mohammad-r. akbarzadeh-t

Clean, noise-free data are ideal but often unattainable in biological control systems. Filters are usually employed to remove noise. But this process also leads to the loss or alteration of information. A considerable challenge is managing the uncertain knowledge using a proper and realistic mathematical representation and staying consistent with biological patterns and behaviors. This study explores the potential of fuzzy logic as a computational paradigm to manage uncertainties in the nonlinear dynamics of human walking. This field has paid little attention to this aspect despite its considerable nonlinear and uncertain behavior due to adaptability, muscle fatigue, environmental noise, and external disturbances.

We employed a fuzzy logic-based controller integrated with functional electrical stimulation (FES) and a gait basin of attraction concept to enhance gait performance. Our controller focused on accommodating imprecision in shank angle deviation and angular velocity rather than relying on predetermined trajectories.

Our findings indicate that more fuzzy rules and partitions improve the similarity of the gait dynamics to those of a healthy human. Moreover, higher membership function overlaps lead to more robust gait control.

The study demonstrates that fuzzy logic can effectively manage uncertainties in the nonlinear dynamics of human walking, improving gait performance and robustness. This approach offers a promising direction for goal-oriented rehabilitation strategies by mimicking the human mind’s ability to handle challenging and unknown environments.

Mimetic Coral Reefs Optimization (MCRO) has proven highly effective for feature selection due to its capacity to explore diverse solution spaces, enhancing model accuracy and robustness. However, integrating MCRO with local search techniques remains challenging, as it tends to be computationally intensive and prone to premature convergence. To address these issues, this paper introduces a Rank-based Adaptive Brooding (RAB) mechanism, designed to refine the local mimetic search strategy within MCRO. RAB adaptively adjusts the brooding operator based on the ranks of coral larvae, minimizing disruption to high-rank larvae and harnessing the exploratory potential of lower-rank larvae. This approach promotes a more balanced exploration-exploitation trade-off, leading to faster convergence and enhanced performance in complex problem spaces. The proposed method's efficacy is tested across eight UCI datasets using KNN, Decision Tree, and SVM classifiers, and the results are evaluated by precision, recall, and F1 score. Empirical results reveal that RAB outperforms existing adaptive strategies with fixed brooding, delivering superior feature selection performance, particularly in high-dimensional datasets. Additionally, the optimization capabilities of RAB were examined using 39 CEC benchmark functions, revealing consistent improvements in feature selection accuracy while demonstrating variable outcomes in broader optimization tasks. Notably, RAB showed significant enhancements in eight benchmark cases, highlighting its potential for broader applicability in optimization scenarios.

WordNet-like Lexical Databases (WLDs) group English words into sets of synonyms called “synsets.” Synsets are utilized for several applications in the field of text mining. However, they were also open to criticism because although, in theory, not all the members (i.e. word senses) of a synset represent the meaning of that synset with the same degree, in practice, in WLDs they are considered as members of the synset identically. Correspondingly, the fuzzy version of synonym sets, called fuzzy-synsets were proposed. But, to the best or our knowledge. In this study, we present an algorithm for constructing fuzzy version of WLDs of any language, given a corpus of documents and a word-sense-disambiguation system of that language. A theoretical proof is also proposed for the validity of results of the proposed algorithm. Then, inputting the open-American-online-corpus (OANC) and UKB word-sense-disambiguation to the algorithm, we construct and publish online the fuzzified version English WordNet (FWN), and apply them in a Sentiment Analysis problem.

Design and control of surgical robots for minimally invasive surgery have considerable challenges in handling unknown robot dynamics, environmental uncertainties, desirable workspaces, and fast motion reactions. Realistic operational requirements regarding kinematics and dynamics of the robot and its actuators also lead to joint elasticity; therefore, further concerns regarding sustained chattering, vibration, and instability are raised. Accordingly, the robot proposed here is designed based on a hybrid structure, consisting of two parallel and serial manipulators, aiming for the desired rigidity and acceptable manipulability requirements of robotic surgeries. Furthermore, a decentralized sliding mode controller with an indirect adaptive fuzzy estimator based on a voltage control strategy is employed to tackle the challenges of controlling such as chattering phenomenon, control loop's speed, and stability against uncertainties. In contrast to the traditional sliding mode controllers, the control law is free from robot dynamics, the control signals' chattering is reduced, and bounded input-bounded output stability is shown without knowing the uncertainty bounds on robot dynamics. Simulation and experimental studies indicate that this approach is realistic.

Background: Parkinson’s disease (PD) is a neurological disorder caused by decreasing dopamine in the brain. Speech is one of the first functions that are disrupted. Accordingly, speech features are a promising indicator in PD diagnosis for telemedicine applications. The purpose of this study is to investigate the impact of Parkinson’s disease on a minimal set of Jitter and Shimmer voice indicators and studying the difference between male and female speech features in noisy/noiseless environments. Materials and Methods: Our data includes 47 samples from nursing homes and neurology clinics, with 23 patients and 24 healthy individuals. The optimal feature for each category is studied separately for the men’s and women’s samples. The focus here is on the phonation in which the vowel/a/is expressed by the participants. The main features, including Jitter and Shimmer perturbations, are extracted. To find an optimal pair under both noisy and noiseless circumstance, we use the Relief feature selection strategy. Results: This research shows that the Jitter feature for men and women with Parkinson’s is 21 and 33.4, respectively. While the Shimmer feature is 0.1 and 0.06. In addition, by using these two features alone, we reach a correct diagnosis rate of 79% and 81% for noisy and noiseless states, respectively. Conclusion: The PD effects on the speech features can be accurately identified. Evaluating the extracted features suggests that the absolute value of the selected feature in men with PD is higher than for healthy ones. Whereas, in the case of women, this is the opposite.

Precision agriculture is rapidly growing worldwide, which is mainly based on positioning. While with the evolution of technology the accuracy of GPS data is continuously improved, the use of these sensors in the less developed countries is still challenging. The direct price link with the accuracy of the GPSs has led to attempts to use low-cost GPSs. The use of low-cost GPSs comes with various sources of error. In this study, a new method has been proposed to overcome the challenge of improving the accuracy of positioning while reducing equipment prices. The proposed method is based on the nature of the GPS error (random noise and bias) and is divided into two parts. First, the random noise was eliminated by employing the simple classic filter. In this regard, a comparison was made between the Kalman filter, Low-pass filter and the Moving Average filter. The settings of the filters were made in such a way that in addition to reducing the power of random error, it reaches the desired error range in the shortest possible time. The results showed that the Kalman filter was more efficient than the other filters. Bias removal is not possible except by using a DGPS receiver that can receive corrections sent from base stations. To solve this problem, a base station was designed that could send the corrections needed by low-cost receivers. The proposed low-cost differential positioning method leads to a 89% reduction in the horizontal error index, which is the accuracy obtained is suitable for various operations in precision agriculture. Second, the bias was removed by inspiring from DGPS technique, via providing a base station, incorporating three low-cost GPSs. in noise reduction and the proposed low-cost differential positioning at best resulted in 89% reduction in the error index. Such an enhanced accuracy can be used for many applications in precision agriculture.