Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity selection with a CNN-GRU architecture to enable extended-horizon PM2.5 forecasting in Isfahan, Iran, a city characterized by complex pollution dynamics and limited monitoring coverage. Unlike existing approaches that rely on computationally intensive transformer models or external simulation tools, our method integrates three key innovations: (i) DTW-based historical sampling to identify similar pollution patterns across peer stations, (ii) a lightweight CNN-GRU architecture augmented with meteorological features, and (iii) a scalable design optimized for sparse networks. Experimental validation using multi-year hourly data from eight monitoring stations demonstrates superior performance compared to state-of-the-art deep learning methods, achieving R2 = 0.91 for 24-hour forecasts. Notably, this is the first study to demonstrate stable 10-day PM2.5 forecasting (R2 = 0.73 at 240 hours) without performance degradation, addressing critical early-warning system requirements. The framework's computational efficiency and independence from external tools make it particularly suitable for deployment in resource-constrained urban environments.

The rapid urbanization of cities and increasing vehicular congestion have posed significant challenges to traffic management and safety. This study explores the transformative potential of artificial intelligence (AI) and machine vision technologies in revolutionizing traffic systems. By leveraging advanced surveillance cameras and deep learning algorithms, this research proposes a system for real-time detection of vehicles, traffic anomalies, and driver behaviors. The system integrates geospatial and weather data to adapt dynamically to environmental conditions, ensuring robust performance in diverse scenarios. Using YOLOv8 and YOLOv11 models, the study achieves high accuracy in vehicle detection and anomaly recognition, optimizing traffic flow and enhancing road safety. These findings contribute to the development of intelligent traffic management solutions and align with the vision of creating smart cities with sustainable and efficient urban infrastructure.

Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained generative models with external retrieval mechanisms, have shown significant success in various natural language processing (NLP) tasks. However, applying RAG models in Persian language as a low-resource language, poses distinct challenges. These challenges primarily involve the preprocessing, embedding, retrieval, prompt construction, language modeling, and response evaluation of the system. In this paper, we address the challenges towards implementing a real-world RAG system for Persian language called PersianRAG. We propose novel solutions to overcome these obstacles and evaluate our approach using several Persian benchmark datasets. Our experimental results demonstrate the capability of the PersianRAG framework to enhance question answering task in Persian.

An analysis of satellite images appears to show damage to an Iranian military facility in a drone attack last week, including holes in the building's roof, according to The Associated Press news agency. Cloudy weather had prevented satellite pictures of the site of the facility from showing the effect of the attack on January 28. While Iran has offered no explanation yet of what the facility in the city of Isfahan manufactured, the assault threatened to again raise tensions in the region, with Tehran blaming Israel for the drone attack, a conclusion that was also reached by United States officials. Video taken of the attack showed an explosion at the site after anti-aircraft fire targeted the drones, likely from one of the drones reaching the building's roof. Iran's military has claimed that it shot down two other drones before they reached the site.

An Iranian military facility was hit with a drone strike Jan. 29, 2023. Iran on Thursday blamed Israel for a drone strike that hit a military factory near the city of Isfahan over the weekend and threatened revenge, saying it "reserves its legitimate and inherent right" to respond. Reports surfaced earlier this week citing a U.S. official who attributed the attack to Israel, but Tehran's accusation could prolong what appears to have become a covert war between the Middle Eastern nations. "Early investigations suggest that the Israeli regime was responsible for this attempted act of aggression," Iranian Ambassador Amir Saeid Iravani said in a letter to the United Nations, though he did not cite the evidence Tehran has to back its accusations. Eyewitness footage shows what is said to be the moment of an explosion at a military industry factory in Isfahan, Iran, Jan. 29, 2023, in this still image obtained from a video.

Iran has blamed Israel for last week's drone attack on a military factory near the central city of Isfahan, promising revenge for what appeared to be the latest episode in a long-running covert war. The Iranian claim, carried by the semi-official ISNA news agency on Thursday, corroborates remarks made by United States officials following the attack. The attack came amid tension between Iran and the West over Tehran's nuclear activity and its supply of arms – including long-range "suicide drones" – for Russia's war in Ukraine, as well as months of anti-government demonstrations at home. In a letter to the United Nations chief, Iran's UN envoy, Amir Saeid Iravani, said "primary investigation suggested Israel was responsible" for Saturday night's attack, which Tehran had said caused no casualties or serious damage. "Iran reserves its legitimate and inherent right to defend its national security and firmly respond to any threat or wrongdoing of the Zionist regime [Israel] wherever and whenever it deems necessary," Iravani said in the letter.

A drone attack on an Iranian military facility that resulted in a large explosion in the center of the city of Isfahan on Saturday was the work of the Mossad, Israel's premier intelligence agency, according to senior intelligence officials who were familiar with the dialogue between Israel and the United States about the incident. The facility's purpose was not clear, and neither was how much damage the strike caused. But Isfahan is a major center of missile production, research and development for Iran, including the assembly of many of its Shahab medium-range missiles, which can reach Israel and beyond. Weeks ago, American officials publicly identified Iran as the primary supplier of drones to Russia for use in the war in Ukraine, and they said they believed Russia was also trying to obtain Iranian missiles to use in the conflict. But U.S. officials said they believed this strike was prompted by Israel's concerns about its own security, not the potential for missile exports to Russia. The strike came just as Secretary of State Antony J. Blinken was beginning a visit to Israel, his first since Benjamin Netanyahu returned to office as prime minister.

Israel appears to have been behind a drone attack on a military factory in Iran, United States officials say. Iran said on Sunday that it intercepted drones targeting the facility near the central city of Isfahan, adding there were no casualties. The extent of damage could not be independently ascertained. Iranian state media released footage showing a flash in the sky and emergency vehicles at the scene. Israel was behind the drone attack, The Wall Street Journal cited unnamed US officials and people familiar with the strike as saying.

Iran's defence ministry has reported several drone attacks on a military plant in the country's central city of Isfahan. The attacks were "unsuccessful" and there were no casualties, the ministry said in a statement early on Sunday. "One of [the drones] was hit by the … air defence and the other two were caught in defence traps and blew up," said the statement carried by the state news agency, IRNA. "Fortunately, this unsuccessful attack did not cause any loss of life and caused minor damage to the workshop's roof," it said. The ministry did not say who was suspected of carrying out the attack.

Electrocardiogram (ECG) is the most frequent and routine diagnostic tool used for monitoring heart electrical signals and evaluating its functionality. The human heart can suffer from a variety of diseases, including cardiac arrhythmias. Arrhythmia is an irregular heart rhythm that in severe cases can lead to heart stroke and can be diagnosed via ECG recordings. Since early detection of cardiac arrhythmias is of great importance, computerized and automated classification and identification of these abnormal heart signals have received much attention for the past decades. Methods: This paper introduces a light deep learning approach for high accuracy detection of 8 different cardiac arrhythmias and normal rhythm. To leverage deep learning method, resampling and baseline wander removal techniques are applied to ECG signals. In this study, 500 sample ECG segments were used as model inputs. The rhythm classification was done by an 11-layer network in an end-to-end manner without the need for hand-crafted manual feature extraction. Results: In order to evaluate the proposed technique, ECG signals are chosen from the two physionet databases, the MIT-BIH arrhythmia database and the long-term AF database. The proposed deep learning framework based on the combination of Convolutional Neural Network(CNN) and Long Short Term Memory (LSTM) showed promising results than most of the state-of-the-art methods. The proposed method reaches the mean diagnostic accuracy of 98.24%. Conclusion: A trained model for arrhythmia classification using diverse ECG signals were successfully developed and tested. Significance: Since the present work uses a light classification technique with high diagnostic accuracy compared to other notable methods, it could successfully be implemented in holter monitor devices for arrhythmia detection.