2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)最新文献

{"title":"Smartphone Malware Detection using Permissions and McNemar test","authors":"G. Kumari, Anshul Arora","doi":"10.1109/ICSCSS57650.2023.10169391","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169391","url":null,"abstract":"A recent report has shown that the availability of smartphones is increasing at an alarming rate and hence the number of mobile malware is exponentially increasing with the increase in popularity of smartphones. Looking at the level of threat from malware applications for Android users, it becomes essential to detect malware applications in a quick and effective way. One such way is to use permissions. To make an effective system for malware detection using permissions, a large dataset and different permissions are required to analyze the pattern. With a large number of permissions for analysis, the time of computation increases drastically. The time of computation can be reduced if the number of datasets or the number of permissions gets reduced. Reducing the number of features is preferred over decreasing the number of datasets. Further, the number of permissions can be rduced only if the permissions that are most distinguishing are selected by ignoring the permissions that don’t play a huge role in distinguishing between malware and benign applications. Thus, a novel method is required to rank the permissions based on how well that permission can be used to detect the nature of the application. This study introduces a statistical technique named McNemar test to find the correlation of a set of permissions with malware and benign applications and rank the permissions. The correlation gives a numerical value for the overlapping of each permission in malware and benign applications. The greater the correlation value lesser will be its usefulness in distinguishing the nature of the application. Such ranking helps us eliminate irrelevant permissions. This ranking can be further used for detection using various machine-learning algorithms. As a result, this study has narrowed down the total set of permissions from 129 to 38 and got 97% detection accuracy with the Random Forest classifier.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115007650","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}

{"title":"Comparative Study of Machine Learning Algorithms for Fake Review Detection with Emphasis on SVM","authors":"P. Naresh, Samavedam Venkataramana Naga Pavan, Abdul Razzakh Mohammed, N. Chanti, Modepu Tharun","doi":"10.1109/ICSCSS57650.2023.10169190","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169190","url":null,"abstract":"Online reviews have become an essential factor in consumer decision-making, with the credibility and authenticity of such reviews being a major concern. Fake reviews, including those generated by computers and humans, can significantly influence the opinions and decisions of consumers, resulting in a loss of trust in online platforms. The e-commerce sector has seen a rise in the prevalence of fake reviews, with some sellers engaging in deceptive practices to manipulate the ratings and rankings of their products. One such practice is creating fake positive reviews for their own products or paying individuals to do so. This can mislead customers into believing that the products are of high quality and popular when they are subpar. Another practice involves leaving fake negative reviews for a competitor’s products to damage their reputation and gain a competitive advantage. In addition, some sellers offer discounts or incentives to customers in exchange for positive reviews, leading to biased and inaccurate assessments of the quality of their products. These practices can harm the sales of honest sellers and undermine the trust of consumers in the e-commerce marketplace. This study proposes a supervised machine learning approach to identify fake reviews. The study compares the performance of six classification algorithms, namely Logistic Regression, K Nearest Neighbours, Support Vector Classifier, Decision Tree Classifier, Random Forests Classifier, and Multinomial Naive Bayes. The models are trained on a text dataset of 40433 reviews collected from https://osf.io/. The paper analyses the various features and techniques used in the different algorithms to detect fake reviews. The study concludes that supervised machine learning algorithms can effectively detect fake reviews and can be used to prevent their dissemination, thus enhancing the credibility and reliability of online reviews.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116975969","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}

{"title":"Real-Time Quality Assurance of Fruits and Vegetables using Hybrid Distance based MKELM Approach","authors":"G. Devika, Priya, Chandra Sekhar Rao Bandaru, R. V. Srinivas, N. Girdharwal, M. Devi","doi":"10.1109/ICSCSS57650.2023.10169197","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169197","url":null,"abstract":"Sustainable development relies on a number of pillars, one of which being agriculture. Sustainable agriculture, in light of expected population expansion, must ensure food security while remaining economically and socially viable and having a minimal impact on biodiversity and natural ecosystems. Deep learning has shown to be an advanced method for analyzing large amounts of data, having applications in fields as diverse as image processing and object recognition. Recently, it’s being used in the fields of food engineering and science. Food recognition, quality detection of produce, meat, and seafood, the food supply chain, and contamination were only some of the problems these systems set out to solve. Artificial intelligence (AI) is a common tool in the field of precision agriculture for making predictions about the quality of harvested crops. This is especially true when assessing crops at various post-harvest stages. Certain postharvest diseases or damages, like rot, can completely wipe out crops and even produce toxins that are hazardous to humans, making disease and damage identification a top priority. Preprocessing with a gabor filter, enhancement with HE, segmentation with a K-means algorithm, and feature extraction with LBP and BIC make up the suggested method. Lastly, DB-KELM is used to train the model. As compared to ELM and KELM, the proposed method performs better.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121019097","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}

{"title":"Investigation on Leaf Disease Diagnosis in Rice Plant using Machine Learning Approaches","authors":"D. S. Benita, J. Anitha, S. Alex","doi":"10.1109/ICSCSS57650.2023.10169616","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169616","url":null,"abstract":"The discovery of crop diseases in the early phase is vital in the agricultural field. This helps in treating the crop with necessary actions to avoid the disease’s spread in the early stages. Research shows crop yields and quality may generally be improved by utilizing machine learning techniques. This work examines the performance of various machine learning models that helps to identify an efficient model to diagnose crop diseases in the early phase thus reducing the time and cost expense. Initially, the input images are collected from the Rice Leaf Disease Image dataset and pre-processed for further processing. The feature extraction process makes use of the pre-processed image and extracts useful insights from it. These extracted features are then given into the machine learning models which predict the target value. The various machine learning algorithms used in this research work include K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), Naive Bayes (NB), Decision Tree (DT), and Random Forest (RF). The predicted results are compared against the actual values for every model which provides the performance metrics of these models. According to the computed performances, the Random Forest Classifier provides the highest accuracy in classifying whether the rice plant leaf has the disease or not.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126875993","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}

{"title":"Machine Learning based Lung Cancer Detection & Analysis","authors":"A. Indumathi, M. Sathanapriya., N. Vinodh, Merugu Ashok, N. Aishwarya","doi":"10.1109/ICSCSS57650.2023.10169329","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169329","url":null,"abstract":"The key to treat cancer is early detection. This study has reviewed the fractal image analysis technique for cancer cell detection. Typical abnormalities in cancer cells include uncontrolled cell proliferation. Measurement of morphological complexity and study of figures with atypical shapes are both possible with fractal analysis. Investigations were conducted using simulations of human breast cancer cells. We investigated and compared changes in the fractal dimension between cancer cells and normal cells. The preliminary results demonstrate that the picture based fractal analysis technique is able to locate breast cancer cells. It has a great deal of potential to shed light on the morphological classification of tumor growth and could be used as a marker for early cancer identification and the effectiveness of cancer treatments. The segmentation and data enhancement categorization scheme has been completed. e and The accuracy of lung cancer detection is greater. Cancer can spread to other organs and impair their normal activities, making it a fatal condition. The cancer grows more deadly as it advances in stage. The doctor will do a number of tests to ascertain the degree and seriousness of the disease, and based on the results, the stage of cancer will be determined. Before giving a chance to develop and spread, certain cancers can be detected early. Early cancer discovery results in significantly better treatment outcomes and less physical, emotional, and financial suffering.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115214185","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}

{"title":"Design of Novel Rectangular Microstrip Patch Antenna with Improved Gain and Performance Analysis","authors":"N. Sengottaiyan, P. Kalyanasundaram, S. Ramesh, Ravikumar Gurusamy, V. Rajmohan","doi":"10.1109/ICSCSS57650.2023.10169317","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169317","url":null,"abstract":"The proposed design involves in the fabrication of high gain rectangular patch antenna in which the core part is Duroid 6010 substrate. The performance is analyzed with RT-Duroid 5880 patch substrate-based antennas. FEKO software is evolved in the design of RT-Duroid 5880 rectangular patch antennas and collecting the data set from 40 samples with a pre-test 95 % confidence interval and an alpha error threshold of 0.05. First group was designed with the RT-Duroid 5880 substrate and the second one was developed with the Duroid 6010. 20 samples of both Duroid 6010 and RT-Duroid 5880 were collected. A total of 40 groups were collected. The novel microstrip patch antenna operates in the frequency spectrum of 2 GHz to 3 GHz band. When performing a t-test of independent samples on the two groups under consideration, the mean gain of Duroid 6010 and RT-Duroid 5880 are 0.8820 and 3.0755 respectively with the expected significance of 0.001 (p<0.05). The gain of RT-Duroid 5880 antenna and Duroid 6010 are 4.66 dB and 1.2 dB respectively. The directivity is 3.45 dB for RT-Duroid 5880 substrate and 2.52 dB for Duroid 6010 substrate. From this study it appears that the design of the RT-Duroid 5880 is significantly better than the design of the Duroid 6010.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116117742","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}

{"title":"A Reliable Method for Detecting False Alarm Notification in VANET","authors":"Poorva Shukla, R. Patel, Sunita Varma","doi":"10.1109/ICSCSS57650.2023.10169667","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169667","url":null,"abstract":"VANET is a vehicular ad hoc network which is a sub part of WSN (Wireless Sensor Network). In VANET technology, alert or alarm plays a major role. With the help of an alert or alarm driver may alert for the upcoming event, but what happens when these alarms are false. It means these may give false information about an event that is happening on the route. The notification of wrong information dissemination may be called a false alarm notification and there are various challenges faced by VANET technology to detect false alarm notification like Lack of accurate and reliable information, Limited processing power, Dynamic topology, Limited communication range. So proposed algorithm is to detect false alarm notifications and to overcome the challenges faced by VANET. The proposed algorithm is based on rules based approach which means these give notification about the false alarm information or may generate alarm for the same. The main objective of this paper is to detect the false alarm for a vehicle, which means that the algorithm should identify notifications that do not represent an actual event with the help of location time and type of alert.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116138732","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}

{"title":"Crime Type Prediction based on Various Occurrence using Parallel LSTM","authors":"M. Saradha, T. Nithesh Priyan, D. U. Shreeram, S. Viknesh","doi":"10.1109/ICSCSS57650.2023.10169580","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169580","url":null,"abstract":"Crime is a widespread societal issue that has a negative impact on people's standard of living and the nation's prosperity. It's a major consideration for potential residents and tourists alike when deciding whether or not to settle in a given area. As crime rates rise, police departments have a growing need for cutting-edge GIS and data mining tools to enhance crime analytics and strengthen public safety. The suggested method includes preprocessing, feature selection, and evaluating the model's performance. We begin by cleaning up the raw crime statistics. For more predictable signals, this comprises both spatial and temporal regularization. Feature selection is performed using a rough spanning tree. To measure the effectiveness of the model, we employ parallel LSTM. When compared to two established approaches, the new strategy fares quite well.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122490232","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}

{"title":"Flood Extent Mapping with Unmanned Aerial Vehicles Data using Deep Convolutional Neural Network","authors":"Vaishnavi Barkhade, Shruti Mahakarkar, Rahul Agrawal, Chetan Dhule, Nekita Chavan Morris","doi":"10.1109/ICSCSS57650.2023.10169842","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169842","url":null,"abstract":"Flooding is a common occurrence that results in human fatalities, severe environmental harm, and major infrastructural damage. A method for mapping areas with apparent and subterranean vegetation flooding that integrates CNN and region growing (RG). To determine the number of floods beneath plants that are hidden from photojournalism using the digital elevation model(dem), the Region Growing technique is applied, whereas to extract areas which are flooded a Convolutional classifier is used. The CNN-based classifier is trained using a data augmentation strategy to enhance the classification outcomes. This paper develops an automatic flood detection system for UAV aerial photographs using deep learning algorithms. Unmanned aerial vehicles (UAVs) have the potential to offer high-resolution data with the ability to quickly and accurately detect inundated areas under intricate urban environments. This research makes use of unmanned aerial vehicles to develop an automated imaging system that can identify waterlogged areas from aerial pictures. The suggested method combines CNN and region growth methodologies for mapping regions with visible and subsurface vegetation flooding, resulting in a more complete flood detection system.UAVs offer high-resolution data collecting as well as the rapid and precise detection of flooded regions in complicated urban contexts. The use of data augmentation improves the classification results of the CNN-based classifier.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128385535","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}

{"title":"Emotion Detection using Speech and Face in Deep Learning","authors":"S. Shajith Ahamed, J. Jabez, M. Prithiviraj","doi":"10.1109/ICSCSS57650.2023.10169784","DOIUrl":"https://doi.org/10.1109/ICSCSS57650.2023.10169784","url":null,"abstract":"Humans have a unique ability to demonstrate and understand emotions through a variety of models of communication. Based on their emotions or mood swings we can judge whether the human subject is in good psychological condition or not. The most visible apparent deficiencies of today’s Emotion capturing systems were their inability to understand the emotions of such patients like mental health disorder, social emotion Agnosia, alexithymia or even autism by using facial expressions. It can be used in schools to help students who find it difficult to express their feelings (introverts) or who have unstable mental health concerns, such as depression, and hence the teacher’s or health workers can communicate with their parents and work through their problems. These days, technology allows employers to recognize individuals who are overly stressed in the workplace and release them from their duties. In research work a Deep Learning algorithm is utilized to create an integrated tool to identify the facial emotions and the stress level or emotion quotient from speech. Tools that can assist people in recognizing the emotions of those around them could be very beneficial in treatment settings as well as in regular social encounters. Emotion detection using speech and face in deep learning has made significant progress in recent years, but there are still several challenges that need to be addressed. Here are some of the main challenges: Limited Dataset: The availability of labeled datasets for emotion detection is limited, especially for less common emotions or for specific cultural contexts. This makes it challenging to train deep learning models that can generalize well to new data. Variability in Data: The data used for emotion detection can vary widely in terms of quality, noise, and variability. For example, speech data can be affected by environmental noise, accents, and speaking styles, while facial data can be affected by lighting conditions, facial expressions, and occlusion. Feature Extraction: Extracting relevant features from speech and facial data can be challenging, especially when dealing with complex emotions that are not easily captured by simple features. This requires careful design of feature extraction algorithms and feature engineering techniques. Interpretability: Deep learning models are often seen as “black boxes” that are difficult to interpret. This can make it challenging to understand how the model is making decisions and to diagnose errors or biases in the model.Ethical and Privacy Concerns: Emotion detection using speech and facial data raises ethical and privacy concerns, as it can be used for sensitive applications such as surveillance, emotion profiling, and behavioral prediction. This requires careful consideration of ethical and privacy issues in the design and deployment of deep learning models for emotion detection.","PeriodicalId":217957,"journal":{"name":"2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116355233","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}