A S M Sharifuzzaman Sagar

A S M Sharifuzzaman Sagar, Mohammed Bennamoun, Farid Boussaid et al.

In multimodal misinformation, deception usually arises not just from pixel-level manipulations in an image, but from the semantic and contextual claim jointly expressed by the image-text pair. Yet most deepfake detectors, engineered to detect pixel-level forgeries, do not account for claim-level meaning, despite their growing integration in automated fact-checking (AFC) pipelines. This raises a central scientific and practical question: Do pixel-level detectors contribute useful signal for verifying image-text claims, or do they instead introduce misleading authenticity priors that undermine evidence-based reasoning? We provide the first systematic analysis of deepfake detectors in the context of multimodal misinformation detection. Using two complementary benchmarks, MMFakeBench and DGM4, we evaluate: (1) state-of-the-art image-only deepfake detectors, (2) an evidence-driven fact-checking system that performs tool-guided retrieval via Monte Carlo Tree Search (MCTS) and engages in deliberative inference through Multi-Agent Debate (MAD), and (3) a hybrid fact-checking system that injects detector outputs as auxiliary evidence. Results across both benchmark datasets show that deepfake detectors offer limited standalone value, achieving F1 scores in the range of 0.26-0.53 on MMFakeBench and 0.33-0.49 on DGM4, and that incorporating their predictions into fact-checking pipelines consistently reduces performance by 0.04-0.08 F1 due to non-causal authenticity assumptions. In contrast, the evidence-centric fact-checking system achieves the highest performance, reaching F1 scores of approximately 0.81 on MMFakeBench and 0.55 on DGM4. Overall, our findings demonstrate that multimodal claim verification is driven primarily by semantic understanding and external evidence, and that pixel-level artifact signals do not reliably enhance reasoning over real-world image-text misinformation.

A S M Sharifuzzaman Sagar, Yu Chen, Jun Hoong Chan

Traditional predictive coding networks, inspired by theories of brain function, consistently achieve promising results across various domains, extending their influence into the field of computer vision. However, the performance of the predictive coding networks is limited by their error feedback mechanism, which traditionally employs either local or global recurrent updates, leading to suboptimal performance in processing both local and broader details simultaneously. In addition, traditional predictive coding networks face difficulties in dynamically adjusting to the complexity and context of varying input data, which is crucial for achieving high levels of performance in diverse scenarios. Furthermore, there is a gap in the development and application of specific loss functions that could more effectively guide the model towards optimal performance. To deal with these issues, this paper introduces a hybrid prediction error feedback mechanism with dynamic modulation for deep predictive coding networks by effectively combining global contexts and local details while adjusting feedback based on input complexity. Additionally, we present a loss function tailored to this framework to improve accuracy by focusing on precise prediction error minimization. Experimental results demonstrate the superiority of our model over other approaches, showcasing faster convergence and higher predictive accuracy in CIFAR-10, CIFAR-100, MNIST, and FashionMNIST datasets.

A S M Sharifuzzaman Sagar, Tajken Salehen, Md Abdur Rob

Brain-computer interfaces (BCIs) collect, analyze, and convert brain activity into instructions and send it to the detection system. BCI is becoming popular in under-brain activities in certain conditions such as attention-based tasks. Researchers have recently used combined neuroimaging techniques such as EEG+fNIRS and EEG+fMRI to solve many real-world problems. Drowsiness detection or sleep inertia is one of the central research areas for the combined neuroimaging techniques. This paper aims to investigate the recent application of combined neuroimaging-based BCI on drowsiness detection or sleep inertia. To this end, this is the only overview paper of the combined neuroimaging-based drowsiness detection system.

Samsil Arefin Mozumder, A S M Sharifuzzaman Sagar

Human existence is getting more sophisticated and better in many areas due to remarkable advances in the fields of automation. Automated systems are favored over manual ones in the current environment. Home Automation is becoming more popular in this scenario, as people are drawn to the concept of a home environment that can automatically satisfy users' requirements. The key challenges in an intelligent home are intelligent decision making, location-aware service, and compatibility for all users of different ages and physical conditions. Existing solutions address just one or two of these challenges, but smart home automation that is robust, intelligent, location-aware, and predictive is needed to satisfy the user's demand. This paper presents a location-aware intelligent RSSI-based home automation system (IRHA) that uses Wi-Fi signals to detect the user's location and control the appliances automatically. The fingerprinting method is used to map the Wi-Fi signals for different rooms, and the machine learning method, such as Decision Tree, is used to classify the signals for different rooms. The machine learning models are then implemented in the ESP32 microcontroller board to classify the rooms based on the real-time Wi-Fi signal, and then the result is sent to the main control board through the ESP32 MAC communication protocol to control the appliances automatically. The proposed method has achieved 97% accuracy in classifying the users' location.

Samsil Arefin Mozumder, A S M Sharifuzzaman Sagar

The conventional fishing industry has several difficulties: water contamination, temperature instability, nutrition, area, expense, etc. In fish farming, Biofloc technology turns traditional farming into a sophisticated infrastructure that enables the utilization of leftover food by turning it into bacterial biomass. The purpose of our study is to propose an intelligent IoT Biofloc system that improves efficiency and production. This article introduced a system that gathers data from sensors, store data in the cloud, analyses it using a machine learning model such as a Decision regression tree model to predict the water condition, and provides real-time monitoring through an android app. The proposed system has achieved a satisfactory accuracy of 79% during the experiment.