Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099214
Fazal Hussain Awan, Aliya Anwar, K. Jamil, Rana Faizan Gul, Sohaib Mustafa, Shah Muhammad Bajkani
The main objective of this study is to examine the status and challenges of green human resource management practices in Pakistan. Additionally, it proposes a theoretical framework to fill the acknowledged gaps and build a sustainable environment. The study also examines the mediating effect of employee loyalty and organizational commitment between GHRM and employee work performance within renewable projects in Pakistan. To conduct this study, the structural equation modeling method was adopted; variables were analyzed to check the direct and indirect effects on work performance. Furthermore, a survey was conducted on 384 employees from renewable energy projects in Pakistan, selected through stratified random sampling. The findings of this study reveal that implementing green human resource practices will have a spillover effect on employees' work performance.
{"title":"Impact of green human resource practices on work performance of Renewable Projects in Pakistan","authors":"Fazal Hussain Awan, Aliya Anwar, K. Jamil, Rana Faizan Gul, Sohaib Mustafa, Shah Muhammad Bajkani","doi":"10.1109/iCoMET57998.2023.10099214","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099214","url":null,"abstract":"The main objective of this study is to examine the status and challenges of green human resource management practices in Pakistan. Additionally, it proposes a theoretical framework to fill the acknowledged gaps and build a sustainable environment. The study also examines the mediating effect of employee loyalty and organizational commitment between GHRM and employee work performance within renewable projects in Pakistan. To conduct this study, the structural equation modeling method was adopted; variables were analyzed to check the direct and indirect effects on work performance. Furthermore, a survey was conducted on 384 employees from renewable energy projects in Pakistan, selected through stratified random sampling. The findings of this study reveal that implementing green human resource practices will have a spillover effect on employees' work performance.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124768837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099261
Sara Javed, S. Anwar, M. Umair
Lung cancer is considered as one of the most significant causes of deaths globally. Diagnosis at an initial stage, using computed tomography chest scans could give a better chance to the patient to survive by providing an opportunity for effective care plans and treatment. We propose a new deep-learning method to learn high level image representation towards attaining a significant classification accuracy. This technique consists of three important steps, which are data preparation, pre-processing of data, and classification. The proposed model is a multi-layer convolutional neural network (CNN) that uses different convolutional layers, pooling layers, flatten, dense layers, dropout layers, and performs classification. Two pretrained models which are VGG16 and Densenet, that takes weights using ImageNet pretraining are also employed. This work utilized chest CT-scan image dataset. The dataset contains the images in PNG or JPG format which are suitable for the model. The data contains three types of chest cancers which are adenocarcinoma, large cell carcinoma, and squamous cell carcinoma as well as normal controls. Our experimental results showed that the proposed models achieved the maximum accuracy of 99.75% using the multi-layer CNN model, of 97.25% using Densenet-201, and of 96% using VGG-16.
{"title":"Multi-layer Convolutional Approach for Lung Cancer Detection using CXR","authors":"Sara Javed, S. Anwar, M. Umair","doi":"10.1109/iCoMET57998.2023.10099261","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099261","url":null,"abstract":"Lung cancer is considered as one of the most significant causes of deaths globally. Diagnosis at an initial stage, using computed tomography chest scans could give a better chance to the patient to survive by providing an opportunity for effective care plans and treatment. We propose a new deep-learning method to learn high level image representation towards attaining a significant classification accuracy. This technique consists of three important steps, which are data preparation, pre-processing of data, and classification. The proposed model is a multi-layer convolutional neural network (CNN) that uses different convolutional layers, pooling layers, flatten, dense layers, dropout layers, and performs classification. Two pretrained models which are VGG16 and Densenet, that takes weights using ImageNet pretraining are also employed. This work utilized chest CT-scan image dataset. The dataset contains the images in PNG or JPG format which are suitable for the model. The data contains three types of chest cancers which are adenocarcinoma, large cell carcinoma, and squamous cell carcinoma as well as normal controls. Our experimental results showed that the proposed models achieved the maximum accuracy of 99.75% using the multi-layer CNN model, of 97.25% using Densenet-201, and of 96% using VGG-16.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126853691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10109001
Sapna Kumari, Muhammad Owais Raza, Arsha Kumari
In the last few decades, tremendous change is observed in rainfall patterns which are majorly influenced by two major factors 1) climate change and 2) CO2 emission. Erratic rainfall patterns caused catastrophic effects on agriculture and human life in developing countries like Pakistan, where major economic growth is largely dependent on agriculture. The main objective of this study is to evaluate a performance different Machine learning algorithms for forecasting rainfall patterns using dimensionality reduction techniques on climate change indicators. For this purpose rainfall data was collected for Pakistan. Principle component analysis (PCA), Pearson correlation, and Greedy search algorithms were used for feature selection and the evolution of models was performed using Root Mean Square error (RMSE), Root Absolute Error (RAE), and Coefficient of determination metrics. Results show that features obtained using the Pearson correlation produced the least error and Bayesian linear regression performed with the highest accuracy followed by Neural Network regression.
在过去的几十年里，降雨模式发生了巨大的变化，这主要受到两个主要因素的影响:1)气候变化和2)二氧化碳排放。在巴基斯坦等主要经济增长主要依赖农业的发展中国家，不稳定的降雨模式对农业和人类生活造成了灾难性影响。本研究的主要目的是评估使用气候变化指标降维技术预测降雨模式的不同机器学习算法的性能。为此目的收集了巴基斯坦的降雨数据。使用主成分分析(PCA)、Pearson相关和贪心搜索算法进行特征选择，并使用均方根误差(RMSE)、根绝对误差(RAE)和决定系数(Coefficient of determination)指标进行模型进化。结果表明，使用Pearson相关性获得的特征误差最小，贝叶斯线性回归获得的特征精度最高，其次是神经网络回归。
{"title":"Performance Evaluation Of Machine Learning Algorithms For Rainfall Prediction Using Dimensionality Reduction Techniques","authors":"Sapna Kumari, Muhammad Owais Raza, Arsha Kumari","doi":"10.1109/iCoMET57998.2023.10109001","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10109001","url":null,"abstract":"In the last few decades, tremendous change is observed in rainfall patterns which are majorly influenced by two major factors 1) climate change and 2) CO2 emission. Erratic rainfall patterns caused catastrophic effects on agriculture and human life in developing countries like Pakistan, where major economic growth is largely dependent on agriculture. The main objective of this study is to evaluate a performance different Machine learning algorithms for forecasting rainfall patterns using dimensionality reduction techniques on climate change indicators. For this purpose rainfall data was collected for Pakistan. Principle component analysis (PCA), Pearson correlation, and Greedy search algorithms were used for feature selection and the evolution of models was performed using Root Mean Square error (RMSE), Root Absolute Error (RAE), and Coefficient of determination metrics. Results show that features obtained using the Pearson correlation produced the least error and Bayesian linear regression performed with the highest accuracy followed by Neural Network regression.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129254037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099161
Z. U. Kamangar, G. Shaikh, Saif Hassan, Nimra Mughal, U. A. Kamangar
The dependence on digital images is increasing in different fields. i.e, education, business, medicine, or defense, as they are shifting towards the online paradigm. So, there is a dire need for computers and other similar machines to interpret information related to these images and help the users understand the meaning of it. This has been achieved with the help of automatic Image captioning using different prediction models, such as machine learning and deep learning models. However, the problem with the traditional models, especially machine learning models, is that they may not generate a caption that accurately represents that Image. Although deep learning methods are better for generating captions of an image, it is still an open research area that requires a lot of work. Therefore, a model proposed in this research uses transformers with the help of attention layers to encode and decode the image token. Finally, it generates the image caption by identifying the objects along with their colours. The fliker8k and Conceptual Captions datasets are used to train this model, which contains images and captions. The fliker8k contains 8,092 images, each with five captions, and Conceptual Captions contains more than 3 million images, each with one caption. The contribution of this presented work is that it can be utilized by different companies, which require the interpretation of diverse images automatically and the naming of the images to describe some scenario or descriptions related to the images. In the future, the accuracy can be increased by increasing the number of images and captions or incorporating different deep-learning techniques.
{"title":"Image Caption Generation Related to Object Detection and Colour Recognition Using Transformer-Decoder","authors":"Z. U. Kamangar, G. Shaikh, Saif Hassan, Nimra Mughal, U. A. Kamangar","doi":"10.1109/iCoMET57998.2023.10099161","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099161","url":null,"abstract":"The dependence on digital images is increasing in different fields. i.e, education, business, medicine, or defense, as they are shifting towards the online paradigm. So, there is a dire need for computers and other similar machines to interpret information related to these images and help the users understand the meaning of it. This has been achieved with the help of automatic Image captioning using different prediction models, such as machine learning and deep learning models. However, the problem with the traditional models, especially machine learning models, is that they may not generate a caption that accurately represents that Image. Although deep learning methods are better for generating captions of an image, it is still an open research area that requires a lot of work. Therefore, a model proposed in this research uses transformers with the help of attention layers to encode and decode the image token. Finally, it generates the image caption by identifying the objects along with their colours. The fliker8k and Conceptual Captions datasets are used to train this model, which contains images and captions. The fliker8k contains 8,092 images, each with five captions, and Conceptual Captions contains more than 3 million images, each with one caption. The contribution of this presented work is that it can be utilized by different companies, which require the interpretation of diverse images automatically and the naming of the images to describe some scenario or descriptions related to the images. In the future, the accuracy can be increased by increasing the number of images and captions or incorporating different deep-learning techniques.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127678465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099224
Maaz Ahmad, Muhammad Yousaf Ali Khan, E. Mustafa, Nazar Hussain Baloch, Muhammad Ali Khan
Electricity demand has increased intensively in all sectors around the globe from the last decade. Due to industrial revolution, changes in life style and more trends toward urbanization has compelled the researchers to come up with more innovative and smart ideas to use the non-conventional energy resources to meet the desired future electricity demand. Due to greenhouse gases (GHG) and CO2 emission, the fossils fuel based power plants have badly affected the environment, which resulted in natural disasters like heat waves and flood warnings around the universe. Power sector of Pakistan is facing energy crisis since last decade due to demand and supply gap. The country faced short fall of approximately 7000 MW in August 2022. China Pakistan Economic Corridor (CPEC) and Gawadar Port has highlighted the geographical position of Pakistan across the world. The country has huge potential of Renewable Energy Resources (Solar and Wind) in southern areas of Sindh and Baluchistan. In this paper, the ultimate solution is its advantages and future scope to transmit high power over long distance along with its future prospective will be discussed. The High Voltage Direct Current (HVDC) transmission seems to be an ideal opportunity to transmit such bulk amount of power from the southern areas to the load centers due to low line losses, better utilization of conductor size and less prone towards Ferranti rise effect for long distance transmission. Successful operation of Matiari-Lahore Bipolar HVDC Transmission line having ratings $boldsymbol{pm 660}$ KV has pushed the planners to take into account HVDC transmission to integrate Hydel Power Resources of Northern areas into National Grid.
{"title":"Future Prospective of HVDC System in Pakistan","authors":"Maaz Ahmad, Muhammad Yousaf Ali Khan, E. Mustafa, Nazar Hussain Baloch, Muhammad Ali Khan","doi":"10.1109/iCoMET57998.2023.10099224","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099224","url":null,"abstract":"Electricity demand has increased intensively in all sectors around the globe from the last decade. Due to industrial revolution, changes in life style and more trends toward urbanization has compelled the researchers to come up with more innovative and smart ideas to use the non-conventional energy resources to meet the desired future electricity demand. Due to greenhouse gases (GHG) and CO2 emission, the fossils fuel based power plants have badly affected the environment, which resulted in natural disasters like heat waves and flood warnings around the universe. Power sector of Pakistan is facing energy crisis since last decade due to demand and supply gap. The country faced short fall of approximately 7000 MW in August 2022. China Pakistan Economic Corridor (CPEC) and Gawadar Port has highlighted the geographical position of Pakistan across the world. The country has huge potential of Renewable Energy Resources (Solar and Wind) in southern areas of Sindh and Baluchistan. In this paper, the ultimate solution is its advantages and future scope to transmit high power over long distance along with its future prospective will be discussed. The High Voltage Direct Current (HVDC) transmission seems to be an ideal opportunity to transmit such bulk amount of power from the southern areas to the load centers due to low line losses, better utilization of conductor size and less prone towards Ferranti rise effect for long distance transmission. Successful operation of Matiari-Lahore Bipolar HVDC Transmission line having ratings $boldsymbol{pm 660}$ KV has pushed the planners to take into account HVDC transmission to integrate Hydel Power Resources of Northern areas into National Grid.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131462851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099289
Soonh Taj, G. Shaikh, Saif Hassan, Nimra
Speech Emotion Recognition (SER) is a process for recognizing emotions hidden in speech. The main approaches used for SER include speech signal processing which utilizes acoustic speech features. Much research is being conducted to find emotions from famous and widely spoken languages like English, German, and others. However, SER for low-resource languages is still in the growing phase. In this regard, few authors have worked on SER of low resources languages like Persian, Arabic, Urdu, Punjabi, Pushto, and Sindhi. The existing work has limitations like few publicly available datasets and a lack of robustness in their SER model. This study contributes to developing a robust SER model for the Urdu language, leveraging spectral speech features' power and the latest deep learning techniques based on 1D-CNN (Convolutional Neural Network) architecture to recognize Urdu speech emotions. This study uses the first Urdu language benchmark speech dataset, “URDU”, publicly available for SER research. The effectiveness and robustness of the proposed model are proved from experiments. The proposed model based on 1D-CNN architecture achieved the highest ever accuracy of 97% compared to existing work and improved baseline accuracy for the “URDU” dataset.
{"title":"Urdu Speech Emotion Recognition using Speech Spectral Features and Deep Learning Techniques","authors":"Soonh Taj, G. Shaikh, Saif Hassan, Nimra","doi":"10.1109/iCoMET57998.2023.10099289","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099289","url":null,"abstract":"Speech Emotion Recognition (SER) is a process for recognizing emotions hidden in speech. The main approaches used for SER include speech signal processing which utilizes acoustic speech features. Much research is being conducted to find emotions from famous and widely spoken languages like English, German, and others. However, SER for low-resource languages is still in the growing phase. In this regard, few authors have worked on SER of low resources languages like Persian, Arabic, Urdu, Punjabi, Pushto, and Sindhi. The existing work has limitations like few publicly available datasets and a lack of robustness in their SER model. This study contributes to developing a robust SER model for the Urdu language, leveraging spectral speech features' power and the latest deep learning techniques based on 1D-CNN (Convolutional Neural Network) architecture to recognize Urdu speech emotions. This study uses the first Urdu language benchmark speech dataset, “URDU”, publicly available for SER research. The effectiveness and robustness of the proposed model are proved from experiments. The proposed model based on 1D-CNN architecture achieved the highest ever accuracy of 97% compared to existing work and improved baseline accuracy for the “URDU” dataset.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131839606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099134
Saqib Ali, Rasheed Ahmad Shah, Farhan H. Malik, Hussain Sattar Hashmi
Large-sized industrial buildings with high amount of energy requirements are considered industrial microgrids (IμGs). Thus this type of customer needs to attempt to concentrate on optimum intra-building power handling as well as bi-directional energy transfer between the grid and IμG. For this purpose, a bi-level control is required that supervises building-level benefits as well as utility-level incentives at the same time by achieving an optimal compromise between resilience and performance. The proposed control is verified under deterministic and stochastic conditions. Recurrent outages on the electric and natural gas networks as well as intermittent solar irradiation are examples of unpredictable situations. To convert the risk-neutral controller into a risk-averse one and protect the system from load loss during unpredictable carrier interruptions, conditional value at risk has been applied to the objective function. According to simulations, the suggested risk-averse control improves the ability of station battery and plug-in hybrid electric automobiles to retain energy by +22.03% and +20.14%, respectively. To determine an ideal solution more speedily, this research also created a powerful solution methodology by fusing the revised flower pollination algorithm (FPA) and mixed-integer linear programming. By evaluating the results of the suggested unique hybrid algorithm with those of previously established algorithms such as the Salp Swarm Algorithm, Grasshopper Optimization Algorithm, Polar Bear Algorithm, Coyote Optimization, and Two Cored FPA, the proposed algorithm has been validated. Results show a 7.29% decrease in energy cost, a 22.93% decline in GHG emissions, and a 42.253% saving in execution time.
{"title":"Energy Management System in Industrial Microgrids","authors":"Saqib Ali, Rasheed Ahmad Shah, Farhan H. Malik, Hussain Sattar Hashmi","doi":"10.1109/iCoMET57998.2023.10099134","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099134","url":null,"abstract":"Large-sized industrial buildings with high amount of energy requirements are considered industrial microgrids (IμGs). Thus this type of customer needs to attempt to concentrate on optimum intra-building power handling as well as bi-directional energy transfer between the grid and IμG. For this purpose, a bi-level control is required that supervises building-level benefits as well as utility-level incentives at the same time by achieving an optimal compromise between resilience and performance. The proposed control is verified under deterministic and stochastic conditions. Recurrent outages on the electric and natural gas networks as well as intermittent solar irradiation are examples of unpredictable situations. To convert the risk-neutral controller into a risk-averse one and protect the system from load loss during unpredictable carrier interruptions, conditional value at risk has been applied to the objective function. According to simulations, the suggested risk-averse control improves the ability of station battery and plug-in hybrid electric automobiles to retain energy by +22.03% and +20.14%, respectively. To determine an ideal solution more speedily, this research also created a powerful solution methodology by fusing the revised flower pollination algorithm (FPA) and mixed-integer linear programming. By evaluating the results of the suggested unique hybrid algorithm with those of previously established algorithms such as the Salp Swarm Algorithm, Grasshopper Optimization Algorithm, Polar Bear Algorithm, Coyote Optimization, and Two Cored FPA, the proposed algorithm has been validated. Results show a 7.29% decrease in energy cost, a 22.93% decline in GHG emissions, and a 42.253% saving in execution time.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128930912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099271
Sheharyar Khan, S. M. A. Shah, Sadam Hussain Noorani, Aamir Arsalan, M. Ehatisham-ul-Haq, Aasim Raheel, Wakeel Ahmed
Recent years have seen rapid advancements in the human activity recognition field using data from smart sensor devices. A wide variety of real-world applications can be found in different domains, particularly health and security. Smartphones are common devices that let people do a wide range of everyday tasks anytime, anywhere. The sensors and networking capabilities found in modern smartphones enable context awareness for a wide range of applications. This research mainly focuses on recognizing human activities in the wild for which we selected an in-the-wild extra-sensory dataset. Six human activities i.e., lying down, sitting, standing, running, walking, and bicycling are selected. Time domain features are extracted and human activity recognition is performed using three different machine learning classifiers i.e., random forest, k-nearest neighbors, and decision trees. The proposed human activity recognition scheme resulted in the highest classification accuracy of 89.98%, using the random forest classifier. Our proposed scheme outperforms the state-of-the-art human activity recognition schemes in the wild.
{"title":"A Framework for Daily Living Activity Recognition using Fusion of Smartphone Inertial Sensors Data","authors":"Sheharyar Khan, S. M. A. Shah, Sadam Hussain Noorani, Aamir Arsalan, M. Ehatisham-ul-Haq, Aasim Raheel, Wakeel Ahmed","doi":"10.1109/iCoMET57998.2023.10099271","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099271","url":null,"abstract":"Recent years have seen rapid advancements in the human activity recognition field using data from smart sensor devices. A wide variety of real-world applications can be found in different domains, particularly health and security. Smartphones are common devices that let people do a wide range of everyday tasks anytime, anywhere. The sensors and networking capabilities found in modern smartphones enable context awareness for a wide range of applications. This research mainly focuses on recognizing human activities in the wild for which we selected an in-the-wild extra-sensory dataset. Six human activities i.e., lying down, sitting, standing, running, walking, and bicycling are selected. Time domain features are extracted and human activity recognition is performed using three different machine learning classifiers i.e., random forest, k-nearest neighbors, and decision trees. The proposed human activity recognition scheme resulted in the highest classification accuracy of 89.98%, using the random forest classifier. Our proposed scheme outperforms the state-of-the-art human activity recognition schemes in the wild.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130963168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099140
Falaq Qureshi, R. Uddin
In this paper, we discuss the design of different models for teleoperation control by presenting the significant benchmark results for various important force reflecting control architectures used in 1-DOF bilateral teleoperation. They are used to analyze the results of force and distance tracking graphs in free motion and contact mode obtained from various control models by varying dynamics of master, slave, environment, and communication channel. In this regard, different force reflecting teleoperation control architectures are simulated via proposed model design, such as two-channel (2C) architectures, three-channel (3C) and finally four-channel (4C) architecture. These benchmark results are presented for each architecture via MATLAB/Simulink-based simulator.
{"title":"Design of TeleHaptic Simulators for Various Control Architectures","authors":"Falaq Qureshi, R. Uddin","doi":"10.1109/iCoMET57998.2023.10099140","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099140","url":null,"abstract":"In this paper, we discuss the design of different models for teleoperation control by presenting the significant benchmark results for various important force reflecting control architectures used in 1-DOF bilateral teleoperation. They are used to analyze the results of force and distance tracking graphs in free motion and contact mode obtained from various control models by varying dynamics of master, slave, environment, and communication channel. In this regard, different force reflecting teleoperation control architectures are simulated via proposed model design, such as two-channel (2C) architectures, three-channel (3C) and finally four-channel (4C) architecture. These benchmark results are presented for each architecture via MATLAB/Simulink-based simulator.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"14 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115486612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099073
Shakil Ahmed Jiskani, S. Shaikh, Q. Memon, Mohsin Ali Bhutto, Muhammad Fawad Shaikh, M. Kumar
Buildings are one of the major consumers of energy in Pakistan. A case study of electric power consumption in the main campus (i.e. sector-A) of Quaid-e-Awam University of Engineering, Science and Technology, was carried out. This research work was mainly based on the energy audit and analysis of conventional energy conservation measures such as using daylighting and minimizing wastage of energy by reducing the usage time of electrical appliances. The luminance level could be maintained by opening windows installed inside the classrooms. Each classroom and office consisted of two to six windows. The daylighting increased the illumination level and reduced the consumption of electricity by switching off the lighting appliances. The different parameters like indoor temperature and illumination level and amount of electricity saved in kWh were recorded by using various meters. It was found that using the daylight method could save 65,923.52 kWh/year and can save Rs. 922,929.28 pkr (Pakistani rupees).
{"title":"Electrical Energy Audit and Analysis of Energy Conservation Opportunities at University Buildings","authors":"Shakil Ahmed Jiskani, S. Shaikh, Q. Memon, Mohsin Ali Bhutto, Muhammad Fawad Shaikh, M. Kumar","doi":"10.1109/iCoMET57998.2023.10099073","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099073","url":null,"abstract":"Buildings are one of the major consumers of energy in Pakistan. A case study of electric power consumption in the main campus (i.e. sector-A) of Quaid-e-Awam University of Engineering, Science and Technology, was carried out. This research work was mainly based on the energy audit and analysis of conventional energy conservation measures such as using daylighting and minimizing wastage of energy by reducing the usage time of electrical appliances. The luminance level could be maintained by opening windows installed inside the classrooms. Each classroom and office consisted of two to six windows. The daylighting increased the illumination level and reduced the consumption of electricity by switching off the lighting appliances. The different parameters like indoor temperature and illumination level and amount of electricity saved in kWh were recorded by using various meters. It was found that using the daylight method could save 65,923.52 kWh/year and can save Rs. 922,929.28 pkr (Pakistani rupees).","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124106500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：