Recommendation systems have become increasingly important in various online applications. One of the significant types of research in machinelearning (ML) is recommendation systems. A recommender system, alternativel...
Recommendation systems have become increasingly important in various online applications. One of the significant types of research in machinelearning (ML) is recommendation systems. A recommender system, alternatively referred to as a recommendation system, is an information filtering system that supports users in identifying their “rating” or “preference” for an object and makes predictions based on that rating or preference. This research analyzes current recommendation systems applied in ML public instances to explore knowledge discovery. The suggestions systems are developed for musical, online dating, and restaurant applications. The recommendation system serves as a tool to assist users in discovering what they are interested in by providing them with appropriate ideas. To provide personalized recommendations to users, primarily employ collaborative, content-based, session-based, demographic, and hybrid filtering. Classification, clustering, and association rule discovery are the critical datamining and ML techniques most widely employed in recommendation systems. In general, the accuracy of the recent models lies at (75%, 99 % ) and the error rate occurs at (5%, 25 % ) for the ML public instances.
Twitter is one of the broadly used social networking structures with greater than 192 million each day lively customers and a 500 million Tweets. Basically, Twitter is reaching a large target audience, connects quite ...
详细信息
Accurate prediction of student academic performance is crucial for educational institutions and parents to implement proactive intervention strategies. This study employs machinelearning algorithms to predict the gra...
详细信息
ISBN:
(数字)9798350367492
ISBN:
(纸本)9798350367508
Accurate prediction of student academic performance is crucial for educational institutions and parents to implement proactive intervention strategies. This study employs machinelearning algorithms to predict the graduation outcomes of undergraduate students, focusing on the effectiveness of various algorithms. We used the Random Forest algorithm and compared its performance with Decision Tree, Nave Bayes, Artificial Neural Network, and Support Vector machine, utilizing the Orange datamining tool. Our evaluation metrics included Area Under Curve (AUC), accuracy, F1-score, precision, and recall, applied to a dataset of 387 students from the class of 2017 who graduated on time in 2021 and 2022. The features considered were ID, study program, age, sex, GPA of the first semester and GPA of the second semester. The Random Forest algorithm achieved the highest accuracy at 95%. This research contributes to the early identification of students at risk of academic failure and highlights the most effective machinelearning algorithm for predicting academic outcomes in higher education.
Cultivating intelligence is an important part of the process of data analysis and research. Therefore, it is necessary to conduct a comprehensive evaluation of human resource *** talent training quality research is cr...
详细信息
ISBN:
(数字)9798350354171
ISBN:
(纸本)9798350354188
Cultivating intelligence is an important part of the process of data analysis and research. Therefore, it is necessary to conduct a comprehensive evaluation of human resource *** talent training quality research is critical in the comprehensive evaluation of undergraduate majors to improve talents, however it has an issue with erroneous performance positioning. The typical Digital mining algorithm is unable to address the talent training issue in the comprehensive evaluation of undergraduate majors to improve talents, and the result is insufficient. As a result, a Association rule mining algorithm-based the Comprehensive Evaluation of Undergraduate Majors to Improve the Quality of Talent Training is provided, and the the Comprehensive Evaluation of Undergraduate Majors to Improve the Quality of Talent Training is assessed. To begin, the association rule theory is used to discover the influencing elements, and the indicators are split based on the talent training quality research’s needs to decrease interference factors in the talent training quality research. The association rule theory is then used to create a Association rule mining algorithm talent training quality research scheme, and the outcomes of the talent training quality research are thoroughly examined. The MATLAB simulation results reveal that, under particular evaluation conditions, the Association rule mining algorithm outperforms the standard Digital mining algorithm in terms of talent training quality research accuracy and time of influencing variables. The results show that the analysis of intelligent methods is needed to improve the recognition accuracy of talent training. Therefore, the results of the study show that the accuracy of talent identification can be improved by between 10% and 15%.
Few-shot learning for image classification aims at predicting unseen classes with only a few images. Recent works, especially the works on few-shot fine-grained image classification (FSFGIC), have achieved great progr...
详细信息
This study investigates the use of automatically derived visual characteristics in recommender systems and offers several novel contributions to the field of video recommendations. Because it is difficult for customer...
详细信息
Big data Analytics has developed as a judgment technique for unopened organizations to uncover hidden patterns, relationships, industry trends, and consumption patterns. Newline Of the most common sources of big data ...
详细信息
ISBN:
(纸本)9781665450461
Big data Analytics has developed as a judgment technique for unopened organizations to uncover hidden patterns, relationships, industry trends, and consumption patterns. Newline Of the most common sources of big data is Viral marketing data sets, as Web 2.0 null byte technology generate massive social corpora from our everyday routines. Newline in basic language Web 2.0 technology applications including Internet newline data analytics, relationship management, Text Analytics, and opinion line break mining depend heavily on *** before compared to prestige cellular networks, 5G cellular networks have many major updates, such as network data analytics-based network data analytics, which will allow network administrators to either implement their own machinelearning (ML)-based data analytics methodologies or incorporating third-party solutions into their networks. This study originally presents the structure and protocols of network data analytics based on the 3rd Generation Partnership Project (3GPP) standard standards. Then, based on the fields specified by the 3GPP specification, a cell-based artificial data set for 5G networks is *** slice, a major 5G technology, divides a physical network into many virtual end-to-end networks, each of which may receive logically separate network resources to offer richer services. 5G mobile data and sensor data are combining to produce an increasing network traffic. Traffic explosion has grown into a mixed network type, involving network viruses, worms, network theft, and hostile assaults. How to differentiate traffic kinds, restrict fraudulent traffic, and make optimal use of sensor data in the context of a 5G network slice, as well as the importance of this researchAdditionally, some abnormalities are added to this collected data (for examples, unexpected increased volume in a particular tissue), and so these irregularities are categorized within each compartment, subscriber's category, and remote controlle
How safe our food supply is and how productive our agriculture is are both significantly impacted by plant diseases. For prompt cures and efficient management of plant diseases, accurate diagnosis, close observation, ...
How safe our food supply is and how productive our agriculture is are both significantly impacted by plant diseases. For prompt cures and efficient management of plant diseases, accurate diagnosis, close observation, and foresight are necessary. Methods like deep learning, feature extraction, and picture recognition are frequently used in disease detection. For farmers, agronomists, and decision-makers, machinelearning can be used to distinguish, monitor, and forecast illness affecting plants. The Plant Village data set is meticulously segmented for disease prediction training and testing; as a result, several plant species are acknowledged and given new names to make an accurate database. The classifier is then trained using training data, and the output will then be detected with the highest accuracy possible. Therefore, this study presented a CNN-based system for disease detection in plants and also evaluated the overall performance of various classifiers at the study's records set to decide which had the most accuracy. The performance and usability of machinelearning models must be improved through ongoing research and development if we are to eventually see more effective and sustainable farming practices. The created model also maps the soil and crop database and recommends appropriate crops depending on the number of nutrients available in the soil, enabling farmers to choose the right crops to be sown in their fields. Therefore, it is important to identify crop diseases as soon as possible. Farmers will profit from using a quick, creative approach and a crop recommendation system.
The social media is becoming an increasing trend for sharing the thoughts, ideas, opinions, etc. based on online reviews which generates a tremendous amount of unstructured data (ie. User posts). For processing those ...
详细信息
ISBN:
(纸本)9781665428644
The social media is becoming an increasing trend for sharing the thoughts, ideas, opinions, etc. based on online reviews which generates a tremendous amount of unstructured data (ie. User posts). For processing those unstructured data supervised learning algorithms are preferred which helps for better performance optimization. Few years ago, Deep learning (DL) techniques (ie. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN)) models has become popular in healthcare applications by giving the rise in complicacy of the healthcare data. Deep learning (DL) Techniques provides an effective and efficient model for data analysis by uncovering the masked patterns and find the meaningful information from the significant amount of health data whereas the traditional analytics does not able to produce within a stipulated period. Specifically, Deep learning (DL) techniques consist of yielding good results by using the models of patternrecognition for social healthcare networks. The study of this paper focuses on by investigating the models of deep learning (DL) techniques applied to classify the text in social media healthcare networks. The main intention of this review provides an insight for training the data and to classify the text by analyzing and extracting the raw input and produce the output with the help of Natural language processing (NLP). Overall, the purpose of this review is to enhance the performance of the text classifier based on effectiveness to improve accuracy and text processing speed by using a suitable methodology in order produce the promising results in the future.
Recent advancements in artificial intelligence and machinelearning have significantly improved healthcare, especially in the development of assistive technologies for rehabilitation. This paper introduces a method fo...
详细信息
ISBN:
(数字)9798331544546
ISBN:
(纸本)9798331544553
Recent advancements in artificial intelligence and machinelearning have significantly improved healthcare, especially in the development of assistive technologies for rehabilitation. This paper introduces a method for hand rehabilitation that utilizes the capabilities of tiny machinelearning to enhance speech classification in a rehabilitation device. The proposed method employs a CNN model capable of classifying speech signals that are indicative of different hand movement patterns. Patients emit these speech signals during prescribed hand exercises, which are crucial for their rehabilitation process. The main focus of this study is on training and deploying a speech classification system that can work in the resource-limited environment of TinyML platforms. We detail the process of capturing speech data, preprocessing it, and extracting the most features relevant to different hand movements. Our results show that using TinyML to help with hand rehabilitation works. The method we came up with shows how TinyML could change the way rehabilitative devices are controlled, and it also shows us what personalized and easy-to-use rehabilitation tools might look like in the future.
暂无评论