International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Home Automation Using Internet of Things and Machine Learning
Get PDFThis paper proposes an energy-efficient home automation system leveraging the Internet of Things (IoT) and machine learning. The system, implemented in Python on a Raspberry Pi, enables remote control of appliances (lights, televisions, air conditioners) via a web interface accessible from any local network device. Machine learning is introduced in the second phase, utilizing linear regression to automate appliance management based on historical data stored in a database. This work demonstrates the feasibility of IoT and machine learning for cost-effective and efficient home automation, laying the groundwork for the future development of database-driven smart homes with advanced machine learning algorithms
The Customer Reviews Analysis Platform by Correlating Sentiment Analysis and Text Clustering
No full textCustomer reviews and feedback are of paramount importance in the improvement cycle of any industry, product, or service. Formerly, product ratings were the basis for performance evaluation and key drivers of improvements. However, ratings were unable to depict the complete picture and were not adequate for an in-depth analysis of any product or service. Hence, customer reviews become the ultimate source of providing feedback for a specific detailed analysis as well as contributing to performance metrics. Although, customer reviews provide a very essential measure for performance evaluation, extracting important features and topics from customer reviews has been challenging due to its unlabeled and variant nature. This paper focuses on extracting topics from customer review data and bringing in use the of implicit knowledge for analytics. To extract topics and clusters from review data, unsupervised machine learning algorithms such as K-Means and Latent Dirichlet Allocation (LDA) are used. These topics are then correlated with sentiment analysis - score of positive or negative feedback - of each customer review. The products or services are then categorized with the help of the topics or domains they belong to alongside the sentiments. This provides a valuable analysis such as the score of positive, neutral, and negative feedback for each customer review input to new customers as well as product managers. This research work aims to use the hotel reviews dataset to categorize and rank hotels based on the different services captured in the text from customer reviews. The research work makes use of the hotel reviews dataset for categorizing and ranking hotels based on the different services discussed in the customer\u27s reviews text. Moreover, this paper also provides a visualization of both text clustering algorithms depicting the topics in each cluster for an insightful analysis
Multi-Digit Number Recognition System: Single-Digit CNNs for Multi-Digit Detection and Recognition Using MNIST Dataset
Get PDFThis research focuses on creating a deep-learning model for identifying multi-digit numbers, which addresses the critical demand for accuracy in real-world applications. The study presents novel approaches to multi-digit recognition, providing a thorough resolution to an unsolved problem in the field of computer vision. In order to improve model generalization, the study makes use of convolutional neural networks (CNNs) that were trained on the MNIST dataset and augmented with rotation and scaling approaches. Multi-digit number prediction is a multi-step process. detection to isolate each digit. Each digit is then clipped and stored separately with its own label. Subsequently, the algorithm predicts the digit for each cropped picture and saves them. This method is repeated for all identified contours, with each predicted digit concatenated to get the final multi-digit prediction. Finally, the projected multi-digit sequence is compared to the ground truth for assessment. The CNN achieves remarkable training and validation accuracies of 99.60% and 99.28%, proving its ability to recognize multi-digit numbers. This study emphasizes the importance of advanced methods in developing deep learning models for multi-digit recognition, which promise enhanced automation and efficiency across a variety of digital technology industries
Change Detection of Land Cover Using Geo-Spatial Techniques in District Hyderabad, Sindh, Pakistan
Get PDFUrban expansion worldwide is leading to significant changes in land cover, with built-up areas increasingly encroaching on agricultural and barren lands. This study utilizes geospatial techniques to analyze land cover changes in District Hyderabad, Sindh, Pakistan, from 2013 to 2023, marking a pioneering effort in this region. Landsat images from 2013, 2018, and 2023, sourced from the US Geological Survey database, were analyzed using the maximum likelihood technique of supervised image classification. Four major land cover classes—vegetation cover, built-up land, water bodies, and barren land—were identified. The analysis reveals a notable increase in built-up areas, rising from 41% in 2013 to 68% in 2023. In contrast, vegetation cover has decreased by 14%, water bodies by 6%, and barren land by 7% over the past decade. These changes indicate Hyderabad\u27s shift from a rural to an urban landscape, driven by socioeconomic development. The findings underscore the importance of sustainable development practices that reconcile urban growth with environmental preservation. This study provides essential data for urban planning, conservation efforts, and further research on land cover dynamics
A Systematic Review of Desertification Identification with Multispectral LANDSAT Image and Deep Learning Models
Get PDFThe use of multispectral Landsat images and deep learning models for desertification detection has been reviewed in this research. The role of deep learning models is found to significantly increase the identification accuracy of the researchers, complemented by the inclusion of Landsat imagery to capture key desertification indicators. The research reviews difficulties including geographical resolution, data variability, uncertainty, and validation, alongside different desertification identification methods, techniques, advancement, and limitations. The research also highlighted the necessity of historical data, data continuity, and data fusion, among other issues on data availability and quality. The research advocates for the combination of high-resolution photography, climate and weather data, and socioeconomic data for better desertification detection while the research has identified more complex deep learning architectures, better uncertainty estimation, explainability and interpretability improvement, and the integration of process-based models as potential areas of research. The research concludes by highlighting the importance of precise desertification identification in effective land administration and ecological preservation
Enhancing Security in Mobile Cloud Computing: An Analysis of Authentication Protocols and Innovation
Get PDFIntroduction/Importance of Study: Cloud computing is a model facilitating ubiquitous, convenient, and on-demand network access to a shared pool of computing resources, offering flexibility, reliability, and scalability .
Objective: This study investigates authentication mechanisms in Mobile Cloud Computing (MCC) to enhance security and address emerging challenges.
Novelty statement: Our research contributes novel insights into authentication protocols in MCC, offering solutions to security issues not previously addressed.
Material and Method: The study analyzed various authentication mechanisms in MCC using NIST evaluation criteria, considering their alignment with security needs and resource constraints.
Result and Discussion: Our findings underscore the importance of selecting authentication mechanisms that balance security and performance in MCC environments, highlighting the need for ongoing innovation in security measures.
Concluding Remarks: The study emphasises the significance of robust authentication protocols tailored to MCC\u27s unique security requirements for ensuring data integrity and privacy
Using Spatial Covariance of Geometric and Shape Based Features for Recognition of Basic and Compound Emotions
Get PDFIntroduction. Compound emotion recognition has been an emerging area of research for the last decade due to its vast applications in surveillance systems, suspicious person detection, detection of mental disorders, pain detection, automated patient observation in hospitals, and driver monitoring.
Objectives: This study focuses on emotions, highlighting the fact that the existing knowledge lacks adequate research on compound emotions. This research work emphasizes compound emotions along with basic emotions.
Novelty Statement: The contribution of this paper is three-fold. The study proposes an approach relying on geometric and shape-based features using SVM and then fusing the obtained geometric and shape-based features for both basic as well as compound emotion recognition.
Materials and Method: This study provides a comparison with six state-of-the-art approaches in terms of percentage accuracy and time.
Dataset: The experiments are performed on a publicly available compound emotion recognition dataset that contains images with facial fiducial points and action units.
Result and Discussion: The results show that the proposed approach outperforms the existing approaches. The best accuracy achieved is 98.57% and 77.33% for basic and compound emotion recognition, respectively. The proposed approach is compared with existing state-of-the-art deep Neural Network architecture. The comparison of the proposed approach has been extended further to various existing classifiers both in terms of percentage accuracy and time.
Concluding Remarks: The extensive experiments reveal that the proposed approach using SVM outperforms the state-of-the-art deep Neural network architecture and existing classifiers including Naive Bayes, AdaBoost, Decision Table, NNge, and J48
Evaluating and Predicting the Land Use Land Cover Changes and its Impact on Land Surface Temperature using CA-Markov model: A study of District Mardan, Pakistan
Get PDFThe Rapid population growth is a global phenomenon that reshapes landscapes and impacts environmental conditions. This study aims to analyze the effects of urbanization on Land Use Land Cover (LULC) changes and their impact on Land Surface Temperature (LST) in District Mardan from 2002 to 2022, while also predicting future LULC and LST changes for the year 2042. Utilizing remotely sensed data and Geographic Information Systems (GIS), the study evaluates the correlation between the conversion of natural landscapes to built-up areas and the resulting changes in LST. The primary objectives are to investigate LULC changes over the past two decades, examine how these changes influence LST, and forecast future LULC and LST trends using the CA-Markov model in IDRISI SILVA software for 2042. The analysis of LULC changes from 2002 to 2022 reveals a significant increase in built-up areas and a decrease in vegetation. Built-up land expanded from 10.10% in 2002 to 16.28% in 2022, representing a 6% increase, while vegetation cover decreased by nearly 10% of the total land cover. Concurrently, LST data show that areas experiencing high temperatures have increased since 2002. In 2002, 37% of the total area had temperatures below 30°C, whereas this figure dropped to 28% by 2022. Correlation between LULC and LST indicates that barren surfaces and built-up regions experience higher temperatures, while areas with vegetation and water exhibit lower and more moderate temperatures. The CA-Markov model forecasts that built-up land will increase by 19% by 2042, continuing the current trend, while vegetation areas are expected to decrease by an additional 4% from their 2022 levels. The LST analysis suggests a further increase in high-temperature areas, with a predicted 3% decrease in low-temperature regions. This research highlights the historical trajectory of urbanization and its thermal effects in District Mardan, providing critical insights for sustainable land-use planning and strategies to mitigate urban heat island effects in the coming decades
Energy-Based Cluster Head Selection in WSN
Get PDFWireless Sensor Networks (WSN) are the collection of sensor nodes, deployed in an ad hoc fashion and mostly powered by batteries. Therefore, efficient energy utilization has remained a vital parameter in designing and developing of WSNs to extend the network lifetime. In any network, routing protocols operate for selecting routes for the transfer of data packets from source to destination. Ad Hoc On-Demand Distance Vector (AODV) is a routing protocol used in various wireless ad hoc networks for transmitting data from source node to destination through intermediate motes. Hence, the efficient path selection mechanism can significantly improve energy utilization and elongate the lifetime of the network. This paper provides an investigation using the AODV routing protocol, based on the Cluster Head (CH) selection mechanism and shortest path selection between a source node, CH, and sink using multi-hop communication. The proposed scenarios significantly reduce energy consumption by selecting the shortest path between the source, cluster head, and sink. The Matlab simulation results show the comparison between AODV and Cluster head-based AODV (CH-AODV), indicating the CH-AODV consumes much less energy compared to normal AODV protocol
A Detecting Land Use Land Cover Changes Induced by the Dynamics of River Indus, Pakistan, from 1972 -2022, Using Remote Sensing and GIS Techniques
No full textIntroduction/Importance of Study: This study evaluates the shifting of the Indus River and its impact on land use and land cover from 1972 to 2022 using Geographic Information System (GIS) and Remote Sensing (RS) techniques.
Novelty Statement: This research uniquely addresses the intricate relationship between river shifting and LULC changes, providing new insights into flood management and land use planning. Chronic alluvium erosion due to the river\u27s fast flow has led to poverty among residents and annual national asset losses, affecting the economy.
Material and Method: Using satellite images from 1972 to 2022, the research employed GIS and remote sensing techniques to analyse river sinuosity, channel migration, erosion, and accretion patterns, along with LULC changes. Methods included calculating the Indus River\u27s sinuosity index, assessing channel and bank migration, and applying the Normalized Difference Water Index and maximum likelihood classification for accurate LULC assessment.
Result and Discussion: Long-term results indicated that river erosion influenced land area, increasing settlement areas, decreasing vegetation, and causing fluctuations in barren land, water bodies, and agricultural land. Built-up areas expanded considerably, indicating population growth in floodplains. Erosion and deposition have notably affected agricultural and settlement areas, leading to socio-economic stress and internal migration. Satellite images taken during spring and dry seasons (March to May) showed minimal stream flow due to lower rainfall. Maximum erosion and management plans are critical for Reaches A, B, C, H, I, and J from 1972 to 2022. Minor embankment improvements are necessary for these reaches, as initial migration occurred on the right side for Reaches A, B, and C, shifted to the left from D to G, and affected both sides from H to J.
Concluding Remark: This research highlights how important GIS and remote sensing are for studying river changes and their effects on land use. It provides valuable information to help make better decisions about managing floods and planning land use