The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords’ combinations of “machine learning” along with “crop management”, “water management”, “soil management”, and “livestock management”, and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018–2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Machine Learning in Agriculture: A Comprehensive Updated Review.

A survey of public datasets for computer vision tasks in precision agriculture

Clinical Decision Support Systems for Triage in the Emergency Department using Intelligent Systems: a Review.

A rise in the population has immensely increased the pressure on the agriculture sector. With the advent of technology, this decade is witnessing a shift from conventional approaches to the most advanced ones. The Internet of Things (IoT) has transformed both the quality and quantity of the agriculture sector. Hybridization of species along with the real-time monitoring of the farms paved a way for resource optimization. Scientists, research institutions, academicians, and most nations across the globe are moving towards the practice and execution of collaborative projects to explore the horizon of this field for serving mankind. The tech industry is racing to provide more optimal solutions. Inclusion of IoT, along with cloud computing, big data analytics, and wireless sensor networks can provide sufficient scope to predict, process, and analyze the situations and improve the activities in the real-time scenario. The concept of heterogeneity and interoperability of the devices by providing flexible, scalable, and durable methods, models are also opening new domains in this field. Therefore, this paper contributes towards the recent IoT technologies in the agriculture sector, along with the development of hardware and software systems. The public and private sector projects and startup’s started all over the globe to provide smart and sustainable solutions in precision agriculture are also discussed. The current scenario, applications, research potential, limitations, and future aspects are briefly discussed. Based on the concepts of IoT a precision farming framework is also proposed in this article.

/pdf/recent-developments-of-the-internet-of-things-in-agriculture-2c4yp6bn20.pdf

Recent Developments of the Internet of Things in Agriculture: A Survey

With the exponential growth of the human race that means the growth of population, the conventional or ancient farming methods are becoming unable to cope with the growth with satisfaction. Hence advanced farming methods are much needed to approach the necessity of foods of this growing number of people. In the recent few years, smart farming systems based on embedded systems and the Internet of Things (IoT) getting attraction and popularity among people to enhance food production for people. This paper has prescribed farming systems based on the embedded systems, IoT and wireless sensor networks for agri-farm field and livestock farms. This paper includes the description of systems with the electronic circuitry of the systems, used network protocols and smart distant monitoring systems for PCs and Smartphones, etc. Later it includes some propositions and finally, the paper concludes with describing the future scopes of relevant technologies in smart farming.

A smart farming concept based on smart embedded electronics, internet of things and wireless sensor network

The multimedia applications such as audio, video transmission in Mobile Ad Hoc Network (MANET) requires that the path in which such data transmits must be delay sensitive, reliable and energy efficient. An existing MANET routing protocol Ad Hoc On demand Multipath Distance Vector (AOMDV) fails to perform well in terms of QoS metrics such as delay, jitter, packet delivery ratio (PDR) etc., where there is high mobility and heavy traffic. The paths which are stored in the Routing table are not reliable and energy efficient. It is possible to modify the route discovery of AODV so that more than one node disjoint, link reliable and energy efficient paths are stored in the routing table. The proposed protocol Multiconstrained and Multipath QoS Aware Routing Protocol (MMQARP) is novel, which takes care of QoS parameters dynamically and simultaneously along with path finding, so that only link reliable, energy efficient paths are available for data transmission. The extensive simulation study shows that the proposed protocol performs better in terms of PDR, delay and jitter compared to AOMDV protocol.

Multiconstrained and multipath QoS aware routing protocol for MANETs

Wireless sensor network applications in the agricultural sector are gaining popularity with the advancement of the Internet of Things technology. Predominantly, wireless sensor networks are used in agriculture to sense the important agricultural field parameters, such as temperature, humidity, soil moisture level, nitrite content in the soil, groundwater quality, and so on. These sensed parameters will be sent to a remote station, where it will be processed and analyzed to build a decision support system. This paper describes the implementation of a wireless visual sensor network for precision agriculture to monitor paddy crop for weeds using Raspberry Pi. Bluetooth 4.0 was used by visual sensor nodes to send the data to the base station. Base station forwarded the data to the remote station using IEEE 802.11 a/b/g/n standard. The solar cell battery was used to power up the sensor nodes and the base station. At the remote station, images were preprocessed to remove soil background and different shape features were extracted. Random forest and support vector machine classifiers were used to classify the paddy crop and weed based on the shape features. The results and observations obtained from the experimental setup of the system in a small paddy field are also reported. This system could be expected to enhance the crop production by giving timely advice to the crop producers about the presence of weeds so that steps can be taken to eradicate weeds.

/pdf/raspberry-pi-as-visual-sensor-nodes-in-precision-agriculture-23ugtl9pt0.pdf

Raspberry Pi as Visual Sensor Nodes in Precision Agriculture: A Study

Weeds are unwanted plants that grow among crops +ese weeds can significantly reduce the yield and quality of the farm output Unfortunately, site-specific weed management is not followed in most of the cases +at is, instead of treating a field with a specific type of herbicide, the field is treated with a broadcast herbicide application +is broadcast application of the herbicide has resulted in herbicide-resistant weeds and has many ill effects on the natural environment +is has prompted many research studies to seek the most effective weed management techniques One such technique is computer vision-based automatic weed detection and
identification Using this technique, weeds can be detected and identified and a suitable herbicide can be recommended to the farmers +erefore, it is important for the computer vision technique to successfully identify and classify the crops and weeds from the digital images +is paper investigates the multiple classifier systems built using support vector machines and random forest
classifiers for plant classification in classifying paddy crops and weeds from digital images Digital images of paddy crops and weeds from the paddy fields were acquired using three different cameras fixed at different heights from the ground Texture, color, and shape features were extracted from the digital images after background subtraction and used for classification A simple and
new method was used as a decision function in the multiple classifier systems An accuracy of 9136% was obtained by the multiple classifier systems and was found to outperform single classifier systems

/pdf/paddy-crop-and-weed-discrimination-a-multiple-classifier-1v7foygy7i.pdf

Paddy Crop and Weed Discrimination: A Multiple Classifier System Approach

Computers have become an integral part of human lives. Computers are used in almost every field even in agriculture. Technologies like computer vision-based pattern recognition are being used to detect diseases and pests like weeds affecting the crop. The Weeds are unwanted plants growing among crops competing for nutrients, water, and sunlight. It can significantly reduce the quality and yield of the crops incurring a huge loss to the farmers. This paper investigates the use of texture features extracted from Laws’ texture masks for discrimination of Carrot crops and weeds in digital images. Laws’ texture method is one of the popular methods used to extract texture features in medical image processing, though not much explored in plant-based images or agricultural images. This experiment was carried out on two categories of benchmark digital image datasets of Carrot crop and Carrot weed respectively, which are publicly available. A total of 70 texture features were extracted. The dimensionality reduction technique was used to get the optimal features. These features were then used to train the Random Forest classifier. The results and observations from the experiment showed that the classifier achieved above 94% accuracy.
Keywords: precision agriculture, crop, weed, texture analysis, classifier
DOI: 10.25165/j.ijabe.20201301.4920

Citation: Kamath R, Balachandra M, Prabhu S. Crop and weed discrimination using Laws’ texture masks. Int J Agric & Biol Eng, 2020; 13(1): 191–197.

Crop and weed discrimination using Laws’ texture masks

Abstract Weeds are unwanted plants in a farm field and have harmful effects on the crops. Sometimes rigorous weeds bring down the crop yield significantly, causing huge losses to farmers. A prevalent method of controlling weeds is the use of chemical herbicides. These herbicides are known to cause harmful effects on our environment. One of the ways to control the ill effects of herbicides is to follow the Site-Specific Weed Management (SSWM). Site-specific weed management is to use the right herbicide for the right amount on agricultural land. This paper investigates a semantic segmentation approach to classify two types of weeds in paddy fields, namely sedges and broadleaved weeds. Three semantic segmentation models such as SegNet, Pyramid Scene Parsing Network (PSPNet), and UNet were used in the segmentation of paddy crop and two types of weeds. Promising results with an accuracy over 90% has been obtained. We believe that this can be used to recommend suitable herbicide to farmers, thus contributing to site-specific weed management and sustainable agriculture.

https://www.tandfonline.com/doi/pdf/10.1080/23311916.2021.2018791?needAccess=true

Mamatha Balachandra

Papers

Multiconstrained and multipath QoS aware routing protocol for MANETs

Raspberry Pi as Visual Sensor Nodes in Precision Agriculture: A Study

Paddy Crop and Weed Discrimination: A Multiple Classifier System Approach

Crop and weed discrimination using Laws’ texture masks

Classification of paddy crop and weeds using semantic segmentation