International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
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
Realistic Face Super-Resolution via Generative Adversarial Networks: Enhancing Facial Recognition in Real-world Scenarios
Get PDFhe accuracy of real-world facial recognition operations faces challenges because of the difficulties connected to Low-Resolution image quality. This indicates that super-resolution methods play a vital role in improving recognition outcomes. Currently, available SR techniques do not achieve generalization due to their dependence on synthetic LR data that uses basic down sampling processes. The proposed GAN-based approach establishes a solution to this challenge through its simulation of actual degradation algorithms which combine Gaussian blur with noise addition and color modification and JPEG compression. Random application of augmentation parameters allows the GAN model to acquire knowledge about diverse and realistic low-resolution data distribution patterns during training. A unique unaligned face image pair dataset was made specifically for research using Zoom-In and Zoom-Out methods to capture high-resolution and low-resolution images from the same individuals. The dataset presents authentic real-life scenarios better than conventional paired collection methods. Based on experimental results our method produces substantial gains in performance compared to other super-resolution methods across both self-created face data as well as established surveillance data. The proposed model achieves higher visual quality standards while improving facial recognition accuracy under different operational situations. In conclusion, this study implements an effective SR solution for facial recognition which tackles problems with standard training datasets while creating authentic face image data. The proposed method shows promise for enhancing SR applications which need high-quality facial recognition capability in surveillance systems and other security-based operations
A Hybrid Model for Crop Disease Detection Based on Deep Learning and Support Vector Machine
Get PDFPakistan\u27s agriculture sector is the backbone of its economy, contributing significantly to its gross domestic product (GDP). However, a key challenge in this sector is to counteract the crop diseases timely because these diseases result in reduced production, increased cost and eventually lead to economic loss. Traditional disease control methods are costly, time-consuming, and often lack technical support, resulting in poor disease management and harmful environmental consequences. This research harnesses the unmatched capability of Artificial Intelligence (AI) and deep learning for timely disease detection in crops. This research introduces a hybrid model that combines deep learning models with a machine learning classifier for disease detection. AlexNet, Vgg-16, ResNet50, and MobileNet are the deep learning models that have been employed for the detection of various diseases in crop leaves of rice, potato, and corn. These models have been trained by using healthy and diseased leaf images of the mentioned crops and then these models are combined with a Support Vector Machine (SVM) classifier to enhance the accuracy of detection. Experimental results show the outstanding performance of this hybrid approach for timely disease detection in crops. It is further observed that the combination of MobileNet and SVM results in an impressive accuracy of 95.68% in disease detection. This technological approach would be beneficial for farmers in the effective management and control of crop diseases thus improving the crop yield and ultimately contributing to economic growth
AI-powered Body Type Analysis for Fashion Recommendation System
Get PDFThis paper presents an AI-powered fashion recommendation system that analyzes body types to offer personalized clothing suggestions. The system uses Convolutional Neural Networks (CNN) to classify male body shapes into three categories (ectomorph, mesomorph, endomorph) and matches them with suitable fashion items. We developed a web-based platform using the React-Django framework, allowing users to upload photos, receive a body type analysis, and get customized fashion advice. Testing shows our approach achieves a 94% success rate in body type classification, significantly outperforming existing methods. This study addresses a key gap in current fashion recommendation systems, which often overlook body type considerations for men. Our solution provides an effective and user-friendly way to enhance online shopping and build greater trust in fashion choices
Harnessing LSTM Networks for Traffic Flow Forecasting: A Deep Learning Approach
Get PDFAccurate traffic flow forecasting in areas with different types of vehicles and varied driving behaviors is crucial for improving urban transportation systems and reducing congestion. In this paper, we introduce a Long Short-Term Memory (LSTM) approach to predict short-term traffic flow in such diverse conditions. Our model uses time-series data from real-world traffic sensors, capturing the patterns and dependencies that occur over time in mixed traffic environments. We tested the model using a dataset from seven days, with six days for training and one day for testing. The LSTM model achieved an R2 value of 0.96, a Mean Squared Error (MSE) of 2.82, and a Mean Absolute Error (MAE) of 1.13. These results demonstrate the effectiveness of LSTM networks in predicting traffic flow in complex traffic conditions, surpassing traditional machine learning models. This study provides valuable insights into using deep learning techniques for intelligent transportation systems (ITS)
A Computational Simulation of Fractional Advection-Diffusion Model Using Differential Quadrature and Local Radial Basis Functions
Get PDFThis article presents a local radial basis function-based differential quadrature method for solving the time-fractional advection-diffusion equation. Backward difference formula is utilized to approximate Caputo fractional derivative. Differential quadrature approach is employed to compute the space derivatives by 3-point central scheme in the neighborhood of a node. Two types of radial basis functions are utilized in numerical simulations. Accuracy and computational efficiency of proposed technique is assessed via , error norms, fractional order, time and spatial step sizes, rate of convergence and execution time. Three nonhomogeneous test problems are solved to validate the method, and the results are compared with finite volume method to show its superiority
Effect of Concentration Variation on Zirconium Nickel Cobalt Metal Organic Framework-Based Electrode Material
Get PDFIn this research, two samples of a ZrNiCo ZIF-67 with the change in molar concentration of metal to linker (1:1 and 1:2) were synthesized via the co-precipitation method. Then electrode fabrication was done. An attractive candidate for supercapacitor electrodes, ternary metal oxides ZIF 67 exhibit several desirable properties, including a large surface area, porosity, chemical stability, tailoring ability, redox activity, and low environmental impact. The porous polyhedral structure of ZrNiCo ZIF-67, which incorporates connected nanoparticles of varied compositions, greatly enhances the charge storage capacity. They are essential to a robust and sustainable energy future, and they have social, ecological, and economic significance. Electrochemical methods such as cyclic voltammetry (CV), galvanostatic charge and discharge (GCD), and electrochemical impedance spectroscopy (EIS) are among the various characterizations used to assess the electrode\u27s performance. Other approaches include X-ray diffraction to study the crystal structure. With a specific capacitance of 232 F/g at a current density of 1 A/g, the ZrNiCo ZIF-67 (1:2) electrode material performs better than the other ZrNiCo ZIF-67 (1:1) materials. In order to create nanocomposites ZrNiCo ZIF-67 (1:2) with improved electrochemical characteristics, this research provides an easy and practical method. These materials can then be used as electrodes in supercapacitors for high specific capacitance
ASAN MANDI: Digital Transformation of Pakistan’s Fruit and Vegetable Market
Get PDFPakistan’s agricultural sector, particularly its traditional Mandi markets, suffers from inefficiencies due to manual processes that result in time delays & data inaccuracies. ASAN MANDI is a mobile application to automate & centrally manage data for improving productivity, transparent transactions, and profits for farmers and traders. The app is developed using cross-platform technology (Flutter) and integrated primary modules, including electronic billing (e-billing), digital ledger management, real-time inventory tracking system, etc. All testing was conducted on devices with varying specifications to ensure app usability, interface consistency, and the effectiveness of urban and rural study devices. Results highlighted the reductions of manual errors made, time and effort in transaction processing and inventory management, with 88% of users asserting satisfaction towards the intuitiveness of app design as well as bilingual support (Urdu and English). Nonetheless, network dependence in remote regions and user adjustment were some challenges to be addressed in the future. To summarize, ASAN MANDI is a useful platform to address the issues being faced in conventional agricultural markets of Pakistan and could be a role model for other developing economies striving to improve their agricultural productivity
Design and Implementation of a Multi-Strategy Algorithmic Trading Bot
Get PDFThe financial markets require speed and accuracy, and thus, the quick take-up of algorithmic trading systems has ensued. This study presents a hybrid trading bot based on machine learning algorithms and technical indicators such as Moving Average (MA) and Relative Strength Index (RSI). The integration of Random Forest significantly improved signal accuracy and reduced false positives. Back testing over 1 year showed a win rate of 73.2% and a return on investment (ROI) of 42.5%, confirming the effectiveness of the hybrid model. The bot is designed to analyze the market in real-time, and it makes trades autonomously, regulates risk, and adjusts to volatile markets
Trend Analysis and Prediction for Extreme Temperature of Lahore, Pakistan
Get PDFThis paper aims to examine the trends of the maximum temperature (Tmax) and minimum temperature (Tmin) in Lahore over a period of 42 years (1988 to 2029). The study employs the Mann-Kendall statistical test to analyze the linear trends of both Tmin and Tmax annually and seasonally. To determine the linear trends in temperature extremes (Te), a linear curve fitting method was employed. In modeling Tmax and Tmin, a sine function was utilized. The results showed that Tmin exhibited an increasing trend both annually and seasonally, except for winter, where no significant trend was observed. Conversely, Tmax showed a decreasing trend both annually and seasonally, except for the monsoon and pre-monsoon periods, where no significant trends were found. Furthermore, the study divided the Te data from 1988 to 2019 into two time series: from 1988 to 2003 and from 2004 to 2019. The findings indicated that Tmin had no significant trend, while Tmax demonstrated an increasing trend for the first time series. In contrast, both Tmin and Tmax exhibited increasing trends for the second time series. Moreover, when the time series was divided into six parts for trend analysis, mixed trends, whether increasing or decreasing, were observed. To investigate the periodicity of Te, the sine function was applied, and the results showed that Tmin had no periodicity. However, Tmax exhibited periodicity, and it was observed that the peak pattern repeated in reverse after 2004. Based on the proposed sine function model, the study predicted the future pattern of the maximum temperature variation in Lahore for the next ten years (i.e., 2020 to 2029)