Sensors in agriculture are in use from weather monitoring to autonomous watering. Using low-cost sensors allows designers to create a prototype for a hardware environment to implement data acquisition and mining process. Thus, the relation between sensors can be understood and a test environment for sensor fusion can be created. In this paper, different input devices are synchronized by using a microcontroller system and each data, obtained from the sensors, are sent wirelessly by an (Internet of Things) IoT device to the cloud, by recording and monitoring from the graphical user interface on the web as a real-time environment to apply data mining algorithms thereafter. This study uses the regression trees to obtain the sensor data relations from 8 different data related to light, temperature, humidity, rain, soil moisture, atmospheric pressure, air quality, and dew point. Each sensor data has a different effect on the agricultural monitoring, however, reducing the number of sensors can reduce the cost of a system, by giving still accurate observations via sensor substitution proposed. Therefore, by using the regression trees, the classification of sensor data is inspected in this study. A test prototype of the hardware together with the software design is created for data monitoring and sensor fusion in different combinations. In the end, after fusion tests for all possible cases, outstanding results for each sensor substitution is presented. Temperature and dew point can be obtained using other sensors by fusing the train data on the regression tree by 92% and 84% accuracy respectively with a 5% numerical error margin in the leaf nodes on the regression tree.

Stochastic computing (SC) is an alternative computing paradigm that processes data in the form of uniform bit-streams. SC is fault-tolerant and can compute on small, efficient circuits. However, SC is primarily used in scientific research, and its practical implementations for end-users are rare. Digital sound source localization (SSL) is a useful signal processing technique that locates speakers using multiple microphones. SC has not been integrated into SSL in practice or theory. In this work, for the first time to the best of our knowledge, we implement an SSL algorithm in the stochastic domain and develop a functional SC-based sound source localizer. The practical part of this work shows that the proposed stochastic circuit does not depend on conventional analog-to-digital conversion and can process data in the form of pulse-width-modulated (PWM) signals. The proposed SC design consumes up to 39% less area than the conventional binary design. It can also consume less power depending on the computational accuracy, for example, 6% less power consumption for 3-bit inputs. We propose a new cross-correlation (CC) design based on the state-of-the-art Sobol bit-streams for further area and power saving. The proposed design utilizes a MUX unit for bit-stream generation. It saves the area footprint up to 64% and the power consumption up to 82% compared to the counter-based SC design of CC, which relies on a comparator for bit-stream generation. The presented stochastic circuits, are not limited to SSL and are readily applicable to other practical applications such as radar ranging, wireless location, sonar direction finding, beamforming, and sensor calibration. The project’s source code is made available for public access.

Image processing has been applied to various process of agricultural industry in order to achieve fast and accurate operation. Applying image processing techniques to classify wheat seeds based on their varieties is also objective method in real time applications. Seed analysis and classification can provide additional knowledge in their production, seeds quality control and in impurities identification. Also, it is very important to confirm the variety of the wheat before planting. Because each variety needs its own condition for taking good yield. In this study, a method is proposed to identify the wheat varieties grown in Turkey by using image analysis techniques, with the motivation of developing a fully automatic grain type and variety identification system. The proposed method is based on texture analysis (Gray Level Co-occurence Matrix (GLCM) and Linear Binary Pattern (LBP) methods) and k-Nearest Neighbor type classifier.

The rapid computerized simulation of stochastic computing (SC) systems is a challenging problem. A method for agile simulation of SC image processing is proposed in this work. The input operands are processed with the aid of a correlation-controlled contingency table (CT) construct without using actual stochastic bit-streams. The proposed approach underlines the validity of CT simulation with (i) image compositing, (ii) pattern detection, and (iii) bilinear interpolation case studies. Using the corresponding error models, we emulate the state-of-the-art pseudo-random and quasi-random bit-streams. Experimental results show that the proposed approach achieves similar computation accuracy to the traditional SC simulation while performing runtime-and memory-efficient computations. The execution time reduces more than 200× for the image compositing task when emulating random bit-streams with CT. Pattern detection and bilinear interpolation further showed 76× and 22× lower memory usage, respectively, when employing CT.

Hyperdimensional vector processing is a nascent computing approach that mimics the brain structure and offers lightweight, robust, and efficient hardware solutions for different learning and cognitive tasks. For image recognition and classification, hyperdimensional computing (HDC) utilizes the intensity values of captured images and the positions of image pixels. Traditional HDC systems represent the intensity and positions with binary hypervectors of 1K–10K dimensions. The intensity hypervectors are cross-correlated for closer values and uncorrelated for distant values in the intensity range. The position hypervectors are pseudo-random binary vectors generated iteratively for the best classification performance. In this study, we propose a radically new approach for encoding image data in HDC systems. Position hypervectors are no longer needed by encoding pixel intensities using a deterministic approach based on quasi-random sequences. The proposed approach significantly reduces the number of operations by eliminating the position hypervectors and the multiplication operations in the HDC system. Additionally, we suggest a hybrid technique for generating hypervectors by combining two deterministic sequences, achieving higher classification accuracy. Our experimental results show up to $102\times $ reduction in runtime and significant memory-usage savings with improved accuracy compared to a baseline HDC system with conventional hypervector encoding.

Hyperdimensional computing (HDC) is an emerging computing paradigm with significant promise for efficient and robust learning. In HDC, objects are encoded with high-dimensional vector symbolic sequences called hypervectors. The quality of hypervectors, defined by their distribution and independence, directly impacts the performance of HDC systems. Despite a large body of work on the processing parts of HDC systems, little to no attention has been paid to data encoding and the quality of hypervectors. Most prior studies have generated hypervectors using inherent random functions, such as MATLAB’s or Python’s random function. This work introduces an optimization technique for generating hypervectors by employing quasi-random sequences. These sequences have recently demonstrated their effectiveness in achieving accurate and low-discrepancy data encoding in stochastic computing systems. The study outlines the optimization steps for utilizing Sobol sequences to produce high-quality hypervectors in HDC systems. An optimization algorithm is proposed to select the most suitable Sobol sequences via indexes for generating minimally correlated hypervectors, particularly in applications related to symbol-oriented architectures. The performance of the proposed technique is evaluated in comparison to two traditional approaches of generating hypervectors based on linear-feedback shift registers and MATLAB random functions. The evaluation is conducted for three applications: 1) language; 2) headline; and 3) medical image classification. Our experimental results demonstrate accuracy improvements of up to 10.79%, depending on the vector size. Additionally, the proposed encoding hardware exhibits reduced energy consumption and a superior area-delay product.