Effective management of patients with diabetic foot infection is a crucial concern. A delay in prescribing appropriate antimicrobial agent can lead to amputation or life threatening complications. Thus, this electronic nose (e-nose) technique will provide a diagnostic tool that will allow for rapid and accurate identification of a pathogen. This study investigates the performance of e-nose technique performing direct measurement of static headspace with algorithm and data interpretations which was validated by Headspace SPME-GC-MS, to determine the causative bacteria responsible for diabetic foot infection. The study was proposed to complement the wound swabbing method for bacterial culture and to serve as a rapid screening tool for bacteria species identification. The investigation focused on both single and poly microbial subjected to different agar media cultures. A multi-class technique was applied including statistical approaches such as Support Vector Machine (SVM), K Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA) as well as neural networks called Probability Neural Network (PNN). Most of classifiers successfully identified poly and single microbial species with up to 90% accuracy. The results obtained from this study showed that the e-nose was able to identify and differentiate between poly and single microbial species comparable to the conventional clinical technique. It also indicates that even though poly and single bacterial species in different agar solution emit different headspace volatiles, they can still be discriminated and identified using multivariate techniques.

Device-free localization (DFL) has become a hot topic in the paradigm of the Internet of Things. Traditional localization methods are focused on locating users with attached wearable devices. This involves privacy concerns and physical discomfort especially to users that need to wear and activate those devices daily. DFL makes use of the received signal strength indicator (RSSI) to characterize the user’s location based on their influence on wireless signals. Existing work utilizes statistical features extracted from wireless signals. However, some features may not perform well in different environments. They need to be manually designed for a specific application. Thus, data processing is an important step towards producing robust input data for the classification process. This paper presents experimental procedures using the deep learning approach to automatically learn discriminative features and classify the user’s location. Extensive experiments performed in an indoor laboratory environment demonstrate that the approach can achieve 84.2% accuracy compared to the other basic machine learning algorithms.

The trend of stingless bees’ farm in Malaysia has increased recently as it has been proven that its honey gives various benefits to human beings. This trend requires beekeepers to do more frequent inspections of beehives. However, the current practice of opening the cover to inspect the colony and honey will disrupt colony activity. According to a recent study, these stingless bees can only survive between 22 and 38 degrees Celsius, and harsh weather conditions might lead to the collapse of bee colonies. In order to ensure a consistent honey production, the IoT monitoring system will be implemented on an artificial stingless beehive. The system is equipped with an embedded system that utilizes a NodeMCU ESP8266, temperature and humidity sensors, and load cell sensors. Next, honey compartment weight, temperature and humidity inside stingless beehive, and temperature and humidity outside stingless beehive will be uploaded to the Internet of Things (IoT) platforms, namely Thingspeak and Cayenne. The data is sent to Thingspeak via the REST API while to Cayenne by the MQTT API. All data from the artificial stingless bee hive indicating the occurrence of colony rising and has been uploaded to the IoT platform. By analysing the data that were recorded for 13 days, all of the input data such as the weight of the honey compartment, the temperature in the hive, and the humidity in the hive, display its respective characteristics. For the honey compart weight, it has been found that the stingless bee colony is rising as a result of the increasing honey and colony in the compartment weight. Regarding the hive temperature, it has been determined that the temperature inside the hive is stable around 26°C to 38°C in normal weather conditions. Whereas for humidity inside the hive, it is remained between 76.5% and 85.6% due to the moisture from the honey inside the compartment. Lastly, these results indicate that the colony living in the artificial hive of stingless bees is healthy and growing.

Achieving optimal machine learning model performance is often hindered by the limited availability of diverse datasets, a challenge exacerbated by small sample sizes in real-world scenarios. In this study, we address this critical issue in classification tasks by integrating the Dropout technique into the Extreme Learning Machine (ELM) classifier. Our research underscores the effectiveness of Dropout-ELM in mitigating overfitting, especially when data is scarce, leading to enhanced generalization capabilities. Through extensive experiments on synthetic and real-world datasets, our findings consistently demonstrate that Dropout-ELM outperforms traditional ELM, yielding significant accuracy improvements ranging from 0.19% to 16.20%. By strategically implementing dropout during training, we promote the development of robust models that reduce reliance on specific features or neurons, resulting in increased adaptability and resilience across diverse datasets. Ultimately, Dropout-ELM emerges as a potent tool to counter overfitting and bolster the performance of ELM-based classifiers, particularly in scenarios with limited data. Its established efficacy positions it as a valuable asset for enhancing the reliability and generalization of machine learning models, providing a robust solution to the challenges posed by constrained training data.

Profoundly hearing-impaired community (PHIC) cannot moderate wisely an acoustic noise emanated from moving vehicle in outdoor environment. Due to this, they have difficulties to distinguish type and the distance of moving vehicles especially the one comes from the rear. Hence, they are at risk whenever they are outdoors. In this paper, a simple system is proposed to identify the type and distance (zone-based) of a moving vehicle using a multi-classifier system (MCS). One-third octave filter bands approach has been used for extracting the significant feature from the noise emanated by the moving vehicle. The extracted features were associated with the type and zone of the moving vehicle and the MCS based on multilayer perceptron has been developed. The developed multilayer perceptron model with the same hidden neuron and training algorithm has been proposed for MCS. This network has been tested for single classifier and MCS. The developed MCS has improved the classification accuracy compared to single classifier.

Under certain situations, researchers were forced to work with small sample-sized (SSS) data. With very limited sample size, SSS data have the tendency to undertrain a machine learning algorithm and rendered it ineffective. Some extreme cases in SSS problems will have to deal with large feature-to-instance ratio, where the high number of features compared to small number of instances will overfit the classification algorithm. This paper intends to solve small sample-sized classification problems through hybrid of random subspace method and random linear oracle ensemble by utilizing binary feature subspace splitting and oracle selection scheme. Experimental results on artificial data indicate the proposed algorithm can outperform single decision tree and linear discriminant classifiers in small sample-sized data, but its performance is identical to k-nearest neighbor classifier due to both shared similar selection approach. Results from real-world medical data indicate the proposed method has better classification performance than its corresponding single base classifier especially in the case of decision tree.