cyber-Physical Architecture for Microgrids based on Deep learning and LORA Technology

This paper proposes a cyber-physical architecture for the secured social operation of isolated hybrid microgrids (HMGs). On the physical side of the proposed architecture, an optimal scheduling scheme considering various renewable energy sources (RESs) and fossil fuel-based distributed generation units (DGs) is proposed. Regarding the cyber layer of MGs, a wireless architecture based on low range wide area (LORA) technology is introduced for advanced metering infrastructure (AMI) in smart electricity grids. In the proposed architecture, the LORA data frame is described in detail and designed for the application of smart meters considering DGs and ac-dc converters. Additionally, since the cyber layer of smart grids is highly vulnerable to cyber-attacks, t1his paper proposes a deep-learning-based cyber-attack detection model (CADM) based on bidirectional long short-term memory (BLSTM) and sequential hypothesis testing (SHT) to detect false data injection attacks (FDIA) on the smart meters within AMI. The performance of the proposed energy management architecture is evaluated using the IEEE 33-bus test system. In order to investigate the effect of FDIA on the isolated HMGs and highlight the interactions between the cyber layer and physical layer, an FDIA is launched against the test system. The results showed that a successful attack can highly damage the system and cause widespread load shedding. Also, the performance of the proposed CADM is examined using a real-world dataset. Results prove the effectiveness of the proposed CADM in detecting the attacks using only two samples.

cs.LG↗

arXiv2023

Deep Learning-Based Cyber-Attack Detection Model for Smart Grids

In this paper, a novel artificial intelligence-based cyber-attack detection model for smart grids is developed to stop data integrity cyber-attacks (DIAs) on the received load data by supervisory control and data acquisition (SCADA). In the proposed model, first the load data is forecasted using a regression model and after processing stage, the processed data is clustered using the unsupervised learning method. In this work, in order to achieve the best performance, three load forecasting methods (i.e. extra tree regression (ETR), long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM)) are utilized as regression models and their performance is compared. For clustering and outlying detection, the covariance elliptic envelope (EE) is employed as an unsupervised learning method. To examine the proposed model, the hourly load data of the power company of the city of Johor in Malaysia is employed and Two common DIAs, which are DIAs targeting economic loss and DIAs targeting blackouts, are used to evaluate the accuracy of detection methods in several scenarios. The simulation results show that the proposed EE-BiLSTM method can perform more robust and accurate compared to the other two methods.

cs.LG↗

arXiv2022

AI-based Optimal scheduling of Renewable AC Microgrids with bidirectional LSTM-Based Wind Power Forecasting

In terms of the operation of microgrids, optimal scheduling is a vital issue that must be taken into account. In this regard, this paper proposes an effective framework for optimal scheduling of renewable microgrids considering energy storage devices, wind turbines, micro turbines. Due to the nonlinearity and complexity of operation problems in microgrids, it is vital to use an accurate and robust optimization technique to efficiently solve this problem. To this end, in the proposed framework, the teacher learning-based optimization is utilized to efficiently solve the scheduling problem in the system. Moreover, a deep learning model based on bidirectional long short-term memory is proposed to address the short-term wind power forecasting problem. The feasibility and performance of the proposed framework as well as the effect of wind power forecasting on the operation efficiency are examined using IEEE 33-bus test system. Also, the Australian Wool north wind site data is utilized as a real-world dataset to evaluate the performance of the forecasting model. Results show the effective and efficient performance of the proposed framework in the optimal scheduling of microgrids.

eess.SY↗

arXiv2019

Statistical-Based Privacy-Preserving Scheme with Malicious Consumers Identification for Smart Grid

As smart grids are getting popular and being widely implemented, preserving the privacy of consumers is becoming more substantial. Power generation and pricing in smart grids depends on the continuously gathered information from the consumers. However, having access to the data relevant to the electricity consumption of each individual consumer is in conflict with its privacy. One common approach for preserving privacy is to aggregate data of different consumers and to use their smart-meters for calculating the bills. But in this approach, malicious consumers who send erroneous data to take advantage or disrupt smart grid cannot be identified. In this paper, we propose a new statistical-based scheme for data gathering and billing in which the privacy of consumers is preserved, and at the same time, if any consumer with erroneous data can be detected. Our simulation results verify these matters.

cs.CR↗

arXiv2002

On the $β$-Function and Conformal Anomaly of Noncommutative QED with Adjoint Matter Fields

In the first part of this work, a perturbative analysis up to one-loop order is carried out to determine the one-loop $β$-function of noncommutative U(1) gauge theory with matter fields in the adjoint representation. In the second part, the conformal anomaly of the same theory is calculated using the Fujikawa's path integral method. The value of the one-loop $β$-function calculated in both methods coincides. As it turns out, noncommutative QED with matter fields in the adjoint representation is asymptotically free for the number of flavor degrees of freedom $N_{f}<3$.

hep-th↗