Current Issue (Volume - 4 | Issue - 6) at IgMin Research

Although assessing fish stocks is essential for sustainable management, quantitative, multi-species evaluations that integrate fishing effort and biological production are scarce in Tunisian reservoirs. This study provides the first comprehensive, standardised assessment of six key species (Cyprinus carpio, Chelon ramada, Luciobarbus callensis, Sander lucioperca, Scardinius erythrophthalmus, and Rutilus rubilio) across eight major reservoirs. It combines multi-mesh gillnet sampling (2013-2016) with yield-per-recruit (Y/R) modelling using VIT so...ftware and cohort analysis using FISAT II.The results reveal a general state of under-exploitation, yet highlight significant differences between species and between reservoirs. Exploitation rates (E) ranged from severe under-exploitation of mullets (E = 0.09) to near-optimal levels of carp in Sidi Saad (E = 0.48). Although fishing mortality exceeded 60% of total mortality for barbel and pikeperch, Y/R analysis confirmed their under-exploited status. This is supported by high biomass per recruit (up to 2,769 g for barbel in Sidi Barrak) and rapid stock renewal rates (over 79% for pikeperch). Notably, estimated surplus production indicates that current landings could be substantially increased without compromising stock sustainability.We conclude that Tunisian reservoirs have significant untapped fishery potential. However, rather than increasing effort uniformly, we recommend making targeted, site- and species-specific adjustments, coupled with reinforced monitoring of population structure and exploitation rates, in order to prevent any shift towards overfishing. This integrated diagnostic approach provides a replicable scientific baseline for the future adaptive management of North African inland fisheries.Read more

Humid biogas generated from anaerobic digestion causes significant energy degradation and equipment corrosion in renewable energy systems. Traditional moisture control methods are either economically unviable for local plants or lack long-term operational stability in aggressive, H₂S-rich gas streams. This study presents an intelligent moisture control system that combines dielectric barrier sensing with multi-parametric error correction. Experimental validation was conducted using a 50-liter laboratory digester operating under mesophilic and... thermophilic conditions. A 32-bit ARM Cortex-M4 microcontroller deployed an adaptive polynomial approximation coupled with a Fuzzy Logic model to dynamically compensate for temperature drift. Furthermore, a periodic thermal regeneration algorithm (heating the sensor film up to 75 °C for 45 s) was established to prevent chemical degradation without losing system measurement readiness. The experimental results demonstrated that the intelligent module reduced the maximum absolute error of relative humidity measurements to ±1.8% across a wide temperature range (20–55 °C), achieving a high coefficient of determination (R² = 0.994). Real-time compensation of moisture dynamics within a combined heat and power (CHP) unit stabilized the cylinder effective pressure variations by 7 times. Consequently, specific biogas consumption decreased by 7.8%, leading to an absolute increase in electrical efficiency of 2.6%. The proposed hybrid sensing configuration effectively solves the compromise between high analytical cost and sensor durability. The system ensures robust fuel-to-air ratio optimization, preventing fuel underburn and eliminating downstream acid condensation risks in localized renewable energy sectors.Read more

The discovery of novel functional materials is frequently accelerated by machine learning (ML) techniques that visualize vast chemical spaces in low-dimensional projections. However, projecting high-dimensional materials data into a fixed 2D space can introduce significant distortions, hindering the reliable identification of new candidates. In this work, we present a robust statistical framework for unsupervised materials discovery that mitigates these challenges. Our methodology combines Principal Component Analysis with information criteria ...to determine the optimal dimensionality for representing a given material's dataset, thereby minimizing information loss. We apply this approach to a library of thousands of Li-based compounds, described by their chemical and structural features. Following dimensionality reduction to the statistically optimal space, we employ a non-linear unsupervised learning algorithm to identify novel materials in proximity to a user-defined reference compound. The efficacy of our methodology is demonstrated by its ability to identify candidate materials that have been experimentally reported to exhibit properties similar to the chosen reference, validating our approach as a more reliable pipeline for accelerated materials discoveryRead more

Predicting the direction of stock market movements is a challenging task due to its fuzzy, chaotic, volatile, nonlinear, and complex nature. However, with advancements in artificial intelligence, abundant data availability, and improved computational capabilities, creating robust models capable of accurately predicting stock market movement is now feasible. This study aims to develop a predictive model using news headlines to forecast the direction of stock market movements. It conducts a comparative analysis of four supervised classification d...eep learning models —long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional long short-term memory (BiLSTM), and bidirectional gated recurrent unit (BiGRU)—to predict the next day’s movement direction of the close price of the Nepal Stock Exchange (NEPSE) index. Sentiment scores from the news headlines are computed using the Valence Aware Dictionary for Sentiment Reasoning (VADER) and the TextBlob sentiment analyzer. The models’ performance is evaluated based on sensitivity, specificity, accuracy, and the area under the receiver operating characteristic (ROC) curve (AUC). Experimental results indicate that all four models perform similarly when using sentiment scores from either VADER or TextBlob. Additionally, GRU and BiGRU models show consistent performance across both sentiment analyzers. However, LSTM and BiLSTM perform slightly better with TextBlob sentiment scores compared to those from VADER. These findings are further validated through statistical tests.Read more

Audio signal classification plays a significant role in various real-world applications such as speech recognition, environmental sound analysis, and music genre identification. Traditional approaches often depend on manually extracted features, which may not capture the full complexity of audio data. This paper presents a deep learning-based method for automatic classification of audio signals using a One-Dimensional Convolutional Neural Network (1D-CNN) and a Recurrent Neural Network (RNN). The CNN model is utilized to extract spatial feature...s from spectrogram representations, while the RNN model effectively captures temporal dependencies within the audio sequences. Both models were trained and evaluated on a labelled dataset, and their performance was compared using metrics such as accuracy, precision, probability of detection (POD), and F1-score. The experimental results demonstrate that CNN has achieved high classification accuracy compared to RNN, with CNN excelling at spatial feature extraction and RNN providing temporal feature learning. The proposed approach confirms that deep learning models can significantly enhance the performance and reliability of audio signal classification systems.Read more

Plant polyphenols are ubiquitous secondary metabolites in plants whose antioxidant, anti-inflammatory, antimicrobial, and cardioprotective activities have been systematically elucidated. They exert their physiological functions by scavenging intracellular reactive oxygen species, precisely regulating inflammatory mediators, and inhibiting pathogenic proliferation, exhibiting tremendous application potential in functional foods, biomedicine, and natural cosmetics. However, the inherent chemical instability of polyphenols leads to severe structur...al degradation and bioactivity loss during extraction, processing, and storage. This manifests not only as detectable content reduction but also as significant "hidden bioactivity loss" without apparent content changes, which has emerged as the core bottleneck restricting their industrial translation. Most existing reviews are limited to single-stage optimizations, and a systematic regulatory framework spanning the entire process of biosynthesis, extraction, and processing has not yet been established. In this narrative critical review, we construct an integrated system for polyphenol content enhancement and stability regulation across the entire value chain from biosynthesis to extraction and processing. We critically elaborate on stress-mediated biosynthetic mechanisms, extraction loss control strategies, and processing stabilization technologies, with the ultimate goal of improving their resource utilization efficiency and advancing the industrial innovation and application of plant polyphenols.Read more