International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Adaptive clustering in energy efficient routing protocol for mobile nodes in WSNs
Get PDFIntroduction: Wireless Sensor Networks (WSN) is a collection of large number of small sensor nodes which communicate sensed data over a radio channel covering wide geographical region.
Problem statement: A number of algorithms have been developed to enhance the network lifetime of WSN by efficiently utilizing the sources of energy. The most commonly used approach is clustering that is prone to uneven load balancing and instability issues. Furthermore, topological changes in WSN structure especially with mobile nodes significantly effect network lifetime.
Methodology: In this study, we have proposed an Adaptive-Cluster-based Energy Efficient Routing Protocol (A-EECBRP), which employs a novel geometrical Voronoi-based configuration to solve load balancing and mobility issues while maintaining network stability and coverage. Furthermore, energy cost function and Energy Harvesters (EH) devices were implemented to reduce energy consumption and increase network life. Moreover, the concept of handshaking and random waypoint model for nodes movement between cluster groups was examined to define mobile nodes.
Results: Simulation results obtained from network analysis performed on MATLAB® showed that A-EECBRP reduced energy consumption by almost 1500 rounds as compared to LEACH-M. This significantly improved the network lifetime of WSN as compared to the LEACH-M routing protocol. Therefore, our proposed scheme provides a huge potential for implementing energy-efficient routing protocols in mobile wireless sensor networks
Interpretation of Expressions through Hand Signs Using Deep Learning Techniques
Get PDFIt is a challenging task to interpret sign language automatically, as it comprises high-level vision features to accurately understand and interpret the meaning of the signer or vice versa. In the current study, we automatically distinguish hand signs and classify seven basic gestures representing symbolic emotions or expressions like happy, sad, neutral, disgust, scared, anger, and surprise. Convolutional Neural Network is a famous method for classifications using vision-based deep learning; here in the current study, proposed transfer learning using a well-known architecture of VGG16 to speed up the convergence and improve accuracy by using pre-trained weights. We obtained a high accuracy of 99.98% of the proposed architecture with a minimal and low-quality data set of 455 images collected by 65 individuals for seven hand gesture classes. Further, compared the performance of VGG16 architecture with two different optimizers, SGD, and Adam, along with some more architectures of AlexNet, LeNet05, and ResNet50.
Impact of Land-use Change on Agricultural Production & Accuracy Assessment through Confusion Matrix
Get PDFLand modification and its allied resources have progressively become a severe problem presently pulling the worldwide attention and now it rests at the central point of the conservation of the environment and sustainability. The present research aimed to examine the land-use changes and their impact on agricultural production using remote sensing and GIS techniques over the study area that comprised of Tehsil Shorkot, District Jhang, Punjab, Pakistan. Images were pre-processed by using the Arc GIS and ERDAS Imagine 15 software for stacking of the layers, sub-setting, and mosaicking of the satellite bands. After the pre-processing of the images, supervised image classification scheme was applied by employing a maximum likelihood algorithm to recognize the land-use changes which have been observed in the area under study. The area under water was occupied 9.6 km2 in 2010 that increased to 21.04 km2 in 2015 and decreased to 19.4 km2in 2020. Built-up land was 16.6 km2 in 2010 that increased to 19.4 km2 in 2015 and 26.8 km2 in 2020. The total area under vegetation was computed as 513.2 km2 in 2010 that increased to 601.6km2 in 2015 and further increased to 717.7 km2in 2020. Forest land use showed decreasing trend as the covered area in 2010 was occupied 90.8 km2 that decreased to 86.7 km2 in 2015 and further decreased to 61.84 km2 in 2020. In 2010, barren land use was occupied 528.54 km2 that considerably decreased to 429.64 km2 in 2015 further decreased to 333.1 km2 in 2020. Barren land drastically decreased into watered, built-up, and vegetation land uses. The findings of this study will be helpful for the future conservation of various land-use types, urban and regional planning, and an increase in agricultural production of various crops in the study area.
Full Tex
Performance Evaluation of Classification Algorithms for Intrusion Detection on NSL-KDD Using Rapid Miner
Get PDFThe rapid advancement of the internet and its exponentially increasing usage has also exposed it to several vulnerabilities. Consequently, it has become an extremely important that can prevent network security issues. One of the most commonly implemented solutions is Intrusion Detection System (IDS) that can detect unusual attacks and unauthorized access to a secured network. In the past, several machine learning algorithms have been evaluated on the KDD intrusion dataset. However, this paper focuses on the implementation of the four machine learning algorithms: KNN, Random Forest, gradient boosted tree and decision tree. The models are also implemented through the Auto Model feature to determine its convenience. The results show that Gradient Boosted trees have achieved the highest accuracy (99.42%) in comparison to random forest algorithm that achieved the lowest accuracy (93.63%).
Full Tex
A Comparative Analysis of Camera, LiDAR and Fusion Based Deep Neural Networks for Vehicle Detection
Get PDFSelf-driving cars are an active area of interdisciplinary research spanning Artificial Intelligence (AI), Internet of Things (IoT), embedded systems, and control engineering. One crucial component needed in ensuring autonomous navigation is to accurately detect vehicles, pedestrians, or other obstacles on the road and ascertain their distance from the self-driving vehicle. The primary algorithms employed for this purpose involve the use of cameras and Light Detection and Ranging (LiDAR) data. Another category of algorithms consists of a fusion between these two sensor data. Sensor fusion networks take input as 2D camera images and LiDAR point clouds to output 3D bounding boxes as detection results. In this paper, we experimentally evaluate the performance of three object detection methods based on the input data type. We offer a comparison of three object detection networks by considering the following metrics - accuracy, performance in occluded environment, and computational complexity. YOLOv3, BEV network, and Point Fusion were trained and tested on the KITTI benchmark dataset. The performance of a sensor fusion network was shown to be superior to single-input networks.
Full Tex
Tomato Disease Classification using Fine-Tuned Convolutional Neural Network
Get PDFTomatoes have enhanced vitamins that are necessary for mental and physical health. We use tomatoes in our daily life. The global agricultural industry is dominated by vegetables. Farmers typically suffer a significant loss when tomato plants are affected by multiple diseases. Diagnosis of tomato diseases at an early stage can help address this deficit. It is difficult to classify the attacking disease due to its range of manifestations. We can use deep learning models to identify diseased plants at an initial stage and take appropriate measures to minimize loss through early detection. For the initial diagnosis and classification of diseased plants, an effective deep learning model has been proposed in this paper. Our deep learning-based pre-trained model has been tuned twofold using a specific dataset. The dataset includes tomato plant images that show diseased and healthy tomato plants. In our classification, we intend to label each plant with the name of the disease or healthy that is afflicting it. With 98.93% accuracy, we were able to achieve astounding results using the transfer learning method on this dataset of tomato plants. Based on our understanding, this model appears to be lighter than other advanced models with such considerable results and which employ ten classes of tomatoes. This deep learning application is usable in reality to detect plant diseases.
Full Tex
Efficacy of Flood relief measures - 2010: A case study of district Layyah, Punjab-Pakistan
No full textIn 2010, Pakistan experienced a massive flood that took the lives of 1985 individuals, in addition to causing huge damage to livestock, shelters, and domestic goods. Multiple local and international organizations extended support to the victims of the 2010 Pakistan flood. Beside relief support, media highly criticized their relief activities. The study was conducted in the district of Layyah, in the Punjab province of Pakistan. The study primarily aims at determining aspects of the flood relating to: ground situation and extent of damages, quality of services provided by the government and non-government organizations (NGOs). The study gathers data and analysis of data was carried out with simple statistical techniques. Ground situation in the country appeared alarming: flood affected 160,000 square kilometer of land, damaged to crop approached US$ 0ne billion, and affected around 20 million people. In the study area 40 % of livestock could not survive, 94.5 % houses were completed abolished and 38.7 % of domestic goods were heavily damaged. District government role was appreciated by 66.4 % of the respondents. Around 50 % of the respondents reported against the performance of the Provincial Disaster Management Authority and National Disaster Management Authority. 96.2 % of the respondents recognized the role of NGOs while respondents suggested working of NGOs through district governments.
Full Tex
Prospects of Biosynthetically produced Nanoparticles in Biocontrol of Pests and Phytopathogens: A review: Prospects of Biosynthetically produced Nanoparticles in Biocontrol of Pests and Phytopathogens
No full textModern nanotechnology is playing a vital role in our daily life by contributing in different domains such as usage of nanoparticles for target-specific drug delivery system, as these nanoparticle are being used as scratch proof coating on glass for tracking of biomolecules. Some emerging applications of nanoparticles include usage of nanoparticles for diagnostic purposes such as biomedical imaging and as green technology producing nano pesticides. The use of endophytic or plant beneficial bacteria for the production of metallic nanoparticles have shown promising results in not only controlling the pest but also contributing in enhanced developmental growth due to their small size, target specificity, and enhanced interaction with the plant in controlled environment. As for increasing environmental crisis, use of biological methods to remediate the environment is becoming a necessity. Green technology based nano-materials being used now a days in multiple fields, especially in bio-control of pests. This review is based on the microbial synthesized metallic nanoparticles, which are being used as nano pesticides (nanoparticles are pesticides)
A Study of Reasons behind Unproductivity and Indecisiveness in public Institutions of Urban Planning in Pakistan
Get PDFUrban Planning plays a crucial role in managing the systematic growth of the cities. Over time, it has been observed that institutions dealing with the planning, development & regulations are suffering from unproductivity because of numerous reasons. The objective of the study is to find the social, psychological, administrative, structural & academic factors affecting the most in the non-performance and unproductivity of the institutions dealing with the Urban Planning & Development and their respective severity so that the causes of those factors could be evaluated & so as remedial measures & reforms could be suggested. The performance evaluation is needed for the organizations working in the Urban Planning field. Otherwise, the Master plan/strategic plan/ development plan will remain merely an academic concept. It’s about giving a chance to look deep inside your organization to enhance its efficiency and effectiveness
Floristic Composition, Biological Spectrum and Distribution Pattern of Floral Biodiversity in Jalalabad Taisot Valley, Gilgit Baltistan
Get PDFJalalabad is a small village in Gilgit District in Pakistan, located around 20 km east of Gilgit city. Jalalabad village is one of the beautiful valleys located at 35°53.921 N latitude, 074°29.382 E longitude at an altitude of 1500. The present study was carried out from July-August 2021-2022 and was comprised of two main parts. The first part was floristic diversity, the second part was phytosociological studies. The collected specimens consist of (156) plant species that belonged to 119 genera and 49 families. The life forms of the collected species were 62 (72%) where Hemicryptophyte were dominant, 33 (22%) Therophytes, 14 (9%) Chaemophyte, 42 (27%) Phanerophyte and Geophytes were 4 (2%). The breakup of the habit categories shows that the herbs with 103 (66%) species were dominant to show the flora of the study area, followed by shrubs with 17 (10%) species which shows the flora of the study area. Subshrubs by 9 (6%) and trees 27 (22%) contained the flora of the study area. We studied three stands and in each stand, we placed twenty quadrate to recognize the dominant flora based on IVI. We recognized the dominant lifeform Hemicryptophytes and dominant taxa Thaymus linearis held at the highest value (64.259) based on IVI. The phytosociological studies provided all required information from each stand like dominant habit categories, dominant life forms, and dominant taxa in the study area.