International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Computer-Aided System for the Detection of Rheumatoid Arthritis
Get PDFRheumatoid Arthritis (RA) is a chronic disease that causes disability in movement. RA classification is critical for effective diagnosis and treatment planning. This work explores the application of the EfficientNetB6 architecture using transfer learning to classify RA severity into three categories: Healthy, Moderate and Severe. Medical imaging dataset containing X-Ray images, enhanced with contrast limited adaptive histogram equalization (CLAHE), data augmentation techniques and fine-tuning of hyper-parameters were applied in this work. We compared EfficientNetB6 with all the models of EfficientNet family and all other state of the art models. When we combined EfficientNetB6 with CLAHE, we achieved the highest accuracy of 96.06%. Without using CLAHE accuracy dropped by 4% to 5% for all the models. For healthy class model, we achieved precision, recall and F1-score of 99.36%,97.81%,98.58% respectively, showing robustness in identifying healthy cases. Moderate class yielded precision, recall and F1-score of 89.45%,95.07%,92.17% respectively, demonstrating the model’s effectiveness in identifying moderate cases with minimal false negatives. The Severe class presented more challenges with a precision, recall and F1-score of 85.11%,78.43%, 81.63% highlighting the need for improved recall value. To further improve results we suggest enhancements such as advanced data augmentation and synthetic data generation, particularly for the Severe class consequently aiding clinicians for identification of RA
Evaluation And Mitigation of Industrial Fire Hazards in The Faisalabad Industrial Estate Development and Management Company (Fiedmc) Zones
Get PDFIndustrial fire hazards are a major threat to lives, infrastructure, and economic activities, especially in growing urban areas. Although industries significantly contribute to the national industrial sector but it may easily catch fire, resulting in a brutal impact on infrastructure, workers, and the environment. This research seeks to assess the characteristics, causes, and frequency of industrial fires within FIEDMC zones, pinpoint the most frequent ignition sources, and propose effective mitigation measures. A quantitative methodology was utilized to gather fire incident data from 2014 to April 2025, drawing from official reports from rescue services and fire stations on-site. The data was analyzed using Power BI to uncover trends in incidents, injuries, and fatalities, while also identifying the most prevalent causes of industrial fires. Factors considered included overloaded wiring, HVAC malfunctions, human error, structural failures, and boiler issues. The visualizations enabled the categorization of causes and the identification of high-risk years and emerging patterns. The results indicated a notable increase in fire incidents and casualties in recent years, particularly from 2020 to 2025. Electrical and mechanical failures were identified as the primary causes, with overloaded wiring alone contributing to 30.43% of fire cases, followed by HVAC problems (18.84%) and human negligence (15.94%). The highest numbers of injuries and fatalities occurred in 2023, with 410 injuries and 80 deaths, reflecting a significant lapse in safety. The study concludes that FIEDMC zones are facing a persistent fire safety crisis influenced by ingrained weaknesses in risk management. Tackling this issue requires long-term, comprehensive solutions, which include regular inspections, worker training, infrastructure improvements, and stricter enforcement of regulations. To reduce risks related to industrial fire hazard require quarterly safety audits, load assessments of all wiring systems, mandatory fire-response training for staff, and the creation of a dedicated fire risk monitoring unit in each estate. Importantly, fire safety must be treated as a management issue, not just a technical one
Analyzing the Predictors of Mortality Among Asphyxiated Neonates
Get PDFBirth asphyxia refers to the inability to initiate and sustain breathing at birth, leading to inadequate oxygen supply to vital organs. It is one of the most common causes of perinatal brain injury, contributing to high rates of morbidity and mortality. Neonatal asphyxia is a major cause of early neonatal death, accounting for an estimated 900,000 deaths annually. It results from impaired respiratory gas exchange in the fetus or newborn, causing hypoxia, hypercapnia, and, in some cases, ischemia. This condition can affect multiple organs, leading to biochemical and functional changes, such as lactic acidosis, which may result in death or severe neurological impairment. Neonatal asphyxia is frequently associated with multiple organ failure, primarily impacting the brain, heart, and kidneys. It can lead to complications affecting motor, sensory, cognitive, and psychological development. Several factors contribute to birth asphyxia, including maternal anemia, diabetes, and placental abruption. Other significant predictors of mortality among asphyxiated neonates include neonatal sepsis, preterm birth, lack of Kangaroo Mother Care (KMC), low birth weight, seizures, need for resuscitation at birth, stage III asphyxia, hypoxic-ischemic encephalopathy (stages II and III), seizures and thrombocytopenia. This systematic review aims to identify the pooled predictors of mortality among asphyxiated neonates. Various online databases, including PubMed, MEDLINE, Google Scholar, and WHO websites, were searched for relevant studies. The review included cross-sectional, case-control, and cohort studies conducted in Pakistan and Ethiopia. Data entry and statistical analysis were performed using Excel and SPSS (version 27). The pooled mortality rate of birth asphyxia was found to be 64.0%. Among asphyxiated neonates, 27.1% who were delivered via spontaneous vaginal delivery (SVD) did not survive. Mortality rates were 39.4% for neonates born after prolonged labor, 42.6% for those delivered following premature rupture of membranes, and 50% for those weighing less than 2500g at birth. Additionally, 60.2% of asphyxiated neonates with seizures and 35.7% requiring resuscitation at birth did not survive. The highest mortality rate (81.1%) was observed in neonates with stage III asphyxia. It is concluded that asphyxiated neonates exhibit a high mortality rate. Key predictors of mortality include neonatal sepsis, vaginal delivery, lack of Kangaroo Mother Care (KMC), low birth weight, seizures, need for resuscitation at birth, stage III asphyxia, advanced maternal age, delivery complications, and prolonged rupture of membranes
AI in the Field: A Review of Deep Learning Methods for Weed Identification in Wheat Crops
Get PDFWeed infestation is a major constraint in wheat production, causing yield losses and higher herbicide dependence. Traditional control methods often lack precision, highlighting the need for intelligent, sustainable solutions. Deep learning has recently emerged as a powerful tool for automated and accurate weed detection in precision agriculture. This review summarizes the latest advances in deep learning applied to wheat weed identification, emphasizing model architectures, datasets, and imaging techniques. Approaches such as YOLO variants, Faster R-CNN, U-Net, and transformer-based models have achieved high accuracy in distinguishing wheat from diverse weed species, even under complex field conditions. Integration of UAV imagery, multispectral sensors, and spectral indices further enhances detection at early growth stages. Recent innovations, including attention mechanisms, feature fusion, optimized loss functions, and lightweight designs, have improved precision, speed, and generalization. Key challenges remain in dataset quality, class imbalance, and cross-field applicability. This work outlines current trends, identifies gaps, and highlights future directions for scalable and sustainable deep learning-based weed detection in wheat agriculture
Harnessing Unconventional Malware Detection Techniques to Equip Proactive and Resilient Cyber Defense Strategies Against the Constantly Changing Landscape of Sophisticated Cyber Threats
Get PDFThe rapidly changing intricacy of malware, specifically in the case of highly secured air-gapped networks, necessitates proactive and resilient detection mechanisms that are highly capable of detecting sophisticated, modern, and obfuscated malware. Instant work focuses on a model for malware detection that is vibrant and resilient and uses deep learning models to look at Windows API call patterns that come from executable files. The original dataset from Kaggle had a big class imbalance (malicious: 42,797; benign: 1,079), but the SMOTE approach helped balance the training data. In this regard, a comparison of seven deep learning models, including Simple ANN, MLP, DropConnect Improved ANN, Residual ANN, DenseNet ANN, RBF Network, and hybrid CNN-LSTM, has been conducted over both 50 and 150 training epochs on various metrics such as recall, accuracy, F1-score, precision, and ROC-AUC. As a result, the CNN-LSTM model, enhanced by an attention mechanism, exhibited superior efficacy in differentiating between benign and malicious samples. In this context, the accuracy improvement is minimal at +0.08%, but the most substantial increase in Class 0 recall is +4.1%, and the F1-score shows an enhancement of +2.7%. The most significant contribution of this study is the attention-augmented architecture that apparently diminishes interpretability and enhances focus on significant behavioral attributes
Half a Century of Warming in Punjab, Pakistan: Statistical Evidence from 1970–2019
Get PDFRegional temperature gradients affect how climate change is defined and assessed from varying perspectives. In this research, temperature trends in the Province of Punjab from 1970 to 2019 were examined. To assess the changes in temperature, the monthly means of temperature (Tmean), maximum temperature (Tmax), and minimum temperature (Tmin) were analyzed using Sen\u27s slope estimator method. Several empirical techniques are applied to assess whether the trends are indeed significant, either positively or negatively, and to what extent diversity exists among different weather stations. Also considered are the expected values in the determination of a comprehensive account of temperature fluctuation and variation. The analysis indicates a significant increase in the mean temperature (Tmean) across Punjab, with a sharper increase from Northern Punjab to Southern Punjab. While maximum temperature (Tmax) shows a steep increase in southern and western regions, minimum temperature (Tmin) shows a predominantly increasing trend in Central Punjab. These findings are going to be useful to those making national policy who are trying to formulate strategies for climate change mitigation and adaptation. This study examines long-term temperature trends in Punjab, Pakistan, from 1970 to 2019 using Mann–Kendall and Sen’s slope estimator methods. Results show a statistically significant warming trend, with mean temperature increasing at 0.04°C per year. Southern and Western Punjab experienced higher rates of warming compared to Northern regions. Maximum temperatures increased more sharply in the south, while minimum temperatures rose more prominently in central Punjab, indicating a declining diurnal temperature range. These findings highlight regional climate disparities and underscore the need for targeted adaptation strategies
Impact of Anticipatory Grief on Quality of Life among Caregivers of Thalassemia Patients: Mediating Role of Physical Activity
Get PDFCaregivers of patients with chronic illness, such as thalassemia, face unique challenges in their lives. During the caretaking of the patient, caregivers face anticipatory grief due to the fear of loss. The goal of the current study was to investigate the impact of anticipatory grief on the quality of life of caregivers of thalassemia patients with the mediating role of physical activity. Differences across genders in a proposed relationship were also studied. Anticipatory grief scale (Theut et al., 1991), international physical activity questionnaire (Geneva, 1998) & quality of life scale (Flanagan, 1970), alongside the demographic sheet and written informed consent form, were employed for collecting data among 300 caregivers using cross cross-sectional survey research design that included multiple cities of Punjab. Results indicate that anticipatory grief has a significant negative relationship with quality of life and physical activity. Physical activity has a significant positive relationship with quality of life. Results also indicate that women show significantly higher levels of anticipatory grief than men. Men show a higher level of quality of life than women. The findings of the study provided strong empirical support for the predicted role of anticipatory grief on quality of life among caregivers. These findings further highlight that physical activity should be part of parents\u27 lives to deal with grief related to the health of a child
UAV-Based Flood Mapping and Damage Assessment in Harnai Khawar, Swat, Khyber Pakhtunkhwa, Pakistan
Get PDFFloods is among the most destructive hydrological hazards in Pakistan, particularly across the steep, data‑sparse basins of Khyber Pakhtunkhwa (KPK). The 2022 monsoon produced catastrophic damage in the Swat Valley, disrupting transport, irrigation, and housing. This article demonstrates an Unmanned Aerial Vehicle (UAV) workflow for rapid, high‑resolution flood mapping, damage quantification, and risk zonation in the Barwai Khwar sub‑watershed of the Swat River Basin. Pre‑event context was assembled from Google Earth Pro imagery (12 June 2022), and post‑event aerial surveys were flown using a DJI Phantom 4 Pro (v2.0) with GNSS‑supported Ground Control Points (GCPs). Imagery was processed in Agi soft Meta shape to generate Ortho mosaics and surface products, then analyzed in a GIS to delineate inundation, channel widening, structural damage, and agricultural losses. The floodplain width locally expanded from approximately 7 m to 76 m; damaged linear infrastructure includes ~2.18 km of retaining walls and 39 m of bridges. Surface impacts include ~6,271 m² of residential area and ~22.56 ha of cropland affected. The approach provided near‑centimeter spatial detail, enabling precise polygonal accounting for recovery planning and identification of high‑risk margins where unprotected construction coincides with steep banks and tight meanders. Findings confirm the value of UAV photogrammetry as a fast, replicable, and cost‑effective complement to satellite‑based disaster assessment in Pakistan’s mountain valleys, supporting preparedness, reconstruction, and resilient land‑use decisions
Early Detection and Classification of Lung Cancer using Segment Anything Model 2 and Dense Net
Get PDFLung cancer is one of the most perilous diseases worldwide with high incidence and low survival rates due to late diagnosis. Accurate detection and diagnosis of lung nodules is important for early-stage detection. Machine learning and deep learning techniques have greatly improved the precision of lung nodule segmentation and classification in Computed Tomography (CT) images. The study presents a novel approach to segmenting and classifying nodules by combining foundational models with deep learning architectures. We have used the Segment Anything Model (SAM2) to segment lung nodules and Dense Net to classify them as benign and malignant. SAM2 has been tested on the datasets using different prompts to achieve better results. Foundational Models and Deep Learning architecture’s integration significantly improved Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) in medical images. Experimental results proved the effectiveness of the proposed model for early-stage detection and classification of lung nodules from CT scans. SAM2 model achieves a Dice Similarity Coefficient (DSC) of 97.87% and an Intersection over Union (IoU) of 95.82% for segmentation, and the Dense Net model\u27s classification accuracy is 97.34%. The experimental results demonstrate the performance of our model compared to existing techniques
Recycling of Laptop Spent Li-Ion Batteries and Characterization of Extracted Materials
Get PDFAs the use of smart devices increases, the energy demand continues to grow, leading to higher consumption of lithium-ion batteries (LIBs) in portable electronics such as laptops, tablets, smartphones, and electric vehicles. This increased usage has resulted in a rising number of discarded batteries, which contain hazardous chemicals and heavy metals that pose serious environmental risks. Recycling these batteries efficiently is essential for both environmental protection and economic sustainability. This study explores a recycling method for used laptop and notebook batteries through a pretreatment and solvent dissolution process, using mild phosphoric acid as the leaching agent. The hydro-metallurgical process successfully recovers 5.124% lithium and 42.143% cobalt, yielding lithium carbonate and cobalt hydroxide. The batteries, which consist of 50.80% lithium cobalt oxide (LiCoO₂) cathodes on aluminum and graphite anodes on copper foils, serve as the primary source of material recovery. The recovered lithium carbonate and cobalt hydroxide are then used to synthesize active powder for cathode material. Advanced characterization techniques, including Cyclic Voltammetry (CV), Raman spectroscopy, and Electrochemical Impedance Spectroscopy (EIS), are employed to analyze the electrochemical properties of the recovered materials and synthesized powders. The results confirm the effectiveness of this recycling method in recovering valuable materials while reducing environmental impact. By addressing the growing problem of battery waste, this approach supports the sustainable production of new batteries through the reuse of critical materials. The study emphasizes the importance of developing efficient recycling technologies to promote a circular economy and reduce dependence on raw material extraction