A5040463901- Stock Market Forecasting Methods
- Recommender Systems and Techniques
- Handwritten Text Recognition Techniques
- Topic Modeling
- Text and Document Classification Technologies
- Vehicle License Plate Recognition
- Natural Language Processing Techniques
- Image Retrieval and Classification Techniques
- Image Processing and 3D Reconstruction
- Speech Recognition and Synthesis
- Data Management and Algorithms
- Forecasting Techniques and Applications
- Human Mobility and Location-Based Analysis
- Energy Load and Power Forecasting
- Advanced Image Processing Techniques
- Energy Efficient Wireless Sensor Networks
- Financial Markets and Investment Strategies
- Precipitation Measurement and Analysis
- Advanced Computational Techniques and Applications
- Vehicular Ad Hoc Networks (VANETs)
- Opportunistic and Delay-Tolerant Networks
- Digital Marketing and Social Media
- Mobile Ad Hoc Networks
- Music and Audio Processing
- Geographic Information Systems Studies
Nirma University
2014-2024
In modern times, it has become very essential for e-commerce businesses to empower their end customers write reviews about the services that they have utilized. Such provide vital sources of information on these products or services. This is utilized by future potential before deciding purchase new These opinions are also exploited marketers find out drawbacks own and alternatively related competitor's in turn allows identify weaknesses strengths products. Unfortunately, this significant...
Optimizing a stock market portfolio requires decision making at two distinct stages, first is to select the stocks and second assign distribution of investment amount among these selected stocks. Given historical data stocks, role optimization models proportion Selection weight assignment are co-occurring activities. Investors prime motive maximize return minimize risk portfolio. Stock uncertain volatile therefore, Artificial Intelligence, Machine Learning Soft Computing techniques viable...
Gujarati is one of the ancient Indian languages spoken widely by people Gujarat state. This paper concerned with recognition handwritten numerals. For numerals zoning based Feature extraction method used. Numeral image divided in 16×16, 8×8, 4×4 and 2×2 Zones. After feature through method, Naive Bayes classifier multilayer feed forward neural network are implemented for classification database generation, 14,000 samples each numeral The overall rates this used using 93.03%, 95.92%, 91.89%...
Abstract It has always been a challenge to accurately forecast the behavior of stock market due its extremely nonlinear and dynamic nature. Numerous studies have shown that technical indicators describing stocks in conjunction with machine learning models can serve as useful tools for forecasting market. There are various challenges, one them is choice right prediction models. believed there no optimal set work well all scenarios environment such The statement also applies different definite...
Social bookmarking system is a web-based resource sharing that allows users to upload, share and organize their resources i.e. bookmarks publications.The has shifted the paradigm of from an individual activity limited desktop collective on web.It also facilitates user annotate his with free form tags leads large communities collaboratively create accessible repositories web resources.Tagging process its own challenges like ambiguity, redundancy or misspelled sometimes tends avoid it as he...
Languages have played a major role in Indian history and they continue to influence the lives of Indians till date. Plentiful research on optical character recognition (OCR) techniques for languages such as Hindi, Tamil, Bangla, Kannada, Gurumukhi, Malayalam Marathi has already been carried out. Research efforts Gujarati are few yet gain momentum. This paper intends bring attention. Methods based artificial neural network (ANN), support vector machine (SVM) naive Bayes (NB) classifier...
The paper explores the use of convolutional neural networks (CNNs) to predict movement stock market from a classification perspective.Standard methods yield results with very low confidence and precision.We therefore propose CNN enhanced by multi-size feature maps spatial mapping that will provide more accurate two-way for collection stocks.We also transforming indicators data into map/image so they can be processed using CNN.Our model fairs at an average 80% weighted F1-score movement.A...