Context: Agriculture stands as a pivotal driver of economic progress within a nation, yet the realm of technical advancements within this sector remains distressingly neglected by a multitude of governments. While far...
Context: Agriculture stands as a pivotal driver of economic progress within a nation, yet the realm of technical advancements within this sector remains distressingly neglected by a multitude of governments. While farmers contribute untiring efforts to tend to their fields, substantial time is squandered on tasks like irrigation and safeguarding crops from birds and animal threats [1, 2]. This unwavering dedication often exacts a toll on farmers’ health, leading to ailments and respiratory issues stemming from exposure to noxious gases emitted by certain crops. Extensive research endeavours [3-9] have been undertaken to alleviate the burdens faced by farmers. These efforts, however, frequently culminate in singular applications such as automated irrigation systems or electric perimeters for crop protection. A subset of researchers has also delved into probing the prevalence of harmful gases across agricultural fields. This paper proposes an innovative approach to address these challenges through the utilization of Internet of Things (IoT) technology. Objective: The proposed solution canters on a NodeMCU powered intelligent crop field Monitoring-Protection-Alert (MPA) system, which serves as a technical path to revolutionize farming practices. The core objective underpinning the proposed system is the acquisition of real-time insights emanating from the crop field. This critical initiative empowers farmers with timely and accurate data, enabling them to make informed and precise decisions pertaining to their agricultural domain. Methods: By seamlessly integrating various sensors, the system detects the presence of birds, animals, and noxious gases in real-time. Furthermore, it enhances crop productivity by continuously monitoring soil parameters, including temperature and moisture levels, thereby optimizing irrigation processes. For seamless communication, the system is fortified with a GSM module that promptly alerts farmers about potential threats to their crops.
Cricket is one of the games having the most number of followers and spectators in India. Among them, T20 League cricket is getting more attention. This paper have focused on performing an exploratory data analysis on ...
Cricket is one of the games having the most number of followers and spectators in India. Among them, T20 League cricket is getting more attention. This paper have focused on performing an exploratory data analysis on Indian Premier League or IPL dataset utilizing the previous match details to draw hidden insights and patterns in data and further using it for the prediction of match outcomes. Indian Premier League or IPL results are always unpredictable, a large number of factors like venue, toss decision, player’s performance etc., determines the result of matches. Hence, on performing the analysis have drawn many important insights like whether home ground favors the winning of match, whether toss decision plays any role, who is the player of match of the season etc., were identified. Then, machine learning algorithms are applied on the relevant features for the prediction of matches. Finally, the accuracies of these algorithms are plotted to compare the performances to figure out the most accurate among them. The results illustrates that XGB Classifier showed the highest accuracy rate of 69.12%.
作者:
Vaishali B. BhagatV. M. ThakareSagar PandeResearch Scholar
PG Department of Computer Science and Engineering Sant Gadge Baba Amravati University Amravati Maharashtra India Professor and Head
PG Department of Computer Science and Engineering Sant Gadge Baba Amravati University Amravati Maharashtra India Assistant Professor
Intelligent System School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India
In this era of technology, online data is increasing enormously in various forms be it images, videos, texts, sound, etc. Now with increasing data, there arises the issue of storage and that’s the time when Bigdata a...
In this era of technology, online data is increasing enormously in various forms be it images, videos, texts, sound, etc. Now with increasing data, there arises the issue of storage and that’s the time when Bigdata and its tools come into the picture. To analyze the big data and process it with the available traditional methods, becomes an extremely strenuous task. And to overcome this drawback, there are various big data tools and techniques available. Some of the techniques that are used to analyze big data are the techniques of data mining such as clustering, classification, division, and prediction. The tools that are used in analyzing the big data are MongoDB, NoSQL, HPCC, Apache Storm, Spark, Apache Hadoop, also these tools are used in handling big data. In this paper, analysis of big data tools and techniques has been done with different examples and instances. To understand the tools better, their summaries along with examples are presented.
The growth in the number of sellers in both the offline and online markets has necessitated the development of analytic tools that may assist assess whether a company is reaching its sales targets. Our proposal Sales ...
The growth in the number of sellers in both the offline and online markets has necessitated the development of analytic tools that may assist assess whether a company is reaching its sales targets. Our proposal Sales Upsurge System explains the requirement for a system to evaluate the product offered utilising Machine learning, data mining approaches, and algorithms such as Affinity analysis, Association rule learning- Apriori. Our proposed system idea for this project is to create a system (website) that takes the input of sold products, categories the data obtained, analyses the data, and extracts the sales trend, and then optimizes the data based on market requirements, thereby maximize the value of sales and merchandise planning and increasing the organization's overall sales and profits.
Intelligent video surveillance and transportation systems have become more important in the field of security in recent years for identifying abnormal events that happen along the side of the road. Recent developments...
Intelligent video surveillance and transportation systems have become more important in the field of security in recent years for identifying abnormal events that happen along the side of the road. Recent developments in surveillance systems include the automatic detection of abnormal events in video surveillance. However, only one normal event is accessible for the learning process in the context of abnormal event detection. In this scenario, the idea addresses a novel unsupervised deep one class learning architecture. It can produce optical flow pictures from original movies in addition to generating concise spatio-temporal characteristics for abnormal event detection resolutions. To guarantee that the "deep-one" class learning is classified correctly, it is built using a customized loss function which is the combination of 3 terms: Reconstruction Loss (RL), Generation Loss (GL), and Compactness Loss (CL). On a relatively challenging dataset known as the UCSD anomalous detection dataset, the suggested technique achieved better results than the existing methods, the Satellite Smoke Scene Detection dataset, and the Cross View Geo localization dataset. The experimental results assure that the proposed work provides higher accuracy then the state of art techniques.
Electrification is one of the appropriate way to establish a clean and energy efficient transportation. The impact of electric vehicle on the environment is considered as a serious issue. The locomotive industry as we...
Electrification is one of the appropriate way to establish a clean and energy efficient transportation. The impact of electric vehicle on the environment is considered as a serious issue. The locomotive industry as well as power sector gets benefitted by the reliable technology provided by the electric vehicle. This green vehicle also helps in creating an alternative power source for household applications and provide ancillary services to the grid. It also helps in integrating the intermittent resources for vehicle charging. As this vehicle generates prominent feature of less maintenance and ease of charge at residential premises. The electric vehicle creates a significant role in power sector mainly in the application of smart grid and act as a smart vehicle through grid communication. The challenges imposed by the electric vehicle and its effects in the transportation and energy sector are elaborately addressed in this paper.
Unregulated glucose levels in the blood lead to the chronic disease diabetes. Diabetic foot ulcers (DFUs) and other devastating outcomes may be avoided with early detection. The lower limb of a diabetic patient may ne...
Unregulated glucose levels in the blood lead to the chronic disease diabetes. Diabetic foot ulcers (DFUs) and other devastating outcomes may be avoided with early detection. The lower limb of a diabetic patient may need to be amputated if they experience a DFU. DFU is difficult to diagnose and usually requires a number of expensive and time-consuming clinical investigations for the treating physician. Applying deep learning, machine learning, and computer vision techniques in today's age of data deluge has resulted in a number of solutions that can help doctors make more accurate diagnoses in less time. As a result, researchers have recently focused more on developing methods for automatically identifying DFU. Preprocessing, segmentation, feature extraction, and model training are all used in the suggested method. It does noise reduction and RGB to HSI color space conversion during preprocessing. OSTU thresholding segmentation is used for the separation. It uses histogram for feature extraction and Improved CNN-SVM for model training. The new method is compared to two common approaches, including CNN and CNN-SVM, and fares better than both.
Outcome based education (OBE) is student-centered instruction model that stresses on judging student performance through outcomes. Outcomes include knowledge, skills and behavior. Outcome-Based Education model is bein...
详细信息
Outcome based education (OBE) is student-centered instruction model that stresses on judging student performance through outcomes. Outcomes include knowledge, skills and behavior. Outcome-Based Education model is being adopted at a fast pace at Technical institutions all over the world. It is considered as a massive leap forward to convalesce technical education and help Engineers compete with their global counterparts. OBE gives more weightage on what the students will be able to ‘do instead of what they will ‘know’. Hence it is important to develop the instructional model to improve knowledge, skill, behaviour of the students. Knowledge structure is the micro level component and the part of the course outcome which will enable the student to gain the confidence of ‘doing’ instead of ‘knowing’. This paper proposes an Instructional Model by developing a knowledge structure in Power Electronics engineering.
This paper proposes a novel security method for protecting biometric fingerprint templates and storing them safely by creating a combined fingerprint template from different fingerprints, thereby creating a new virtua...
This paper proposes a novel security method for protecting biometric fingerprint templates and storing them safely by creating a combined fingerprint template from different fingerprints, thereby creating a new virtual identity during enrolment. However, the second fingerprint image combined would be an image that was dynamically created by merging parts of several different images based on a merging algorithm used. We further extract the minutiae features from the two fingerprints. A combined fingerprint template is produced using the extracted information. Finally, the biometric values from the template are stored in a user-defined tree created. A new virtual identity is thus created to protect biometric templates from hackers and crackers. Even though the hacker has access to the database, they will not be able to match the biometric template with a person’s identity. Thus, when the database is stolen, the method avoids compromising complete minutiae features belonging to a single fingerprint. The proposed method achieves 0.3% FRR and 0.1% FAR. Hence, it balances both the recognition and security of the system.
In recent years, there is a tremendous explosion in the amount of text data on the internet and in the archives of news articles, scientific papers, legal documents and even in online product reviews. Text summarizati...
In recent years, there is a tremendous explosion in the amount of text data on the internet and in the archives of news articles, scientific papers, legal documents and even in online product reviews. Text summarization is playing an important role in automatic content creation, minutes of meeting generation, helping disabled people and also for quick online document reading. To achieve these, several automation techniques have been proposed in various researches. In this regard, performing an exclusive survey on different methods, approaches of automatic text summarization which are published in different articles in most recent three years.
暂无评论