Scandinavian Journal of Information Systems

Using pre-existing datasets to combine published information with new metrics would help researchers construct a broader picture of chromatin in disease

Moataz Dowaidar — 2023-05-02

Using pre-existing datasets to combine published information with new metrics would help researchers construct a broader picture of chromatin in disease. A computational biology goal is the near-real-time integration of epigenomic data sets, irrespective of the laboratory they were generated in—similar to a blood pressure, ECG or troponin test. In addition, epigenome modeling must become dynamic, considering cell-to-cell variability and changes over time due to normal physiological or pathological stressors. Probabilistic modeling and machine learning can help such model creation, while finding (and quantifying) previously identified developing chromatin properties that match heart health changes. A 3D genome representation, for example, may reveal a structural or accessibility attribute connected to health or disease that no single epigenomic test alone can discover. Such strategies can expand basic knowledge of biology and illness.

Incorporating wet and dry lab training components to teach schemes to foster the formation of more diverse technical repertoires. Data mining and fresh data collection will revolutionize how we handle chromatin challenges in coming years. Knowing how computers solve problems (as opposed to how people do) and how to computationally phrase questions would create a shared vocabulary that completes tasks. Team members don't need all the big data skills, but a collaborative attitude is important for effective large-scale epigenomic research. UCLA's QCBio Collaboratory is a great platform for teaching non-programmers and facilitating cooperation to resolve biological issues.

It also encourages the use of open source technology by making genomics datasets available to non-experts.There are already many bioinformatics tools—and others will be developed to introduce new understanding—but basic knowledge of how computers work and how to answer big-data questions will continue to empower scientists to test the most meaningful hypotheses with appropriate tools to reveal new insights about cardiac biology.

Secure-Medishare: A Comprehensive Secure Medical Data-Sharing System Using Blockchain, Watermarking, Steganography, And Optimized Hybrid Cryptography

Walzade Arti Krushnarao and Dr. Sharanbasappa Gandage — 2023-06-15

Medical data plays a crucial role in healthcare, enabling accurate diagnosis, treatment planning, and research. However, the secure sharing of sensitive medical data and images remains a significant challenge. Existing techniques often fall short in terms of protecting data integrity, confidentiality, and authenticity. To address these limitations, this paper introduces SECURE-MEDISHARE, a novel secure medical data-sharing system that integrates blockchain technology, watermarking, steganography, and enhanced cryptography.The proposed SECURE-MEDISHARE system aims to provide robust security mechanisms for medical data sharing. Unlike centralized systems, which are susceptible to single points of failure and unauthorized access, SECURE-MEDISHARE utilizes blockchain technology to ensure decentralized and tamper-resistant storage and sharing of medical data. SECURE-MEDISHARE employs watermarking for data integrity and authentication and steganography for confidential transmission of metadata, ensuring authenticity, privacy, and confidentiality of medical data. Furthermore, an optimized hybrid cryptography technique is implemented to secure the transmission and storage of medical data, safeguarding confidentiality and privacy.SECURE-MEDISHARE offers several advantages over existing techniques. It provides enhanced security and privacy protection, efficient data sharing and retrieval, and improved trust among healthcare providers. The system ensures the integrity and authenticity of medical data, preventing unauthorized modifications or tampering. Additionally, the decentralized nature of blockchain technology reduces the risk of data breaches and single points of failure. Experimental results show that SECURE-MEDISHARE generates hashes quickly, taking only 65 milliseconds for 100 blocks. Optimized hybrid cryptography used in SECURE-MEDISHARE also outperforms other cryptography combinations, with encryption and decryption times of 5.635 seconds for 96-bit data. These findings highlight the efficiency and effectiveness of SECURE-MEDISHARE for secure medical data and image sharing. The experimental evaluation confirms that SECURE-MEDISHARE is a reliable and robust solution for secure medical data sharing in healthcare environments.

Enhanced Ensemble Fusion Model For Stress Classification And Prediction

Suryavanshi Prashant Maharudra and Dr. Sharanbasappa Gandage — 2023-06-15

Stress has become a common phenomenon in modern society, and it has been identified as a major factor that affects people's health and well-being. Stress can be caused by various factors, such as work pressure, financial difficulties, relationship problems, and health issues. Prolonged exposure to stress can lead to physical and mental health problems, including anxiety, depression, cardiovascular diseases, and obesity. Accurate stress classification and prediction can help individuals and organizations identify the sources and levels of stress and take appropriate measures to manage stress and prevent negative outcomes. By identifying individuals who are at risk of stress, proactive interventions can be initiated to prevent negative outcomes. Additionally, stress classification and prediction can be useful for designing effective stress management programs and policies that can improve the well-being and productivity of individuals and organizations.Existing systems for stress classification and prediction have limitations in terms of accuracy and efficiency. To overcome these limitations, this paper proposes an Enhanced Ensemble Fusion (EEF)model that combines three ensemble classifiers, namely stacking, bagging, and boosting, using a blending classifier. The EEF model is composed of several classifiers, including the stacking classifier, the bagging classifier, and the boosting classifier, each using an Enhanced J48, Enhanced SVM, and Enhanced Naive Bayes classifier. An Enhanced Logistic Regression classifier is used as a meta-classifier for the stacking classifier. The model was evaluated on a Swell-EDA dataset and WESAD-EDA dataset, and the results show that it outperformed existing systems in terms of accuracy and robustness. The Enhanced Ensemble Fusion Model achieved anaccuracyof 72.86% for WESAD-EDA dataset and 50% for Swell-EDA datasetwhich is significantly higher than the accuracy of individual classifiers and existing ensemble methods. The proposed model provides a promising approach for stress classification and prediction, which can be useful in various applications, such as healthcare, human resources, and education.

Oe-Mdl: Optimized Ensemble Machine And Deep Learning For Fake News Detection

Raut Rahul Ganpat and Dr. Sonawane Vijay Ramnath — 2023-06-15

The proliferation of fake news in today's digital era has raised concerns about the credibility and trustworthiness of online information. The detection of fake news has become an essential task to protect individuals, organizations, and societies from misinformation and its potential consequences. Existing fake news detection techniques, including rule-based, supervised machine learning, and NLP approaches, have limitations. Rule-based methods lack adaptability, supervised machine learning struggles with generalization, and NLP techniques face challenges in capturing context and nuanced language. To overcome these limitations, this paper introduces the Optimized Ensemble Machine and Deep Learning (OE-MDL) algorithm for effectively detecting fake news. The proposed OE-MDL algorithm addresses the disadvantages of existing techniques by offering several improvements. Firstly, preprocessing methods are employed, including lowercase conversion, tokenization, stop word removal, word stemming, lemmatization, and spell-checking. Additionally, n-grams generation and the computation of term frequency-inverse document frequency (TF-IDF) scores are utilized. By considering a broad range of linguistic and statistical features, OE-MDL aims to capture the nuanced signals that differentiate fake news from real news. Furthermore, OE-MDL combines optimized machine learning (OML) and optimizeddeep learning (ODL) phases for improved classification accuracy and robustness. In the OML phase, base classifiers like optimizedRandomForest, optimizedJ48, optimizedSMO, optimizedNaiveBayes, and optimizedIBk are stacked with anoptimizedMultilayer Perceptron as the Meta classifier. This stacked classifier serves as the base for a bagging classifier, which becomes the classifier for an AdaBoostM1 boosting classifier. In the ODL phase, a Dl4jMlpClassifier serves as the base for a bagging classifier, which becomes the classifier for an AdaBoostM1 boosting classifier. The OML and ODL classifiers are combined using a blending classifier with weighted voting to classify the training set. The trained blending classifier predicts the authenticity of news articles in the testing set. The experimental results demonstrate that the OE-MDL algorithm outperforms existing techniques with the highest accuracy (84.27%), precision (74.17%), recall (85.18%), and F1-Score (79.29%), offering an effective solution to combat the spread of fake news.

Controllability Problems And Stability Problems Of Nonlinear Discrete Dynamical Systems By Using Functional Analytic Techniques

Udit Kumar Patel and Dr. Anjna Rajoria — 2023-06-15

infinite-dimensional system that may be used to represent propagation and transport processes as well as population dynamics (reproduction, development, and extinction). There will always be a delay in economic systems since choices and effects are separated by a non-zero time. In communication networks, the start and delivery of data is also accompanied by a non-zero time interval. The delay might be caused by a model simplification in some situations. Such systems are distinguished by the fact that their energetic may be characterized using discrepancy equations that incorporate data about the system's history. There are numerous approaches to express such systems numerically

A Machine Learning Model for Automating Irrigation System

Khadri S S and Dr. Arpana Bharani — 2023-06-15

The India most people are dependent on agriculture-based businesses. It also contributes to our economy. Automation in agriculture will help improve crop production quality and quantity. Additionally, help to minimize the resources required. But automation in agriculture requires a significant amount of investment. Therefore, in order to minimize the automation cost of the agricultural irrigation system a Machine Learning (ML) technique is proposed. The aim of the proposed ML model is to reduce the sensor implementation cost and running cost of the complete remote sensor network. Therefore, we considered a dataset of soil moisture and temperature dataset where the predictable is an irrigation treatment type. The dataset is pre-processed first to transform data for learning, then the k-means clustering is applied for behavioral data analysis. This process groups the similar sensor reading and enhances the learning performance regarding the accuracy and learning time. Finally, two machine learning techniques have been implemented to train and predict the irrigation treatment. This technique minimizes the expenses of implementing the sensors on the ground and their execution and maintenance costs. However, the entire system’s performance depends on the accuracy of the prediction model, therefore in near future, we need to work on improving the prediction accuracy of the proposed model.

Detection and Prevention of Wormhole Attack in Mobile Ad-Hoc Networks Using Trust Tunneling

Versha Matre and Dr. Sharanbasappa Gandage — 2023-06-15

Wireless networks are susceptible to multiple attacks, including an attack known as the wormhole attack. The wormhole attack is actually strong, and preventing the attack has proven to be actually sensitive. A strategic placement of the wormhole can perform in a significant breakdown in communication across a wireless network. In similar attacks two or another malicious colluding nodes produce an advanced- situation virtual tunnel in the network, which is placed to transport packets between the tunnel endpoints. These tunnels emulate shorter links in the network and so act as advantage to unknowing network nodes which by default seek low-lying routes. This work present a novel trust-based trick for connecting and separating nodes that produce a wormhole in the network without engaging any cryptographic measure. With the support of extended simulations, we substantiate that our device functions effectively in the sight of malicious colluding nodes and doesn't assess any inessential stipulations upon the network joint and assignment aspect.

Argumentative Texts As A Strategy For Critical Thinking Development In Engineering Students

Eli Romeo Carrillo Vásquez — 2023-06-15

The Future of Jobs report (World Economic Forum, 2020) reveals that the analysis capacity and critical thinking will be one of the most requested work skills by the year 2025, in addition to being the one presenting the biggest relative growth in recent years.

Additionally, critical thinking (CP) is one of the soft skills that are most in demand in the labor market (Rebele & Pierre, 2019). This evidences the urgency of the development of critical thinking in the professional formative stage of students (Davies, 2013).

Likewise, critical thinking is widely recognized as one of the hallmarks of high-quality education (Kölbel & Jentges, 2017), so it has been reported that CP is directly related to educational performance (Enríquez Canto et al., 2021)

A Study On The Fault Recognition Utilizing Svm Classifier

Manidipa Acharjya and Dr. Rahul Mishra — 2023-06-15

WSNs should focus on fault-tolerant event detection and change detection. According to recent articles, 1.21 percent and 2.12 percent of work has been done in detection and estimation, wireless radio, and link characteristics, respectively. The goal of this research is to contribute to the event region detection in WSN by using the suggested technique to optimize the network's fault tolerance capacity. This research is being expanded to investigate the effect of a noisy communication channel on event detection. The research contributes to the detection of non-binary fault-tolerant event regions by taking into account symmetric and non-symmetric sensor fault probability. Because mushrooms are sensitive to temperature fluctuations, this research could be applied to temperature monitoring in mushroom cultivation. For detecting systematic errors, the third section proposes a sequential change detection algorithm. This work will be useful in time-critical applications, particularly in industrial applications where data must be handled before processing.

Enhancing Performance Parameters for Smart Video Surveillance Application with AIoT via Collaborative Cloud and Edge Computing

Ms. Trupti K. Wable, Dr. Rahul Mishra — 2023-06-15

The traditional cloud-based paradigm is under tremendous pressure on network bandwidth and communication latency, which is why a newly emerging paradigm of computing paradigm is involved. As a result, AIoT applications can be implemented in a cloud-based environment, where model building and model abuse are embedded in the cloud and edges, respectively. However, engineers still face the challenge of building AIoT systems in practice due to the natural diversity of IoT devices, diminishing accuracy of trained models, security and privacy issues, etc. In this paper, I want to introduce the development of an industrial edge- cloud based collaboration platform aimed at facilitating the implementation of AIoT applications. In addition, a land use case was filed in this paper, which proved the effectiveness of the AIoT application building on the platform. In this paper we simply do the comparatively study of edge system for surveillance and cloud-edge system for surveillance and measure various parameter using both system and conclude which system is best.

The New Workplace and Digital Education: Generation Z and Millennials

Ms. Shubhika Gaur, Dr. Garima Srivastava, Ms. Apoorva Kapoor — 2023-06-15

There is a clear mismatch between individuals' skills and those that businesses are sourcing in today's business environment. The workforce ought to still be in a position to complement the value of technology, despite the fact that business leaders ought to ensure that automation, digitization, and the extraction of the value of data—such as through artificial intelligence—are fundamental priorities for the organization. The way knowledge is acquired has changed as a result of technology's growing popularity. This is especially crucial for Generation Z and Millennials, who are currently adjusting to the new workplace and largely acquiring knowledge online. The COVID-19 pandemic, on the other hand, has upset the balance of this new work that combines business, digital technologies, and innovative work practices. Millennials and Generation Z must embrace technology and upgrade training programs if they are to successfully transition.

As a result, the best method for harnessing the transition to the new workplace through digital learning has been identified in this paper. Additionally, this paper has evaluated how markets change or evolve over time. The current COVID-19 pandemic has been noted to have an impact on the labor markets today and in the future. Their implications would include varying employment markets, shifting demands and supplies for skills, and demographic trends (Millennials and Generation Z).

Facial Action Recognition Using Multikernel Learning to Combine Heterogeneous Features

Bombale Girisha Ramhari, Dr. Rais Abdul Hamid Khan — 2023-06-15

Facial action recognition is a challenging problem because facial expressions can be ambiguous and appear differently on different individuals. In this paper, we propose a novel approach based on multikernel learning to identify facial actions. The approach is a combination of heterogeneous features derived from local binary pattern (LBP), histograms of oriented gradients (HOG), and deep convolutional neural networks (CNNs) features. The proposed method is evaluated on the Cohn-Kanade (CK+) and BU3DFE datasets. Our experimental results demonstrate that the proposed method substantially outperforms the state-of-the-art single and multi-kernel approaches with respect to accuracy. The experiments also show that the proposed method can exploit the complementarity of different features, resulting in improved recognition performance. This is evidenced by the significant gains over the single-kernel approaches.

Common Fixed Point Theorem in ϵ- Chainable Fuzzy Metric Space Using Absorbing Maps

Sonal Dixit and Dr. Animesh Kumar Gupta — 2023-06-23

We prove some common fixed point theorems for set – valued and single – valued mappings in fuzzy metric and fuzzy 2 – metric space Also generalization and extension of Known results are there by obtained.

Impact of HRM Practices on Organizational Performance - A Study of Indian IT Sector

Yashaswee Dash and Sanjita Lenka — 2023-06-25

The study intends to investigate the way organizational performance is related with human resource management practices in the Information Technology (IT) sector in Odisha, India with a special focus on performance appraisal, training practices, and recruitment & selection. A number of studies are available exploring this research topic in western countries, but limited researches are found concerning India's HRM landscape. Therefore, this article aims to examine the relationship between HR practices and organizational performance in Indian context. Structural equation modeling is used to elicit the relationship clearly. The findings of this study indicate a positive association between performance appraisal and training practices with organizational performance. These results suggest that effective performance appraisal systems and robust training practices have a beneficial impact on organizational performance in the IT sector in India and more particularly in Odisha. This information can assist organizations in understanding the importance of implementing sound HRM practices to enhance their overall performance and competitiveness in the market. IT industry in India is well-known for its significant impact on the country's economy and high levels of employee engagement. Examining the influence of HRM practices on organizational performance within this specific context can provide valuable insights for both researchers and practitioners.

Speech Recognition based detection of Real-time Objects with Tensor Flow

Vijay Karnatak, Satwik Teotia, Renu Yadav — 2023-06-25

A system for persons who are blind or visually impaired that runs on Android. For users who are visually impaired, it offers object detection in the close vicinity. This technique aids those who are blind in recognising everyday objects such as a chair, table, phone, etc. in their environment. This system helps the blind person buy at the supermarket by using an RGB colour camera to capture images of the immediate area and deep learning to recognise the type and placement of objects in front of the blind person. This method builds two sets of picture databases with a combined total of nine categories, each with an object detection system based on an SSD network as well as an object classification system based on a MobileNets network, to train a neural network. In order to install an object categorization network on an Android phone, this system is constructed of an Android - TensorFlow interface. The Android terminal now has a voice announcement feature that notifies the blind person in real time when an object is recognised. For persons with vision impairments, this system has been shown to be more effective.

Artificial Intelligence-Driven Innovations in Agriculture

Kasidit Chueinwittaya, C.Vijai, Worakamol Wisetsri* — 2023-07-18

According to a have a glance at the Food and Agriculture Organization of the UN, the world is projected to realize nine billion by 2050. Speedy world growth, shortage of agricultural land, shortage of seasoner resources, erratic weather changes, and marketplace wants square measure the first factors. of these can cause large food shortages in the future. it's terribly difficult to fulfill our demands in our current agricultural system. A solution to this can be expected in artificial intelligence technology. This artificial intelligence technology that we have is going to bring a huge change in the agriculture sector. Artificial intelligence in agriculture is sure to not only create employment opportunities for crores of people but also bring about a huge agricultural revolution in the future. This article examines the use of artificial intelligence in agriculture and agribusiness and analyzes the challenges of using robots and drones and artificial intelligence technology and various weeding and crop monitoring systems.

Triple-Entry Accounting With Blockchain Technology

Kasidit Chueinwittaya, C.Vijai, Worakamol Wisetsri* — 2023-07-18

Although double-entry accounting has been used for more than 600 years this days’ era of disruptive technological alternate using blockchain and FinTech has caused the emergence of some other promising accounting method: triple-entry accounting. Blockchain changes the dynamics of business processes and since the accounting department must intervene all company processes, it is to know the effect of blockchain in different business processes. Triple-entry accounting with Blockchain, while it is well made, basically can improve accounting.

Classification of Indian Music using intrinsic mode functions based features

*Saurabh Sarkar, Sandeep Singh Solanki, Soubhik Chakraborty — 2023-08-02

Indian music is very rich in emotional content and technicalities. It is also contrasting having multiple genres which may be broadly classified as Classical (Hindustani or Carnatic) music, Semi-classical music (including Ghazals) and Light (including folk) music. The so called “rasa” or emotional content in Indian music is of much significance, e.g. selection of the right kind of music for therapeutic intervention by the music therapist who might be an expert in western art music (WAM) but could be new to Indian music. This paper presents a novel classification technique based on empirical mode decomposition (EMD). In this work, two genres of Indian music, Classical and Semi-Classical, are considered. There is a significant increase in classification accuracy as compared to previous works involving generic audio features.

Occupational Alteration: Examination Of Fingerprints And Psychological Behaviour On Carpenters

Mansi Singh , Dr. Sahil Sharma — 2023-08-02

Fingerprint alteration is a major concern with their basic need in the crime world which holds the individuality of people to being individual. It holds the pattern with their unique ridges and makes the two fingerprints identical. Forensic science relies heavily on the accurate examination and analysis of fingerprints for crime scene investigations. However, the occupational alterations experienced by carpenters who are involved in this process, along with their psychological behavior, can have implications for the reliability & effectiveness of their work. Carpenters, due to the nature of their occupation, may experience alterations to their fingerprints caused by the repetitive friction and pressure exerted on their hands while handling tools and materials. These alterations can affect the ridge patterns and quality of the fingerprints. This abstract aims to explore the relationship between occupational alterations, psychological behavior, and the role of carpenters in fingerprint examination within the field of forensic science.

Energy-Efficient Routing Protocol for Next-Generation Application in the Internet of Things and Wireless Sensor Networks

Avneesh Gour, Dr. Nishant Kumar Pathak — 2023-08-15

Our Invention “Energy-Efficient Routing Protocol for Next-Generation Application in the Internet of Things and Wireless Sensor Networks” is a the fact that the majority of sensor nodes in wireless sensor networks (WSNs) are powered by energy-constrained batteries is one of the main problems with these networks, as it significantly affects the effectiveness, dependability, and durability of the system. As a result, several clustering strategies have been created to improve WSNs' energy efficiency. The use of multiple-input multiple-output (MIMO) antennas is required for fifth-generation (5G) transmissions in many Internet of Things (IoT) applications in order to provide enhanced capacity in a multipath spectrum environment. We think that balancing the energy usage per unit area is preferable to using a single sensor that can provide greater load balancing use. In 5G networks, the IoT devices are enmeshed with a variety of MIMO transmission interfaces. An efficient clustering strategy for quickly growing IoT systems is both absent and urgently required to handle a range of user situations now that MIMO is more frequently available on IoT devices. The quality of experience (QoE) for transmitting in clusters for IoT networks is the main goal of the intelligent MIMO-based 5G balanced energy-efficient protocol that we suggested in this research. In compared to the current protocols, the suggested protocol uses 30% less energy while improving network longevity and energy efficiency.

Social Media and Focus-group Based Purchase-Intention Determinants of Automobile Industry In India

Anuradha Banerjee, Basav Roychoudhury, Bidyut Jyoti Gogoi — 2023-08-15

The current research is of exploratory nature that finds out and analyzes antecedents of automobile purchase intention (API) of Indian customers in recent times. The pandemic of Covid has recently calm down and markets are working hard towards prosperity. Many customers have deferred their purchase plans and many are looking for more price-efficient alternatives. However, there are others who are looking for safe and personal mobility to maintain social distancing. In this context, it is worthwhile to study the influencers of API of customers. Based on price value of the vehicle a customer already owns, components of his next choice of vehicle is determined here by extracting and analyzing social media review comments. Subsequently these are compared with responses of prospective buyers which were obtained by conducting focus group interviews where participants belong to various price ranges expressed in millions or M in short. The price ranges are obtained through cluster analysis of responses found from social media. For focus group interviews, we reached out to respondents belonging to three major cities of India - Chennai, Kolkata and Mumbai. Responses of the participants have been analyzed both qualitatively and quantitatively. Qualitative analysis helped us to extract names of the antecedents where quantitative analysis estimates their overall impact on API. Function approximation is applied to quantify the antecedents separately for focus group and social media. Values of antecedents have been mathematically expressed as function of purchase price of the vehicle a customer already owns. This information is extremely useful for vehicle manufacturers as well as salespersons. Using the technique proposed here, a vehicle manufacturer is able to figure out expectations of existing customers in terms of vehicle functionalities whereas sales persons are able to identify automobile product features they should accentuate while demonstrating a vehicle to a potential customer

Constructing A Conceptual Framework For Implementing Assistive Learning Technology To Enhance Word Problem Solving Skills In Children With Autism

ZAREENA ROSLI, FAAIZAH SHAHBODIN, CHE KU NURAINI CHE KU MOHD — 2023-08-25

Mathematical learning difficulties are the most "resistant" within intervention programmes for autistic children. Nonetheless, mathematics cannot be eliminated from the curriculum because it develops skills that will facilitate the child's social adaptation. The essence of mathematics education lies in problem-solving, as it instructs students on when to employ their acquired mathematical knowledge in practical situations, rather than simply following computational procedures. Understanding mathematics word problems may be challenging for many autisms spectrum disorder (ASD) children because it also requires literary skills. The main aim of word problem comprehension is to foster a clear understanding of the meaning behind mathematical word problems. To achieve this, it is crucial for individuals to visualize the events described in the narrative text, which contributes to the development of an accurate scenario model. However, supporting children with Autism Spectrum Disorder (ASD) in mastering word problem comprehension poses significant challenges due to various academic and cognitive factors they encounter. This study focuses on utilizing virtual reality learning technologies to explore and identify the foundational concepts that underpin word problem comprehension in autistic children. The ultimate goal is to assess how effectively these children can learn to solve word problems, leading to the development of a clear research objective. By investigating the potential integration of virtual reality into word problem learning, this research aims to provide valuable insights into supporting students in grasping word problem situations. Successfully completing this project will pave the way for incorporating more technology into special education, benefiting learners with special needs

Comparative Analysis Of Cyclostationary Feature Detection Techniques For Spectrum Sensing In Cognitive Radio Networks

Mr. Haribhau Shinde, Dr. Sandeep Garg — 2023-08-30

Modern wireless communication systems place a great deal of emphasis on the efficient use of radio frequency spectrum. Cognitive Radio networks (CR) have emerged as a promising solution to address spectrum scarcity by enabling opportunistic access to underutilized spectrum bands. In order to avoid interference, spectrum sensing, an integral part of CR, is based on detecting the presence of primary users. As part of this study, we present a comprehensive comparative analysis of the effectiveness of cyclostationary feature detection techniques for the detection of spectrum features in cognitive radio networks. Cyclostationary analysis takes advantage of the periodic properties of signals and noises to enhance the detection capability. In this paper, prominent cyclostationary-based methods, such as cyclic autocorrelation, cyclic periodogram and spectral correlation density, are examined in detail to determine their performance, robustness, and computational complexity. As a result of real-world scenarios and simulation results, it is possible to gain insight into the strengths and limitations of these techniques, thereby assisting in the selection of the optimal spectrum sensing strategy for cognitive radio networks

Artificial Neural Network Data Subscription System for Prediction by Level5 Algorithm

Binu C T and Dr.Mohan Kumar.S, Dr.Chitra Ravi — 2023-09-05

Artificial Neural Network is a techhnology which helps to get future data and for decision making.The existing algorithm in the system is slower in execution timeThe proposed Level5 algorithm is much faster and 99.9% accurate.There are different ANN methods named feed forward,recurrent network,back propagation,counter propagation,cascading Neural Network,Hopfield Network and perception Neural Network.These methods input may vary based on past,present and future data.The proposed Level5 Algorithm have data,code for past present and future of data and priority as input and obtain most accurate and faster result.

Hindi/Marathi-BART: An Efficient Sequence-to-Sequence Model for Abstractive Text Summarization for Hindi and Marathi language

Neha Rane, Dr. Sharvari S. Govilkar — 2023-09-05

The efficacy of neural sequence-to-sequence models for text summarization has been dramatically enhanced by attention-based architectures. Despite the fact that these models are effective at summarizing English documents, they are not readily transferable to other languages, leaving room for development. This paper presents Hindi/Marathi-BART, a sequence-to-sequence model designed particularly for the Hindi and Marathi languages based on the BART architecture. The model is pre-trained on a large corpus of Hindi and Marathi texts to acquire language-specific features and then fine-tuned for abstractive summarization using benchmark datasets. Despite having substantially fewer parameters, Hindi/Marathi-BART outperforms other cutting-edge models in terms of ROUGE scores, as demonstrated by experimental results. Although the ROUGE score is commonly used to evaluate the quality of automatically generated summaries, it does not adequately convey the semantic similarity between automatically generated and reference summaries. To circumvent this limitation, we augment ROUGE with BERTScore, a more sophisticated evaluator that measures the token-level semantic similarity between the generated and reference summaries. Using Hindi/Marathi-BART can facilitate the development of natural language processing (NLP) applications for these two languages. We will disseminate the model to the research community in an effort to stimulate additional investigation and application.

Segmentation Method to Obtain Required Area of Interest Using Deep Learning

Shreedevi P, H S Mohana — 2023-09-05

Segmentation is very important in the area of the analysis of the image or image in the videos. Crowd behavior analysis is very valuable economically and has numerous potential applications, including intelligent video surveillance, virtual reality, public safety, and other areas. In densely populated areas, humans might be regarded as a collection of several groups with similar motion characteristics. Groups are essential components of a crowd. A quick crowd segmentation strategy based on crowd spatiotemporal linkages is presented to get fundamental crowd interactions for subsequent crowd behavior analysis. The processing of medical images, face identification, pedestrian detection, and other applications make extensive use of image segmentation technologies. Segmentation is on Region-base, edge detection, segmentation based on clustering, segmentation based on weakly-supervised learning in CNN, etc. are some of the current picture segmentation techniques. This approach takes into account both pedestrian spatial information and crowd motion data. The technique may be used on different crowd scenarios and can get the same segmentation results in less time. The effectiveness and efficiency of the suggested approach for crowd segmentation are shown by extensive experiment results on videos of real-world crowd scenarios.

The Effect Of Organizational And Occupational Stress On The Health And Performance Of Police Officers

Anup Athawale, Dr. Sunowar Ameer — 2023-09-10

The research explores the effect of organizational and occupational stress factors on the physical and mental well-being of police officers. Furthermore, it examines potential connections between heightened stress levels among officers and incidents of custodial violence, analyzing resulting behavioral changes, decision-making patterns, and the use of force during such situations. The research methodology adopted for the paper is qualitative descriptive analysis and reviewing relevant literature. This study aims to provide insights into stress-related challenges faced by police officers. The findings will contribute to evidence-based interventions, support mechanisms, and potential reforms within law enforcement. Future research directions could delve into specialized stress management techniques, innovative training programs, and structural enhancements to alleviate stress-related risks and promote a more effective and healthier police force.

Research on the effects of online learning on students' learning process and results Coursera courses at FPT University

Tran Khai Minh Phap — 2023-09-10

Up to now, Vietnam has experienced four outbreaks of COVID-19 disease in most provinces’ city across the country. Like other countries, the COVID-19 pandemic has not only had a strong impact on socio-economic activities, but also greatly affect educational activities in Vietnam. Specifically, around March Until April 2020, when the first outbreak of the epidemic broke out in the country, all schools were forced to close and All students must leave school to prevent epidemics, according to Directive No. 16/CT-TTg of the government. According to the system As of April 2020, all 63 provinces and cities have allowed students to stay at home. Up until now, due to complicated developments Due to the complexities of the epidemic, the government of Vietnam has repeatedly implemented social distancing measures across the province. city or even on a national scale. In that context, to prevent the spread of the disease COVID-19, while maintaining the quality of teaching and completing the program on schedule, ensuring students' learning student; many schools have applied online teaching to most students. all levels of education.

Intelligent Sentimental Analysis of Learning Quotient of Students in Education 4.0

Prof.(Dr.) Vivek Kumar, Prof.(Dr.) Tanupriya Choudhury, Neena Bansal — 2023-09-10

Our Research “Intelligent Sentimental Analysis of Learning Quotient of Students In Education 4.0” is a the "Conversation" part of feeling investigation denotes a crucial stage where the outcomes and their suggestions are analyzed, giving an exhaustive translation of the opinion examination results. This portion rises above the domain of crude information and measurements, diving into the importance, setting, and more extensive ramifications of the feelings communicated inside the text-based corpus. Inside this talk, the opinion appropriation is analyzed considering the particular setting and area, revealing insight into any startling patterns, inclinations, or examples. Positive, negative, and unbiased opinion predominance is investigated to recognize whether feelings line up with assumptions and to uncover potential elements adding to feeling varieties.The exhibition measurements of feeling investigation models are fundamentally assessed to understand their exactness and constraints. Inconsistencies between feeling arrangements and genuine opinions are investigated, directing refinement systems. Bits of knowledge into the models' assets and shortcomings enable choices with respect to additional streamlining or the reception of elective procedures.

Evaluating the Efficacy and Security of Steganography Techniques in Cloud Computing

Apeksha Dave, Dr. Sandeep Singh Rajpoot — 2023-09-20

The way data is handled, accessed, and stored has been completely transformed by cloud computing. But maintaining the security and privacy of data in cloud settings is still a major challenge. This work gives a thorough investigation that tackles the goals of creating a reliable steganographic method, measuring its efficacy, gauging its influence on cloud computing performance, and looking into potential flaws and remedies. Assessing how steganography affects cloud computing system performance is the goal here. To examine the impact of steganography on overall system performance, performance assessments and benchmarks are carried out. In order to imitate real-world situations, several file formats and sizes are employed. It looks at potential weaknesses in the suggested steganographic technique and looks into mitigation strategies for these weaknesses. The analysis of security flaws, including attacks and detection methods, results in the development of suitable countermeasures. The results of this study help steganography-based data security in cloud computing settings develop. The study sheds light on the advantages, disadvantages, and possible areas for development of the suggested steganographic approach. The performance assessment and vulnerability analysis provide insight into how steganography affects cloud computing systems and aid in the creation of efficient defences.

Automated Robotic Placement of Secured Object in Appropriate Location Using ML

Madhurjya Baruah, Biplab Kumar Sarkar, Reena Singh — 2023-09-20

The convergence of robotics, automation, and machine learning has ushered in a new era of precision and efficiency in object placement processes. This research investigates the development and implementation of an advanced automated robotic system capable of securely placing objects in designated locations, revolutionizing industries such as manufacturing, logistics, and healthcare. The keywords for this research are: automated robotics, secured object placement, machine learning, computer vision, motion planning, and precision. Our system integrates state-of-the-art machine learning techniques, including computer vision for object recognition and motion planning for path optimization. Reinforcement learning is employed for fine-tuning robotic control, ensuring both accuracy and efficiency in object placement. Through rigorous experimentation, this paper showcases the system's remarkable capabilities, addressing challenges and paving the way for practical applications across a multitude of domains. This research not only promises to enhance automation processes but also underscores the potential for significant advancements in secure, precise, and reliable object manipulation using modern machine learning techniques

The Return of In-person Classes in the State-Run Basic Education Institutions in the Philippines: Viewpoints of Teachers Working in Remote Locations

2023-09-20

Remote schools in the Philippines continue to experience a lack of teaching resources and instructors are continuously challenged to provide quality basic education in the countryside. Teachers with passion and dedication are required in remote institutions to provide the services that are sorely needed. During the resumption of classes, the purpose of this study was to characterize and analyze the transitional experiences of teachers assigned to remote locations. The study utilized phenomenological research methods using in-depth interviews and focus group discussions, this study discovered that assigning teachers far from their hometowns is difficult and not simple not only for them but also for teachers across the nation. The findings revealed that teachers' actual experiences included traveling by sea, riding a motorcycle or "habal-habal" that requires payment, cultural differences, no internet connection or cellular data, and system and curriculum adjustments. Teachers in this study are looking forward to a much better assignment in the future, despite the rewarding experiences they have had serving a disadvantaged community.

The Role of Machine Learning and Deep Learning Approaches in the field of HealthCare

2023-09-28

Healthcare and medical science are the most happening area in the last few decades. There are lot many technological innovations carried out in this field as per the need of the current era. Healthcare has gained a prominent place in human lives. Predictive and analysis tools are urgently needed as a result of the development of technology in health care and medical sciences, which produce vast amounts of data that are beyond the capacity of humans. Their findings will open up a variety of research opportunities while also fostering improved judgments and decision-making in medical and healthcare companies. This leads to addressing the prominent use of advanced technologies namely, artificial intelligence and its subsets which imitate human intellect, evaluate data, and produce truthful outcomes. One of them is machine learning, which uses predetermined computer learning patterns for a certain dataset to achieve novel outcomes with previously undiscovered data.

As machines learn how to optimize themselves to deliver amazing results, this requires the least amount of human interaction. However, it is not without flaws, as these algorithms cannot learn deep patterns and do not learn with accuracy. To address these issues, deep learning algorithms have been developed. There are numerous layers or levels of abstraction in a deep learning environment, which aids in identifying the intricacy of the patterns hidden in the data. This paper is constructed with the goal to scrutinize the place of ML and DL in the healthcare and medical industries. Also, it provides an overview of medical imaging in the machine and deep learning techniques used for analyzing different diseases.